用轻量多尺度分析提升儿童神经母细胞瘤病理分型准确率
Towards Accurate and Lightweight Peripheral Neuroblastic Tumor Diagnosis via Contrastive Multi-scale Pathological Image Analysis
- 设计轻量网络CoHisNet，融合多尺度特征增强细胞形态识别
- 在自建和公开数据集上达到顶尖性能，计算开销更低
- 适合临床病理诊断辅助，尤其适用于小样本儿科肿瘤场景
外周神经母细胞瘤（pNTs）是儿童最常见的颅外实体瘤之一，准确的病理亚型划分对风险分层和治疗决策至关重要。然而，在苏木精-伊红染色全切片图像（WSIs）上进行pNT亚型分类仍面临挑战，原因包括儿科肿瘤队列有限、组织学异质性显著、观察者间差异大，以及现有分类器计算开销高。为此，我们提出CoPath框架，包含CoHisNet和PathVote两部分。CoHisNet是一种轻量级多尺度特征融合网络，用于局部切片分类。通过将Swin Transformer块中的多层感知机和分类头替换为Kolmogorov-Arnold网络层，在紧凑架构下提升非线性特征建模能力。其多尺度交互与对比驱动的特征增强设计可同时捕捉组织级结构与细粒度细胞形态。PathVote进一步引入病理解剖先验知识，将局部切片预测聚合为全切片决策。我们在一个私有双分支pNTs队列和公开的BreakHis乳腺癌病理数据集上验证了CoPath。实验表明，CoPath在性能上优于或媲美通用图像分类器、线性探查下的病理基础模型及专用于病理的分类模型，且计算复杂度显著降低。源代码已开源：https://github.com/JSLiam94/CoPath。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。