Industry news that caught our eye
“A quality improvement project undertaken at a large academic medical center significantly reduced the variation in radiology report templates. The initiative may serve as an example of how radiology can move toward value-based care.
“In our practice, as at other large institutions, there was great variability in report structure among individual radiologists,” wrote Tony W. Trinh, MD, with the department of radiology at Brigham and Women’s Hospital in Boston, and colleagues. “Substantial differences in report structure, content, length, and degree of detail provided by different radiologists can be a source of confusion and frustration for referrers and patients.””
“Prior studies have suggested that women who take aspirin before being diagnosed with breast cancer (BC) may live longer than women who haven’t historically used aspirin, but study data is limited and inconsistent. Research headed by scientists at the University of North Carolina (UNC) at Chapel Hill has now found that DNA methylation may represent the missing link in this relationship. Their population-based study in more than 1,000 women with breast cancer found that global DNA methylation, and methylation of the promoters for two specific cancer-related genes, may impact on whether prediagnosis aspirin use can influence breast cancer-specific mortality, and death from all causes.”
“Growth in the mammography market may begin to slow down in the near future, according to a new analysis from Signify Research.
Author Imogen Fitt described mammography as the breast imaging industry’s “undisputed modality of choice,” but also noted that it could be in for a significant shift. And how did she come to that conclusion? In her analysis, Fitt provided three key reasons…”
“Synthesized digital mammography (SM) was created to help reduce the radiation dose for patients undergoing digital mammography (DM) in digital breast tomosynthesis (DBT), so why haven’t more clinics adopted it?
Researchers of a new study published in the Journal of the American College of Radiology administered a survey to the 2,600 members of the Society of Breast Imaging to find out.
“Combination-dose DM and DBT screening over the lifetime of a screened woman will result in higher radiation dose than screening with DM alone,” wrote Samantha Zuckerman, MD, with the University of Pennsylvania, and colleagues. “Thus, it would be most beneficial to patients if the ‘dose DM’ portion of a DBT screen is replaced by an acceptable SM image so that the benefits of DBT could be maintained at a lower radiation dose than DM–DBT screening.””
“There’s a strong case to be made for mammography to become a “dual test” for both breast cancer screening and cardiovascular disease (CVD) prevention, according to a new review published in the European Journal of Radiology.
Breast cancer screening via mammography can easily detect breast arterial calcifications (BACs) which are associated with CVD and serve as an imaging biomarker for prevention of the disease, wrote Rubina Manuela Trimboli, with the department of biomedical sciences for health at the Università degli Studi di Milano in Milan, Italy, and colleagues.
“Thus, there is a strong rationale for mammography to serve as a preventive test beyond breast cancer screening, spotlighting on the heart and more comprehensively on CV risk,” Trimboli and colleagues wrote.”
“A new machine learning system created by UCLA researchers may help doctors classify breast cancers that are notoriously difficult to diagnose, according to an Aug. 9 study published in JAMA Network Open.
Preinvasive lesions, including some types of atypia and ductal carcinoma in situ (DCIS) can indicate higher cancer risk, wrote corresponding author Joann G. Elmore, MD, MPH, with UCLA’s Division of General Internal Medicine and Health Services Research, but diagnostic disagreements are “remarkably high” for such lesions. Machine learning has shown great promise for differentiating breast cancers, but studies have largely focused solely on tumor detection.”
“Scientists headed by a team at the Institute of Cancer Research, London (ICR) have used artificial intelligence (AI) and machine learning (ML) to discover five new subtypes of breast cancer that could help clinicians deliver the most effective therapies—including immunotherapy—for individual patients, as well as potentially direct the development of new anticancer drugs.
The computational tools find patterns in the genetic, molecular, and cellular make-up of primary luminal A-type breast tumors, which are analyzed alongside data on patient survival.”
“Allowing natural language processing to pore over disparate data stored in electronic health records, researchers in Canada have shown the AI-based technology can reveal real-world experiences and outcomes of patients with stage III breast cancer.
Mark Levine, MD, of McMaster University and colleagues had their work published online Aug. 1 in JCO Clinical Cancer Informatics.”
“Deep learning can improve the accuracy and efficiency of digital breast tomosynthesis (DBT) examinations, according to new findings published in Radiology: Artificial Intelligence.
The study’s authors developed and trained a deep learning system to identify suspicious findings on DBT images, hoping it could help reduce the longer reading times associated with screening patients with DBT. A group of 24 radiologists then read 260 DBT examinations with and without assistance from the deep learning system.”
“AI and deep learning can extract molecular markets of breast cancer from tissue morphology and assist pathologists in a mass-scale molecular profiling, according to new research published in JAMA Network Open.
Researchers studied tissue microarray hematoxylin-eosin-stained images from more than 5,000 breast cancer patients. Using a deep learning model, researchers could profile cancer molecules with “practically no added cost and time,” lead author Gil Shamai, MSc, of the department of electrical engineering at Technion Israel Institute of Technology in Haifa, Israel, et al. wrote.”
“Breast cancer screening using digital breast tomosynthesis has risen rapidly in the United States, but that isn’t the case in all regions or across all institutions, according to a new study published in Current Problems in Diagnostic Radiology.
“Despite the advantages of reduced callback rates, higher sensitivity, and higher specificity associated with digital breast tomosynthesis (DBT) over traditional full-field digital mammography (FFDM), many patients declined DBT at our urban academic breast center,” wrote Kellie Chiu, with University of Maryland Medical Center’s Department of Diagnostic Radiology and Nuclear Medicine, and colleagues.”
“High levels of background parenchymal enhancement (BPE) can have a negative impact on the diagnostic quality of breast MRI interpretations, according to new findings published in Academic Radiology.
“Because of the negative impact of breast density on the sensitivity and specificity of mammography, radiologists are required to document breast density in mammography reports and many states have enacted legislation requiring this information be shared directly with patients,” wrote Dorothy A. Sippo, MD, MPH, department of radiology at Massachusetts General Hospital in Boston, and colleagues. “If BPE has a similar impact on MRI performance, then comparable attention to its importance may be warranted.””
“A deep learning platform created by researchers at the Dana-Farber Cancer Institute can identify cancer in radiology reports as well as clinicians, but in a fraction of the time, according to new research published July 25 in JAMA Oncology.
The model was trained on more than 14,000 imaging reports from 1,112 patients with lung cancer, manually read by human reviewers. After it was applied to another 15,000 reports, the algorithm predicted overall survival with similar accuracy to that of human assessments.”
“The Medical Imaging & Technology Alliance (MITA) released a statement July 23 cheering lawmakers’ efforts to make digital breast tomosynthesis (DBT) screening coverage standard for active and retired members of the military.
U.S. Representative Chrissy Houlahan (D-PA), along with numerous other members of Congress, addressed a letter to the Military Health System (MHS) urging its leadership to provide DBT coverage to TRICARE health beneficiaries. TRICARE is one of the few payers in the U.S. that does not include coverage for the screening exam.”
“For radiology to truly benefit from AI’s potential, the specialty must learn how to get the most information possible out of all available digital data. The authors of a new analysis published by the Journal of the American College of Radiology explored this subject in detail, describing use cases critical for radiology to successfully evolve in the years ahead.
“In 2013 and 2014, the RSNA Radiology Informatics Committee and American College of Radiology (ACR) Commission on Informatics, along with senior leadership from both societies, held two joint retreats to identify gaps in technology that may impose future limitations in our digital workflow…””
““Our focus is becoming ‘the’ lung cancer diagnostic solution company,” Scott Hutton, COO of Biodesix, told MD+DI. “With that we know we need multiple diagnostics tests for different times within a patient’s care continuum. With GeneStrat and VeriStrat being our legacy products – we were looking more late stage.”
The firm acquired U.K.-based Oncimmune’s laboratory and incidental pulmonary nodule malignancy test in the U.S. Oncimmune’s U.S. operations, including a CLIA lab in De Soto, KS, will transition to Biodesix on Nov. 1. The lab is the sole U.S. provider of Oncimmune’s EarlyCDT -Lung test.”
“Over the past few years, I’ve written a number of posts talking about different cancers and new cancer treatments. Fifty years ago, nearly any diagnosis of cancer would have been a death sentence, but today, surviving many cancers has drastically increased.
According to the American Cancer Society:
Lung cancer death rates declined 48% from 1990 to 2016 among men and 23% from 2002 to 2016 among women. From 2011 to 2015, the rates of new lung cancer cases dropped by 3% per year in men and 1.5% per year in women. The differences reflect historical patterns in tobacco use, where women began smoking in large numbers many years later than men and were slower to quit. However, smoking patterns do not appear to explain the higher lung cancer rates being reported in women compared with men born around the 1960s.”
“As researchers and advocates in the United States debate the merits of risk-based breast cancer screening vs. age-based screening, a risk-based program in Northern Ireland (NI) has found significant success. A new study published in Clinical Radiology examined the program in detail.
The program began in April 2013 at the urging of the chief medical officer for NI. A multidisciplinary working group was established to work out the details and get providers throughout the area on the same page, and the researchers examined four years of data for their study.”
“Surveillance MRI can help imaging providers detect more breast cancers, according to a new study published in Radiology. However, it also leads to a much higher biopsy rate.
“People often think more testing is better,” lead author Karen J. Wernli, PhD, an associate investigator at the Kaiser Permanente Washington Health Research Institute in Seattle, said in a prepared statement. “That might be true for some women, but not necessarily all. It’s important for clinicians and women to be aware of both the benefits and harms that can come from imaging.””
“Correlating radiology and pathology reports is an ongoing challenge on the path toward achieving multidisciplinary patient care. One researcher has gotten a little closer to that goal with the help of deep learning techniques, sharing findings in the Journal of the American College of Radiology.
The method uses a language-modeling approaches trained on data from multiple hospitals and ambulatory sites and can serve as an important basis to continually improve specificity and user preferences in automatically correlating radiology and pathology reports, according to the study’s only author, Ross Filice, MD, with MedStar Georgetown University Hospital, Washington, D.C.”
“The use of magnetic resonance imaging brings many benefits to cancer care, but the imaging modality appears to prompt more biopsies than are necessary.
A recent study found that breast cancer patients who were screened with MRIs underwent twice as many biopsies as those that were screened with mammography alone.”
“Implementing a same-day biopsy program can help providers address ongoing disparities in patient care, according to a new study published in the Journal of the American College of Radiology.
A team from Massachusetts General Hospital in Boston conducted the study, noting that numerous disparities are present in breast cancer care in the United States.”
“Machine learning can reduce a radiologists workload by lowering the number of screening mammograms they’re required to read while preserving accuracy, according to results of a feasibility study published in the Journal of the American College of Radiology.
Trent Kyono, with the Department of Computer Science, University of California Los Angeles, and colleagues created their autonomous radiologist assistant (AURA)—a modified version of a previous clinical decision support system—to determine if it could diagnose mammograms as negative while maintaining diagnostic accuracy and noting which scans would still need to be read by a radiologist.”
“New, early data from Grail showed its liquid biopsy test was not only able to detect the presence of 12 different kinds of early-stage cancer but could also identify the disease’s location within the body before it spreads using signatures found in the bloodstream.
The test also demonstrated a very low rate of false positives, at 1% or less. The former Fierce 15 winner presented the returns from a sub-study of its Circulating Cell-free Genome Atlas (CCGA) project at this year’s annual meeting of the American Society of Clinical Oncology (ASCO) in Chicago.”
“Researchers in Texas and Taiwan have collaborated to develop a deep-learning tool that can precisely asses the risk of breast cancer—and with it the need for biopsy—in patients with lesions of questionable concern found in mammograms.
Their key achievement is training an algorithm to home in on a well-defined subgroup of patients, those with mammography findings categorized as BI-RADS 4 (on a scale of 0 to 6 developed by the American College of Radiology).”
“New research suggests annual reading volumes between 4,000 and 10,000 mammograms may produce the highest performance among screening programs with independent double reading.
In addition, cumulative reading volumes of more than 20,000 mammograms resulted in peak radiologic performance, according to results of a new study published May 28 in Radiology.”
“Google’s artificial intelligence development has reached a milestone in lung cancer imaging and prediction, with a CT scan model being able to diagnose cases as well as or better than a group of six radiologists.
Alongside researchers at Northwestern University, New York University-Langone Medical Center and Stanford Medicine, Google’s AI team was able to generate an overall prediction of malignancy from 3D volumetric scans, as well as identify subtle lung nodules.”
“Many women who undergo screening mammography are also eligible for lung cancer screening (LCS), according to a new study published by the Journal of the American College of Radiology. Yet LCS utilization in the United States remains considerably low.
“LCS with low-dose CT has been shown to reduce deaths from lung cancer by 15% to 20% in high-risk current or former smokers,” wrote Diego López, MPH, Harvard Medical School in Boston, and colleagues. “The United States Preventive Services Task Force recommends annual screening for this patient population…””
“On February 15 of this year, Congress passed national breast density legislation, which mandates all mammography reports and summaries notify women of their breast density.
In a recent JAMA commentary, a trio of researchers questioned whether the law will actually help patients, sharing some of their most pressing concerns.”
“Short-interval follow-up MRI can identify early stage breast cancer and reduce unnecessary biopsies, reported authors of a study to be presented at the American Roentgen Ray Society Annual Meeting in Honolulu.
Co-researcher Christine Edmonds, MD, of the department of radiology at Massachusetts General Hospital (MGH) and colleagues analyzed the frequency and cancer yield of American College of Radiology (ACR) Breast Imaging Reporting and Data System (BI-RADS) 3 lesions in patients who received baseline and non-baseline screening MRIs. The team defined non-baseline as those preceded by at least one screening exam.”
“Diffusion-weighted imaging techniques for quantitatively identifying benign and malignant breast lesions achieved comparable diagnostic accuracies, according to a meta-analysis of three methods published April 23 in Radiology.
“Whereas previous meta-analyses have assessed the performance of the (apparent diffusion coefficient) ADC model in differentiating between benign and malignant lesions, more advanced diffusion techniques aim to improve on the results of quantitative (diffusion-weighted imaging) DWI,” wrote Gabrielle C. Baxter from the department of radiology at the University of Cambridge School of Clinical Medicine in Cambridge, England, and colleagues.”
“On May 22, more than 400 American College of Radiology (ACR) members will speak with their elected federal representatives to discuss four legislative priorities as part of Capitol Hill Advocacy Day at the 2019 ACR Annual Meeting.
Limiting surprise medical bills
“Issues surrounding beneficiaries being burdened with high out-of-pocket costs and inadequate provider networks present real issues for patients in need of life saving diagnostic imaging services,” according to an ACR position statement. “The problem of unanticipated out-of-network bills is complex, and requires a balanced approach to resolve.”
A key problem, according to the ACR, is that health insurance plans are leaning on a narrow network of providers to control costs, and as a result even patients who make sure they receive in-network care are still burdened by…”
“A deep learning model is able to accurately assess breast tissue density—an independent risk factor for breast cancer—in mammograms.
In a new study of the model, developed by Massachusetts General Hospital and MIT, nearly 90,000 full-resolution screening mammograms from about 40,000 women were used to train, validate and test the deep learning model.
“We developed a deep learning model that uses full-field mammograms and traditional risk factors, and found that our model was more accurate than the Tyrer-Cusick model (version 8), a current clinical standard,” conclude researchers in a study published earlier this week in the journal Radiology.”
“All women 25 years old and older should undergo a breast cancer risk assessment, according to a new position statement published by the American Society of Breast Surgeons (ASBrS). Annual mammograms, beginning at the age of 40, are recommended if women have an average risk of developing breast cancer. If the risk is greater, annual mammograms and supplemental imaging are recommended.
In addition, the ASBrS emphasized the effectiveness of digital breast tomosynthesis (DBT), also known as 3D mammography.
“Where available, 3D mammography is the preferred sole modality for women with an average risk for breast cancer,” according to the statement. “It is also important to note that most current 3D mammography units result in no greater radiation exposure than traditional 2D units.””
“A team of researchers from MIT and Massachusetts General Hospital (MGH) have created an AI model capable of predicting a patient’s breast cancer risk five years in advance.
The deep learning (DL) model was also equally as accurate for racial minorities who have proven to be more likely to die from cancer, such as black women, according to a May 7 study published in Radiology.”
“Georgia Gov. Brian Kemp has signed the state’s breast density legislation into law. The bill goes into effect on July 1.
HB 62 requires mammography providers to notify patients about their breast density. It is also known as “Margie’s Law,” named after patient advocate Margie Singleton, who had breast cancer missed by a mammogram due to her dense breast tissue.
According to the legislation, the text sent to patients should read as follows…”
“Patients with screening-detected ductal carcinoma in situ (DCIS) who were screened with mammography and ultrasound (US) have similar disease-free survival (DFS) rates, according to a new study published in Radiology. In patients with screening mammography-detected DCIS, an association was observed between dense breasts and second breast cancer.
“Several studies have reported that screening-detected DCIS shows better DFS than does symptomatic DCIS,” wrote lead author Seung Hee Choi of the Sungkyunkwan University School of Medicine in Seoul, Korea, and colleagues. “To our knowledge, however, no studies have evaluated the association between the screening method (mammography or US) and survival outcome after treatment of DCIS.””
“Radiotherapy combined with hormonal therapy after surgery significantly reduced the chance of recurrence in women with early hormone receptor-positive (HR+) breast cancer, according to results of a 10-year trial presented at the European Society for Radiotherapy and Oncology (ESTRO) 38 conference in Milan, Italy.
Results of the 8 A arm of the Australian Breast and Colorectal Cancer Study Group found cancer did not return in the same breast in 97.5% of women who underwent whole-breast irradiation (WBI) and hormonal therapy after a 10 year follow-up period. In women who only received hormonal therapy, that fraction was 92.4%.”
“The handheld ultrasound market has been slow to take off in recent years, but a burst of growth could be on the horizon, according to a new report from Signify Research.
Simon Harris, the report’s author, noted that cardiologists and emergency medicine specialists made up much of the handheld ultrasound market’s initial wave of growth. This was followed by what Harris called “the current wave” of growth, which includes office-based specialists who want the technology so they provide a wider range of services during initial appointments with patients.”
“The American College of Physicians (ACP) now recommends that average-risk women with no symptoms undergo breast cancer screening with mammography every other year, beginning at the age of 50. The ACP explained its decision through a new guidance statement published in Annals of Internal Medicine.
“Beginning at age 40, average-risk women without symptoms should discuss with their physician the benefits, harms, and their personal preferences of breast cancer screening with mammography before the age of 50,” ACP President Ana María López, MD, said in a prepared statement. “The evidence shows that the best balance of benefits and harms for these women, which represents the great majority of women, is to undergo breast cancer screening with mammography every other year between the ages of 50 and 74.””
“In 2018, results from the TAILORx clinical trial revealed that genetic testing could help a majority of women with HR-positive, HER2-negative, axillary node-negative breast cancer bypass chemotherapy since it would not benefit them any more than hormone therapy alone. Now, researchers have determined that the widespread use of such testing could lead to approximately $50 million in savings for the first year of breast cancer care in the United States.
The team, including lead author Angela Mariotto, PhD, of the National Cancer Institute, shared its findings in JNCI: Journal of the National Cancer Institute.”
“The high sensitivity associated with breast MRI makes it an effective tool for detecting breast cancer, but the costs and long acquisition times have kept it from being embraced as a supplemental screening option. Researchers at one institution adopted an abbreviated protocol (AP) for breast MRI for patients with dense breasts, discussing their process in the American Journal of Roentgenology.
It took a full year to implement the protocol as a screening option, the authors noted, as it involves making key decisions and getting various stakeholders on board. These are four key steps providers must take to make such a protocol a reality:”
“A free web tool known as “Chester the AI Radiology Assistant” can assess a person’s chest X-rays online within seconds, ensuring patients’ private medical data remains secure while predicting their likelihood of having 14 diseases.
Chester, though still rudimentary, can process a user’s upload and output diagnostic predictions for atelectasis, cardiomegaly, effusion, infiltration, masses, nodules, pneumonia, pneumothorax, consolidation, edema, emphysema, fibrosis, pleural thickening and hernias with 80 percent accuracy. A green-and-red sliding scale pinpoints the diagnostic probability for each condition, ranging from “healthy” to “risk.””
“The FDA announced Tuesday, April 3, that it is working on a new framework to regulate AI-based medical devices that continually learn from healthcare data.
Scott Gottlieb, MD, who announced his resignation as commissioner of the FDA last month, released a discussion paper outlining the administration’s approach to keep up with the rapid advancement of AI algorithms and ensure their safety. The agency is also asking for feedback about the paper due by June 3.”
“When women learn that they have dense breast tissue after a mammogram, should they seek out supplemental screening? A new study published in the Journal of Breast Imaging asked radiologists what they currently recommend for patients at all risk levels.
“Currently, there are no guidelines recommending the use of supplemental screening in women with dense breasts, although there is legislation in over 30 states requiring women be notified of breast density,” wrote Tisha Singer, MD, Rhode Island Hospital and Alpert Medical School of Brown University in Providence, Rhode Island, and colleagues.”
“Researchers have developed a deep learning (DL) model that assesses a woman’s five-year cancer risk with a single breast MR image, sharing their findings in the American Journal of Roentgenology.
“Although a large number of risk assessment models exist for the general screening population, they are not readily applicable to high-risk patients,” wrote Tally Portnoi, department of electrical engineering and computer science at Massachusetts Institute of Technology in Cambridge, and colleagues.”
“Breast cancer screening with digital breast tomosynthesis (DBT) provides significant value to older women, according to a new study published in Radiology.
The researchers analyzed data from more than 15,000 women aged 65 years or older who underwent digital mammography (DM) alone from March 2008 to February 2011, before their institution had integrated DBT into clinical practice. The team then explored data from more than 20,000 women aged 65 years or older who underwent DBT from January 2013 to December 2015.”
“In a small clinical study, investigators from Marshall University School of Medicine found that the consumption of two ounces of walnuts per day for about two weeks significantly changed gene expression in confirmed breast cancers. The findings from the study were published recently in Nutrition Research through an article titled “Dietary walnut altered gene expressions related to tumor growth, survival, and metastasis in breast cancer patients: A pilot clinical trial.””
“Breast density assessments using digital breast tomosynthesis (DBT) and synthetic mammography (SM) vary significantly compared to those performed using standard digital mammography (DM), according to a new study published by Radiology.
The authors examined data from more than 24,000 women who underwent mammographic breast cancer screening at the Hospital of the University of Pennsylvania (HUP) in Philadelphia between 2010 and 2017. Of the more than 60,000 examinations, 14.7 percent were performed using DM only, and 50.7 percent were performed using DM and DBT together. The final 34.6 percent were performed with SM and DBT together.”
“The FDA announced Wednesday, March 27, that it is taking action to “modernize” breast cancer screening in the United States by amending the Mammography Quality Standards Act of 1992 with a new proposed rule.
“Breast cancer is one of the most worrisome health concerns facing women,” Scott Gottlieb, MD, outgoing FDA commissioner, said in a prepared statement. “The FDA plays a unique and meaningful role in the delivery of quality mammography to help patients get accurate screening to identify breast health problems early, when they can be effectively addressed…””
“Positron emission tomography/computed tomography (PET/CT) scan biomarkers show potential for identifying breast cancer patients who may be able to forgo conventional chemotherapy before surgery. Researchers at the Johns Hopkins Kimmel Cancer Center have identified a biomarker that may accurately predict which patients with dual human epidermal growth factor receptor 2 (HER2)-positive breast cancer might benefit from standalone HER2-targeted agents, without requiring standard chemotherapy. They reported their findings online Feb. 5, 2019, in the Journal of Clinical Oncology.”
“Australian researchers at the University of Queensland have discovered a unique DNA structure that appears to be shared by many cancers and could be used to develop a simple diagnostic test that could be performed in under 10 minutes with the naked eye.
When circulating tumor DNA fragments are placed in water, they begin to fold into 3D shapes different than DNA from healthy cells—driven by the dense clusters of methyl groups found along DNA molecules that have been reprogrammed by cancer.”
“Supplementing screening mammography with whole-breast ultrasound may not be worth the trouble, according to new findings published in JAMA Internal Medicine.
The study’s authors noted that many researchers have advocated for whole-breast ultrasound and mammography to be used together when screening women with dense breast tissue. Others, however, have found the evidence is unclear.”
We present an accurate and reliable method for localizing a mammographic lesion by ultrasound using a simple coordinate system. It does not require special grid equipment or additional personnel. We use our system, step-by-step, on a sample patient and include appropriate image documentation. The nipple is the point of reference or “origin”. The lesion is located on ultrasound using its x and y coordinates, which are the two distances from the nipple in the horizontal and vertical axes, measured with an ordinary ruler or caliper tool. The true distance from the nipple can also easily be measured and reported. Our method is reproducible and shortens ultrasound exam times to less than 10 minutes.”
Evaluating concordance between core biopsy results and imaging findings is an integral component of breast intervention. Pathologic results deemed benign discordant reflect concern that a malignancy may have been incorrectly sampled. Standard of care currently is surgical excision, although a large percentage of these lesions will be benign at final pathologic analysis. The purpose of this study was to determine whether inclusion of contrast-enhanced MRI would optimize patient care.”
“Scientists at the Translational Genomics Research Institute (TGen), an affiliate of City of Hope, report the development of LumosVar, a computer program that can help identify cancer-causing mutations from patient tumor samples. The study (“Leveraging Spatial Variation in Tumor Purity for Improved Somatic Variant Calling of Archival Tumor Only Samples”) appears in Frontiers in Oncology.
“Archival tumor samples represent a rich resource of annotated specimens for translational genomics research. However, standard variant calling approaches require a matched normal sample from the same individual, which is often not available in the retrospective setting, making it difficult to distinguish between true somatic variants and individual-specific germline variants.”
“Sunscreen may not be the only ointment that helps prevent skin cancer. A cream that combines 5-fluorouracil (5-FU) and a synthetic form of vitamin D has been shown to reduce the risk that precancerous skin lesions will progress to squamous cell carcinoma (SCC), the second most common form of skin cancer.
A couple of years ago, the combination cream was evaluated as a means of eliminating actinic keratoses, precancerous lesions that emerge in sun-damaged skin. Although the chance of an individual lesion progressing to cancer is only 1%, most SCCs develop from existing actinic keratosis lesions.”
“Increased background parenchymal enhancement (BPE) levels at breast MRI are associated with a greater risk of developing breast cancer within a year, according to new findings published in the American Journal of Roentgenology.
“Identifying patients with hormonally responsive breast tissue has important clinical implications,” wrote Dorothy A. Sippo, MD, department of radiology at Massachusetts General Hospital in Boston, and colleagues.”
“In December 2018, the Canadian Task Force on Preventive Health Care issued updated breast cancer screening guidelines that recommended women aged 50 to 74 seek screening every two or three years and women aged 40 to 49 not undergo screening. Opinions vary on the effectiveness of these guidelines, as one can see by reading two recent columns published by the Toronto Star.
Physician Lisa Del Giudice, MD, MSc, of Cancer Care Ontario wrote that the task force did the right thing. Jean Seely, MDCM, a breast radiologist at The Ottawa Hospital, wrote that updating the guidelines was a mistake.”
“Just a week after Roche’s Tecentriq became the first immuno-oncology agent the FDA approved for triple-negative breast cancer, the anti-PD-L1 drug has clinched another first-in-class approval—this time in lung cancer.
The Swiss drugmaker said on Tuesday that the FDA had greenlighted Tecentriq in combination with chemotherapy for treatment of previously untreated extensive-stage small cell lung cancer (ES-SCLC), making it the first cancer immunotherapy in the setting and the first FDA-approved option for the disease in more than 20 years.”
“A new study of positron emission tomography (PET) scans has identified a biomarker that may accurately predict which patients with one type of HER2-positive breast cancer might best benefit from standalone HER2-targeted agents, without the need for standard chemotherapy. The study was conducted by researchers at the Johns Hopkins Kimmel Cancer Center in an effort to further individualize therapy and avoid over-treating patients.”
“Over the course of a lifespan, from conception to death, each person encounters a wide variety of environmental stressors such as pollution, tobacco smoke, the sun’s rays, pharmaceutical agents and some constituents of food. Evidence of the exposure and a person’s ability to metabolize these stressors is all hiding in the urine.”
“Chuck Jaffe, MD, CEO of Health Level 7, couldn’t have anticipated the rush to adoption of the FHIR standard, solidified by the rules recently proposed by federal agencies to use it as a basis for achieving interoperability in healthcare. Now, Jaffe sees more benefits ahead as FHIR can play a key role in other areas of healthcare.”
“Good news if you hate needles. Vaccinations, insulin injections, or intravenous drips could one day be replaced by smart pills that inject the medicine directly into your stomach.
What’s new: Many pharmaceutical compounds simply aren’t suited to being taken orally, because they can’t survive the stomach’s harsh, acidic environment. A new device could overcome that problem, allowing virtually any medication to be swallowed, according to a paper published in Science this week.”
“Referring physicians who have the option to send women for breast MRI are unclear on the exam’s clinical usefulness. That goes for specialists as well as primary-care providers. However, at an academic hospital system in Boston, all referring providers have been ordering more breast MRI since Massachusetts began requiring mammographers to inform patients in writing of their breast density.
So found breast radiologists at Beth Israel Deaconess Medical Center when they surveyed their referral base. The Harvard researchers had their findings published online in The Breast.”
“We hear a lot about breast cancer but how much do we really know that explains what we hear? Do you know the different types of breast cancer or what the different stages really mean?
According to the American Cancer Society, breast cancer is broken down into 2 main categories – in situ and invasive. In situ means it is still contained in the infected tissue and invasive means that it has spread to other areas.”
“Be it films, digital images, or integrated file-sharing systems, radiology has historically been the leader in applying technological advancements to workflow and patient care. That trend shows no slackening.
According to industry leaders, 2019 will again be a year where you’ll be introduced to new technologies and see wider-spread implementation of new tools to enhance the way you work and provide services to your patients.
Here are several technologies to consider investing in this year and beyond.”
“A mind-altering medication related to the club drug Special K won U.S. approval Tuesday for patients with hard-to-treat depression, the first in a series of long-overlooked substances being reconsidered for severe forms of mental illness.
The nasal spray from Johnson & Johnson is a chemical cousin of ketamine, which has been used for decades as a powerful anesthetic to prepare patients for surgery. In the 1990s, the medication was adopted as a party drug by the underground rave culture due to its ability to produce psychedelic, out-of-body experiences. More recently, some doctors have given ketamine to people with depression without formal FDA approval.”
“For more than a decade, the specter of unnecessary imaging and over-utilization has plagued radiology. Not only has it been costly, but it’s also exposed countless patients to unneeded—and cumulatively harmful—radiation.
But, with radiologists being the gatekeepers to advanced imaging services, it begs the question: how much responsibility do you, as providers, have in controlling how much imaging is ordered and completed within the healthcare environment? And, what, if anything, can you do to ensure your referring physicians and your facility overall aren’t contributing to the problem?
According to several industry leaders, it’s a role you’re obligated to take on.”
“An imaging procedure commonly performed before starting cancer treatment can provide valuable clues about a patient’s risk for heart problems in the months and years after treatment. However, this information is not always reported and is rarely acted upon in current practice, according to research being presented at the American College of Cardiology’s 68th Annual Scientific Session, March 16-18 in New Orleans.”
“Breast cancer prediction models based on family history are more effective than those that do not focus on that information, according to a new study published in The Lancet Oncology.
The authors studied data on more than 15,000 women from Australia, Canada and the United States who belonged to the Breast Cancer Prospective Family Study Cohort. All women analyzed for the study were between the ages of 20 and 70, did not have breast cancer when they were recruited into the cohort and had an available family history of breast cancer.”
“Second-opinion breast MRI reviews by subspecialized radiologists can improve patient management and increase cancer detection, according to findings published in the Journal of the American College of Radiology.
“Breast imaging is subject to interobserver variability, and studies show breast imaging specialists detect more cancers than general radiologists,” wrote author R. Jared Weinfurtner, MD, Moffit Cancer Center in Tampa, Florida, and colleagues.”
“Women with type 2 diabetes are more likely than those without to develop more advanced, aggressive forms of breast cancer, Reuters reported of a study Feb. 27.
The study, which involved 6,267 women diagnosed with breast cancer between 2002 and 2014, examined the likelihood of developing advanced cancers when diabetes was present versus when it wasn’t. A quarter of the women recruited for the study had been previously diagnosed with diabetes.”
“Breast imaging subspecialists and general radiologists who interpret breast images should adhere to the unique lexicon of the American College of Radiology Breast Imaging Reporting and Data System Atlas (ACR BI-RADS®). The atlas was designed to ensure that breast findings are appropriately analyzed and correctly designated to one of seven BI-RADS categories, each of which implies a specific management recommendation. BI-RADS 3 was created to help reduce the number of false-positive biopsies, while maintaining a high rate of early cancer detection.”
“Long before memory loss occurs in patients with Alzheimer’s, the protein amyloid-beta—which has been implicated in the formation of brain tangles that characterize the disease—starts building up in the spinal fluid. Problem is, detecting the protein there requires an invasive procedure that’s done under anesthesia, making it impossible to deploy on a widespread basis for the early detection of Alzheimer’s.
Researchers at IBM in Australia have developed an alternative to spinal fluid testing: a blood test that they say could predict the buildup of amyloid-beta in spinal fluid with up to 77% accuracy.”
“Researchers at Duke Eye Center have demonstrated how a noninvasive imaging technique can rapidly detect changes to the retina that can indicate Alzheimer’s disease (AD). The technique, known as optical coherence tomography angiography (OCTA), detects changes to or deterioration of the tiny blood vessels at the back of the eye, and is being used by researchers to study the connection between the retina and Alzheimer’s disease.”
“The FDA has granted accelerated approval to the combination of atezolizumab, an antibody marketed by Genentech under the name Tecentriq, and chemotherapy for certain patients with metastatic triple-negative breast cancer. For patients to be eligible, it must be determined by an FDA-approved test that the cancer is PD-L1 positive.
“The Tecentriq regimen is an exciting new treatment option for certain people living with metastatic triple-negative breast cancer, a difficult-to-treat form of the disease,” Hayley Dinerman, executive director of the Triple Negative Breast Cancer Foundation, said in a prepared statement.”
“Doc, am I going to have a heart attack? This is one of the most common questions that patients ask in my office. The truth is, I have no way of predicting the future. They could have a heart attack at any time for all I know. I empathize with their worries, but once I have optimized their risk factors I am often stuck telling them something along the lines of, Well, I don’t have a Magic 8 Ball, but as far as I can tell, you’re doing just fine. Although no test can predict the future, the coronary artery calcium scan (CACS) is near the front of the pack in this regard. Why? Because a coronary artery calcium score outperforms all other risk factors used today in predicting future cardiovascular events.”
“CT scans can reveal valuable information about a patient’s heart health, even if the scan was not specifically ordered for that purpose. According to findings to be presented at the American College of Cardiology’s 68th Annual Scientific Session (ACC.19), however, radiologists do not always include heart-related findings in their reports.
“This is essentially free information because the patients are undergoing the CT scans anyway, and we’d like to see it reported more frequently,” Matthew Hooks, MD, a resident physician at the University of Minnesota in Minneapolis and the study’s lead author, said in a prepared statement.”
“A deep neural network crafted by research specialists at Dartmouth’s Norris Cotton Cancer Center identified different types of lung adenocarcinoma as well as practicing pathologists in a recent study, according to work published March 4 in Scientific Reports.
“Classification of histologic patterns in lung adenocarcinoma is critical for determining tumor grade and treatment for patients,” first author Jason W. Wei and colleagues wrote in the journal. “However, this task is often challenging due to the heterogeneous nature of lung adenocarcinoma and the subjective criteria for evaluation.””
“Most women are willing to wait for their screening mammogram results after the exam or receive their test results within 48 hours, according to new research published in the Journal of the American College of Radiology.
Researchers led by Biren A. Shah, MD, a radiologist at the Virginia Commonwealth University Health System in Richmond, Virginia, also found from survey responses from 2,245 screening mammography patients 18 years and older that most (85.4 percent) preferred to receive abnormal screening mammogram results on a Friday—even if they couldn’t come in for a diagnostic workup until the following week. ”
“Artificial intelligence (AI) systems can achieve a cancer detection accuracy similar to that of an average breast radiologist, according to new findings published by the Journal of the National Cancer Institute.
“Considering the increasing scarcity of radiologists in some countries, including breast screening radiologists, alternative strategies to allow continuation of current screening programs are required,” wrote Alejandro Rodriguez-Ruiz, MSc, Radboud University Medical Center in the Netherlands, and colleagues. “In addition, it is of paramount importance to prevent visible lesions in digital mammography (DM) being overlooked or misinterpreted.””
“A group of imaging societies, including the American College of Radiology (ACR) and Society for Imaging Informatics in Medicine (SIIM), came together to publish a draft document guiding a future of ethical AI.
The European Society of Radiology, RSNA, European Society of Medical Imaging Informatics, Canadian Association of Radiologists and American Association of Physicists in Medicine also worked on establishing the consensus document titled “Ethics of AI in Radiology: European and North American Multisociety Statement.””
“Currently, lung adenocarcinoma requires pathologist’s visual examination of lobectomy slides to determine the tumor patterns and subtypes. This classification has an important role in prognosis and determination of treatment for lung cancer, but it is a difficult and subjective task, according to Saeed Hassanpour, PhD, assistant professor of biomedical data science at Dartmouth Geisel School of Medicine.
Using recent advances in machine learning, the scientists, led by Hassanpour, developed a deep neural network to classify different types of lung adenocarcinoma on histopathology slides, and found that the model performed on par with three practicing pathologists.”
“Nearly all commercially insured women between the ages of 40 and 74 had access to screening mammography without cost sharing after the Affordable Care Act (ACA) was signed into law, according to new research published by the Journal of the American College of Radiology. However, the authors noted, mammography utilization has dropped in recent years due to another significant policy shift.
When the ACA was signed in 2010, it required healthcare plans to eliminate cost sharing for preventive services such as mammography when the service received an “A” or “B” rating from the U.S. Preventive Services Health Task Force (USPSTF). The USPSTF, meanwhile, changed annual screening for women between the ages of 40 and 49 from a “B” rating to a “C” in 2009, leaving the costs associated with such screening in question.”
“Several imaging societies, including the American College of Radiology (ACR) and European Society of Radiology, have published a consensus draft document focused on the ethics of AI in radiology.
RSNA, the Society for Imaging Informatics in Medicine, the European Society of Medical Imaging Informatics, the Canadian Association of Radiologists and the American Association of Physicists in Medicine all also contributed to the document, which is available to read on the ACR’s website.”
“A unique partnership between a Virginia Tech scientist and a University of Virginia oncologist could result in a solution to reduce discomfort during cancer treatment for women.
Tim Long, a professor of chemistry with the Virginia Tech College of Science, and Tim Showalter, a radiation oncologist at UVA’s Cancer Center, are testing a gel that could be used during radiation treatment for cervical cancer.”
“Eight chief medical information officers discuss voice recognition technology and how it could impact the healthcare industry, from clinical documentation to decision support tools.”
“A team of researchers surveyed more than 2,500 women before they underwent screening mammography, asking them about anxiety, how often they think about breast cancer and more. The authors, sharing their findings in the Journal of the American College of Radiology, noted the results could help influence shared decision-making related to breast cancer and breast cancer screening.
The researchers received responses from 2,747 women from five different breast imaging facilities. All surveys occurred between Sept. 1, 2016, and March 31, 2017. More than 51 percent of respondents had no major known breast cancer risk factors, and more than 78 percent had no personal history of breast cancer.”
“Mammography is an essential screening and diagnostic tool for the detection of breast cancer and the assessment of breast density. But according to Victoria L. Mango, MD, a breast radiologist at Memorial Sloan Kettering Cancer Center in New York City, AI can help breast imagers and physicians see beyond basic breast density information provided by mammographic images and improve clinical management overall.
Although federal law now requires mammography facilities to include breast density information in reports for patients and their physicians, mammography screening recommendations are dependent on a women’s age and it can be difficult to determine which women with dense breasts will benefit the most from supplemental testing, according to Mango.”
“A new, noninvasive technique for imaging the carotid artery can offer insight into plaque characteristics in real time, leading one researcher to suggest the modality could become as popular as ultrasound.
That researcher, Daniel Razansky, PhD, and co-authors published their early experience with volumetric multi-spectral optoacoustic tomography (vMSOT) on Feb. 12 in Radiology. The new technique involves holding a handheld device to a patient’s neck as spectroscopy provides images up to 30 mm deep, which is enough to visualize the carotid bifurcation area in most patients, Razansky and co-authors wrote. Many ischemic strokes are related to carotid artery disease originating from that area.”
“Radiologists are mildly happy at work compared to other physician specialties, according to Medscape’s 2019 Radiology Lifestyle, Happiness & Burnout Report, with only 25 percent claiming to be “very or extremely happy” in the workplace.
Medscape surveyed more than 15,000 physicians spanning 29 specialties for their annual report released in January. Their radiology-specific report was published Feb. 20, and in it, radiology ranked 20th among all specialties in terms of workplace happiness. Infectious disease specialists and anesthesiologist ranked alongside radiologists. Plastic surgeons and preventative health specialists were most happy at work, while internal medicine, emergency medicine and rehabilitation specialists rounded out the bottom.”
“For AI to become clinically feasible in women’s imaging, it must excel in the areas of performance, time, workflow and cost, according to an opinion piece published online Feb. 19 in the American Journal of Roentgenology.
The adoption of any new technology must achieve certain metrics to become viable and quantify its impact, wrote authors Ray C. Mayo, MD, and Jessica W. T. Leung, MD, each with the department of diagnostic radiology at The University of Texas MD Anderson Cancer Center in Houston.”
“Researchers have created a machine learning model that identified 98 percent of malignant atypical ductal hyperplasia (ADH) lesions prior to surgery, according to a single-center study published in JCO Clinical Cancer Informatics. The approach saved 16 percent of women from unnecessary surgery.
Lead researcher Saeed Hassanpour, PhD, of Dartmouth University in Hanover, New Hampshire and colleagues analyzed 128 lesions from 124 women with core needle biopsy-confirmed ADH who also underwent surgery.”
“Radiologists who interpret traditional two-dimensional (2D) mammograms required little time in transitioning to reading digital breast tomosynthesis (DBT) exams, or three-dimensional (3D) mammograms, and improved their accuracy in detecting cancer, according to research published online Feb. 26 in Radiology.
The study, led by Diana Miglioretti, PhD, dean’s professor of biostatistics at the University of California Davis Department of Public Health Services, found these radiologists also recalled patients for additional testing at a lower rate on DBT than 2D mammography regardless of whether patients did or did not have dense breasts. ”
“Ultrasound scans of the calcaneus—or the heel bone—were equal to results gathered from dual-energy x-ray absorptiometry (DXA) for assessing bone health, according to new research published online in the March issue of The Journal of the American Osteopathic Association.
The study suggests that ultrasound could be offered as a low-cost, more accessible method of screening for osteoporosis and other bone diseases, wrote researchers led by Carolyn Komar, PhD, associate professor of biomedical sciences at the West Virginia School of Osteopathic Medicine in Lewisburg.”
“There are four areas in which AI must excel to become clinically viable in women’s medical imaging—particularly mammography: performance, time, workflow and cost, according to an opinion article published in the American Journal of Roentgenology.
“AI holds tremendous potential for transforming the practice of radiology, but certain metrics are needed to objectively quantify its impact,” wrote authors Ray C. Mayo, MD, and Jessica W.T. Leung, MD, of the University of Texas MD Anderson Cancer Center in Houston. “As patients, physicians, hospitals and insurance companies look for value, AI must earn a role in medical imaging.”
“Genetic testing should be available for all breast cancer patients to determine hereditary risk in addition to standard imaging exams, according to new guidelines published Feb. 14 by The American Society of Breast Surgeons.
The new recommendations are based on an extensive review of supporting research, especially a study published in the Journal of Clinical Oncology in December which found that patients who met existing National Comprehensive Cancer Network (NCCN) clinical testing criteria had similar rates of genetic mutations in breast cancer genes as patients who did not meet the criteria.”
“When President Donald Trump signed a federal funding bill into law on Feb. 15, it included text that said that all mammography providers must include updated information about breast density in reports sent to both patients and their physicians.
The notifications sent out to patients will inform them about their own personal breast density and explain the importance of that information. More than 30 states currently require such information to be shared with patients after they undergo a mammogram, a number that has been rising steadily for years.”
“DEER PARK, N.Y., Feb. 19, 2019 /PRNewswire/ — National breast density inform legislation was enacted as part of the funding bill signed into law on February 15. The Federal legislation will require mammography facilities to include up-to-date information about breast density in mammography reports provided to patients and their physicians. This follows 36 state laws that require communication about breast density to women after their mammogram, according to DenseBreast-Info.org.
As announced by Senator Dianne Feinstein (CA) on February 16, “As part of the funding bill Congress passed yesterday, the FDA must now ensure mammography reports include appropriate breast-density information. Dense tissue can hide cancer on mammograms, so this information is vital to catching breast cancer early.””
“Speech recognition has become a staple software category in radiology over the past three decades, and other medical specialties have adopted it as well. Yet efforts to assess the toolset’s applications and adaptations have been frustrated by the lack of a unified set of metrics.
Thanks to the resulting jumble, the time is ripe to put speech recognition under a focused research microscope for a full examination.
So suggest the authors of a study published online in the Journal of the American Medical Informatics Association.”
“Imaging follow-up protocols vary greatly by institution and radiologist after benign, concordant MRI-guided percutaneous core needle biopsies (MR-PCNB), according to research published online Feb. 7 in the Journal of the American College of Radiology.
Because no consensus guidelines for imaging follow-up protocols after benign concordant MR-PCNB exist, conflicting data and unclear management guidelines can lead to variability in radiology practices and uncertainty among breast radiologists and their patients, wrote lead author Bhavika K. Patel, MD, of the Mayo Clinic in Phoenix, and colleagues. “
“Significant complications are rarely associated with stereotactic vacuum-assisted breast biopsies (SVABs), according to new research published in the American Journal of Roentgenology.
The study’s authors wrote that unnecessary biopsies and complications related to biopsies are often cited as potential harms of mammographic breast cancer screening, and the U.S. Preventive Services Task Force (USPSTF) specifically used such issues to help explain why it changed its mammography recommendations in 2009. Noting that there has not been much recent research on this specific topic, the team wanted to explore how often such complications occur.”
“A molecular imaging technique using PET technology may improve how the efficacy or failure of hormone therapy is measured for breast cancer patients, according to research published online in the February issue of The Journal of Nuclear Medicine.
Researchers from the University of Wisconsin School of Medicine and Public Health in Madison, Wisconsin, found that positron emission tomography (PET) imaging with 18F-fluorofuranylnorprogesterone (18F-FFNP) can successfully measure changes in progesterone receptor (PR) levels which results from a short-course estrogen treatment, also known as an estradiol challenge.”
“A mobile breast cancer screening unit will soon tour the United Arab Emirates to offer free consultations, mammography screenings and genetic testing for men and women.
According to a recent report from the English-language daily news outlet The National, The Pink Caravan, established in 2011, will have 30 buses filled with nurses and clinicians traveling between February 21 and March 2 to promote early breast cancer diagnosis. A fixed clinic will also be providing services in Abu Dhabi during that time.”
“Dear Dr. Jaffee:
Thank you for collaborating in accelerating standards. Recognizing the importance of your work in moving forward to a truly collaborative, interoperable health system that supports patients in seeking low cost, high quality care, the Centers for Medicare & Medicaid Services (CMS) is excited to contribute our priorities for the upcoming year. Top of mind for CMS is ensuring the seamless flow of data, not only from provider to provider, but also including payers, beneficiaries and the opportunity to facilitate innovation by unleashing data for use by researchers, application developers and others. The CMS priorities that will continue to be highlighted in our work this year are:”
“A 14-layer convolutional neural network (CNN) trained on MRI and pathology data accurately predicted the molecular subtype of breast cancers, according to a Jan. 31 study published in the Journal of Digital Imaging. The method may help personalize treatment plans for the disease.
Trained on available breast MRIs and immunohistochemical (IHC) staining pathology data of 216 patients with known breast cancer, the CNN predicted breast cancer subtype with 70 percent accuracy. A balanced holdout set of 40 patients was used as the testing set.”
“Small cell lung cancer (SCLC) develops mostly in smokers and is so aggressive it almost always becomes resistant to chemotherapy and radiation. The disease is widely believed to originate from pulmonary neuroendocrine cells (PNECs), but they have proven difficult to generate in the lab, making it challenging for oncology researchers to study SCLC and find new therapies.
Researchers from Weill Cornell Medicine in New York have figured out how to grow PNECs from human embryonic stem cells—and in so doing they’ve gained new insight into two genes that are commonly mutated in SCLC. They believe their new model of the disease will be useful for fine-tuning treatments at various stages of tumor development.”
“MacroGenics (MGNX) shares soared on positive results from Sophia, its late-stage clinical study of the efficacy of margetuximab in patents with HER2-positive metastatic breast cancer.
Shares rose 130.4% to $25.60 by the close of trading on Wednesday.
SVB Leerink analyst Jonathan Chang wrote in a note that “little value for the drug in the indication was represented in the stock going into the results,” according to Bloomberg. Nomura sees the stock between $19 and $28 on positive Sophia results, Bloomberg says. Nomera and Leerink played lead roles in MacroGenics’ public offering of 4,500,000 common shares priced at $21.25 in March 2018.”
“Although online portals allow some patients to easily access their radiology reports, a recent study published online Jan. 8 in the American Journal of Roentgenology found that lumbar spine MRI reports in particular are written at a reading level too advanced for the average patient to comprehend.
The National Institutes of Health and the American Medical Association recommend all patient education materials and reports be written at or below a six-grade reading level because the average U.S. adult reads at an eighth-grade level.”
“Researches from Peter the Great St.Petersburg Polytechnic University (SPbPU), Russian Academic Excellence Initiative participant, in collaboration with the radiologists from St.Petersburg Clinical Research for Specialized Types of Medical Care (Oncological) have developed an intelligent software system for lung cancer diagnostics. This software can be installed on any computer. It analyzes patients’ computed tomography (CT) results within 20 seconds and provides an image in which the pathology is clearly marked. Reserachers have named the system Doctor AIzimov (AI for Artificial Intelligence) in honor of the science-fiction writer Isaac Asimov, who developed three famous laws of robotics.”
“Researchers of the laboratory “Medical ultrasound equipment” of Peter the Great St. Petersburg Polytechnic University (SPbPU) developed a high-tech device-transformer for ultrasound examination, named “Ultrasound mobile”. The new equipment is the combination of three modifications in one device.
Currently, each modification functions separately in the medical centers, the scientists of St. Petersburg Polytechnic University became the first who combined it into a single hardware complex. Thus instead of two types of vehicles (stationary and portable), medical institutions can use single equipment for different purposes and in different wards.”
“More consistent follow-up protocols after benign concordant MRI-guided percutaneous core needle biopsies (MR-PCNBs) could lead to better overall patient care, according to a case study published in the Journal of the American College of Radiology.
“If radiologic-pathologic correlation is concordant with benign pathology, then patients may be recommended for imaging follow-up to confirm stability of imaging findings and to aid in early diagnosis of potentially false-negative results,” wrote Bhavika K. Patel, MD, Mayo Clinic in Phoenix, Arizona, and colleagues. “Studies have reported up to a 4 percent false-negative MR biopsy rate.””
“People who have had one melanoma are much likelier to develop future skin cancers.
Researchers from Queen Mary University of London have discovered why—and found a potential therapeutic target to keep this aggressive cancer from coming back.
Melanomas are considered the most dangerous form of skin cancer by experts. When caught early, it is almost always curable. However, it can be difficult to treat once it has spread to other parts of the body.
Approximately 178,560 cases of melanoma were diagnosed in the United States in 2018.”
“The FDA has published a new letter to providers in radiology, pathology, emergency medicine and several other specialties with updated information related to breast implant associated-anaplastic large cell lymphoma (BIA-ALCL).
Patients are at “an increased risk” of developing BIA-ALCL “within the scar capsule adjacent to the implant,” according to the document, which is signed by William Maisel, MD, MPH, CMO of the FDA’s Center for Devices and Radiological Health.”
“When primary care physicians (PCP) interact with their patients at a high level, it leads to improvements in breast cancer screening adherence for all racial and ethnic minority groups, according to new findings published in the Journal of the American College of Radiology.
“As the United States continues to become increasingly diverse, understanding factors that affect access to routine screening mammography is an important step in improving breast cancer disparities among racial/ethnic minority groups,” wrote Efrén J. Flores, MD, department of radiology at Massachusetts General Hospital in Boston, and colleagues.”
“Engineers at the University of Wisconsin (UW)–Madison developed a wound dressing, which uses the energy it harvests to send gentle electrical pulses to an injury site, treatment that helps significantly speed healing, they said in a UW news release.
Indeed, in tests on rodents, the so-called “e-bandage” reduced healing of wounds to three days instead of the usual two weeks it takes for them to completely heal, said Xudong Wang, a professor of materials science and engineering at UW–Madison who led the research.”
“Russian researchers from the Peter the Great St. Petersburg Polytechnic University (SPbPU) and radiologists from St. Petersburg Clinical Research for Specialized Types of Medical Care developed AI software that can distinguish and subsequently mark lung cancers on a CT scan within 20 seconds.
The AI software, dubbed Doctor AI-zimov, can detect lung nodules as small as 2 millimeters on CT scans, according to a prepared statement issued by SPbPU.”
“Interactive, multi-media reporting is readily available within radiology workstations today – yet the majority of diagnostic imaging reports in the UK remain text based. In fact, the format of medical imaging reports created by most radiology departments has not changed much in over 100 years.
But this status quo is about to change. In the short and long term, reporting will undergo a considerable transformation.”
“Upcoming legislation mandating the use of a clinical decision support (CDS) system when ordering advanced imaging tests could affect up to six million emergency department visits annually, according to estimates published in a Jan. 29 Radiology study. The law is set to go into effect in January 2020.
Congress passed The Protecting Access to Medicare Act (PAMA) in 2014, which put forth rules for CMS to establish the Appropriate Use Program for CDS systems that will be implemented in U.S. health systems serving Medicare beneficiaries. Providers who do not consult with a compliant CDS system will not be reimbursed for advanced imaging studies, according to the legislation.”
“Previously established frameworks for creating breast cancer screening bundled payment models are achievable, according to a new study published in the Journal of the American College of Radiology. The approaches could also incorporate the rise of digital breast tomosynthesis (DBT).
In the study, researchers set out to evaluate the feasibility of a mammography bundled payment model and how a model for breast cancer screening created prior to widespread DBT adoption would fare after institutions have embraced the breast cancer screening method.”
“OncoCyte has delivered new positive results from a study of its DetermaVu blood test for lung cancer, which is designed to rule out patients who have a suspicious lung nodule but do not require an immediate biopsy.
The test showed 90% sensitivity in spotting malignant nodules in a prospective study and 75% specificity in identifying those that were benign out of a cohort of 250 patient samples. In addition, the test made its determinations without including any clinical factors in its algorithm, such as the size of the lung nodule, the company said.”
“About one-quarter of adults in the world will experience a stroke in their lifetime, according to new estimates from the Global Burden of Disease Study (GBDS) published online Dec. 20 in the New England Journal of Medicine.
The GBDS 2016 used all available epidemiologic data to assess health loss from 328 diseases across 195 countries and territories from 1990 through 2016. With this information, corresponding author Gregory A. Roth, MD, and colleagues sought to calculate the cumulative lifetime incidence of a first stroke—including ischemic or hemorrhagic strokes—among adults 25 or older.”
“The implementation of digital breast tomosynthesis (DBT) at eight radiology facilities in Vermont led to lower recall rates than full-field digital mammography (FFDM) alone, according to a new study published in the American Journal of Roentgenology. However, the authors observed no improvements in cancer detection rates.
The authors explored data from the Vermont Breast Cancer Surveillance system, including more than 97,000 FFDM examinations and more than 86,000 DBT examinations from 2012 through 2016.”
“New research involving breast cancer patients in the U.S. Military Health System found that black women wait longer to undergo breast cancer surgery after being diagnosed with the disease than white women, according to a study published Jan. 23 in JAMA Surgery.
Researchers led by Kangmin Zhu, MD, PhD, of the John P. Murtha Cancer Center at the Uniformed Services University of the Health Sciences in Rockville, Maryland, noted that the longer time to surgery, however, did not account for the observed racial disparity in overall survival.”
“Bayer is going to the Super Bowl. Not with some glitzy $5 million TV ad, but instead with a print ad in the official Super Bowl LIII program to launch its new awareness campaign around genomic testing for cancer.
The “Test Your Cancer” campaign soft launch begins with the Super Bowl ad along with focused digital ad buys in an effort to make people aware of genomic testing options for solid tumor cancer patients.”
“A new article published in Radiology explores the barriers patients face in undergoing lung cancer screening (LCS), and more importantly, what radiologists can do to encourage their participation.
“Radiologists are essential to every LCS program,” wrote Gary X. Wang, of Massachusetts General Hospital in Boston, and colleagues. “Increased awareness of challenges faced by patients and referring providers will empower radiologists to continue to collaboratively guide nationwide multidisciplinary efforts to implement LCS.””
““The only real cure for cancer is finding it early,” said Padma Sundar, vice president of strategy and market access at CellMax Life, in an interview with MD+DI. In terms of colorectal cancer, she said it takes a long time for an adenoma to develop into cancer, so early detection of these adenomas can be lifesaving.”
“iCAD, Inc. (NASDAQ: ICAD), a global medical technology leader providing innovative cancer detection and therapy solutions, today announced the results of a long-term study conducted at Hoag Memorial Hospital Presbyterian with the Xoft® Axxent® Electronic Brachytherapy (eBx®) System® for the treatment of early-stage breast cancer using intraoperative radiation therapy (IORT).”
“Follow-up recommendations in radiology reports commonly contain little standardization. Machine learning and deep learning (DL) methods are each effective for deciphering reports and may provide the foundation for real-time recommendation extraction, according to a recent study in the Journal of the American College of Radiology.
“Radiology reports with follow-up recommendations are difficult to identify, in part because of their free-text nature and their lack of standardized structure and content,” wrote first author Emmanuel Carrodeguas, MD, of Harvard Medical School in Boston, and colleagues…””
“Scientists at the LSU Health New Orleans School of Medicine have found a new role for a protein in preventing the growth and spread of breast cancer. The results of the study (“Exosomes from Nischarin-Expressing Cells Reduce Breast Cancer Cell Motility and Tumor Growth”), which researchers believe could have a significant impact on cancer therapy, were published in the OnlineFirst section of Cancer Research…”
“Oncology researchers have long believed that “dormant” breast cancer cells—those that have stopped dividing and are merely hiding out in the body—are unresponsive to chemotherapy. Yet those inactive cancer cells can wake up at any time and cause life-threatening metastases.
Scientists at the Fred Hutchinson Cancer Research Center say they’ve figured out how to prevent dormant breast cancer cells from ever waking up, and that the key is to disrupt a signaling system in blood vessels that protects the cells as they sleep…”
“A team of researchers from the University of Illinois at Urbana-Champaign has developed a portable optical imaging system that can visualize molecular features of breast tissue after it’s been surgically removed from a patient, according to research published online Dec. 19 in Science Advances.
Able to track tumor progression, the tool may provide cancer researchers more in-depth information regarding cancer tissue pathology and diagnostics in real-time…”
“Breast-specific gamma imaging (BSGI) performed with comparable sensitives in detecting residual tumor compared to breast MRI, and may be a more useful tool for predicting a complete pathologic response to neoadjuvant chemotherapy (NAC) in those with breast cancer, according to research published online Jan. 8 in the American Journal of Roentgenology.
BGSI is a relatively new nuclear medicine imaging tool that can be used as a complementary modality for initial breast cancer diagnosis, according to Shannon Kim, MD, radiologist at Eastern Virginia Medical School, and colleagues. The authors noted, however, that few studies have compared the accuracy of BSGI and breast MRI for such clinical situations…”
Breast cancer represented 15.3% of all new cancer cases and 6.7% of all cancer deaths in 2018. There were an estimated 266,120 new cases of breast cancer in the U.S. and an estimated 40,920 deaths.
“A novel technique that uses mammography to determine the biological tissue composition of a tumor could help reduce unnecessary breast biopsies, according to a new study appearing in the journal Radiology.1
Mammography has been effective at reducing deaths from breast cancer by detecting cancers in their earliest, most treatable stages. However, many women are called back for additional diagnostic imaging and, in many cases, biopsies, for abnormal findings that are ultimately proven benign. Research estimates this recall rate to be more than 10 percent in the United States.”
“Lung cancer accounts for more deaths than any other cancer in both men and women and caused an estimated 436 deaths per day in the United States in 2014 (1). When diagnosed after symptoms occur, lung cancer is typically advanced, resulting in a dismal 5-year survival rate of 17.4% (2). Although lung cancer is one of the top four deadliest cancers and is curable when detected at an early stage, routine screening for lung cancer has not been performed until recently. Although multiple randomized trials had been conducted, no screening test had been shown to reduce lung cancer–specific mortality until the June 2011 release of data from the landmark National Lung Cancer Screening Trial (NLST) (Fig 1) (3,4).”
“Digital breast tomosynthesis (DBT) implementation in a diagnostic setting can result in an improved cancer detection rate (CDR) and more accurate biopsy recommendations, according to a new case study published in the Journal of the American College of Radiology.
“Although DBT may better characterize malignant and benign features, and therefore have the potential to decrease unnecessary imaging follow-up and ultimately benign biopsies, the current literature is inconsistent,” wrote Emily B. Ambinder, MD, of Johns Hopkins Medical Institutions in Baltimore, Maryland, and colleagues. “Therefore, we aimed to add to this important topic by assessing the impact of DBT on outcomes in the diagnostic setting.””
“Considering the continued focus on quality over quantity and the rise of online reviews, patient experience has never been more important in healthcare than it is today. A new study published by Radiology tracked one radiology department’s efforts to assess its own patient experience, identify improvement opportunities and make a difference.
“Studies in several radiology departments have cited various factors as important to patients including wait times, acknowledgment of concerns, friendliness of support staff, convenience of parking, and comfort of the waiting area,” wrote Neena Kapoor, MD, department of radiology at Brigham and Women’s Hospital in Boston, and colleagues. “However, it is unknown whether these factors are amenable to change or whether improving these factors can measurably improve patient experience.””
“The Vancouver risk calculator (VRC) offers superior guidance in predicting the risk of malignancy in patients receiving CT lung cancer screening compared to the American College of Radiology Lung Imaging Reporting and Data System (Lung-RADS), according to a new study.
Authors of the research, published Jan. 22 in Radiology, did report the Vancouver method was less specific and less accurate when it came to subsolid nodules.
In the study, researchers scored more than 4,400 nodules taken from 2,813 patients as part of the National Lung Screening Trial (NLST). The nodules were scored using VRC with nine parameters and Lung-RADS. Of the total, 4,078 nodules were solid, 330 were subsolid.”
“23andMe, Inc., the leading personal genetics company, today received FDA clearance for a genetic health risk report on a hereditary colorectal cancer syndrome.
The clearance follows the FDA’s authorization for 23andMe’s BRCA1/BRCA2 (Selected Variants) Genetic Health Risk report in March 2018. The MUTYH-Associated Polyposis report was submitted to the FDA using the 510(k) submission pathway, enabled by the BRCA decision in March 2018. These two reports are the only direct-to-consumer genetic health risk reports for inherited cancers that have been authorized or cleared by the FDA for use without prescription.”
“Healthcare organizations across the country are beginning to cash in on early efforts in artificial intelligence and data visualization.
First reports on initial efforts to use these advanced technologies show tantalizing potential.
At Massachusetts General Hospital researchers have developed an AI algorithm to rapidly diagnose and classify brain hemorrhages from unenhanced computed tomography scans, detecting acute incidents and offering prediction capabilities that eventually could help staff in hospital emergency departments evaluate patients with acute stroke symptoms.”
“Major breakthroughs are now possible with less data than ever thanks to artificial intelligence, Alphabet Chief Financial Officer Ruth Porat said during a panel at the World Economic Forum in Davos, Switzerland Tuesday.
Artificial intelligence “learns” patterns by ingesting typically large amounts of data and then using that information to complete a task, like sorting data into different buckets. Porat said less data is required than before to see impactful results from AI, citing a recent example of medical breakthrough aided by Alphabet technology.”
“Novel methods for early detection are critical for improving cancer treatments and outcomes. This is especially true for lung cancer, the most common cause of cancer death worldwide, with over 1.5 million deaths per year. Now, the world’s first genetic sequencing of precancerous lung lesions has allowed researchers for the first time, to discover the differences between the lesions that will become invasive and those that are harmless, and the subsequent development of a method that can accurately predict which lesions will become cancerous.
The work, published on January 21st in Nature Medicine, titled “Deciphering the genomic, epigenomic, and transcriptomic landscapes of preinvasive lung cancer lesions” may pave the way for very early detection and new treatments.”
“Pairing breast MRI with a test that characterizes breast cancer genes can lead to a more personalized treatment approach for patients with ductal carcinoma in situ (DCIS), reported authors of a recent study published in JAMA Oncology.
The study, which included 75 institutions, enrolled 339 women with DCIS on core biopsy who were also eligible for wide local excision (WLE) surgery. Patients received breast MRI before surgery and those results were considered when determining surgical choice. A test called the 12-gene DCIS score assay—a 10-year risk recurrence test on a scale of 0 to 100—guided radiotherapy recommendations.”
“Implementing digital breast tomosynthesis (DBT) can lead to fewer women being committed to short-term follow-up, according to new research published in Academic Radiology.
The authors explored BI-RADS classifications from a single institution that first made DBT available in September 2011. More than 11,000 breast cancer screening examinations with digital mammography (DM) from before implementation (Sept. 1, 2010 to August 31, 2011) were compared with more than 9,000 examinations with DBT and DM after implementation (Jan. 1, 2014 to June 30, 2015). All examinations were read by one of a team of five radiologists.”
“The College of American Pathologists released 11 new evidence-based clinical recommendations to help labs better use quantitative image analysis (QIA) in HER2 testing for breast cancer.
The first-ever guidelines put forth steps to validate QIA before implementing along with maintenance steps to assure quality and control while testing. The college recommends labs validate QIA results by comparing them to an alternative, validated method such as HER2 in-situ hybridization protocol or consensus images.”
“A CT angiography (CTA)-derived score that also incorporated the extent, location and composition of coronary plaque outperformed a model that focused only on the severity of stenosis, researchers reported Jan. 16 in JACC: Cardiovascular Imaging.
Coronary CTA reading is currently guided by the Coronary Artery Disease-Reporting and Data system (CAD-RADS), and that assessment is predicated mostly on the maximal degree of stenosis observed. However, lead author Alexander R. van Rosendael, MD, and colleagues noted that other coronary plaque characteristics including its location (proximal versus distal), composition (calcified, noncalcified or mixed) and the number of plaques have been linked to clinical outcomes in previous studies.”
“Invasive lobular, low-grade and HER-2-negative breast cancers are more detectable with digital breast tomosynthesis (DBT) than conventional full-field digital mammography (FFDM) when imaging patients with dense breasts, according to a new study published in the Korean Journal of Radiology.
The authors asked three blinded radiologists to review DBT and FFDM images from 288 patients with dense breasts with a mean age of 48.5 years. They reviewed the images during two separate review sessions held at least one month apart, making notes where they detected tumors. Two non-blinded radiologists then reviewed DBT and FFDM images as well as ultrasound and MR images. The non-blinded radiologists scored the work of each individual blinded radiologist to determine a “detectability score” for all of the malignancies.”
“Stationary digital breast tomosynthesis (sDBT), which allows views to be collected without moving the x-ray tube, leads to improved reader accuracy compared to mammography, according to new findings published in Academic Radiology.
“In 2016, about one-third of all screening evaluations included DBT, at which time a standard mammogram was also obtained in most cases,” wrote Yueh Z. Lee, MD, PhD, of the department of radiology at the University of North Carolina at Chapel Hill, and colleagues. “However, since combined imaging doubles the radiation dose and increases cost, work continues to improve DBT, with a goal of eliminating the need to collect a standard mammogram at the same time.””
“The U.S. Preventive Services Task Force (USPSTF) has published a draft recommendation statement and draft evidence review that says clinicians should offer “risk-reducing medications” to women at an increased risk for breast cancer. Those women should also be at a low-risk for any adverse effects associated with such medication, the USPSTF added.
This represents a “B” recommendation from the independent group. Offering women not at an increased risk for breast cancer risk-reducing medications gets a “D” recommendation, meaning it is not recommended.”
“Radiologists provide significant value. According to a new analysis published in the Journal of the American College of Radiology, however, the specialty is still judged by “checkbox metrics” that do not illustrate its true value.
Measuring value in healthcare is difficult, primarily because current payment programs are based on specific clinical processes. It’s even more challenging in radiology because it can be hard to connect a radiologist’s efforts to a patient outcome. So, what can be done to improve the daily discussion that revolves around value?”
“Spending on treating chronic conditions has skyrocketed in the United States, but it is an investment that has paid off for patients.
Researchers explored healthcare spending from 1996 to 2015, sharing their findings in Health Affairs. The team focused on spending associated with breast cancer, lung cancer, cerebrovascular disease, chronic obstructive pulmonary disease (COPD), diabetes, HIV/AIDS and ischemic heart disease. In 1996, for example, more than $1.9 billion was spent on treating breast cancer. That number jumped to more than $12.5 billion in 2015. Significant increases were found in all seven conditions, leading the researchers to wonder if more spending has led to better patient outcomes.”
“The Society of Breast Imaging (SBI) has issued a new policy statement on diversity and inclusion, emphasizing the belief that “all people for whom breast cancer screening is appropriate should receive the opportunity to undergo screening.”
The statement, produced by the SBI Communications and Advocacy Task Force, begins by noting that the most effective way to minimize the impact of breast cancer is for all women at an average risk to get annual screening mammograms beginning at the age of 40 and “continue as long as they are in good health.””
“Long wait times can negatively impact patient satisfaction, which then harms the patient-centered, value-based care imaging departments seek to provide. But collecting the necessary data for improvements can be difficult, according to the authors of a case study published in the Journal of Digital Imaging. At one large hospital-based outpatient breast imaging department, researchers implemented a real-time location system (RTLS) to pinpoint problems areas experienced when performing full field digital mammograms (FFDM) and digital breast tomosynthesis (DBT) exams.”
“A new collaboration between Johnson & Johnson Innovation and Veracyte, a genomic diagnostics company, will focus on the detection of lung cancer. The long-term agreement will be used to advance the development and commercialization of novel diagnostic tests to detect lung cancer at its earliest stages, when the disease is most treatable.”
“A research team funded by the US National Institute of Biomedical Imaging and Bioengineering (NIBIB) has devised a new biosensor to diagnose breast cancer less invasively compared to the existing needle biopsy approach.
The new biosensor chip, created by researchers from the Universities of Hartford and Connecticut, is designed to identify a breast cancer biomarker called HER-2 in the blood within 15 minutes.”
“Myriad Genetics presented new data on its EndoPredict test, saying it can accurately forecast which women with newly diagnosed ER-positive, HER2-negative breast cancer will see the most benefits from adjunctive chemotherapy.”
“About 250,000 people die per year due to preventable medical errors, and that’s the biggest motivator there is for more advanced interoperability, says one clinical IT leader. Stan Huff, M.D., chief medical informatics officer (CMIO) at the Salt Lake City, Utah-based Intermountain Healthcare for the past 31 years, has long been a top leader in his field. Working on the leadership team for a health system like Intermountain and serving as a co-chair of the HL7 Clinical Information Modeling Initiative (CIMI), while also having been a former member of the ONC Health IT Standards Committee, Huff has a wealth of knowledge coming from both provider- and standards-focused perspectives.”
“By using radiomics, Chinese researchers found that the diagnostic performance of mammography could improve and offer complementary information to radiologists regarding benign and malignant breast tumors, as reported in the Journal of the American College of Radiology on Dec. 5. Quantitative image analyses, such as computer-aided diagnosis (CAD) algorithms, are continually being developed to help radiologists more objectively and clearly interpret mammograms.”
“Do you have cancer or not? This seemingly simple question could be answered by a simple test that looks for just one DNA signature, an epigenetic pattern that emerges in every cancer. Even better, the test works on circulating free DNA, molecular fragments that drift through easily obtained body fluids…”
“GE Healthcare recently launched the Invenia automated breast ultrasound (ABUS) 2.0 system in the United States. This device is the only U.S. Food and Drug Administration (FDA)-approved ultrasound supplemental breast screening technology, according to GE, specifically designed for detecting cancer in dense breast tissue. When used in addition to mammography, Invenia ABUS can improve breast cancer detection by 55 percent over mammography alone.…”
(#16) RSNA 2018: Cryoablation shows early effectiveness for low-risk breast cancer treatment (Health Imaging November 29, 2018)
“Cryoablation—commonly called cryotherapy—demonstrated early effectiveness in treating women with low-risk breast cancer, reported researchers during a Nov. 29 session at RSNA’s 2018 Annual Meeting. The authors, led by Kenneth R. Tomkovich, MD, with CentraState Medical Center in Freehold, New Jersey, found one case of cancer recurrence out of 180 patients treated over the four-year study period, according to a prepared statement from RSNA. “If the positive preliminary findings are maintained as the patients enrolled in the study continue to be monitored, that will serve as a strong indication of the promise of cryotherapy as an alternative treatment for a specific group of breast cancer patients,” Tomkovich said in the statement…”
“Ground glass nodule detection has risen alongside CT’s increased use in lung cancer screening, but pulmonary GGNs can represent various abnormalities, wrote Chen-Lu Liu, MD, with Nanjing Medical University’s Department of Radiology, and colleagues. Therefore, an improved predictive model is sorely needed…”
(#14) Computer uses machine learning to analyze breast cancer images (AI in Healthcare November 20, 2018)
“With the help of machine learning, researchers were able to train a computer to analyze breast cancer images and classify tumors accurately, according to a study published in NPJ Breast Cancer.
The study was led by researchers at the University of North Carolina (UNC) Lineberger Comprehensive Cancer Center.
“Using artificial intelligence, or machine learning, we were able to do a number of things that pathologists can do at a similar accuracy, but we were also able to do a thing or two that pathologists are not able to do today,” Charles Perou, PhD, the May Goldman Shaw Distinguished Professor of Molecular Oncology, professor of genetics, and of pathology and laboratory medicine at the UNC School of Medicine, said in a statement. “This has a long way to go in terms of validation, but I think the accuracy is only going to get better as we acquire more images to train the computer with…”
“Researchers at the State University of New York at Stony Brook have demonstrated a deep-learning algorithm that can quickly diagnose early-stage lung cancer on CT scans by combining computerized self-trained tumor identification with engineered identification of specific tumor features such as texture…”
“The husband-and-wife duo led the development of a new technique called Precision Breast intraoperative radiation therapy (IORT), which reduces weeks of radiation treatments for patients by adding high-powered imaging to radiation therapy. It is also meant to help spare healthy tissue and organs from being exposed to unnecessary radiation during the imaging process. Development of this new technique first began back in 2014…”
“For the study, researchers trained and tested a deep-learning CNN on how well it could diagnosis skin lesions with melanoma or as benign nevi based on a test set of 100 images. They then compared the CNN’s performance to 58 dermatologists, including 30 experts from 17 different countries…”
“Researchers from Washington University in St. Louis, Missouri used photoacoustic tomography with ultrasound, or photoacoustic imaging, to detect and diagnose early stage ovarian cancer, according to a recent university press release.
Quing Zhu, PhD, professor of biomedical engineering and radiology, at Washington University in St. Louis, and researchers hope the new diagnostic imaging technique could improve early detection in patients with ovarian cancer and help reduce unnecessary surgical intervention, medical costs and improve women’s quality-of-life, according to research published online in the September issue of Radiology…”
“New research published in the Journal of the American College of Radiology suggests that patients place great importance in learning about their imaging results, even if the findings do not directly impact their healthcare. The knowledge obtained from these tests is viewed as “a valuable outcome…”
“Around the world, MRI scanners reaching beyond 10.5 Tesla are being used and developed to produce detailed images of the human brain, and soon the entire human body. There are only three of the $14 million 10.5 Tesla scanners in existence, though all are continuing to push MRI to new limits of magnetic strength, according to an article published Oct. 31 by Nature.com…”
“The American College of Radiology Data Science Institute (ACR DSI) announced Friday, Oct. 26 the release of a series of standardized artificial intelligence (AI) use cases to advance imaging in AI, according to an ACR release. “The ACR DSI use cases present a pathway to help AI developers solve health care problems in a comprehensive way that turns concepts for AI solutions into safe and effective tools to help radiologists provide better care for our patients,” said Bibb Allen Jr., MD, ACR DSI Chief Medical Officer…”
“A large Phase III trial, the Impassion130 trial, has produced results supporting the use of chemotherapy plus immunotherapy as first-line treatment in certain patients with triple-negative breast cancer. The trial evaluated the combination of nab-paclitaxel, which is a chemotherapy drug, and atezolizumab, which is a checkpoint inhibitor. Together, the chemotherapeutic and the checkpoint inhibitor performed better than the chemotherapeutic alone. They increased both progression-free survival and overall survival…”
“More than a decade ago, scientists at the National Cancer Institute began investigating the idea of using patients’ own immune cells to treat their HER2-positive cancers. The technique involved taking dendritic cells from their blood, then genetically modifying them to produce parts of the HER2 protein. The hope was that if the modified cells were then introduced back to the patient, they would generate an immune response against the cancer…”
“The American College of Radiology Data Science Institute (ACR DSI) recently released of a series of standardized artificial intelligence (AI) use cases to help advance imaging in AI. Down the road, they could help create an “AI ecosystem” for radiology, wrote Bibb Allen, MD, chief medical officer of the ACR DSI, in a recent Journal of the American College of Radiology editorial. Allen explained these structured use cases are important because they will greatly assist in driving the adoption of AI tools in clinical practice…”