Join the Machine Learning in Medical Imaging Consortium (MaLMIC) for an opportunity to network on machine learning

Aly Khalifa, PhD Student
University of Toronto

Talk Title: Applications of Automated Treatment Planning in Adaptive Radiotherapy

Talk Abstract: Technological advancements in radiotherapy have significantly enhanced treatment precision and patient safety, but they have also introduced a greater burden of manual, time-intensive tasks for clinicians to manage these innovations effectively. Machine Learning (ML) offers a promising solution to streamline these processes and optimize treatment outcomes.

The work of Aly and his colleagues explores applications of automated treatment planning in adaptive radiotherapy procedures. ML is used to predict an ideal radiation dose distribution based on the position of the tumour during treatment to reduce unnecessary radiation exposure to healthy tissues. In comparison to existing clinical methods, the ML automated technique requires no human intervention during the planning process. This removes the reliance on human skill to drive the treatment process.

The work of Aly and his colleagues demonstrates that ML improves the quality of treatment by reducing the radiation dose delivered to healthy tissues, compared to current clinical adaptation techniques. These findings suggest that automated ML-based approaches could substantially improve clinical workflows and patient outcomes in adaptive radiotherapy.

Sangwook Kim, PhD Student
University of Toronto

Talk Title: Multi-Task Learning for Integrated Automated Contouring and Voxel-Based Dose Prediction in Radiotherapy

Talk Abstract: Deep learning-based automated treatment planning cansignificantly enhance the efficiency and accuracy of radiotherapy. However, current planning approaches often depend on manually generated contours, limiting their efficiency. To address this, Sangwook and his colleagues implemented a multi-task learning framework that integrates automated contouring with voxel-based dose prediction, reducing the need for manual input and streamlining the planning process. Using two datasets – an in-house prostate cancer dataset and the publicly available OpenKBP head and neck cancer dataset – they developed a system that performs simultaneous segmentation and dose prediction.

Compared to conventional methods, the new framework improved the average absolute difference in dose volume histogram metrics by 2.90% for prostate cancer and 13.12% for head and neck cancer. Additionally, it enhanced dose prediction performance while maintaining high segmentation accuracy, with dice score coefficients of 0.824 for prostate and 0.716 for head and neck, compared to baseline scores of 0.818 and 0.674, respectively. These improvements can lead to more precise treatment plans and better patient outcomes.

The multi-task learning framework is not only generalizable to other anatomical sites and conditions but also holds promise for significantly reducing clinical workload and enhancing radiotherapy efficiency. By integrating automated contouring and dose prediction, this newapproach minimizes the need for sequential steps in the planning process, potentially allowing clinics to handle higher patient volumes with greater consistency and accuracy. This work illustrates the potential of AI to enable fully automated, efficient radiotherapy planning, supporting broader adoption of AI-driven tools in clinical practice.