JTsui Lab

Integrating AI in

oncology research and

clinical practice

Welcome to the J. Tsui Lab – Where AI Meets Oncology

At the J. Tsui Lab, we are passionate about pushing the boundaries of what AI can do in oncology. From automating treatment planning to working towards personalized radiation therapy, we’re here to make a difference in the lives of patients.

About

James Tsui

BEng, MSc, MDCM, PhD, FRCPC

Dr. James Tsui is a Radiation Oncologist at the MUHC, an Assistant Professor in Clinical Oncology at the McGill University, the Director of the Radiation Oncology Clinical Trials Unit, and FRQS Junior 1 Clinician-Scientist. He is also an Associate Member of the Graduate Program in Biological and Biomedical Engineering, the McGill Physics Unit, and Surgical and Interventional Sciences.

He completed his Bachelor’s Degree in Electrical Engineering at Concordia University in 2006 and a PhD in computational neuroscience at the Montreal Neurological Institute / McGill University in 2013. He later obtained his MD degree in 2015 and completed his residency training in Radiation Oncology in 2020 at McGill University.

To further his sub-specialization training, he completed a Brachytherapy Fellowship at the Brigham and Women’s Hospital, Harvard, Boston in 2021, and a Professional Master’s Degree in Artificial Intelligence with a focus in Deep Learning at MILA / Université de Montréal in 2023.

His research interests focus on the intersection of machine learning and medicine, with the goal of bringing artificial intelligence into his oncology research and clinical practice.

Areas of Clinical Focus

Current Select Projects

Personalizing Sarcoma Treatment

Our current sarcoma project is focused on integrating AI into the radiation therapy workflow to enhance treatment delivery. In addition,  we are also exploring how to safely administer higher doses of radiation to improve tumor control without increasing the risk of side effects.

Find out more here

Project supported by the Cedars Cancer Foundation

Geriatric-oncology Admission Prediction Tool

This project uses machine learning to predict hospital admissions for elderly cancer patients presenting to the emergency room. The goal is to provide a tool that would facilitate early intervention to reduce patients' length of stay in the emergency department and improve overall care efficiency.

Project supported by the MUHC Foundation

Federated Learning in Radiation Therapy

This project focuses on using a federated approach to develop a deep-learning segmentation tool for lung lesions in Stereotactic Body Radiation Therapy (SBRT). In collaboration with CISSS-CA, CHUS, and CHUM, we aim to build a model that enhances the precision of treatment while ensuring data privacy by sharing model weights across institutions rather than patient data.

Project supported by the Cedars Cancer Foundation

Multimodal AI for Bladder Cancer

This project focuses on predicting patient response to concurrent chemoradiation. By integrating various data modalities, we aim to develop an AI model that can accurately predict treatment outcomes, helping to optimize therapeutic decisions for bladder cancer patients.

Project supported by Dr. Wassim Kassouf lab and by the Montreal General Hospital Foundation

Publications