arXiv 2411.152742024-11-22eess.IVcs.AIcs.CV

基于特征交互式孪生图编码器的图像分析用于从肺癌组织病理图像预测STAS

Feature-interactive Siamese graph encoder-based image analysis to predict STAS from histopathology images in lung cancer

Hunan University（湖南大学）；The Second Xiangya Hospital, Central South University（中南大学湘雅二医院）；Central South University（中南大学）；Hunan Clinical Medical Research Center for Cancer Pathogenic Genes Testing and Diagnosis（湖南省肿瘤致病基因检测与诊断临床医学研究中心）；Shanghai Cancer Institute（上海市肿瘤研究所）；Renji Hospital, School of Medicine, Shanghai Jiaotong University（上海交通大学医学院附属仁济医院）；Shanghai Jiaotong University（上海交通大学）

Liangrui Pan, Qingchun Liang, Wenwu Zeng, Yijun Peng, Zhenyu Zhao, Yiyi Liang, Jiadi Luo, Xiang Wang, Shaoliang Peng

备注：: accept for publication in npj Precision Oncology

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出VERN模型，利用特征交互式孪生图编码器从肺癌组织病理图像中预测STAS，在内部及外部数据集上取得临床级性能，并开放平台以提升诊断效率。

摘要：

经气腔播散（STAS）是肺癌中一种独特的侵袭模式，对预后评估和手术决策至关重要。组织病理学是STAS检测的金标准，但传统方法主观、耗时且易误诊，限制了大规模应用。我们提出了VERN，一种利用特征交互式孪生图编码器的图像分析模型，用于从肺癌组织病理图像中预测STAS。VERN通过特征共享和跳跃连接捕获空间拓扑特征，以增强模型训练。我们使用1,546张组织病理切片构建了一个大型单队列STAS肺癌数据集。VERN在内部验证中达到了0.9215的AUC，在冰冻切片和石蜡包埋切片测试中分别达到了0.8275和0.8829的AUC，展示了临床级性能。在单队列和三个外部数据集上验证后，VERN展现了稳健的预测性能和泛化能力，并提供了一个开放平台（http://plr.20210706.xyz:5000/）以提升STAS诊断的效率和准确性。

英文摘要：

Spread through air spaces (STAS) is a distinct invasion pattern in lung cancer, crucial for prognosis assessment and guiding surgical decisions. Histopathology is the gold standard for STAS detection, yet traditional methods are subjective, time-consuming, and prone to misdiagnosis, limiting large-scale applications. We present VERN, an image analysis model utilizing a feature-interactive Siamese graph encoder to predict STAS from lung cancer histopathological images. VERN captures spatial topological features with feature sharing and skip connections to enhance model training. Using 1,546 histopathology slides, we built a large single-cohort STAS lung cancer dataset. VERN achieved an AUC of 0.9215 in internal validation and AUCs of 0.8275 and 0.8829 in frozen and paraffin-embedded test sections, respectively, demonstrating clinical-grade performance. Validated on a single-cohort and three external datasets, VERN showed robust predictive performance and generalizability, providing an open platform (http://plr.20210706.xyz:5000/) to enhance STAS diagnosis efficiency and accuracy.

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。