Learning to Look Closer: A New Instance-Wise Loss for Small Cerebral Lesion Segmentation

TL;DR

This paper introduces CC-DiceCE, a novel instance-wise loss function for small cerebral lesion segmentation that improves detection recall without sacrificing overall segmentation quality.

Contribution

The paper proposes CC-DiceCE, a new loss function based on CC-Metrics, demonstrating improved lesion detection over existing blob loss in a standardized nnU-Net framework.

Findings

CC-DiceCE increases lesion detection recall.

It maintains segmentation performance with minimal degradation.

Outperforms blob loss across multiple datasets.

Abstract

Traditional loss functions in medical image segmentation, such as Dice, often under-segment small lesions because their small relative volume contributes negligibly to the overall loss. To address this, instance-wise loss functions and metrics have been proposed to evaluate segmentation quality on a per-lesion basis. We introduce CC-DiceCE, a loss function based on the CC-Metrics framework, and compare it with the existing blob loss. Both are benchmarked against a DiceCE baseline within the nnU-Net framework, which provides a robust and standardized setup. We find that CC-DiceCE loss increases detection (recall) with minimal to no degradation in segmentation performance, though with dataset-dependent trade-offs in precision. Furthermore, our multi-dataset study shows that CC-DiceCE generally outperforms blob loss.