Deep learning-based,computer-aided classifier developed with dermoscopic images shows comparable performance to 164 dermatologists in cutaneous disease diagnosis in the Chinese population

作     者：Shi-Qi Wang Xin-Yuan Zhang Jie Liu Cui Tao Chen-Yu Zhu Chang Shu Tao Xu Hong-Zhong Jin Wang Shi-Qi;Zhang Xin-Yuan;Liu Jie;Tao Cui;Zhu Chen-Yu;Shu Chang;Xu Tao;Jin Hong-Zhong

作者机构：Department of DermatologyPeking Union Medical College HospitalChinese Academy of Medical Sciences and Peking Union Medical CollegeBeijing 100730China School of Biomedical InformaticsThe University of Texas Health Science Center at HoustonHoustonTX 77030USA Department of Epidemiology and StatisticsSchool of Basic MedicinePeking Union Medical CollegeInstitute of Basic Medical SciencesChinese Academy of Medical SciencesBeijing 100005China 

出 版 物：《Chinese Medical Journal》 (中华医学杂志（英文版）)

年 卷 期：2020年第133卷第17期

页      面：2027-2036页

核心收录：

学科分类：1002[医学-临床医学] 100206[医学-皮肤病与性病学] 10[医学] 

基　　金：This work was supported by grants from the Beijing Natural Science Foundation(No.7182127) the National Natural Science Foundation of China(No.61871011) the National Key Research and Development Program of China(No.2016YFC0901500) the Non-profit Central Research Institute Fund of Chinese Academy of Medical Sciences(No.2019XK320024) the CAMS Innovation Fund for Medical Sciences(No.2017-I2M-3-020) 

主　　题：Artificial intelligence Convolutional neural network Skin tumor Psoriasis Dermoscopy 

摘      要：Background:Diagnoses of Skin diseases are frequently delayed in China due to lack of dermatologists.A deep learning-based diagnosis supporting system can facilitate pre-screening patients to prioritize dermatologists’*** aimed to evaluate the classification sensitivity and specificity of deep learning models to classify skin tumors and psoriasis for Chinese population with a modest number of dermoscopic ***:We developed a convolutional neural network(CNN)based on two datasets from a consecutive series of patients who underwent the dermoscopy in the clinic of the Department of Dermatology,Peking Union Medical College Hospital,between 2016 and 2018,*** order to evaluate the feasibility of the algorithm,we used two *** I consisted of 7192 dermoscopic images for a multi-class model to differentiate three most common skin tumors and other *** II consisted of 3115 dermoscopic images for a two-class model to classify psoriasis from other inflammatory *** compared the performance of CNN with 164 dermatologists in a reader study with 130 dermoscopic *** experts’consensus was used as the reference standard except for the cases of basal cell carcinoma(BCC),which were all confirmed by ***:The accuracies of multi-class and two-class models were 81.49%±0.88%and 77.02%±1.81%,*** the reader study,for the multi-class tasks,the diagnosis sensitivity and specificity of 164 dermatologists were 0.770 and 0.962 for BCC,0.807 and 0.897 for melanocytic nevus,0.624 and 0.976 for seborrheic keratosis,0.939 and 0.875 for theothersgroup,respectively;the diagnosis sensitivity and specificity of multi-class CNN were 0.800 and 1.000 for BCC,0.800 and 0.840 for melanocytic nevus,0.850 and 0.940 for seborrheic keratosis,0.750 and 0.940 for theothersgroup,*** the two-class tasks,the sensitivity and specificity of dermatologists and CNN for classifying psoriasis were 0.872 and 0.838