Multimodal MRI is essential for brain tumor segmentation, yet missing modalities in clinical practice cause existing methods to exhibit >40% performance variance across modality combinations, rendering them clinically unreliable. We propose AMGFormer, achieving significantly improved stability through three synergistic modules: (1) QuadIntegrator Bridge (QIB) enabling spatially adaptive fusion maintaining consistent predictions regardless of available modalities, (2) Multi-Granular Attention Orchestrator (MGAO) focusing on pathological regions to reduce background sensitivity, and (3) Modality Quality-Aware Enhancement (MQAE) preventing error propagation from corrupted sequences. On BraTS 2018, our method achieves 89.33% WT, 82.70% TC, 67.23% ET Dice scores with <0.5% variance across 15 modality combinations, solving the stability crisis. Single-modality ET segmentation shows 40-81% relative improvements over state-of-the-art methods. The method generalizes to BraTS 2020/2021, achieving up to 92.44% WT, 89.91% TC, 84.57% ET. The model demonstrates potential for clinical deployment with 1.2s inference. Code: https://github.com/guochengxiangives/AMGFormer.

翻译：多模态MRI对于脑肿瘤分割至关重要，然而临床实践中模态缺失导致现有方法在不同模态组合间表现出超过40%的性能波动，使其临床可靠性不足。我们提出AMGFormer，通过三个协同模块实现稳定性显著提升：(1) 四维集成桥接器(QIB)实现空间自适应融合，确保无论可用模态如何均能保持预测一致性；(2) 多粒度注意力协调器(MGAO)聚焦病理区域以降低背景敏感性；(3) 模态质量感知增强器(MQAE)防止受损序列的误差传播。在BraTS 2018数据集上，本方法在15种模态组合中取得89.33% WT、82.70% TC、67.23% ET的Dice分数且波动小于0.5%，解决了稳定性危机。单模态ET分割相较前沿方法实现40-81%的相对提升。该方法可泛化至BraTS 2020/2021数据集，最高达到92.44% WT、89.91% TC、84.57% ET。模型具备1.2秒推理速度，展现出临床部署潜力。代码：https://github.com/guochengxiangives/AMGFormer。