Validating Artificial Intelligence Algorithms for Breast Cancer Detection

While mammograms remain the best available technology for early detection of breast cancer, there are a high number of false positive mammograms and biopsies, leading to increased costs to the medical system on follow-up procedures and increased patient anxiety. This project evaluates the performance of artificial intelligence (AI) systems for breast cancer detection using about 100,000 digital mammograms from the BC Cancer Breast Screening Program. We plan to compare the predictions of the system to those made by breast screening radiologists in routine clinical practice and then compare and contrast the performance of the AI systems to that of individual radiologists. We believe this work will pave the way in using AI models to aid breast cancer detection in routine clinical care.

Faculty Supervisor:

Rasika Rajapakshe

Student:

John Brandon Graham-Knight

Partner:

Lunit Inc

Discipline:

Computer science

Sector:

Health care and social assistance

University:

Program: