Lab Manager | Run Your Lab Like a Business
Pink ribbon representing breast cancer awareness
Pixabay, marijana1

New AI Model Predicts Response to Chemotherapy in Female Breast Cancer Patients

This AI may help oncologists develop individual treatment plans better suited to each patient

Holden Galusha

Holden Galusha is the associate editor for Lab Manager. He was a freelance contributing writer for Lab Manager before being invited to join the team full-time. Previously, he was the...

ViewFull Profile.
Learn about ourEditorial Policies.
Register for free to listen to this article
Listen with Speechify

Engineers from the University of Waterloo have announced a new artificial intelligence (AI) algorithm that can predict the effectiveness of pre-operative chemotherapy in female breast cancer patients. A paper on their work was presented at the Med-NeurIPS international AI conference.

The development of this algorithm, dubbed Cancer-Net BCa (Breast Cancer), is part of a larger network of open-source software projects dedicated to advancing cancer research by means of deep learning and AI. The creation of Cancer-Net BCa was led by Alexander Wong, PhD, professor at the University of Waterloo and Canada research chair in AI and medical imaging. Cancer-Net BCa may help oncologists discern who would, and who would not, respond positively to chemotherapy. This would allow patients predicted to not respond well to avoid the harsh side effects of the treatment while pursuing alternatives treatments. “An AI system that can help predict if a patient is likely to respond well to a given treatment gives doctors the tool needed to prescribe the best personalized treatment for a patient to improve recovery and survival,” said Wong.

Cancer-Net BCa was trained on images of breast cancer generated with synthetic correlated diffusion imaging (CDI), a new modality of magnetic resonance imaging developed by Wong and his team. CDI offers improved delineation of cancerous and healthy tissue by accounting for “signal attenuation at different water diffusion motion sensitivities,” which the researchers hope will boost the algorithm’s predictive accuracy.

“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,” Wong said. Cancer-Net BCa and the dataset of CDI images are publicly available on GitHub for other researchers to use in their own projects.