Study shows excellent agreement between radiologists and Densitas technology using BI-RADS 5th edition classifications
Research comparing radiologist’s assessments of breast density versus automated software was presented today during scientific sessions at the European Congress of Radiology (ECR) in Vienna, Austria.
The study quantifies the agreement between radiologists’ visual assessments of breast density as it appears on a mammogram and those from an automated algorithm. Density assessments were made according to the 5th edition of the American College of Radiology BI-RADS density lexicon which considers both the amount and distribution of mammographic density. Densitas’ DM-Research product was used to generate breast density assessments for the study.
“We tackle real challenges faced by radiologists in the mammography enterprise. Subjectivity has long been a challenge in the visual assessment of breast density,” said Mohamed Abdolell, CEO and founder of Densitas. “Our core technology, shared by our in-clinic products and DM-Research, reduces that subjectivity and demonstrates excellent agreement with expert radiologist’s assessments.”
Study results presented today show substantial to almost perfect agreement between the algorithm and individual radiologists with Kappa statistics ranging from 0.73 to 0.84. Additionally, a Kappa statistic of 0.85 demonstrates almost perfect agreement between the algorithm and the consensus between radiologists. The study concluded that automated breast density software can have substantial to almost perfect agreement with radiologists’ visual assessments of density. Such measures would also be objective and more reliable than radiologist-assigned density scores.
Densitas also offers DM-Density, a clinical version of its breast density assessment product. DM-Density has received the CE Mark from the European Commission and a medical device license from Health Canada.
A poster presentation using the same Densitas technology is also on display at ECR. The purpose of this study was to quantify the magnitude of the association between breast density assessed using the BI-RADS 5th edition density scale and screen-detected breast cancer.
The results of this study indicated that women with extremely dense breasts have five times higher odds of screen-detected breast cancer relative to those with almost entirely fatty breasts. The BI-RADS density classification was automatically assigned to each subject’s mammography image using DM-Research.
The results of this study may have implications for future research investigating the relationship between breast density and breast cancer risk, particularly in the context of breast cancer risk models that include BI-RADS density classifications as a risk factor.
Densitas Inc. is an ISO 13485-certified software medical device company. Densitas develops data-driven solutions that address the clinical and administrative requirements of hospitals and radiology clinics and healthcare providers. Densitas’ vision is to be the recognized leader in transforming the untapped massive volumes of data generated in the breast imaging enterprise into actionable information to advance improved clinical outcomes and appropriateness of care. Densitas is focused on providing solutions for personalized breast health care for women and appropriate use of healthcare resources.
For more information, contact:
Vienna, Austria, March 6, 2016