Your browser doesn't support javascript.
loading
Human-multimodal deep learning collaboration in 'precise' diagnosis of lupus erythematosus subtypes and similar skin diseases.
Li, Qianwen; Yang, Zhi; Chen, Kaili; Zhao, Ming; Long, Hai; Deng, Yueming; Hu, Haoran; Jia, Chen; Wu, Meiyu; Zhao, Zhidan; Zhu, Huan; Zhou, Suqing; Zhao, Mingming; Cao, Pengpeng; Zhou, Shengnan; Song, Yang; Tang, Guishao; Liu, Juan; Jiang, Jiao; Liao, Wei; Zhou, Wenhui; Yang, Bingyi; Xiong, Feng; Zhang, Suhan; Gao, Xiaofei; Jiang, Yiqun; Zhang, Wei; Zhang, Bo; He, Yan-Ling; Ran, Liwei; Zhang, Chunlei; Wu, Wenting; Suolang, Quzong; Luo, Hanhuan; Kang, Xiaojing; Wu, Caoying; Jin, Hongzhong; Chen, Lei; Guo, Qing; Gui, Guangji; Li, Shanshan; Si, Henan; Guo, Shuping; Liu, Hong-Ye; Liu, Xiguang; Ma, Guo-Zhang; Deng, Danqi; Yuan, Limei; Lu, Jianyun; Zeng, Jinrong.
Affiliation
  • Li Q; Department of Dermatology, Hunan Key Laboratory of Medical Epigenomics, The Second Xiangya Hospital of Central South University, Changsha, China.
  • Yang Z; Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education, Xiangtan University, Xiangtan, China.
  • Chen K; Department of Dermatology, Hunan Key Laboratory of Medical Epigenomics, The Second Xiangya Hospital of Central South University, Changsha, China.
  • Zhao M; Department of Dermatology, Hunan Key Laboratory of Medical Epigenomics, The Second Xiangya Hospital of Central South University, Changsha, China.
  • Long H; Department of Dermatology, Hunan Key Laboratory of Medical Epigenomics, The Second Xiangya Hospital of Central South University, Changsha, China.
  • Deng Y; Department of Dermatology, Hunan Key Laboratory of Medical Epigenomics, The Second Xiangya Hospital of Central South University, Changsha, China.
  • Hu H; Department of Dermatology, Hunan Key Laboratory of Medical Epigenomics, The Second Xiangya Hospital of Central South University, Changsha, China.
  • Jia C; Department of Dermatology, Hunan Key Laboratory of Medical Epigenomics, The Second Xiangya Hospital of Central South University, Changsha, China.
  • Wu M; Department of Dermatology, Hunan Key Laboratory of Medical Epigenomics, The Second Xiangya Hospital of Central South University, Changsha, China.
  • Zhao Z; Department of Dermatology, Hunan Key Laboratory of Medical Epigenomics, The Second Xiangya Hospital of Central South University, Changsha, China.
  • Zhu H; Department of Dermatology, Hunan Key Laboratory of Medical Epigenomics, The Second Xiangya Hospital of Central South University, Changsha, China.
  • Zhou S; Department of Dermatology, Hunan Key Laboratory of Medical Epigenomics, The Second Xiangya Hospital of Central South University, Changsha, China.
  • Zhao M; Department of Dermatology, Hunan Key Laboratory of Medical Epigenomics, The Second Xiangya Hospital of Central South University, Changsha, China.
  • Cao P; Department of Dermatology, Hunan Key Laboratory of Medical Epigenomics, The Second Xiangya Hospital of Central South University, Changsha, China.
  • Zhou S; Department of Dermatology, Hunan Key Laboratory of Medical Epigenomics, The Second Xiangya Hospital of Central South University, Changsha, China.
  • Song Y; Department of Dermatology, Hunan Key Laboratory of Medical Epigenomics, The Second Xiangya Hospital of Central South University, Changsha, China.
  • Tang G; Department of Dermatology, Hunan Key Laboratory of Medical Epigenomics, The Second Xiangya Hospital of Central South University, Changsha, China.
  • Liu J; Department of Dermatology, Hunan Key Laboratory of Medical Epigenomics, The Second Xiangya Hospital of Central South University, Changsha, China.
  • Jiang J; Department of Dermatology, Hunan Key Laboratory of Medical Epigenomics, The Second Xiangya Hospital of Central South University, Changsha, China.
  • Liao W; Department of Dermatology, Hunan Children's Hospital, Changsha, China.
  • Zhou W; Department of Dermatology, Hunan Key Laboratory of Medical Epigenomics, The Second Xiangya Hospital of Central South University, Changsha, China.
  • Yang B; Department of Dermatology, Hunan Key Laboratory of Medical Epigenomics, The Second Xiangya Hospital of Central South University, Changsha, China.
  • Xiong F; Department of Dermatology, Hunan Key Laboratory of Medical Epigenomics, The Second Xiangya Hospital of Central South University, Changsha, China.
  • Zhang S; Department of Dermatology, Hunan Key Laboratory of Medical Epigenomics, The Second Xiangya Hospital of Central South University, Changsha, China.
  • Gao X; Department of Dermatology, Hunan Children's Hospital, Changsha, China.
  • Jiang Y; Institute of Dermatology, Chinese Academy of Medical Sciences and Peking Union Medical College, Nanjing, China.
  • Zhang W; Institute of Dermatology, Chinese Academy of Medical Sciences and Peking Union Medical College, Nanjing, China.
  • Zhang B; Institute of Dermatology, Chinese Academy of Medical Sciences and Peking Union Medical College, Nanjing, China.
  • He YL; Department of Dermatology, Beijing Chao-Yang Hospital, Capital Medical University, Beijing, China.
  • Ran L; Department of Dermatology, Beijing Chao-Yang Hospital, Capital Medical University, Beijing, China.
  • Zhang C; Department of Dermatology, Peking University Third Hospital, Beijing, China.
  • Wu W; Department of Dermatology, Peking University Third Hospital, Beijing, China.
  • Suolang Q; Department of Dermatology, People's Hospital of Tibet Autonomous Region, Lhasa, China.
  • Luo H; Department of Dermatology, People's Hospital of Tibet Autonomous Region, Lhasa, China.
  • Kang X; Department of Dermatology, People's Hospital of Xinjiang Uygur Autonomous Region, Urumqi, China.
  • Wu C; Department of Dermatology, People's Hospital of Xinjiang Uygur Autonomous Region, Urumqi, China.
  • Jin H; Department of Dermatology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing, China.
  • Chen L; Department of Dermatology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing, China.
  • Guo Q; Department of Dermatology, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China.
  • Gui G; Department of Dermatology, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China.
  • Li S; Department of Dermatology, The First Bethune Hospital of Jilin University, Changchun, China.
  • Si H; Department of Dermatology, The First Bethune Hospital of Jilin University, Changchun, China.
  • Guo S; Department of Dermatology, The First Hospital of Shanxi Medical University, Taiyuan, China.
  • Liu HY; Department of Dermatology, The First Hospital of Shanxi Medical University, Taiyuan, China.
  • Liu X; Department of Dermatology, The Hei Long Jiang Provincial Hospital, Harbin, China.
  • Ma GZ; Department of Dermatology, The Hei Long Jiang Provincial Hospital, Harbin, China.
  • Deng D; Department of Dermatology, The Second Affiliated Hospital of Kunming Medical University, Kunming, China.
  • Yuan L; Department of Dermatology, The Second Affiliated Hospital of Kunming Medical University, Kunming, China.
  • Lu J; Department of Dermatology, The Third Xiangya Hospital, Central South University, Changsha, China.
  • Zeng J; Department of Dermatology, The Third Xiangya Hospital, Central South University, Changsha, China.
J Eur Acad Dermatol Venereol ; 2024 Apr 15.
Article in En | MEDLINE | ID: mdl-38619440
ABSTRACT

BACKGROUND:

Lupus erythematosus (LE) is a spectrum of autoimmune diseases. Due to the complexity of cutaneous LE (CLE), clinical skin image-based artificial intelligence is still experiencing difficulties in distinguishing subtypes of LE.

OBJECTIVES:

We aim to develop a multimodal deep learning system (MMDLS) for human-AI collaboration in diagnosis of LE subtypes.

METHODS:

This is a multi-centre study based on 25 institutions across China to assist in diagnosis of LE subtypes, other eight similar skin diseases and healthy subjects. In total, 446 cases with 800 clinical skin images, 3786 multicolor-immunohistochemistry (multi-IHC) images and clinical data were collected, and EfficientNet-B3 and ResNet-18 were utilized in this study.

RESULTS:

In the multi-classification task, the overall performance of MMDLS on 13 skin conditions is much higher than single or dual modals (Sen = 0.8288, Spe = 0.9852, Pre = 0.8518, AUC = 0.9844). Further, the MMDLS-based diagnostic-support help improves the accuracy of dermatologists from 66.88% ± 6.94% to 81.25% ± 4.23% (p = 0.0004).

CONCLUSIONS:

These results highlight the benefit of human-MMDLS collaborated framework in telemedicine by assisting dermatologists and rheumatologists in the differential diagnosis of LE subtypes and similar skin diseases.
Fulltext
Add to My VHL
Print
XML
PubMed Links
Search on Google

Full text: 1 Collection: 01-internacional Database: MEDLINE Language: En Journal: J Eur Acad Dermatol Venereol Journal subject: DERMATOLOGIA / DOENCAS SEXUALMENTE TRANSMISSIVEIS Year: 2024 Document type: Article Affiliation country: China
Fulltext
Add to My VHL
Print
XML
PubMed Links
Search on Google

Full text: 1 Collection: 01-internacional Database: MEDLINE Language: En Journal: J Eur Acad Dermatol Venereol Journal subject: DERMATOLOGIA / DOENCAS SEXUALMENTE TRANSMISSIVEIS Year: 2024 Document type: Article Affiliation country: China