Deep skin diseases diagnostic system with Dual-channel Image and Extracted Text
BackgroundDue to the lower reliability of laboratory tests, skin diseases are more suitable for diagnosis with AI models. There are limited AI dermatology diagnostic models combining images and text; few of these are for Asian populations, and few cover the most common types of diseases.MethodsLever...
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-10-01
|
| Series: | Frontiers in Artificial Intelligence |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frai.2023.1213620/full |
| _version_ | 1797656073476243456 |
|---|---|
| author | Huanyu Li Huanyu Li Peng Zhang Zikun Wei Tian Qian Yiqi Tang Kun Hu Xianqiong Huang Xinxin Xia Yishuang Zhang Haixing Cheng Fubing Yu Wenjia Zhang Kena Dan Xuan Liu Shujun Ye Guangqiao He Xia Jiang Liwei Liu Yukun Fan Tingting Song Guomin Zhou Ziyi Wang Daojun Zhang Junwei Lv |
| author_facet | Huanyu Li Huanyu Li Peng Zhang Zikun Wei Tian Qian Yiqi Tang Kun Hu Xianqiong Huang Xinxin Xia Yishuang Zhang Haixing Cheng Fubing Yu Wenjia Zhang Kena Dan Xuan Liu Shujun Ye Guangqiao He Xia Jiang Liwei Liu Yukun Fan Tingting Song Guomin Zhou Ziyi Wang Daojun Zhang Junwei Lv |
| author_sort | Huanyu Li |
| collection | DOAJ |
| description | BackgroundDue to the lower reliability of laboratory tests, skin diseases are more suitable for diagnosis with AI models. There are limited AI dermatology diagnostic models combining images and text; few of these are for Asian populations, and few cover the most common types of diseases.MethodsLeveraging a dataset sourced from Asia comprising over 200,000 images and 220,000 medical records, we explored a deep learning-based system for Dual-channel images and extracted text for the diagnosis of skin diseases model DIET-AI to diagnose 31 skin diseases, which covers the majority of common skin diseases. From 1 September to 1 December 2021, we prospectively collected images from 6,043 cases and medical records from 15 hospitals in seven provinces in China. Then the performance of DIET-AI was compared with that of six doctors of different seniorities in the clinical dataset.ResultsThe average performance of DIET-AI in 31 diseases was not less than that of all the doctors of different seniorities. By comparing the area under the curve, sensitivity, and specificity, we demonstrate that the DIET-AI model is effective in clinical scenarios. In addition, medical records affect the performance of DIET-AI and physicians to varying degrees.ConclusionThis is the largest dermatological dataset for the Chinese demographic. For the first time, we built a Dual-channel image classification model on a non-cancer dermatitis dataset with both images and medical records and achieved comparable diagnostic performance to senior doctors about common skin diseases. It provides references for exploring the feasibility and performance evaluation of DIET-AI in clinical use afterward. |
| first_indexed | 2024-03-11T17:24:00Z |
| format | Article |
| id | doaj.art-b0b117de4df843ab983b9cf6d4e2a579 |
| institution | Directory Open Access Journal |
| issn | 2624-8212 |
| language | English |
| last_indexed | 2024-03-11T17:24:00Z |
| publishDate | 2023-10-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Artificial Intelligence |
| spelling | doaj.art-b0b117de4df843ab983b9cf6d4e2a5792023-10-19T07:45:31ZengFrontiers Media S.A.Frontiers in Artificial Intelligence2624-82122023-10-01610.3389/frai.2023.12136201213620Deep skin diseases diagnostic system with Dual-channel Image and Extracted TextHuanyu Li0Huanyu Li1Peng Zhang2Zikun Wei3Tian Qian4Yiqi Tang5Kun Hu6Xianqiong Huang7Xinxin Xia8Yishuang Zhang9Haixing Cheng10Fubing Yu11Wenjia Zhang12Kena Dan13Xuan Liu14Shujun Ye15Guangqiao He16Xia Jiang17Liwei Liu18Yukun Fan19Tingting Song20Guomin Zhou21Ziyi Wang22Daojun Zhang23Junwei Lv24The Third Affiliated Hospital of Chongqing Medical University (CQMU), Chongqing, ChinaShanghai Botanee Bio-technology AI Lab, Shanghai, ChinaSchool of Medicine, Shanghai University, Shanghai, ChinaShanghai Botanee Bio-technology AI Lab, Shanghai, ChinaThe Third Affiliated Hospital of Chongqing Medical University (CQMU), Chongqing, ChinaShanghai Botanee Bio-technology AI Lab, Shanghai, ChinaShanghai Botanee Bio-technology AI Lab, Shanghai, ChinaDepartment of Dermatology, Army Medical Center, Chongqing, ChinaSchool of Public Health, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Pokfulam, Hong Kong SAR, ChinaSchool of Pharmacy, East China University of Science and Technology, Shanghai, ChinaThe Third Affiliated Hospital of Chongqing Medical University (CQMU), Chongqing, ChinaThe Third Affiliated Hospital of Chongqing Medical University (CQMU), Chongqing, ChinaShanghai Botanee Bio-technology AI Lab, Shanghai, ChinaThe Third Affiliated Hospital of Chongqing Medical University (CQMU), Chongqing, ChinaFaculty of Science, The University of Sydney, Sydney, NSW, AustraliaFaculty of Science, The University of Melbourne, Parkville, VIC, AustraliaThe Third Affiliated Hospital of Chongqing Medical University (CQMU), Chongqing, ChinaThe Third Affiliated Hospital of Chongqing Medical University (CQMU), Chongqing, ChinaChongqing Shapingba District People's Hospital, Chongqing, ChinaThe Third Affiliated Hospital of Chongqing Medical University (CQMU), Chongqing, ChinaThe Third Affiliated Hospital of Chongqing Medical University (CQMU), Chongqing, China0Shanghai Medical College, Fudan University, Shanghai, China1Huazhong Agricultural University, Wuhan, Hubei, ChinaThe Third Affiliated Hospital of Chongqing Medical University (CQMU), Chongqing, ChinaShanghai Botanee Bio-technology AI Lab, Shanghai, ChinaBackgroundDue to the lower reliability of laboratory tests, skin diseases are more suitable for diagnosis with AI models. There are limited AI dermatology diagnostic models combining images and text; few of these are for Asian populations, and few cover the most common types of diseases.MethodsLeveraging a dataset sourced from Asia comprising over 200,000 images and 220,000 medical records, we explored a deep learning-based system for Dual-channel images and extracted text for the diagnosis of skin diseases model DIET-AI to diagnose 31 skin diseases, which covers the majority of common skin diseases. From 1 September to 1 December 2021, we prospectively collected images from 6,043 cases and medical records from 15 hospitals in seven provinces in China. Then the performance of DIET-AI was compared with that of six doctors of different seniorities in the clinical dataset.ResultsThe average performance of DIET-AI in 31 diseases was not less than that of all the doctors of different seniorities. By comparing the area under the curve, sensitivity, and specificity, we demonstrate that the DIET-AI model is effective in clinical scenarios. In addition, medical records affect the performance of DIET-AI and physicians to varying degrees.ConclusionThis is the largest dermatological dataset for the Chinese demographic. For the first time, we built a Dual-channel image classification model on a non-cancer dermatitis dataset with both images and medical records and achieved comparable diagnostic performance to senior doctors about common skin diseases. It provides references for exploring the feasibility and performance evaluation of DIET-AI in clinical use afterward.https://www.frontiersin.org/articles/10.3389/frai.2023.1213620/fullartificial intelligencecomputer visionskin diseasedermatitisdigital medicine |
| spellingShingle | Huanyu Li Huanyu Li Peng Zhang Zikun Wei Tian Qian Yiqi Tang Kun Hu Xianqiong Huang Xinxin Xia Yishuang Zhang Haixing Cheng Fubing Yu Wenjia Zhang Kena Dan Xuan Liu Shujun Ye Guangqiao He Xia Jiang Liwei Liu Yukun Fan Tingting Song Guomin Zhou Ziyi Wang Daojun Zhang Junwei Lv Deep skin diseases diagnostic system with Dual-channel Image and Extracted Text Frontiers in Artificial Intelligence artificial intelligence computer vision skin disease dermatitis digital medicine |
| title | Deep skin diseases diagnostic system with Dual-channel Image and Extracted Text |
| title_full | Deep skin diseases diagnostic system with Dual-channel Image and Extracted Text |
| title_fullStr | Deep skin diseases diagnostic system with Dual-channel Image and Extracted Text |
| title_full_unstemmed | Deep skin diseases diagnostic system with Dual-channel Image and Extracted Text |
| title_short | Deep skin diseases diagnostic system with Dual-channel Image and Extracted Text |
| title_sort | deep skin diseases diagnostic system with dual channel image and extracted text |
| topic | artificial intelligence computer vision skin disease dermatitis digital medicine |
| url | https://www.frontiersin.org/articles/10.3389/frai.2023.1213620/full |
| work_keys_str_mv | AT huanyuli deepskindiseasesdiagnosticsystemwithdualchannelimageandextractedtext AT huanyuli deepskindiseasesdiagnosticsystemwithdualchannelimageandextractedtext AT pengzhang deepskindiseasesdiagnosticsystemwithdualchannelimageandextractedtext AT zikunwei deepskindiseasesdiagnosticsystemwithdualchannelimageandextractedtext AT tianqian deepskindiseasesdiagnosticsystemwithdualchannelimageandextractedtext AT yiqitang deepskindiseasesdiagnosticsystemwithdualchannelimageandextractedtext AT kunhu deepskindiseasesdiagnosticsystemwithdualchannelimageandextractedtext AT xianqionghuang deepskindiseasesdiagnosticsystemwithdualchannelimageandextractedtext AT xinxinxia deepskindiseasesdiagnosticsystemwithdualchannelimageandextractedtext AT yishuangzhang deepskindiseasesdiagnosticsystemwithdualchannelimageandextractedtext AT haixingcheng deepskindiseasesdiagnosticsystemwithdualchannelimageandextractedtext AT fubingyu deepskindiseasesdiagnosticsystemwithdualchannelimageandextractedtext AT wenjiazhang deepskindiseasesdiagnosticsystemwithdualchannelimageandextractedtext AT kenadan deepskindiseasesdiagnosticsystemwithdualchannelimageandextractedtext AT xuanliu deepskindiseasesdiagnosticsystemwithdualchannelimageandextractedtext AT shujunye deepskindiseasesdiagnosticsystemwithdualchannelimageandextractedtext AT guangqiaohe deepskindiseasesdiagnosticsystemwithdualchannelimageandextractedtext AT xiajiang deepskindiseasesdiagnosticsystemwithdualchannelimageandextractedtext AT liweiliu deepskindiseasesdiagnosticsystemwithdualchannelimageandextractedtext AT yukunfan deepskindiseasesdiagnosticsystemwithdualchannelimageandextractedtext AT tingtingsong deepskindiseasesdiagnosticsystemwithdualchannelimageandextractedtext AT guominzhou deepskindiseasesdiagnosticsystemwithdualchannelimageandextractedtext AT ziyiwang deepskindiseasesdiagnosticsystemwithdualchannelimageandextractedtext AT daojunzhang deepskindiseasesdiagnosticsystemwithdualchannelimageandextractedtext AT junweilv deepskindiseasesdiagnosticsystemwithdualchannelimageandextractedtext |