发表机构
Kunsan National University; Tsinghua University（群山国立大学; 清华大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出CrossScale-GLIO框架，通过结构感知最优传输对齐MRI与病理图的拓扑关系，在胶质瘤亚型分类和检索上取得显著提升，并验证拓扑保持的关键作用。
AI 中文摘要
磁共振成像和组织病理学以截然不同的尺度观察同一胶质瘤。我们提出CrossScale-GLIO，一种视觉多模态框架，将MRI表示为肿瘤栖息地图，将组织学表示为细胞微环境图，然后通过以诊断语言锚定的结构感知最优传输目标进行对齐。在配对和外部胶质瘤队列中，CrossScale-GLIO实现了配对测试亚型宏F1为0.789，IDH AUROC为0.934，1p/19q AUROC为0.884，MGMT AUROC为0.802。相对于仅特征传输，亚型增益为2.8个百分点（95%置信区间：1.2至4.4，校正p=0.0019）。双向患者检索达到Recall@1值0.286和0.278，Recall@5值0.621和0.608。病理学家将81.2%的高质量栖息地-微环境对评为生物学上合理的。删除最高质量对使正确类别概率降低0.184，而随机删除则降低0.049。保持度不变的图重连使亚型宏F1降低0.034，检索Recall@1降低0.090，直接证实了保持的关系拓扑驱动跨尺度对应。
英文摘要
Magnetic resonance imaging and histopathology observe the same glioma at radically different scales. We present CrossScale-GLIO, a visual multimodal framework that represents MRI as a tumor-habitat graph and histology as a cell-niche graph, then aligns them with a structure-aware optimal transport objective anchored by diagnostic language. Across paired and external glioma cohorts, CrossScale-GLIO achieved a paired-test subtype macro-F1 of 0.789, IDH AUROC of 0.934, 1p/19q AUROC of 0.884, and MGMT AUROC of 0.802. The subtype gain over feature-only transport was 2.8 percentage points (95% CI: 1.2 to 4.4, adjusted p = 0.0019). Bidirectional patient retrieval reached Recall@1 values of 0.286 and 0.278, and Recall@5 values of 0.621 and 0.608. Pathologists rated 81.2% of high-mass habitat-niche pairs as biologically plausible. Deleting the highest-mass pair reduced correct-class probability by 0.184, compared with 0.049 under random deletion. Degree-preserving graph rewiring reduced subtype macro-F1 by 0.034 and retrieval Recall@1 by 0.090, directly confirming that preserved relational topology drives cross-scale correspondence.
