Researchers Develop AI Technology That May Be Able To Predict Chemo’s Effectiveness
Chemotherapy is often given before breast cancer surgery in an effort to shrink larger tumors, which may help the surgeon remove the cancer completely, decrease the amount of cancer in the lymph nodes, or lower the odds of recurrence. A team in Canada recently developed a tool that may help determine how effective this order of treatment will be.
Engineers at the University of Waterloo have developed artificial intelligence technology aimed at predicting whether breast cancer patients would benefit from chemo ahead of surgery. A paper on the topic was presented at the AI international conference NeurIPS 2022. The effort is part of the open-source Cancer-Net initiative led by Dr. Alexander Wong, a professor of systems design engineering.
Dr. Wong says, “Determining the right treatment for a given breast cancer patient is very difficult right now, and it is crucial to avoid unnecessary side effects from using treatments that are unlikely to have real benefit for that patient.
“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.”
To create their AI system, the engineers used images of breast cancer from an MRI modality Dr. Wong and his team created called synthetic correlated diffusion imaging, or CDI. They trained the AI with CDI images depicting breast cancer cases and information on their outcomes. In practice, the AI system would use a patient’s CDI images to predict if chemotherapy ahead of surgery would be effective for them. The team believes this may be helpful for oncologists when recommending treatment options.
Dr. Wong says, “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.”
Currently, pre-surgery chemo is often the treatment course for larger breast cancers, those that have spread to the lymph nodes, and inflammatory, HER2-positive, and triple negative breast cancers.
