Dosimetric impact of physician style variations in contouring CTV for post-operative prostate cancer: A deep learning-based simulation study

TL;DR

This study uses deep learning to simulate how variations in physician contouring styles affect dose distribution to organs-at-risk in post-operative prostate cancer radiotherapy, revealing most dose metrics remain within acceptable limits despite variability.

Contribution

It introduces a deep learning-based simulation framework to analyze the dosimetric impact of physician style variations in CTV contouring without requiring multiple physician annotations.

Findings

Physician style variations affect organ dose distributions.

Most dose metrics stay within clinical limits despite contouring differences.

Deep learning accurately predicts dose variations caused by style differences.

Abstract

Inter-observer variation is a significant problem in clinical target volume(CTV) segmentation in postoperative settings, where there is no gross tumor present. In this scenario, the CTV is not an anatomically established structure, but one determined by the physician based on the clinical guideline used, the preferred tradeoff between tumor control and toxicity, their experience and training background, and other factors. This results in high inter-observer variability between physicians. This variability has been considered an issue, but the absence of multiple physician CTV contours for each patient and the significant amount of time required for dose planning have made it impractical to study its dosimetric consequences. In this study, we analyze the impact that variations in physician style have on dose to organs-at-risk(OAR) by simulating the clinical workflow via deep learning. For a given patient previously treated by one physician, we use deep learning-based tools to simulate how other physicians would contour the CTV and how the corresponding dose distributions would look for this patient. To simulate multiple physician styles, we use a previously developed in-house CTV segmentation model that can produce physician style-aware segmentations. The corresponding dose distribution is predicted using another in-house deep learning tool, which, can predict dose within 3% of the prescription dose, on average, on the test data. For every test patient, four different physician style CTVs are considered, and four different dose distributions are analyzed. OAR dose metrics are compared, showing that even though physician style variations result in organs getting different doses, all the important dose metrics except Maximum Dose point are within the clinically acceptable limit.