“A tool such as TRACE4BDensity can help us advise women with dense breasts to have, after a negative mammogram, supplemental screening with ultrasound, MR or contrast-enhanced mammography,” said study co-author Dr. Francesco Sardanelli, from the IRCCS Policlinico San Donato in San Donato, Italy.

Previous studies also back the use of AI for identifying and triaging cases of breast cancer in women with dense and extremely dense breasts. For example, Researchers involved in Dense Tissue and Early Breast Neoplasm Screening (DENSE) Trial, a large study based in the Netherlands, developed and used a deep learning application that was able to rule out the disease in patients with dense breast tissue who underwent MR scans.

Out of 9,162 breasts, 838 had at least one lesion, of which 77 were malignant, and 8,324 had no lesions. The solution considered 90.7% of the MRs with lesions to be non-normal and dismissed about 40% of the lesion-free MRs without missing any cancers. This freed up radiologists to focus on more complex cases.

"The results were better than expected. Forty percent is a good start. However, we have still 60% to improve," study lead author Erik Verburg, from the Image Sciences Institute at the University Medical Center Utrecht in the Netherlands, said in a statement.

The results of the Italian study were published in Radiology: Artificial Intelligence.

Back to HCB News

Women's Health Homepage