Automatic Diagnosis of Infectious Keratitis Based on Slit Lamp Images Analysis
Infectious keratitis (IK) is a common ophthalmic emergency that requires prompt and accurate treatment. This study aimed to propose a deep learning (DL) system based on slit lamp images to automatically screen and diagnose infectious keratitis. This study established a dataset of 2757 slit lamp imag...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Journal of Personalized Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4426/13/3/519 |
| _version_ | 1797610775147184128 |
|---|---|
| author | Shaodan Hu Yiming Sun Jinhao Li Peifang Xu Mingyu Xu Yifan Zhou Yaqi Wang Shuai Wang Juan Ye |
| author_facet | Shaodan Hu Yiming Sun Jinhao Li Peifang Xu Mingyu Xu Yifan Zhou Yaqi Wang Shuai Wang Juan Ye |
| author_sort | Shaodan Hu |
| collection | DOAJ |
| description | Infectious keratitis (IK) is a common ophthalmic emergency that requires prompt and accurate treatment. This study aimed to propose a deep learning (DL) system based on slit lamp images to automatically screen and diagnose infectious keratitis. This study established a dataset of 2757 slit lamp images from 744 patients, including normal cornea, viral keratitis (VK), fungal keratitis (FK), and bacterial keratitis (BK). Six different DL algorithms were developed and evaluated for the classification of infectious keratitis. Among all the models, the EffecientNetV2-M showed the best classification ability, with an accuracy of 0.735, a recall of 0.680, and a specificity of 0.904, which was also superior to two ophthalmologists. The area under the receiver operating characteristics curve (AUC) of the EffecientNetV2-M was 0.85; correspondingly, 1.00 for normal cornea, 0.87 for VK, 0.87 for FK, and 0.64 for BK. The findings suggested that the proposed DL system could perform well in the classification of normal corneas and different types of infectious keratitis, based on slit lamp images. This study proves the potential of the DL model to help ophthalmologists to identify infectious keratitis and improve the accuracy and efficiency of diagnosis. |
| first_indexed | 2024-03-11T06:18:53Z |
| format | Article |
| id | doaj.art-1ae8be3262534670a36e5fbe46fd363e |
| institution | Directory Open Access Journal |
| issn | 2075-4426 |
| language | English |
| last_indexed | 2024-03-11T06:18:53Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Personalized Medicine |
| spelling | doaj.art-1ae8be3262534670a36e5fbe46fd363e2023-11-17T12:03:29ZengMDPI AGJournal of Personalized Medicine2075-44262023-03-0113351910.3390/jpm13030519Automatic Diagnosis of Infectious Keratitis Based on Slit Lamp Images AnalysisShaodan Hu0Yiming Sun1Jinhao Li2Peifang Xu3Mingyu Xu4Yifan Zhou5Yaqi Wang6Shuai Wang7Juan Ye8Department of Ophthalmology, College of Medicine, The Second Affiliated Hospital of Zhejiang University, Hangzhou 310009, ChinaDepartment of Ophthalmology, College of Medicine, The Second Affiliated Hospital of Zhejiang University, Hangzhou 310009, ChinaSchool of Mechanical, Electrical and Information Engineering, Shandong University, Weihai 264209, ChinaDepartment of Ophthalmology, College of Medicine, The Second Affiliated Hospital of Zhejiang University, Hangzhou 310009, ChinaDepartment of Ophthalmology, College of Medicine, The Second Affiliated Hospital of Zhejiang University, Hangzhou 310009, ChinaDepartment of Ophthalmology, College of Medicine, The Second Affiliated Hospital of Zhejiang University, Hangzhou 310009, ChinaCollege of Media Engineering, Communication University of Zhejiang, Hangzhou 310018, ChinaSchool of Mechanical, Electrical and Information Engineering, Shandong University, Weihai 264209, ChinaDepartment of Ophthalmology, College of Medicine, The Second Affiliated Hospital of Zhejiang University, Hangzhou 310009, ChinaInfectious keratitis (IK) is a common ophthalmic emergency that requires prompt and accurate treatment. This study aimed to propose a deep learning (DL) system based on slit lamp images to automatically screen and diagnose infectious keratitis. This study established a dataset of 2757 slit lamp images from 744 patients, including normal cornea, viral keratitis (VK), fungal keratitis (FK), and bacterial keratitis (BK). Six different DL algorithms were developed and evaluated for the classification of infectious keratitis. Among all the models, the EffecientNetV2-M showed the best classification ability, with an accuracy of 0.735, a recall of 0.680, and a specificity of 0.904, which was also superior to two ophthalmologists. The area under the receiver operating characteristics curve (AUC) of the EffecientNetV2-M was 0.85; correspondingly, 1.00 for normal cornea, 0.87 for VK, 0.87 for FK, and 0.64 for BK. The findings suggested that the proposed DL system could perform well in the classification of normal corneas and different types of infectious keratitis, based on slit lamp images. This study proves the potential of the DL model to help ophthalmologists to identify infectious keratitis and improve the accuracy and efficiency of diagnosis.https://www.mdpi.com/2075-4426/13/3/519deep learninginfectious keratitisslit lamp imageautomatic classification |
| spellingShingle | Shaodan Hu Yiming Sun Jinhao Li Peifang Xu Mingyu Xu Yifan Zhou Yaqi Wang Shuai Wang Juan Ye Automatic Diagnosis of Infectious Keratitis Based on Slit Lamp Images Analysis Journal of Personalized Medicine deep learning infectious keratitis slit lamp image automatic classification |
| title | Automatic Diagnosis of Infectious Keratitis Based on Slit Lamp Images Analysis |
| title_full | Automatic Diagnosis of Infectious Keratitis Based on Slit Lamp Images Analysis |
| title_fullStr | Automatic Diagnosis of Infectious Keratitis Based on Slit Lamp Images Analysis |
| title_full_unstemmed | Automatic Diagnosis of Infectious Keratitis Based on Slit Lamp Images Analysis |
| title_short | Automatic Diagnosis of Infectious Keratitis Based on Slit Lamp Images Analysis |
| title_sort | automatic diagnosis of infectious keratitis based on slit lamp images analysis |
| topic | deep learning infectious keratitis slit lamp image automatic classification |
| url | https://www.mdpi.com/2075-4426/13/3/519 |
| work_keys_str_mv | AT shaodanhu automaticdiagnosisofinfectiouskeratitisbasedonslitlampimagesanalysis AT yimingsun automaticdiagnosisofinfectiouskeratitisbasedonslitlampimagesanalysis AT jinhaoli automaticdiagnosisofinfectiouskeratitisbasedonslitlampimagesanalysis AT peifangxu automaticdiagnosisofinfectiouskeratitisbasedonslitlampimagesanalysis AT mingyuxu automaticdiagnosisofinfectiouskeratitisbasedonslitlampimagesanalysis AT yifanzhou automaticdiagnosisofinfectiouskeratitisbasedonslitlampimagesanalysis AT yaqiwang automaticdiagnosisofinfectiouskeratitisbasedonslitlampimagesanalysis AT shuaiwang automaticdiagnosisofinfectiouskeratitisbasedonslitlampimagesanalysis AT juanye automaticdiagnosisofinfectiouskeratitisbasedonslitlampimagesanalysis |