OAR-Weighted Dice Score: A spatially aware, radiosensitivity aware metric for target structure contour quality assessment

TL;DR

This paper introduces the OAR-DSC, a novel spatially aware and radiosensitivity-aware metric for evaluating target structure contours in radiation therapy, addressing limitations of the traditional DSC.

Contribution

The paper presents the OAR-DSC, a new metric that incorporates nearby organs-at-risk and their radiosensitivity into contour quality assessment.

Findings

OAR-DSC differentiates contours closer to OARs with similar DSC.

OAR-DSC can improve deep learning auto-contouring loss functions.

The metric emphasizes the importance of spatial and radiosensitivity considerations.

Abstract

The Dice Similarity Coefficient (DSC) is the current de facto standard to determine agreement between a reference segmentation and one generated by manual / auto-contouring approaches. This metric is useful for non-spatially important images; however, radiation therapy requires consideration of nearby Organs-at-Risk (OARs) and their radiosensitivity which are currently unaccounted for with the traditional DSC. In this work, we introduce the OAR-DSC which accounts for nearby OARs and their radiosensitivity when computing the DSC. We illustrate the importance of this through cases where two proposed contours have similar DSC, but lower OAR-DSC when one contour expands closer to the surrounding OARs. This work is important because the OAR-DSC may be used by deep learning auto-contouring algorithms in a radiation therapy specific loss function, thereby progressing on the current disregard for the importance of these differences on the final radiation dose plan generation, delivery, and risks of patient toxicity.