通过注意力监督提升脑肿瘤分割的可解释性，精度媲美大模型且推理更快。
SegGuidedNet: Sub-Region-Aware Attention Supervision for Interpretable Brain Tumor Segmentation
- 设计轻量级注意力门控模块，对不同肿瘤区域进行空间判别性监督。
- 在BraTS2021/2023上平均Dice达0.905/0.897，优于单模型基线，接近十模型集成效果。
- 无需后处理即可提供可视化解释，适合临床部署和医生理解结果。
从多参数MRI中准确分割脑肿瘤亚区域对治疗规划至关重要，但受形态多样性、类别不平衡及影像序列间重叠表现影响，仍具挑战。本文提出SegGuidedNet，一种三维残差编码器-解码器网络，引入新型SegAttentionGate模块，通过轻量辅助损失显式监督解码器生成各亚区域（坏死核心、瘤周水肿、增强肿瘤）的空间判别性注意力图，参数增加不足0.2%。该监督机制在保持视觉模糊类别间判别力的同时，实现无额外成本的推理时空间可解释性。在独立测试集上（各含251例），SegGuidedNet在BraTS2021和BraTS2023 GLI上分别取得0.905（ET=0.873, TC=0.906, WT=0.935）和0.897（ET=0.859, TC=0.902, WT=0.931）的平均Dice值，超越基于集成的nnU-Net与HNF-Netv2，接近10模型集成的Swin UNETR，在推理成本上仅为后者的极小部分。跨两届基准测试的一致表现验证了方法的泛化能力，提供兼具竞争力精度与内置可解释性的轻量级临床实用框架。
原文摘要 · Abstract (English)
Accurate segmentation of brain tumour sub-regions from multi-parametric MRI is critical for treatment planning yet remains challenging due to morphological variability, class imbalance, and overlapping appearances of tumour regions across imaging sequences. We propose SegGuidedNet, a three-dimensional residual encoder--decoder network introducing a novel SegAttentionGate module that explicitly supervises the decoder to produce spatially discriminative attention maps for each tumour sub-region necrotic core, peritumoral oedema, and enhancing tumour via a lightweight auxiliary loss, adding less than 0.2% parameter overhead. This sub-region supervision maintains decoder discriminability between visually ambiguous classes while providing free-of-cost spatial interpretability at inference without any post-hoc explanation method. Evaluated independently on BraTS2021 and BraTS2023 GLI across 251 held-out subjects each, SegGuidedNet achieves mean Dice of 0.905 (ET= 0.873, TC=0.906, WT=0.935) and 0.897 (ET=0.859, TC=0.902, WT=0.931) respectively, surpassing ensemble-based nnU-Net and HNF-Netv2 as a single model and approaching Swin UNETR a 10-model ensemble within 2--4 Dice points at a fraction of the inference cost. The consistency of results across two benchmark editions further confirms the generalisability of the proposed approach, offering competitive accuracy with built-in interpretability in a lightweight, clinically practical framework.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。