Lv Changming, Wu Yulian
Department of Surgery, The Fourth Affiliated Hospital, Zhejiang University School of Medicine, Yiwu, CHN.
Department of Surgery, The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, CHN.
Cureus. 2025 May 29;17(5):e85060. doi: 10.7759/cureus.85060. eCollection 2025 May.
Gastrointestinal tumors are among the malignancies with the highest global incidence and mortality rates, and their diagnosis and treatment heavily rely on histopathological examination. However, traditional pathological assessment faces challenges such as strong subjectivity, heavy workload, and low diagnostic consistency. In recent years, with advancements in high-resolution digital slide scanning technology and the rapid development of deep learning algorithms, pathomics has emerged as a novel tool for the precise diagnosis and treatment of gastrointestinal tumors. By extracting high-throughput quantitative features from whole slide images and combining machine learning and deep learning techniques, pathomics enables automated tumor typing, prognosis prediction, and treatment response evaluation. This article reviews the research progress of pathomics in gastrointestinal tumors, focusing on its applications in gene mutation prediction, prognosis assessment, and treatment response prediction, while analyzing current challenges and future directions.
胃肠道肿瘤是全球发病率和死亡率最高的恶性肿瘤之一，其诊断和治疗在很大程度上依赖于组织病理学检查。然而，传统的病理评估面临着主观性强、工作量大、诊断一致性低等挑战。近年来，随着高分辨率数字切片扫描技术的进步和深度学习算法的快速发展，病理组学已成为一种用于胃肠道肿瘤精确诊断和治疗的新型工具。通过从全切片图像中提取高通量定量特征，并结合机器学习和深度学习技术，病理组学能够实现肿瘤的自动分型、预后预测和治疗反应评估。本文综述了病理组学在胃肠道肿瘤中的研究进展，重点介绍了其在基因突变预测、预后评估和治疗反应预测中的应用，同时分析了当前面临的挑战和未来的发展方向。
