Development of an AI Assisted Denoising Technique for Optical Coherence Tomography Imaging for Breast Cancer Margin Assessment

Breast cancer is the most common cancer (excluding non-melanoma skin cancer) in 109 countries including Canada. Approximately 70% of the breast cancer surgeries are breast-conserving lumpectomy procedures. Histopathology analysis typically require 2-4 days, resulting in the need for a second surgery if a margin is positive. Perimeter Medical is developing advanced Optical Coherence Tomography (OCT) imaging tools to visualize margins at the time of surgery. One of the keys needs is the training of medical professionals who would interpret images during surgery. Intern will contribute to development of an AI based solution that will have a click to reveal functionality to identify different features in OCT images. Intern will develop a binary classifier to identify calcifications which might be an early sign of cancer. Intern will learn various aspects of AI development from data labeling, curation to model building and optimization while Perimeter Medical accelerates the development of training tool.

Faculty Supervisor:

Kumaradevan Punithakumar;Michelle Noga

Student:

Partner:

Perimeter

Discipline:

Computer science

Sector:

Artificial Intelligence; Health and Related Sciences & Technology; Biotechnology

University:

University of Alberta

Program: