GS-EMA: Integrating Gradient Surgery Exponential Moving Average with Boundary-Aware Contrastive Learning for Enhanced Domain Generalization in Aneurysm Segmentation (2402.15239v1)
Abstract: The automated segmentation of cerebral aneurysms is pivotal for accurate diagnosis and treatment planning. Confronted with significant domain shifts and class imbalance in 3D Rotational Angiography (3DRA) data from various medical institutions, the task becomes challenging. These shifts include differences in image appearance, intensity distribution, resolution, and aneurysm size, all of which complicate the segmentation process. To tackle these issues, we propose a novel domain generalization strategy that employs gradient surgery exponential moving average (GS-EMA) optimization technique coupled with boundary-aware contrastive learning (BACL). Our approach is distinct in its ability to adapt to new, unseen domains by learning domain-invariant features, thereby improving the robustness and accuracy of aneurysm segmentation across diverse clinical datasets. The results demonstrate that our proposed approach can extract more domain-invariant features, minimizing over-segmentation and capturing more complete aneurysm structures.
- “Hemodynamics of thrombus formation in intracranial aneurysms: an in-silico observational study,” APL Bioengineering, 2023.
- “In silico clinical trials: concepts and early adoptions,” Briefings in bioinformatics, vol. 20, no. 5, pp. 1699–1708, 2019.
- “Domain-invariant feature exploration for domain generalization,” Transactions on Machine Learning Research, 2022.
- “Feddg: Federated domain generalization on medical image segmentation via episodic learning in continuous frequency space,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 1013–1023.
- “Dofe: Domain-oriented feature embedding for generalizable fundus image segmentation on unseen datasets,” IEEE Transactions on Medical Imaging, vol. 39, no. 12, pp. 4237–4248, 2020.
- “Self-supervised learning in medicine and healthcare,” Nature Biomedical Engineering, vol. 6, no. 12, pp. 1346–1352, 2022.
- “Towards principled disentanglement for domain generalization,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 8024–8034.
- “Adaptive semi-supervised segmentation of brain vessels with ambiguous labels,” arXiv preprint arXiv:2308.03613, 2023.
- “Gradient surgery for multi-task learning,” Advances in Neural Information Processing Systems, vol. 33, pp. 5824–5836, 2020.
- “Domain generalization via gradient surgery,” in Proceedings of the IEEE/CVF international conference on computer vision, 2021, pp. 6630–6638.
- “Gsmorph: Gradient surgery for cine-mri cardiac deformable registration,” in MICCAI 2023, Cham, 2023, pp. 613–622, Springer Nature Switzerland.
- “Source free domain adaptation for medical image segmentation with fourier style mining,” Medical Image Analysis, vol. 79, pp. 102457, 2022.
- “@ neurist: infrastructure for advanced disease management through integration of heterogeneous data, computing, and complex processing services,” 2010, vol. 14, pp. 1365–1377, IEEE.
- “Swin-unet: Unet-like pure transformer for medical image segmentation,” in European conference on computer vision. Springer, 2022, pp. 205–218.
- “nnu-net: a self-configuring method for deep learning-based biomedical image segmentation,” Nature methods, vol. 18, no. 2, pp. 203–211, 2021.
- “High-throughput 3dra segmentation of brain vasculature and aneurysms using deep learning,” Computer Methods and Programs in Biomedicine, vol. 230, pp. 107355, 2023.
- “Causality-inspired single-source domain generalization for medical image segmentation,” IEEE Transactions on Medical Imaging, vol. 42, no. 4, pp. 1095–1106, 2022.
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.