发表机构
Seoul National University; OUTTA; Chung-Ang University; Kyung Hee University; Samsung Medical Center; NVIDIA AI Technology Center（首尔大学; OUTTA; 中央大学; 庆熙大学; 三星医疗中心; NVIDIA AI技术中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出顺序感知2.5D多实例学习框架OAS-MIL，利用MRI轴向顺序预测肝内胆管癌神经周围侵犯，实现0.770的AUROC，优于基线方法。
AI 中文摘要
神经周围侵犯（PNI）是肝内胆管癌（ICC）中一种不利的组织病理学标志，但通常仅在切除后才被确认。术前T2加权MRI可能提供预测PNI的非侵入性影像线索，尽管标签仅在患者层面可用，缺乏切片或体素级别的标注。我们提出了顺序感知板层多实例学习（OAS-MIL），一种用于患者层面PNI预测的弱监督框架。每个以肿瘤为中心的MRI裁剪块被表示为来自连续轴向切片的重叠2.5D板层的有序序列。一个共享编码器提取板层级特征，这些特征通过置换不变的集合注意力分支和双向序列注意力分支进行聚合。在患者层面使用五折标签分层交叉验证，OAS-MIL实现了0.770的平均AUROC，优于所评估的体积和MIL基线方法。这些结果表明，轴向顺序为基于MRI的弱监督PNI预测提供了有用的归纳偏置。
英文摘要
Perineural invasion (PNI) is an adverse histopathologic marker in intrahepatic cholangiocarcinoma (ICC), but it is usually confirmed only after resection. Preoperative T2-weighted MRI may provide noninvasive imaging cues predictive of PNI, although labels are available only at the patient level without slice- or voxel-level annotations. We propose Order-Aware Slab Multiple Instance Learning (OAS-MIL), a weakly supervised framework for patient-level PNI prediction. Each tumor-centered MRI crop is represented as an ordered sequence of overlapping 2.5D slabs formed from contiguous axial slices. A shared encoder extracts slab-level features, which are aggregated by a permutation-invariant set-attention branch and a bidirectional sequence-attention branch. Using five-fold label-stratified cross-validation at the patient level, OAS-MIL achieved a mean AUROC of 0.770, outperforming the evaluated volumetric and MIL baselines. These results suggest that axial order provides a useful inductive bias for weakly supervised PNI prediction from MRI.
