Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.05682 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915186424676352 |
|---|---|
| author | Zhang, Zhenxuan Wu, Hongjie Huang, Jiahao Xie, Baihong Gao, Zhifan Du, Junxian Lally, Pete Yang, Guang |
| author_facet | Zhang, Zhenxuan Wu, Hongjie Huang, Jiahao Xie, Baihong Gao, Zhifan Du, Junxian Lally, Pete Yang, Guang |
| contents | Multi-contrast magnetic resonance imaging (MRI) plays a vital role in brain tumor segmentation and diagnosis by leveraging complementary information from different contrasts. Each contrast highlights specific tumor characteristics, enabling a comprehensive understanding of tumor morphology, edema, and pathological heterogeneity. However, existing methods still face the challenges of multi-level specificity perception across different contrasts, especially with limited annotations. These challenges include data heterogeneity, granularity differences, and interference from redundant information. To address these limitations, we propose a Task-oriented Uncertainty Collaborative Learning (TUCL) framework for multi-contrast MRI segmentation. TUCL introduces a task-oriented prompt attention (TPA) module with intra-prompt and cross-prompt attention mechanisms to dynamically model feature interactions across contrasts and tasks. Additionally, a cyclic process is designed to map the predictions back to the prompt to ensure that the prompts are effectively utilized. In the decoding stage, the TUCL framework proposes a dual-path uncertainty refinement (DUR) strategy which ensures robust segmentation by refining predictions iteratively. Extensive experimental results on limited labeled data demonstrate that TUCL significantly improves segmentation accuracy (88.2\% in Dice and 10.853 mm in HD95). It shows that TUCL has the potential to extract multi-contrast information and reduce the reliance on extensive annotations. The code is available at: https://github.com/Zhenxuan-Zhang/TUCL_BrainSeg. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_05682 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Task-oriented Uncertainty Collaborative Learning for Label-Efficient Brain Tumor Segmentation Zhang, Zhenxuan Wu, Hongjie Huang, Jiahao Xie, Baihong Gao, Zhifan Du, Junxian Lally, Pete Yang, Guang Image and Video Processing Computer Vision and Pattern Recognition Multi-contrast magnetic resonance imaging (MRI) plays a vital role in brain tumor segmentation and diagnosis by leveraging complementary information from different contrasts. Each contrast highlights specific tumor characteristics, enabling a comprehensive understanding of tumor morphology, edema, and pathological heterogeneity. However, existing methods still face the challenges of multi-level specificity perception across different contrasts, especially with limited annotations. These challenges include data heterogeneity, granularity differences, and interference from redundant information. To address these limitations, we propose a Task-oriented Uncertainty Collaborative Learning (TUCL) framework for multi-contrast MRI segmentation. TUCL introduces a task-oriented prompt attention (TPA) module with intra-prompt and cross-prompt attention mechanisms to dynamically model feature interactions across contrasts and tasks. Additionally, a cyclic process is designed to map the predictions back to the prompt to ensure that the prompts are effectively utilized. In the decoding stage, the TUCL framework proposes a dual-path uncertainty refinement (DUR) strategy which ensures robust segmentation by refining predictions iteratively. Extensive experimental results on limited labeled data demonstrate that TUCL significantly improves segmentation accuracy (88.2\% in Dice and 10.853 mm in HD95). It shows that TUCL has the potential to extract multi-contrast information and reduce the reliance on extensive annotations. The code is available at: https://github.com/Zhenxuan-Zhang/TUCL_BrainSeg. |
| title | Task-oriented Uncertainty Collaborative Learning for Label-Efficient Brain Tumor Segmentation |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.05682 |