Image IQ: 30-year-old, Breastfeeding, with Nontender Breast Lump

Five artificial intelligence (AI) algorithms for mammography assessment were better at predicting breast cancer risk over five years than the Breast Cancer Surveillance Consortium (BCSC) risk model, according to new retrospective research involving over 13,000 women.

In this podcast episode, Dr. Shalom Kalnicki, from Montefiore and Albert Einstein College of Medicine, discusses the disparities minority patients face with cancer screenings and what can be done to increase access during the pandemic.

In a large retrospective study involving over 523,000 digital breast tomosynthesis (DBT) exams and over one million digital mammography (DM) exams, researchers found that DBT was associated with significantly lower recall rates but showed no advantage over DM in the diagnosis of interval or advanced breast cancer.

Dr. Laurence Klotz discusses micro-ultrasound as a faster, less invasive, more cost-effective screening strategy compared to mpMRI in this podcast.

Emerging breast ultrasound research showed the use of computer-aided diagnosis (CAD), powered by deep learning, led to 24 percent and 36.9 percent improvements in accuracy and specificity, respectively, in the use of BI-RADS classifications by radiologists without breast ultrasound expertise.

Six reader studies on digital mammography revealed a pooled sensitivity rate of 80.8 percent for stand-alone artificial intelligence (AI) in comparison to 72.4 percent for radiologist assessment while seven historic cohort studies showed a 75.8 percent pooled sensitivity rate for stand-alone AI versus 72.6 percent for radiologist interpretation of digital mammography.