Post-Operative Glioma Segmentation via Loss Stabilization, Normalization and Subspace Attention

πŸ“… 2026-07-23
πŸ“ˆ Citations: 0
✨ Influential: 0
πŸ“„ PDF
πŸ€– AI Summary
This study addresses the significant performance degradation of post-operative glioma segmentation under cross-institutional clinical protocols due to domain shift. To mitigate this issue, the authors propose brain-mask percentile normalization combined with voxel-level contrastive learning to stabilize training dynamics. Furthermore, they introduce a Subspace-Aware Class Attention (SACA) module to recalibrate bottleneck features and enhance sensitivity to contrast-enhancing tumor regions. Integrated into the nnU-Net framework, the proposed method achieves a Dice coefficient of 0.94 for whole lesion segmentation on the MU-GLIOMA-POST dataset. The SACA-augmented variant reduces boundary error to an HD95 of 2.92 mm and yields a relative 9.1% improvement in sensitivity to enhancing tumor regions.
πŸ“ Abstract
Tracking residual tumor after surgery is essential for catching recurrence early, but automating post-operative glioma segmentation remains a difficult task. Although transformer-based architectures, such as SwinUNETR, achieved impressive results, few studies test how well they generalize across clinical protocols. In this paper, we conduct an ablation study on the MU-GLIOMA-POST and UCSF-ALPTDG datasets and show that the standard Generalized Dice Loss (GDL) is unstable under domain shift: the Whole Lesion (WL) Dice drops from 0.88 on the internal validation set to 0.73 on the external UCSF test set. To address this, we pair brain-masked percentile normalization with voxel-level contrastive learning. We also propose a Subspace-Aware Class Attention (SACA) module that re-calibrates the bottleneck features and raises Enhancing Tumor (ET) sensitivity by 8% (9.1% relative improvement) on internal validation. Ensembling these refinements with nnU-Net brings every stable configuration to a WL Dice of 0.94, and the SACA variant ensemble achieves the best boundary error (HD95) of 2.92 mm on MU-GLIOMA-POST.
Problem

Research questions and friction points this paper is trying to address.

post-operative glioma segmentation
domain shift
generalization
residual tumor tracking
Dice loss instability
Innovation

Methods, ideas, or system contributions that make the work stand out.

loss stabilization
percentile normalization
contrastive learning
subspace attention
post-operative glioma segmentation
A
Alexandru Crişan
Babes,-Bolyai University, Cluj-Napoca, Romania
D
Diana Borza
Babes,-Bolyai University, Cluj-Napoca, Romania