人工智能在乳房外Paget病病理诊断及鉴别中的应用  

Application of artificial intelligence in histopathologic diagnosis and differentiation of extramammary Paget’s disease

作　　者：朱一维 吴哲 陈星材 粘永健[2] 罗娜 张恋 吴毅[2] 翟志芳 ZHU Yiwei;WU Zhe;CHEN Xingcai;NIAN Yongjian;LUO Na;ZHANG Lian;WU Yi;ZHAI Zhifang(Department of Dermatology,First Affiliated Hospital,Army Medical University(Third Military Medical University),Chongqing,400038;Department of Digital Medicine,Faculty of Biomedical Engineering and Medical Imaging,Army Medical University(Third Military Medical University),Chongqing,400038;Department of Dermatology,the Third Affiliated Hospital of Chongqing Medical University,Chongqing,401120,China)

机构地区：[1]陆军军医大学(第三军医大学)第一附属医院皮肤科,重庆400038 [2]陆军军医大学(第三军医大学)生物医学工程与影像医学系数字医学教研室,重庆400038 [3]重庆医科大学附属第三医院皮肤科,重庆401120

出　　处：《陆军军医大学学报》2024年第16期1897-1905,共9页Journal of Army Medical University

基　　金：重庆市技术创新与应用发展专项重点项目(CSTB2022TIAD-KPX0181)。

摘　　要：目的建立乳房外Paget病(extramammary Paget’s disease,EMPD)组织病理诊断的人工智能(artificial intelligence,AI)诊断模型,并评价其对EMPD诊断及鉴别诊断的效能。方法收集2003年9月至2023年2月于陆军军医大学第一附属医院皮肤科就诊并行皮肤组织活检术,且病理明确诊断为EMPD、Bowen病、皮肤鳞状细胞癌(squamous cell carcinoma,SCC)以及表皮增生肥厚为主要病理特征的非肿瘤性皮肤病患者的病理资料。以EMPD为主要研究对象,与Bowen病、SCC以及非肿瘤性皮肤病病理图像进行鉴别,通过ResNet101、DenseNet121深度学习神经网络对4种疾病的组织病理进行分类诊断并评价模型效能。结果ResNet101诊断模型诊断EMPD、Bowen病、SCC及非肿瘤性皮肤病的20倍组织病理图像的AUC值分别为0.97、0.98、1.00、0.96,准确度为(0.925±0.011);40倍组织病理图像AUC值分别为1.00、0.99、1.00、0.97,准确度为(0.943±0.017)。DenseNet121诊断模型诊断EMPD、Bowen病、SCC及非肿瘤性皮肤病的20倍组织病理图像的AUC值分别为0.98、0.95、0.99、1.00,准确度为(0.912±0.034);40倍组织病理图像AUC值分别为0.99、0.96、1.00、1.00,准确度为(0.971±0.012)。表示分类诊断模型能够将EMPD与Bowen病、SCC及非肿瘤性皮肤病等的低倍组织病理图像进行有效区分。ResNet101计算量为786.6 M、参数量为4.5 M,DensNet121计算量为289.7 M、参数量为0.8 M。结论本研究建立的组织病理图像人工智能诊断模型对EMPD的诊断及鉴别诊断具有较高效能,并推荐DenseNet121为皮肤病理图片的诊断模型。Objective To establish an artificial intelligence(AI)diagnostic model for the histopathologic diagnosis of extramammary Paget’s disease(EMPD)and to evaluate its efficiency for the diagnosis and differential diagnosis of EMPD.Methods All non-tumor skin disease patients who underwent skin tissue biopsy in Department of Dermatology of First Affiliated Hospital of Army Medical University from September 2003 to February 2023 were recruited,and their pathological data were collected,including EMPD,Bowen’s disease(BD),squamous cell carcinoma(SCC),and epidermal hyperplasia and hypertrophy.With EMPD as the main research subject,the histopathological images of BD,SCC,and non-tumor skin diseases were included in the study.The histopathological data of 4 types of diseases was classified and diagnosed by ResNet101 and DenseNet121 deep learning neural networks,and the performance of these models was evaluated.Results The AUC values of the ResNet101 diagnostic model for the diagnosis of EMPD,BD,SCC and non-tumor skin diseases on the images at×20 magnification were 0.97,0.98,1.00 and 0.96,respectively,with an accuracy of 0.925±0.011,while the AUC values on the images at×40 magnification were 1.00,0.99,1.00 and 0.97,respectively,with an accuracy of 0.943±0.017.The AUC values of the DenseNet121 diagnostic model for the diagnosis of 4 diseases on the images at×20 magnification were 0.98,0.95,0.99 and 1.00,respectively,with an accuracy of 0.912±0.034,while the AUC values on the images at×40 magnification were 0.99,0.96,1.00 and 1.00,respectively,with an accuracy of 0.971±0.012.Our results indicated that the histopathologic diagnostic model could effectively differentiate EMPD from BD,SCC and non-tumor skin diseases at low power magnification.The FLPOs of ResNet101 was 786.6 M,and the parameter was 4.5 M;The FLPOs of DensNet121 was 289.7 M,and the parameter was 0.8M.Conclusion Our AI diagnostic model is of good effectiveness in the diagnosis and differential diagnosis of EMPD.DenseNet121 is recommended as the dermatopatho

关 键 词：乳房外PAGET病 人工智能 诊断模型 病理诊断 

分 类 号：R319[医药卫生—基础医学] R730.4R739.5