深度学习技术在肾癌诊断中的应用  

Application of deep learning technology in diagnosis of renal cell carcinoma

作　　者：焦攀攀 杨瑞 郑庆源 王磊[1] 陈志远[1] 刘修恒[1] JIAO Panpan;YANG Rui;ZHENG Qingyuan;WANG Lei;CHEN Zhiyuan;LIU Xiuheng(Dept.of Urology,Renmin Hospital of Wuhan University,Wuhan 430060,Hubei,China)

机构地区：[1]武汉大学人民医院泌尿外科,湖北武汉430060

出　　处：《武汉大学学报(医学版)》2025年第3期321-326,共6页Medical Journal of Wuhan University

基　　金：湖北省中央引导地方科技发展专项项目(编号:2022BGE232);教育部产学合作协同育人项目(编号:220700001151109)。

摘　　要：传统影像学和组织病理学检查虽在肾癌的诊断中发挥了重要作用,但存在诸多弊端。深度学习技术通过有效提取图像特征,可在CT和MRI图像上实现对肾癌的初步鉴别和良恶性判断。在组织病理学检查上,深度学习技术可以准确预测病理学切片上肾癌的分型并进行预后预测。深度学习技术在肾癌的诊疗中展现出了巨大的潜力,但仍然需要多中心、大样本的高质量研究才能服务于临床工作。Traditional radiology and pathological examinations are pivotal in diagnosing renal cancer,yet they have their limitations.Through the efficient extraction of image features,deep learning technology facilitates the initial differentiation and malignancy assessment of renal cancer on CT and MRI images.In pathological examinations,deep learning accurately predicts the classification of renal cancer on histopathological slides and offers prognostic insights.While deep learning technology shows significant promise in the diagnosis and treatment of renal cancer,its full potential can be realized through high-quality,multicenter studies with large sample sizes to effectively benefit clinical practice.

关 键 词：肾癌 深度学习 计算机断层扫描 磁共振成像 组织病理学检查 卷积神经网络 

分 类 号：R692.9[医药卫生—泌尿科学]