Radiology in public focus

Disparities Seen in Same-Day Breast Diagnostic and Biopsy Services

Different sociodemographic groups, especially racial and ethnic minorities, are less likely to receive timely breast cancer diagnostic services after an abnormal screening mammogram, according to a study published in Radiology.

Study author Marissa B. Lawson, MD, MS, assistant professor of radiology at the University of Washington School of Medicine in Seattle, and colleagues analyzed data from six Breast Cancer Surveillance Consortium registries, covering over 3.5 million screening mammograms from 1.1 million women across 136 U.S. facilities.

Despite having similar availability of diagnostic breast imaging services, there were substantial differences in whether patients received some of these services by race and ethnicity and neighborhood-level socioeconomic status.

“Future studies should assess other factors that may impact whether patients receive specific diagnostic breast imaging services, such as insurance status or patient preferences,” Dr. Lawson said. 

Read the related RSNA News story.

Researchers Develop AI Model to Segment MRI Images

Researchers in Switzerland have developed and tested a robust AI model that automatically segments major anatomic structures in MRI images, independent of sequence, according to a study published in Radiology.

Jakob Wasserthal, PhD, Radiology Department research scientist at University Hospital Basel, and colleagues built an open-source automated segmentation tool called the TotalSegmentator MRI based on nnU-Net, a self-configuring framework that has set new standards in medical image segmentation.

A similar model for CT (TotalSegmentator CT) is being used by over 300,000 users worldwide to process over 100,000 CT images daily.

The researchers trained TotalSegmentator MRI using 616 MRI and 527 CT exams to create sequence-independent segmentations of 80 major anatomic structures. The model performed well across different MRI scanners and image setting, achieving a high Dice score of 0.839 and outperforming other publicly available segmentation models.

“To our knowledge, our model is the only one that can automatically segment the highest number of structures on MRIs of any sequence,” Dr. Wasserthal said. “It’s a tool that helps improve radiologists’ work, makes measurements more precise and enables other measurements to be done that would have taken too much time to do manually.”

Read the related RSNA News story.

COVID-19 Virus Causes Higher Cardiac Risk

A new study found severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection was associated with the rapid growth of plaque in the coronary arteries and an increased risk of cardiovascular events. The results were published in Radiology.

Senior author Junbo Ge, MD, professor and director of the Cardiology Department at Zhongshan Hospital, Fudan University in Shanghai and colleagues investigated the impact of SARS-CoV-2 infection using coronary CT angiography (CCTA) to assess coronary inflammation, determined by analyzing changes in tissue surrounding the coronary arteries, as well as plaque burden and type.

The retrospective study analyzed 803 patients who underwent CCTA between September 2018 and October 2023, including 25 who had SARS-CoV-2 before imaging.

Compared to uninfected patients, individuals with SARSCoV-2 had faster plaque growth, a higher incidence of highrisk plaques (20.1% vs. 15.8%), more coronary inflammation (27% vs. 19.9%) and an increased risk of target lesion failure (10.4% vs. 3.1%).

“Inflammation following COVID-19 can lead to ongoing plaque growth, particularly in high-risk, noncalcified plaques.” Dr. Ge said. “Patients with SARS-CoV-2 infection are at increased risk for myocardial infarction, acute coronary syndrome and stroke for up to a year.”

Read the related RSNA News story.