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.
@article{arxiv.2511.17146,
title = {Learning to Look Closer: A New Instance-Wise Loss for Small Cerebral Lesion Segmentation},
author = {Luc Bouteille and Alexander Jaus and Jens Kleesiek and Rainer Stiefelhagen and Lukas Heine},
journal= {arXiv preprint arXiv:2511.17146},
year = {2026}
}