Machine Learning for Personalized Radiation Therapy Treatment Planning Optimization using Historical Data

Radiation therapy treatment planning is a critical and highly complex step in cancer treatment, requiring significant expertise and time to adapt and personalize treatments to each patient’s condition. Current planning methods often rely on manual expertise and standardized approaches, which can limit the degree of personalization and contribute to variability in outcomes. This project addresses these challenges by leveraging machine learning techniques to learn from past patient treatment in order to inform the design of effective treatments for future patients. We cluster ML/AI techniques to meaningfully categorize patients into clusters based on their specific demographic, anatomical, geometric, and disease diagnostic features, and design personalized radiotherapy treatment plans informed by historical data. The goal is to provide clinicians with decision-support tools that improve efficiency, consistency, and personalization in treatment planning. Through close collaborations with WRHN, the methods are expected to be integrated into clinical practice, improving the quality of care for patients in Canada and enhancing the effectiveness of the workload for staff at the Canadian Cancer Centre.

Faculty Supervisor:

Houra Mahmoudzadeh

Student:

Partner:

École nationale supérieure d'informatique

Discipline:

Engineering

Sector:

Artificial Intelligence; Health and Related Sciences and Technology

University:

University of Waterloo

Program: