ROBUST-WT: Robust Uncertainty-aware Segmentation Transform via Whitening and Training Enhancements
Quick Take
The study enhances the WT-PSE model for robust medical image segmentation, achieving a Dice score of 0.956 on the fundus optic disc benchmark, surpassing the previous score of 0.939. Key improvements include domain-adaptive augmentations and a hybrid loss function, addressing limitations in training and performance consistency across different imaging devices.
Key Points
- Introduces domain-adaptive augmentations like random erasing and gamma correction.
- Implements a hybrid BCE and Dice loss for better edge-aware segmentation.
- Employs a curriculum-based Dice weight scheduling strategy for training stability.
- Achieves a final epoch Dice score of 0.956, improving upon the baseline score of 0.939.
- Enhancements allow consistent performance gains without altering the WT-PSE architecture.
Article Content
From source RSS / original summaryarXiv:2606. 03069v1 Announce Type: new Abstract: Generalized segmentation of medical images prevents performance degradation when different imaging devices and clinical protocols are used across multiple domains. The Whitening Transform-based Probabilistic Shape Regularization Extractor (WT-PSE), published in IEEE Transactions on Medical Imaging in 2024, addresses this challenge by employing feature decorrelation and Wasserstein distance-based knowledge distillation to achieve robust cross-domain segmentation.
This study systematically examines improvements to the WT-PSE learning framework. Four limitations in the original implementation are identified: limited training augmentations that fail to simulate real scanner variations, reliance on per-pixel binary cross-entropy loss that is sensitive to edge noise, the absence of a scheduled loss weighting strategy that may destabilize early training, and the lack of ablation switches for controlled scientific comparison.
To address these issues, we propose four enhancements: (1) domain-adaptive augmentation including random erasing, gamma correction, and salt-and-pepper noise; (2) a hybrid BCE and Dice loss function for improved edge-aware segmentation under noisy conditions; (3) a curriculum-based Dice weight scheduling strategy; and (4) command-line control flags for systematic ablation studies.
Experiments on the fundus optic disc segmentation benchmark demonstrate that the improved pipeline achieves a final epoch optic-disc Dice score of 0. 956 and an ASD score of 13. 31, outperforming the baseline epoch-5 Dice score of 0. 939. These results indicate that training-level improvements can provide consistent performance gains without modifying the underlying WT-PSE architecture.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →Plan2Map: A Multimodal Benchmark for Document-Grounded Geospatial Boundary Reconstruction from Planning Records
Plan2Map introduces a 208-case benchmark for reconstructing geospatial boundaries from UK planning documents. The GeoPlanAgent system achieves a mean IoU of 0.736, significantly outperforming baseline models, highlighting the challenges in localization and map registration.
