Artificial intelligence (AI) technology has been developed by engineers at the University of Waterloo to determine whether chemotherapy before surgery would be beneficial to breast cancer patients.

The new artificial intelligence (AI) algorithm, which is part of the open-source Cancer-Net initiative led by Dr. Alexander Wong, may help unsuitable candidates stay away from serious side effects of chemotherapy and make it easier for those who are suitable to have better surgical outcomes.

“It is crucial to avoid unnecessary side effects from using treatments that are unlikely to have real benefit for that patient,” said Wong, a professor of systems design engineering. “Determining the right treatment for a given breast cancer patient is very difficult right now.”

“An AI system that can assist in predicting whether a patient is likely to respond well to a particular treatment provides doctors with the tool necessary to prescribe the best personalized treatment for a patient in order to improve recovery and survival,”

The AI software was trained with images of breast cancer taken using a brand-new magnetic image resonance technique known as synthetic correlated diffusion imaging (CDI), which was developed by Wong and his team and is led by graduate student Amy Tai of the Vision and Image Processing (VIP) Lab.

The AI can determine whether new patients would benefit from pre-operative chemotherapy based on their CDI images using information gleaned from CDI images of previous breast cancer cases and their outcomes.

The pre-surgical treatment, which is known as neoadjuvant chemotherapy, can shrink tumors to make surgery possible or easier and reduce the need for major surgeries like mastectomies.

Wong, director of the VIP Lab and Canada Research Chair in Artificial Intelligence and Medical Imaging, stated, “I’m quite optimistic about this technology as deep-learning AI has the potential to see and discover patterns that relate to whether a patient will benefit from a given treatment.”

A report on the Cancer-Net BCa project: As part of NeurIPS 2022, a major international conference on artificial intelligence, Breast Cancer Pathologic Complete Response Prediction using Volumetric Deep Radiomic Features from Synthetic Correlated Diffusion Imaging was recently presented at Med-NeurIPS.

Through the Cancer-Net initiative, the new AI algorithm and the entire dataset of CDI images of breast cancer have been made available to the public for other researchers to use to advance the field.