基于对比多尺度病理图像分析的精准轻量型外周神经母细胞性肿瘤诊断研究
Towards Accurate and Lightweight Peripheral Neuroblastic Tumor Diagnosis via Contrastive Multi-scale Pathological Image Analysis
AI总结：
提出CoPath框架（含CoHisNet与PathVote），通过对比多尺度病理图像分析实现轻量型外周神经母细胞性肿瘤精准诊断，性能优于多数同类模型且计算复杂度更低。
摘要：
外周神经母细胞性肿瘤（pNTs）是儿童最常见的颅外实体肿瘤之一，准确的病理亚型分型对风险分层和治疗方案制定至关重要。然而，由于儿科肿瘤队列有限、组织学异质性显著、观察者间差异以及现有全切片图像（WSI）分类器的计算负担，苏木精-伊红染色WSI上的pNT亚型分型仍具挑战性。为应对这些挑战，本文提出CoPath框架，由CoHisNet和PathVote组成。CoHisNet是一种用于patch级组织病理分类的轻量型多尺度特征融合网络，通过将Swin Transformer块中的多层感知器组件及分类头替换为Kolmogorov-Arnold Network层，在紧凑架构下提升了非线性特征建模能力；其多尺度交互和对比驱动的特征增强设计使模型既能捕捉组织层面结构，又能获取细粒度细胞形态。PathVote进一步融入病理先验的组织成分信息，将patch级预测聚合为WSI级决策。本文在私有双分支pNTs队列和公开的BreakHis乳腺癌组织病理数据集上对CoPath进行验证，实验结果显示，与通用图像分类器、线性探测下的病理基础模型及病理专用分类模型相比，CoPath达到了相当或更优的性能，同时保持了显著更低的计算复杂度，源代码可在指定URL获取。
英文摘要：
Peripheral neuroblastic tumors (pNTs) are among the most common extracranial solid tumors in children, and accurate pathological subtyping is important for risk stratification and treatment planning. However, pNT subtyping on hematoxylin-eosin whole-slide images (WSIs) remains challenging because of limited pediatric tumor cohorts, marked histological heterogeneity, inter-observer variability, and the computational burden of existing WSI classifiers. To address these challenges, we propose CoPath, a framework consisting of CoHisNet and PathVote. CoHisNet is a lightweight multi-scale feature-fusion network for patch-level histopathological classification. By replacing the multilayer perceptron components in Swin Transformer blocks and the classification head with Kolmogorov-Arnold Network layers, CoHisNet improves nonlinear feature modeling under a compact architecture. Its multi-scale interaction and contrast-driven feature-enhancement design enables the model to capture both tissue-level structures and fine-grained cellular morphology. PathVote further incorporates pathology-informed tissue-component priors to aggregate patch-level predictions into WSI-level decisions. We validated CoPath on a private two-branch PpNTs cohort and the public BreakHis breast cancer histopathology dataset. Experimental results show that CoPath achieves competitive or superior performance compared with general image classifiers, pathology foundation models under linear probing, and pathology-specific classification models, while maintaining substantially lower computational complexity. The source code is available at https://github.com/JSLiam94/CoPath.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
