Radiology resident recognized for research into compressing mammograms for accurate and speedy electronic transmission.
Research aimed at improving early breast cancer detection by making mammogram images easier to transmit via the Internet has earned a fourth-year radiology resident the 2014 Residents in Radiology Executive Council Award.
This award, given to only three residents, was presented to Mark Kovacs, a resident at the Santa Barbara Cottage Hospital, at the American Roentgen Ray’s annual meeting in San Diego, where he presented his research.
Kovacs investigated a method that would allow mammograms to be easily transmitted electronically and without affecting diagnostic accuracy. Kovacs found the solution in lossy data compression, a technique that removes data from files and reduces the file size to one-eightieth of its original size. A typical four-view mammogram is 200 megabytes, but the reduced size with lossy data compression was only 2.5 megabytes, which is about the size of a cell phone photo and easily transmittable via the web.
To confirm the compression didn’t affect diagnostic accuracy, Kovacs conducted a study of 194 patients, which revealed that participating mammographers were able to accurately detect the presence of early stage breast tumors as small as 1 centimeter in diameter in mammograms that received the lossy data compression.
“Studies show that the number one factor in increasing breast cancer detection rates is the experience of the physician reading the mammogram,” Kovacs said in a release. “One of the limiting factors in getting screening mammograms to expert readers is the enormous file size of full-field digital mammograms. If the Federal Drug Administration allowed the use of lossy compressed mammograms for primary interpretation, it could usher in a new era of practical tele-mammography that could help improve early detection rates for breast cancer.”
AI-Initiated Recalls After Screening Mammography Demonstrate Higher PPV for Breast Cancer
March 18th 2025While recalls initiated by one of two reviewing radiologists after screening mammography were nearly 10 percent higher than recalls initiated by an AI software, the AI-initiated recalls had an 85 percent higher positive predictive value for breast cancer, according to a new study.
ECR Mammography Study: Pre-Op CEM Detects 34 Percent More Multifocal Masses than Mammography
February 28th 2025In addition to contrast-enhanced mammography (CEM) demonstrating over a 90 percent detection rate for multifocal masses, researchers found that no significant difference between histological measurements and CEM, according to study findings presented at the European Congress of Radiology.
Study: Mammography AI Leads to 29 Percent Increase in Breast Cancer Detection
February 5th 2025Use of the mammography AI software had a nearly equivalent false positive rate as unassisted radiologist interpretation and resulted in a 44 percent reduction in screen reading workload, according to findings from a randomized controlled trial involving over 105,000 women.