Radiology in public focus

Press releases were sent to the medical news media for the following articles appearing in a recent issue of Radiology.

Tomosynthesis with Synthetic Mammography Improves Breast Cancer Detection

Digital breast tomosynthesis (DBT), in combination with synthetic mammography, improves cancer detection over digital mammography alone, according to a Radiologystudy from Italy.

Francesca Caumo, MD, from the Breast Radiology Department of the Veneto Institute of Oncology in Padua, Italy, and colleagues analyzed results from more than 32,000 women who were screened for breast cancer and then rescreened two years later.

In total, 32,870 women, average age 58, were rescreened, including 16,198 with DBT synthetic mammography and 16,672 with mammography. DBT at the first round and at rescreening detected a higher proportion of early-stage cancers than screening with digital mammography.

The cancer detection rate was 8.1 per 1,000 for rescreening with DBT and synthetic mammography compared with 4.5 per 1,000 for rescreening with mammography. There was no difference in the recall rate at rescreening with both DBT and synthetic mammography and mammography.

At rescreening, the proportion of tumors stage-II or above was 14.5% with DBT and synthetic mammography, considerably higher than the 8.5% rate with mammography.

“The lower number of stage II or above cancers with the DBT plus synthetic mammography screening test demonstrates that DBT has the capability of anticipating the detection of cancers that might become advanced in the following two years,” Dr. Caumo said. “This gives a higher benefit to our patients.”


Images in a 55-year-old woman with a spiculated mass localized in the upper central quadrant (arrow in A, B, D, and E) of right breast detected with digital breast tomosynthesis (DBT) plus synthetic mammography (SM). Breast density was classified as category C with the Breast Imaging Reporting and Data System. Mass was invasive ductal carcinoma, stage I, and was estrogen and progesterone receptor positive and human epidermal growth factor receptor 2 negative. A, Image from SM in craniocaudal view. B, Single-slice DBT image in craniocaudal view. C, Magnification of the lesion depicted in B. D, Image from SM in mediolateral oblique view. E, Single-slice DBT image in mediolateral oblique view. F, Magnification of the lesion depicted in E.

Caumo et al, Radiology 2020 ©RSNA 2020

Digital Breast Tomosynthesis Improves Invasive Cancer Detection

Breast cancer screening with digital breast tomosynthesis (DBT) offers significant advantages over digital mammography, including improved cancer detection and lower false negative rates, according to a study in Radiology.

Melissa A. Durand, MD, Yale University School of Medicine and Smilow Cancer Hospital in New Haven, CT, and colleagues examined more than 380,000 screening examinations to compare the performance of DBT and digital mammography.

Among the performance metrics they assessed were the rates of false negative screening examinations. Since false negative cancers tend to be more aggressive than screen-detected cancers, a reduction in them may be considered a surrogate for longer-term screening outcomes such as advanced disease or death.

Analysis showed that screening with DBT improved sensitivity and specificity for breast cancer and identified more invasive cancers with fewer nodal or distant metastases. Screening with DBT demonstrated a trend toward lower rates for overall false negatives and symptomatic false negatives. The results also showed advantages for DBT in imaging women with mammographically dense breasts.

“Together with reduced recall rates and, thus, less patient anxiety, I would anticipate that DBT will continue to move forward as the standard of care to replace regular mammography,” Dr. Durand said.


Images show symptomatic false-negative cancer in a 73-year-old Black woman who presented with a palpable abnormality 64 days after negative screening mammography. (a) Negative screening left digital breast tomosynthesis (DBT) mammogram. (b) Diagnostic DBT mammogram shows a new palpable mass (arrow). (c) Spot-compression DBT mammogram enables confirmation of mass (arrow). (d) Ultrasound (US) image shows hypoechoic mass with angular margins. Subsequent US-guided biopsy revealed estrogen receptor– and progesterone receptor– positive and human epidermal growth factor receptor 2–negative invasive ductal carcinoma.

Durand et al, Radiology 2020 ©RSNA 2020

AI Tool Improves Breast Cancer Detection on Mammography

Artificial intelligence (AI) can enhance the performance of radiologists in reading breast cancer screening mammograms.

In the study in Radiology: Artificial Intelligence, Serena Pacilè, PhD, clinical research manager at Therapixel, and her team, used MammoScreen, an AI tool that can be applied with mammography to aid in cancer detection. The software was developed at Therapixel.

The AI system is designed to identify regions suspicious for breast cancer on 2D digital mammograms and assess their likelihood of malignancy.

Fourteen radiologists assessed a dataset of 240 2D digital mammography images acquired between 2013 and 2016 that included different types of abnormalities. Half of the dataset was read without AI and the other half with the help of AI during a first session and without during a second session.

Average sensitivity for cancer increased slightly when using AI support. AI also helped reduce the rate of false negatives.

“The results show that MammoScreen may help to improve radiologists’ performance in breast cancer detection,” Dr. Pacilè said.

The U.S. Food and Drug Administration cleared MammoScreen for use in the clinic, where it could help reduce the workload of radiologists, according to Dr. Pacilè.


Mammograms in a 51-year-old woman with invasive ductal carcinoma. The upper panels show the craniocaudal and the mediolateral oblique views. The lower panels show a close-up of the left breast area containing the lesion. The case is one of the false-negative cases included in the dataset. Accordingly, the initial screening assessment was a BI-RADS 2, meaning visible findings were judged as benign. After 1 year, the patient presented for another screening examination. This time, a focal asymmetry with associated distortion within the left breast was noticed; the patient was recalled and diagnosed with a 1.5-cm mass in the upper outer quadrant of the left breast on the craniocaudal view (circle).

Pacilè et al, Radiology 2020 © RSNA 2020

For Your Information

Access the Radiology: Artificial Intelligence study, "Improving Breast Cancer Detection Accuracy of Mammography with the Concurrent Use of an Artificial Intelligence Tool."

Data Science Pathway Prepares Radiology Residents for Machine Learning

A recently developed data science pathway for fourth-year radiology residents will help prepare the next generation of radiologists to lead the way into the era of artificial intelligence (AI) and machine learning (AI-ML).

In a study in Radiology: Artificial Intelligence, Walter F. Wiggins, MD, PhD, Brigham and Women’s Hospital in Boston, and his resident colleagues, M. Travis Caton, MD, and Kirti Magudia, MD, PhD, devised a data science pathway to provide a well-rounded introductory experience in AI-ML for fourth-year residents.

The pathway, which combines formal instruction with practical problem-solving in collaboration with data scientists, offers ample opportunities for residents to work directly with data scientists to better understand how they approach image analysis problems with ML tools.

 This communication, in turn, helped the data scientists better understand how radiologists approach a radiology problem in a clinical setting. The data scientists could be easily implemented in clinical practice.

“An important component of a curriculum like this is to learn the language the data scientists speak and teach them a little bit about the language that we as radiologists speak so that we can have better, more effective collaborations,” Dr. Wiggins said. “Going through that process over several different projects was where I think I gained the best experience throughout all of this.”


Individual AI-ML Projects from the DSP. Each trainee contributed to design, data curation and model development of individual projects including hemorrhage detection on CT (A), abdominal body composition (B), and lumbar spine segmentation and stenosis assessment (C).

Wiggins et al, Radiology 2020 ©RSNA 2020

Media Coverage of RSNA

In November, 8,119 RSNA-related news stories were tracked in the media. These stories had over 4 billion audience impressions.


Coverage included Sirius-XM, One America News (National), WINS-AM (New York), KCBS-AM (New York), KTLA-TV (Los Angeles), KNX-AM (Los Angeles), WBBM-AM (Chicago), WCAU-TV (Philadelphia), KYW-AM (Philadelphia), WPHT-AM (Philadelphia), KRLD-AM (Dallas), WBTS-TV (Boston), Yahoo! News,, New York Post, U.S. News & World Report, Forbes, ScienceDaily, HealthDay,, Houston Chronicle, Pittsburgh Post-Gazette, The Arizona Republic,, Healthcare Business News, Health Imaging News, Diagnostic Imaging and Applied Radiology.

American Heart Month: Share With Your Patients

Visit, the public information website produced by RSNA and ACR, for easy-to-read patient information about the risks associated with coronary artery disease and available screening methods such as calcium scoring with cardiac CT.