Journal Article

Adaptive composite loss for volumetric whole heart segmentation

Sutassananon, Krittanat, Kusakunniran, Worapan, Siriapisith, Thanongchai, Orgun, Mehmet

2025

Overview

Accurate segmentation in medical imaging requires loss functions that capture both regional overlap and boundary alignment. This study evaluates composite losses combining binary cross-entropy (BCE) and a boundary-based term under fixed and adaptive weighting schemes, using U-Net and SwinUNETR on the MM-WHS dataset. For U-Net, a small boundary contribution with adaptive weighting yielded the best results: Standard SoftAdapt (90/10 BCE + BoundaryDoU) achieved the highest Dice score ( ), surpassing both the baseline ( ) and fixed ratios. In contrast, SwinUNETR achieved its strongest performance with a fixed 70% BCE + 10% boundary ratio (0.919 ± 0.02). The result showed that combining a boundary-based loss term helps improve the segmentation accuracy. However, the performance gain is dependent on the architecture of the segmentation model; convolution-based U-Net benefited from the adaptive loss weighting scheme, whereas Transformer-based SwinUNETR without strong inductive bias did not benefit from increased influence of the boundary loss term.

• Publisher: Nature Publishing Group UK,Nature Publishing Group,Nature Portfolio
• Subject: 639/705 / 639/705/117 / Accuracy / Adaptive loss function / Algorithms / Blood vessels / Cardiac volumes / Cardiovascular disease / Composite loss function / Convolutional neural networks / Datasets / Design / Entropy / Heart / Heart - diagnostic imaging / Humanities and Social Sciences / Humans / Image Processing, Computer-Assisted - methods / Localization / multidisciplinary / Science / Science (multidisciplinary) / Segmentation / Whole heart segmentation