Task-oriented Uncertainty Collaborative Learning for Label-Efficient Brain Tumor Segmentation

2025-03-07

AI Summary

In semi-supervised multi-contrast MRI brain tumor segmentation with limited annotations, key challenges include weak cross-modality feature interaction, insufficient task-specific modeling, and interference from redundant information. To address these, we propose a Task-oriented Prompt Attention (TPA) module and a Dual-path Uncertainty Refinement (DUR) strategy. TPA enables dynamic contrast-specific feature modeling via iterative prompt mapping and a prompt-prediction closed-loop mechanism. DUR performs iterative robust optimization through uncertainty-guided dual-path decoding. Evaluated under scarce annotation settings, our method achieves state-of-the-art performance: 88.2% Dice score and 10.853 mm HD95—significantly reducing reliance on labeled data compared to existing approaches. This work establishes a novel paradigm for accurate, resource-efficient clinical segmentation in low-data scenarios.

Technology Category

• Machine Learning: Semi-Supervised Learning
• Computer Vision: Segmentation
• Reasoning under Uncertainty: Uncertainty Representations

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling

Abstract

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.

Problem

• Addresses multi-contrast MRI brain tumor segmentation challenges
• Reduces reliance on extensive labeled data for segmentation
• Improves segmentation accuracy with limited annotations

Innovation

• Task-oriented prompt attention module
• Dual-path uncertainty refinement strategy
• Cyclic process for prompt utilization