Case F (2): Workflow Improvement of Image-guided Radiotherapy: Segmentation Uncertainty Quantification for Improving the Image-Guided Radiotherapy Workflow

Background: Deep learning based image segmentation plays a critical role in adaptive image guided prostate cancer radiotherapy workflows. However, due to the occurrence of errors, model predictions require careful review and potential manual correction by expert therapists before being used in treatment planning. The correction process could become more efficient if therapists were alerted to areas containing possible segmentation errors. Uncertainty estimation techniques can be used to assess deep learning segmentation quality. These techniques are promising, as they show reasonable correlation with segmentation errors.

Objective: The objective of this project is applying uncertainty quantification specifically to adaptive radiotherapy and investigating the innovations needed to enable clinical workflow improvement.