Universal topology refinement for medical image segmentation with polynomial feature synthesis

Conference item

Although existing medical image segmentation methods provide impressive pixel-wise accuracy, they often neglect topological correctness, making their segmentations unusable for many downstream tasks. One option is to retrain such models whilst including a topology-driven loss component. However, this is computationally expensive and often impractical. A better solution would be to have a versatile plug-and-play topology refinement method that is compatible with any domain-specific segmentation pipeline. Directly training a post-processing model to mitigate topological errors often fails as such models tend to be biased towards the topological errors of a target segmentation network. The diversity of these errors is confined to the information provided by a labelled training set, which is especially problematic for small datasets. Our method solves this problem by training a model-agnostic topology refinement network with synthetic segmentations that cover a wide variety of topological errors. Inspired by the Stone-Weierstrass theorem, we synthesize topology-perturbation masks with randomly sampled coefficients of orthogonal polynomial bases, which ensures a complete and unbiased representation. Practically, we verified the efficiency and effectiveness of our methods as being compatible with multiple families of polynomial bases, and show evidence that our universal plug-and-play topology refinement network outperforms both existing topology-driven learning-based and post-processing methods. We also show that combining our method with learning-based models provides an effortless add-on, which can further improve the performance of existing approaches.

Authors: Li, L; Wang, H; Baugh, M; Ma, Q; Zhang, W

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Springer
• Host title: Medical Image Computing and Computer Assisted Intervention – MICCAI 2024: 27th International Conference, Marrakesh, Morocco, October 6–10, 2024, Proceedings, Part IX
• Pages: 670-680
• Series: Lecture Notes in Computer Science
• Series number: 15009
• Place of publication: Cham, Switzerland
• Publication date: 2024-10-03
• Acceptance date: 2024-06-17
• Event title: 27th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2024)
• Event location: Marrakesh, Morocco
• Event website: https://conferences.miccai.org/2024/
• Event start date: 2024-10-06
• Event end date: 2024-10-10
• DOI: 10.1007/978-3-031-72114-4_64
• EISSN: 1611-3349
• ISSN: 0302-9743
• EISBN: 9783031721144
• ISBN: 9783031721137
• Language: English
• Keywords: topology; segmentation; synthesis