Verena Bitto, Xiaofeng Jiang, Michael Baumann, Jakob Nikolas Kather, Ina Kurth
{"title":"深度学习从常规病理预测鳞状肿瘤实体的生存:来自头颈部、食道癌、肺癌和宫颈癌的见解。","authors":"Verena Bitto, Xiaofeng Jiang, Michael Baumann, Jakob Nikolas Kather, Ina Kurth","doi":"10.1016/j.modpat.2025.100845","DOIUrl":null,"url":null,"abstract":"<p><p>Computational pathology-based models are becoming increasingly popular for extracting biomarkers from images of cancer tissue. However, their validity is often only demonstrated on a single unseen validation cohort, limiting insights into their generalizability and posing challenges for explainability. In this study, we developed models to predict overall survival using haematoxylin and eosin (H&E) slides from formalin-fixed paraffin-embedded (FFPE) samples in head and neck squamous cell carcinoma (HNSCC). By validating our models across diverse squamous tumor entities, including head and neck (hazard ratio [HR] = 1.58, 95% CI = 1.17-2.12, p = 0.003), esophageal (non- significant), lung (HR = 1.31, 95% CI = 1.13-1.52, p < 0.001) and cervical (HR = 1.39, 95% CI = 1.10-1.75, p = 0.005) squamous cell carcinomas, we showed that the predicted risk score captures relevant information for survival beyond HNSCC. Correlation analysis indicated that the predicted risk score is strongly associated with various clinical factors, including human papillomavirus status, tumor volume and smoking history, although the specific factors vary across cohorts. These results emphasize the relevance of comprehensive validation and in-depth assessment of computational pathology-based models to better characterize the underlying patterns they learn during training.</p>","PeriodicalId":18706,"journal":{"name":"Modern Pathology","volume":" ","pages":"100845"},"PeriodicalIF":7.1000,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Deep Learning Predicts Survival Across Squamous Tumor Entities From Routine Pathology: Insights from Head and Neck, Esophagus, Lung and Cervical Cancer.\",\"authors\":\"Verena Bitto, Xiaofeng Jiang, Michael Baumann, Jakob Nikolas Kather, Ina Kurth\",\"doi\":\"10.1016/j.modpat.2025.100845\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Computational pathology-based models are becoming increasingly popular for extracting biomarkers from images of cancer tissue. However, their validity is often only demonstrated on a single unseen validation cohort, limiting insights into their generalizability and posing challenges for explainability. In this study, we developed models to predict overall survival using haematoxylin and eosin (H&E) slides from formalin-fixed paraffin-embedded (FFPE) samples in head and neck squamous cell carcinoma (HNSCC). By validating our models across diverse squamous tumor entities, including head and neck (hazard ratio [HR] = 1.58, 95% CI = 1.17-2.12, p = 0.003), esophageal (non- significant), lung (HR = 1.31, 95% CI = 1.13-1.52, p < 0.001) and cervical (HR = 1.39, 95% CI = 1.10-1.75, p = 0.005) squamous cell carcinomas, we showed that the predicted risk score captures relevant information for survival beyond HNSCC. Correlation analysis indicated that the predicted risk score is strongly associated with various clinical factors, including human papillomavirus status, tumor volume and smoking history, although the specific factors vary across cohorts. These results emphasize the relevance of comprehensive validation and in-depth assessment of computational pathology-based models to better characterize the underlying patterns they learn during training.</p>\",\"PeriodicalId\":18706,\"journal\":{\"name\":\"Modern Pathology\",\"volume\":\" \",\"pages\":\"100845\"},\"PeriodicalIF\":7.1000,\"publicationDate\":\"2025-07-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Modern Pathology\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1016/j.modpat.2025.100845\",\"RegionNum\":1,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"PATHOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Modern Pathology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1016/j.modpat.2025.100845","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PATHOLOGY","Score":null,"Total":0}
引用次数: 0
摘要
基于计算病理学的模型在从癌症组织图像中提取生物标志物方面越来越受欢迎。然而,它们的有效性通常只在一个看不见的验证队列中得到证明,这限制了对其普遍性的了解,并对可解释性提出了挑战。在这项研究中,我们建立了预测头颈部鳞状细胞癌(HNSCC)中福尔马林固定石蜡包埋(FFPE)样本的总生存期的模型,使用血红素和伊红(H&E)玻片。通过在不同的鳞状肿瘤实体中验证我们的模型,包括头颈部(风险比[HR] = 1.58, 95% CI = 1.17-2.12, p = 0.003)、食管癌(无显著性)、肺癌(HR = 1.31, 95% CI = 1.13-1.52, p < 0.001)和宫颈(HR = 1.39, 95% CI = 1.10-1.75, p = 0.005)鳞状细胞癌,我们发现预测的风险评分可以获取HNSCC以外生存的相关信息。相关分析表明,预测风险评分与多种临床因素密切相关,包括人乳头瘤病毒状态、肿瘤体积和吸烟史,尽管具体因素因队列而异。这些结果强调了全面验证和深入评估基于计算病理学的模型的相关性,以更好地表征他们在训练中学习的潜在模式。
Deep Learning Predicts Survival Across Squamous Tumor Entities From Routine Pathology: Insights from Head and Neck, Esophagus, Lung and Cervical Cancer.
Computational pathology-based models are becoming increasingly popular for extracting biomarkers from images of cancer tissue. However, their validity is often only demonstrated on a single unseen validation cohort, limiting insights into their generalizability and posing challenges for explainability. In this study, we developed models to predict overall survival using haematoxylin and eosin (H&E) slides from formalin-fixed paraffin-embedded (FFPE) samples in head and neck squamous cell carcinoma (HNSCC). By validating our models across diverse squamous tumor entities, including head and neck (hazard ratio [HR] = 1.58, 95% CI = 1.17-2.12, p = 0.003), esophageal (non- significant), lung (HR = 1.31, 95% CI = 1.13-1.52, p < 0.001) and cervical (HR = 1.39, 95% CI = 1.10-1.75, p = 0.005) squamous cell carcinomas, we showed that the predicted risk score captures relevant information for survival beyond HNSCC. Correlation analysis indicated that the predicted risk score is strongly associated with various clinical factors, including human papillomavirus status, tumor volume and smoking history, although the specific factors vary across cohorts. These results emphasize the relevance of comprehensive validation and in-depth assessment of computational pathology-based models to better characterize the underlying patterns they learn during training.
期刊介绍:
Modern Pathology, an international journal under the ownership of The United States & Canadian Academy of Pathology (USCAP), serves as an authoritative platform for publishing top-tier clinical and translational research studies in pathology.
Original manuscripts are the primary focus of Modern Pathology, complemented by impactful editorials, reviews, and practice guidelines covering all facets of precision diagnostics in human pathology. The journal's scope includes advancements in molecular diagnostics and genomic classifications of diseases, breakthroughs in immune-oncology, computational science, applied bioinformatics, and digital pathology.