发表机构
University of Science and Technology of China (USTC); Suzhou Institute for Advanced Research, USTC; Donghua University（中国科学技术大学; 中国科学技术大学苏州高等研究院; 东华大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对多模态MRI缺失问题，提出LASSNet，通过层级感知可用性条件融合和三尺度关系-空间融合，在BraTS2019和BraTS2023上分别取得76.7%和83.2%的平均Dice分数。
AI 中文摘要
多模态MRI的脑肿瘤分割依赖于四种成像序列的互补证据，然而由于采集成本、协议差异、扫描失败或患者状况，一个或多个模态可能不可用。现有工作已探索了重建、知识迁移和直接特征融合，但未明确缺失模态融合是否应随表示层级而变化。高分辨率侧向特征保留空间细节，而压缩的瓶颈特征编码语义和跨模态上下文。因此，我们假设融合应同时以模态可用性和特征层级为条件。我们提出了层级感知可用性条件空间-语义融合网络（LASSNet），包含两个层级专用模块。层级可用性条件融合（HACF）通过可用模态的计数归一化聚合、掩码条件通道调制和局部3D细化构建四个侧向表示。三尺度关系-空间融合（TriRSF）在多个瓶颈分辨率下建模可用模态描述符之间的关系和空间上下文，随后进行跨尺度聚合和可用性条件全局空间注意力。共享的从粗到细解码器从TriRSF语义开始，逐步注入HACF特征，无需重建缺失输入。在所有15种非空模态配置中，LASSNet在BraTS2019和BraTS2023上分别获得WT、TC和ET的平均Dice分数为76.7%和83.2%。
英文摘要
Brain tumor segmentation from multimodal MRI relies on complementary evidence across four imaging sequences, yet one or more modalities may be unavailable because of acquisition cost, protocol variation, scan failure, or patient condition. Existing work has explored reconstruction, knowledge transfer, and direct feature fusion, but leaves open whether missing-modality fusion should change with representation level. High-resolution lateral features retain spatial detail, whereas compressed bottleneck features encode semantic and inter-modality context. We therefore hypothesize that fusion should be conditioned jointly on modality availability and feature hierarchy. We propose the Level-Aware Availability-Conditioned Spatial-Semantic Fusion Network (LASSNet), which contains two level-specialized modules. Hierarchical Availability-Conditioned Fusion (HACF) constructs four lateral representations using count-normalized aggregation of available modalities, mask-conditioned channel modulation, and local 3D refinement. Tri-Scale Relational-Spatial Fusion (TriRSF) models relations among available modality descriptors and spatial context across multiple bottleneck resolutions, followed by cross-scale aggregation and availability-conditioned global spatial attention. A shared coarse-to-fine decoder starts from TriRSF semantics and progressively injects HACF features, without reconstructing missing inputs. Across all 15 non-empty modality configurations, LASSNet obtains mean Dice scores of 76.7% and 83.2% over WT, TC, and ET on BraTS2019 and BraTS2023, respectively.
Comments9 pages, 2 figures, 3 tables
