发表机构
Seoul National University; OUTTA; Kyung Hee University; Seoul National University School of Medicine; NVIDIA AI Technology Center（首尔大学; OUTTA; 庆熙大学; 首尔大学医学院; 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
针对胆管癌MRI中PNI线索细微稀疏的问题，提出SCINTILLA-SNN脉冲网络，结合分层骨干与多尺度脉冲聚合模块，在182例队列上实现AUROC 0.748并降低能耗23.18倍。
AI 中文摘要
术前预测胆管癌（CCA）中的神经周围侵犯（PNI）具有临床价值，但由于磁共振成像（MRI）上PNI相关线索细微、稀疏且空间上局限于肿瘤边界周围，这一任务仍具挑战性。标准3D CNN和Transformer架构以密集或空间均匀的方式处理体积数据，这可能会稀释细微的PNI相关证据，同时需要在3D特征网格上进行大量乘加运算。为解决这些限制，我们提出SCINTILLA-SNN，一种由四阶段分层骨干网络和多尺度脉冲聚合（MSSA）模块组成的3D脉冲网络，用于PNI预测。骨干网络通过脉冲卷积阶段和局部脉冲窗口调制阶段提取分层体积表示。基于所得的分阶段表示，MSSA将每个空间标记映射到可学习的内容值，并通过源自放电率和时间步级膜电位变异性的脉冲动力学门控对其进行调制。所得分数称为诊断标记分数，用于选择性聚合稀疏的PNI相关证据。对182例CCA患者的10年回顾性队列进行的实验表明，SCINTILLA-SNN在5折交叉验证下达到0.748的AUROC，同时与同一网络的密集仅MAC计算相比，估计推理能耗降低了23.18倍。
英文摘要
Preoperative prediction of perineural invasion (PNI) in cholangiocarcinoma (CCA) is clinically valuable but remains challenging because PNI-related cues on magnetic resonance imaging (MRI) are subtle, sparse, and spatially localized around the tumor boundary. Standard 3D CNN and transformer architectures process volumetric data in a dense or spatially uniform manner, which can dilute subtle PNI-related evidence while requiring a large number of multiply-accumulate operations over 3D feature grids. To address these limitations, we propose SCINTILLA-SNN, a 3D spiking network composed of a four-stage hierarchical backbone and a Multi-Scale Spike Aggregation (MSSA) module for PNI prediction. The backbone extracts hierarchical volumetric representations through spiking convolutional stages and local spike window modulation stages. Given the resulting stage-wise representations, MSSA maps each spatial token to a learnable content value and modulates it with a spike-dynamics gate derived from firing rate and timestep-wise membrane-potential variability. The resulting score, referred to as the diagnostic token score, is used to selectively aggregate sparse PNI-related evidence. Experiments on a 10-year retrospective cohort of 182 CCA patients show that SCINTILLA-SNN achieves an AUROC of 0.748 under 5-fold cross-validation, while reducing the estimated inference energy by 23.18$\times$ compared with dense MAC-only computation of the same network.
