Several breast-cancer technology companies are using AI to shorten imaging workflows and support treatment decisions, according to a review of startups in Nvidia’s Inception program. The applications span automated ultrasound, mammogram analysis and predictions from digital pathology slides.
ISono Health’s FDA-cleared ATUSA system captures a standardized 3D breast ultrasound in roughly two minutes per breast, compared with up to 45 minutes for a conventional handheld scan. The company says its model was trained on more than 1.5 million ultrasound frames and that the system is 28% more sensitive than handheld 2D ultrasound. A 3,200-patient multicenter study is underway to validate performance further.
Whiterabbit.ai’s FDA-cleared WRDensity software assesses breast density from mammograms and has been used in hundreds of thousands of patients, Nvidia says. The company is also researching tools for cancer detection and negative-screen triage.
Ataraxis AI analyzes pathology slides and clinical variables to estimate recurrence risk and treatment response. Nvidia reports that two models have been validated across more than 10 institutions and multiple clinical trials and are in clinical use. These systems support clinicians rather than replace diagnosis; performance claims, applicable patient groups and regulatory status need to be checked tool by tool.