发表机构
Seoul National University; OUTTA; Chung-Ang University; Samsung Medical Center, Sungkyunkwan University School of Medicine; Samsung Changwon Hospital; NVIDIA AI Technology Center（首尔国立大学; OUTTA; Chung-Ang 大学; 三星医疗中心，成均馆大学医学院; 三星昌原医院; 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
研究针对3D MRI中神经周围侵犯（PNI）预测难题，提出LoSA-Net架构，通过TNA、SAFM和CSRA技术，在168例胆管癌患者的对比增强MRI扫描中，该网络AUC达0.7567，优于卷积和Transformer基线。
AI 中文摘要
神经周围侵犯（PNI）是肿瘤侵袭性的临床相关指标，影响手术决策，因此可靠的术前评估很重要。然而，PNI在MRI上的细微特征常与附近解剖结构相似，常规下采样或过度全局特征聚合会削弱这些精细神经周围线索，降低传统体积模型的有效性。我们提出LoSA-Net，一种用于3D MRI中边界敏感PNI预测的局部化和尺度自适应架构。其中，Talking Neighborhood Attention（TNA）通过局部自注意力和逐头混合保留神经对齐细节，Scale-Adaptive Feature Mixing（SAFM）使用多尺度深度处理调节感受野，Cross-Scale Refinement and Alignment（CSRA）在各阶段保持语义上下文和高分辨率边界之间的一致性。在168例胆管癌患者的对比增强MRI扫描中，LoSA-Net的AUC为0.7567，在匹配的预处理和优化设置下优于代表性的卷积和Transformer基线。
英文摘要
Perineural invasion (PNI) is a clinically relevant indicator of tumor aggressiveness and can influence surgical decision-making, motivating interest in reliable preoperative assessment. The subtle MRI features of PNI, however, often resemble nearby anatomy, complicating noninvasive prediction. These fine perineural cues are easily attenuated by routine downsampling or overly global feature aggregation, reducing the effectiveness of conventional volumetric models. We present LoSA-Net, a localized and scale-adaptive architecture for boundary-sensitive PNI prediction in 3D MRI. Talking Neighborhood Attention (TNA) preserves nerve-aligned detail through localized self-attention with head-wise mixing, and Scale-Adaptive Feature Mixing (SAFM) modulates the receptive field using multi-scale depthwise processing. Cross-Scale Refinement and Alignment (CSRA) maintains consistency between semantic context and high-resolution boundaries across stages. In contrast-enhanced MRI scans from 168 patients with cholangiocarcinoma, LoSA-Net achieves an AUC of 0.7567 and outperforms representative convolutional and transformer baselines under matched preprocessing and optimization settings.
CommentsPublished in the 2026 IEEE 23rd International Symposium on Biomedical Imaging (ISBI 2026); accepted for oral presentation
Journal ref2026 IEEE 23rd International Symposium on Biomedical Imaging (ISBI), 2026
DOI：10.1109/ISBI61048.2026.11515401
