Skip to content
The popularity of artificial intelligence is growing, but it is capable of more than just creating texts or illustrations. Researchers from the University of Waterloo have developed AI technology to determine the appropriateness of chemotherapy for breast cancer patients before surgery.
About the AI algorithm from Cancer-Net
The new AI algorithm is part of the Cancer-Net open-source initiative led by Dr. Alexander Wong. Its goal is to help unsuitable candidates avoid the serious side effects of chemotherapy. And for women who are suitable for such treatment, the technology helps achieve better results from surgery.
Cancer-Net BCa is “Breast Cancer Pathologic Complete Response Prediction using Volumetric Deep Radiomic Features from Synthetic Correlated Diffusion Imaging”. The project has been recently presented at Med-NeurIPS as part of NeurIPS 2022, a major international conference on AI.
About breast cancer
Determining the right treatment for a given breast cancer patient is very difficult right now. And it’s crucial to avoid unnecessary side effects from using treatments that are unlikely to have real benefit.
Alexander Wong, Professor of System Design Engineering and Director of the VIP Lab and the Canada Research Chair in Artificial Intelligence and Medical Imaging
The Ministry of Health in Ukraine states that cancer is curable if it is detected at stage I – in 95% of women, stage II – in 80%, and stage III – in 50%.
Breast cancer is the second most common type of cancer in women in Canada and the United States, representing over 25% of all new female cancer cases. Neoadjuvant chemotherapy treatment has recently risen in usage as it may shrink inoperable tumors. This is a type of induction therapy that is performed as a first step to shrink the tumor before the main treatment, which is usually surgery. In this way, the tumor becomes operable. In the same time, it’s difficult to predict a patient’s pathologic response to neoadjuvant chemotherapy.
How AI works
An AI system that can help predict if a patient is likely to respond well to a given treatment. That gives doctors the tool needed to prescribe the best personalized treatment. This will increase the chances of recovery and survival.
Professor Alexander Wong
In a project led by Amy Tai, a graduate student with the Vision and Image Processing (VIP) Lab, the AI software was trained with images of breast cancer made with a new magnetic image resonance modality. It was invented by Wong and his team and is called synthetic correlated diffusion imaging (CDI).
The AI receives CDI images of old breast cancer cases and information about their outcomes. Based on this data, the algorithm predict whether pre-operative chemotherapy will help new patients. It can make surgery possible or easier, as well as reduce the need for mastectomy, or breast removal.
I’m quite optimistic about this technology. Deep-learning AI has the potential to see and discover patterns that relate to whether a patient will benefit from a given treatment.
Professor Alexander Wong
The new AI algorithm and the full dataset of CDI breast cancer images have been made publicly available. It was provided by the Cancer-Net initiative so that other researchers can help advance the field.
Another latest study by American scientists proved that mastectomy is not the only treatment option for women with multiple breast tumors.
