Abstract: In multimodal magnetic resonance imaging (MRI) brain tumor segmentation, different MRI modalities make markedly different contributions to tumor subregions. Conventional channel concatenation or simple feature addition cannot adequately characterize modality-specific information, and existing segmentation networks generally lack explicit explanations of modality contributions. These limitations affect the accuracy, robustness, and interpretability of multimodal MRI brain tumor segmentation. To address these issues, a membership-based multimodal MRI brain tumor segmentation network is proposed. The network employs a Private-Shared Encoder to separately extract modality-specific pathological features and cross-modality shared anatomical representations, thereby alleviating multimodal feature entanglement. In the Fuzzy Fusion Layer, a Data-Prior Co-driven Membership Module (DPC-MM) integrates data-driven responses with medical-prior guidance to generate voxel-wise modality memberships, which characterize the dynamic contributions of different MRI modalities across tumor regions. The Fuzzy Feature Aggregation Module (FFAM) then weights the private features of each modality according to their memberships and residually fuses them with shared features, enhancing the representation of tumor spatial heterogeneity and fuzzy boundaries. The network outputs multimodal membership maps and brain tumor segmentation results. Five-fold cross-validation on the BraTS2021 dataset yielded Dice scores of 0.9223±0.0061, 0.8873±0.0064, and 0.8593±0.0110 for whole tumor (WT), tumor core (TC), and enhancing tumor (ET), respectively, with a mean Dice of 0.8897±0.0069. The mean 95th-percentile Hausdorff distance (HD95), average surface distance (ASD), and expected calibration error (ECE) were 5.18±0.53 mm, 3.15±0.54 mm, and 0.1442±0.0073, respectively. Further multi-method comparison experiments were conducted on the BraTS2021 and BraTS2018 HGG datasets. The proposed method achieved Mean Dice values of 0.9037 and 0.8393 and Mean HD95 values of 4.7764 mm and 5.1885 mm, respectively, demonstrating good overall segmentation performance. The results show that the proposed network achieves region-adaptive multimodal feature fusion through voxel-wise modality memberships, while maintaining high segmentation accuracy, boundary quality, and probability calibration. In addition, the generated multimodal membership maps visually reveal differences in modality utilization across spatial locations and tumor subregions, providing a quantitative and visual modality-level representation for model interpretation.

摘要： 多模态磁共振成像（MRI）脑肿瘤分割中，不同MRI模态对肿瘤亚区的贡献存在显著差异，传统通道拼接或简单特征相加难以充分刻画模态特异性，且现有分割网络通常缺少对模态贡献的显式解释，这些问题限制了多模态MRI脑肿瘤分割的准确性、鲁棒性和可解释性。针对上述问题，构建了基于隶属度的多模态MRI脑肿瘤图像分割网络。该网络采用私有-共享解耦编码器（Private-Shared Encoder）分别提取各模态特异性病理特征和跨模态共享解剖表征，以缓解多模态特征纠缠；在模糊融合层（Fuzzy Fusion Layer）中，设计数据与先验协同驱动的隶属度模块（Data-Prior Co-driven Membership Module，DPC-MM），通过数据驱动响应与医学先验引导共同生成体素级模态隶属度，用于表征不同MRI模态在不同肿瘤区域中的动态贡献，并利用模糊特征融合模块（Fuzzy Feature Aggregation Module，FFAM）对各模态私有特征进行隶属度加权，然后与共享特征残差融合，从而增强对肿瘤空间异质性和模糊边界的表征能力。网络最终输出多模态隶属度图及脑肿瘤分割结果。在BraTS2021数据集上进行五折交叉验证，结果显示，整体肿瘤（WT）、肿瘤核心（TC）和增强肿瘤（ET）的Dice系数分别为0.9223±0.0061、0.8873±0.0064和0.8593±0.0110，平均Dice为0.8897±0.0069；平均95% Hausdorff距离（HD95）、平均表面距离（ASD）和期望校准误差（ECE）分别为5.18±0.53 mm、3.15±0.54 mm和0.1442±0.0073。进一步在BraTS2021和BraTS2018 HGG数据集开展多方法对比实验，所提方法的Mean Dice分别为0.9037和0.8393，Mean HD95分别为4.7764 mm和5.1885 mm，体现出较好的综合分割性能。实验结果表明，所提网络能够利用体素级模态隶属度实现区域自适应的多模态特征融合，在获得较高分割精度的同时保持较好的边界质量和概率校准性。同时，所生成的多模态隶属度图能够直观呈现模型在不同空间位置和肿瘤亚区中的模态使用差异，为多模态MRI脑肿瘤分割提供可量化和可视化的模态级解释表示。