UPMAD-Net: A Brain Tumor Segmentation Network with Uncertainty Guidance and Adaptive Multimodal Feature Fusion

2025-05-06

AI Summary

To address the challenges of brain tumor segmentation—namely, irregular tumor morphology, indistinct boundaries, and substantial inter-modal intensity variations—this paper proposes an uncertainty-guided end-to-end 3D segmentation network. Methodologically, it innovatively integrates region-growing priors into a U-Net architecture, employs Monte Carlo Dropout for uncertainty estimation, and introduces an adaptive multi-modal feature fusion module coupled with an uncertainty-weighted loss to enhance robustness in low-confidence regions. Additionally, it incorporates multi-scale feature fusion (MSFF) and an adaptive attention mechanism (AAM). Evaluated on BraTS2021 test set, the method achieves Dice scores of 89.18% (ET), 93.67% (WT), and 91.23% (TC); on BraTS2019 validation set, it attains 87.43% (ET), 90.92% (WT), and 90.40% (TC), consistently outperforming state-of-the-art approaches.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• 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
• Security and Privacy: Browser and end-point security

Abstract

Background: Brain tumor segmentation has a significant impact on the diagnosis and treatment of brain tumors. Accurate brain tumor segmentation remains challenging due to their irregular shapes, vague boundaries, and high variability. Objective: We propose a brain tumor segmentation method that combines deep learning with prior knowledge derived from a region-growing algorithm. Methods: The proposed method utilizes a multi-scale feature fusion (MSFF) module and adaptive attention mechanisms (AAM) to extract multi-scale features and capture global contextual information. To enhance the model's robustness in low-confidence regions, the Monte Carlo Dropout (MC Dropout) strategy is employed for uncertainty estimation. Results: Extensive experiments demonstrate that the proposed method achieves superior performance on Brain Tumor Segmentation (BraTS) datasets, significantly outperforming various state-of-the-art methods. On the BraTS2021 dataset, the test Dice scores are 89.18% for Enhancing Tumor (ET) segmentation, 93.67% for Whole Tumor (WT) segmentation, and 91.23% for Tumor Core (TC) segmentation. On the BraTS2019 validation set, the validation Dice scores are 87.43%, 90.92%, and 90.40% for ET, WT, and TC segmentation, respectively. Ablation studies further confirmed the contribution of each module to segmentation accuracy, indicating that each component played a vital role in overall performance improvement. Conclusion: This study proposed a novel 3D brain tumor segmentation network based on the U-Net architecture. By incorporating the prior knowledge and employing the uncertainty estimation method, the robustness and performance were improved. The code for the proposed method is available at https://github.com/chenzhao2023/UPMAD_Net_BrainSeg.

Problem

• Segments brain tumors with irregular shapes and vague boundaries
• Improves accuracy using multi-scale feature fusion and attention mechanisms
• Enhances robustness via uncertainty estimation in low-confidence regions

Innovation

• Uses multi-scale feature fusion for tumor segmentation
• Employs adaptive attention mechanisms for contextual information
• Applies Monte Carlo Dropout for uncertainty estimation