一种用于GBM生存预测的准确且可解释的Hyper图神经网络
An Accurate and Interpretable Hyper Graph Neural Network for GBM Survival Prediction
浏览论文内容
中文总结 AI 辅助
提出多模态sheaf超图神经网络，结合概念瓶颈层与EST正则化，在GBM生存预测中实现准确性与可解释性兼顾，C指数0.643且方差最低。
中文摘要 AI 辅助
胶质母细胞瘤（GBM）的生存预测要求模型既准确又可解释，然而现有方法将这些目标视为相互竞争，高性能模型牺牲透明度，而可解释模型则接受预测能力下降。我们认为这种权衡并非固有。图神经网络为提取可解释、可说明的表示提供了结构基础，而不会损害判别能力。此外，当前方法通常依赖单一成像模态，未能充分利用多模态MRI和临床元数据中可用的互补信息。我们提出了一种多模态框架，集成三个组件以同时实现这两个目标：（1）一个sheaf超图神经网络，通过方向性、非对称消息传递捕获组织斑块间的高阶关系；（2）一个概念瓶颈层，将学习到的表示压缩为临床基础概念，强制实现事前可解释性；（3）一个扩展充分性检验（EST）正则化器，在训练期间惩罚不忠实的解释，确保模型解释真实反映内部决策过程。临床和基因组特征通过门控融合纳入，保留分子标记物的主导预后信号，同时保持概念级可追溯性。在UPenn-GBM数据集的593名患者上，采用5折交叉验证评估，我们的框架实现了0.643的一致性指数，且在所有比较模型中具有最低的折级方差（标准差=0.015）。据我们所知，这是首个将sheaf超图卷积、概念瓶颈监督和EST正则化统一用于脑MRI可解释生存预测的工作。
英文摘要
Survival prediction for glioblastoma multiforme (GBM) demands models that are both accurate and interpretable, yet existing approaches treat these objectives as com- peting, where performant models sacrifice transparency, while interpretable models accept degraded predictive power. We argue that this trade-off is not inherent. Graph neural net- works offer a structural foundation for extracting interpretable, explainable representations without compromising discriminative ability. Furthermore, current methods typically rely on a single imaging modality, underutilizing the complementary information available across multi-modal MRI and clinical metadata. We propose a multi-modal framework that inte- grates three components to address both objectives simultaneously: (1) a sheaf hypergraph neural network that captures higher-order relationships among tissue patches through direc- tional, asymmetric message passing; (2) a concept bottleneck layer that compresses learned representations into clinically grounded concepts, enforcing ante-hoc interpretability; and (3) an extension sufficiency test (EST) regularizer that penalizes unfaithful explanations during training, ensuring that model explanations genuinely reflect the internal decision process. Clinical and genomic features are incorporated through gated fusion, preserving the dominant prognostic signal of molecular markers while retaining concept-level traceabil- ity. Evaluated on 593 patients from the UPenn-GBM dataset under 5-fold cross-validation, our framework achieves a concordance index of 0.643 with the lowest fold-level variance among all compared models (std = 0.015). To our knowledge, this is the first work to unify sheaf hypergraph convolution, concept bottleneck supervision, and EST regularization for interpretable survival prediction from brain MRI
