Automated detection of myopic maculopathy using five-category models based on vision outlooker for visual recognition
PurposeTo propose a five-category model for the automatic detection of myopic macular lesions to help grassroots medical institutions conduct preliminary screening of myopic macular lesions from limited number of color fundus images.MethodsFirst, 1,750 fundus images of non-myopic retinal lesions and...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-04-01
|
| Series: | Frontiers in Computational Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fncom.2023.1169464/full |
| _version_ | 1797843758033666048 |
|---|---|
| author | Cheng Wan Jiyi Fang Xiao Hua Lu Chen Lu Chen Shaochong Zhang Shaochong Zhang Weihua Yang Weihua Yang |
| author_facet | Cheng Wan Jiyi Fang Xiao Hua Lu Chen Lu Chen Shaochong Zhang Shaochong Zhang Weihua Yang Weihua Yang |
| author_sort | Cheng Wan |
| collection | DOAJ |
| description | PurposeTo propose a five-category model for the automatic detection of myopic macular lesions to help grassroots medical institutions conduct preliminary screening of myopic macular lesions from limited number of color fundus images.MethodsFirst, 1,750 fundus images of non-myopic retinal lesions and four categories of pathological myopic maculopathy were collected, graded, and labeled. Subsequently, three five-classification models based on Vision Outlooker for Visual Recognition (VOLO), EfficientNetV2, and ResNet50 for detecting myopic maculopathy were trained with data-augmented images, and the diagnostic results of the different trained models were compared and analyzed. The main evaluation metrics were sensitivity, specificity, negative predictive value (NPV), positive predictive value (PPV), area under the curve (AUC), kappa and accuracy, and receiver operating characteristic curve (ROC).ResultsThe diagnostic accuracy of the VOLO-D2 model was 96.60% with a kappa value of 95.60%. All indicators used for the diagnosis of myopia-free macular degeneration were 100%. The sensitivity, NPV, specificity, and PPV for diagnosis of leopard fundus were 96.43, 98.33, 100, and 100%, respectively. The sensitivity, specificity, PPV, and NPV for the diagnosis of diffuse chorioretinal atrophy were 96.88, 98.59, 93.94, and 99.29%, respectively. The sensitivity, specificity, PPV, and NPV for the diagnosis of patchy chorioretinal atrophy were 92.31, 99.26, 97.30, and 97.81%, respectively. The sensitivity, specificity, PPV, and NPV for the diagnosis of macular atrophy were 100, 98.10, 84.21, and 100%, respectively.ConclusionThe VOLO-D2 model accurately identified myopia-free macular lesions and four pathological myopia-related macular lesions with high sensitivity and specificity. It can be used in screening pathological myopic macular lesions and can help ophthalmologists and primary medical institution providers complete the initial screening diagnosis of patients. |
| first_indexed | 2024-04-09T17:11:10Z |
| format | Article |
| id | doaj.art-25cd088d10d842c49312584ba6a11ea1 |
| institution | Directory Open Access Journal |
| issn | 1662-5188 |
| language | English |
| last_indexed | 2024-04-09T17:11:10Z |
| publishDate | 2023-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Computational Neuroscience |
| spelling | doaj.art-25cd088d10d842c49312584ba6a11ea12023-04-20T05:52:44ZengFrontiers Media S.A.Frontiers in Computational Neuroscience1662-51882023-04-011710.3389/fncom.2023.11694641169464Automated detection of myopic maculopathy using five-category models based on vision outlooker for visual recognitionCheng Wan0Jiyi Fang1Xiao Hua2Lu Chen3Lu Chen4Shaochong Zhang5Shaochong Zhang6Weihua Yang7Weihua Yang8College of Electronic Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, ChinaCollege of Electronic Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, ChinaNanjing Star-mile Technology Co., Ltd., Nanjing, ChinaShenzhen Eye Hospital, Jinan University, Shenzhen, ChinaShenzhen Eye Institute, Shenzhen, ChinaShenzhen Eye Hospital, Jinan University, Shenzhen, ChinaShenzhen Eye Institute, Shenzhen, ChinaShenzhen Eye Hospital, Jinan University, Shenzhen, ChinaShenzhen Eye Institute, Shenzhen, ChinaPurposeTo propose a five-category model for the automatic detection of myopic macular lesions to help grassroots medical institutions conduct preliminary screening of myopic macular lesions from limited number of color fundus images.MethodsFirst, 1,750 fundus images of non-myopic retinal lesions and four categories of pathological myopic maculopathy were collected, graded, and labeled. Subsequently, three five-classification models based on Vision Outlooker for Visual Recognition (VOLO), EfficientNetV2, and ResNet50 for detecting myopic maculopathy were trained with data-augmented images, and the diagnostic results of the different trained models were compared and analyzed. The main evaluation metrics were sensitivity, specificity, negative predictive value (NPV), positive predictive value (PPV), area under the curve (AUC), kappa and accuracy, and receiver operating characteristic curve (ROC).ResultsThe diagnostic accuracy of the VOLO-D2 model was 96.60% with a kappa value of 95.60%. All indicators used for the diagnosis of myopia-free macular degeneration were 100%. The sensitivity, NPV, specificity, and PPV for diagnosis of leopard fundus were 96.43, 98.33, 100, and 100%, respectively. The sensitivity, specificity, PPV, and NPV for the diagnosis of diffuse chorioretinal atrophy were 96.88, 98.59, 93.94, and 99.29%, respectively. The sensitivity, specificity, PPV, and NPV for the diagnosis of patchy chorioretinal atrophy were 92.31, 99.26, 97.30, and 97.81%, respectively. The sensitivity, specificity, PPV, and NPV for the diagnosis of macular atrophy were 100, 98.10, 84.21, and 100%, respectively.ConclusionThe VOLO-D2 model accurately identified myopia-free macular lesions and four pathological myopia-related macular lesions with high sensitivity and specificity. It can be used in screening pathological myopic macular lesions and can help ophthalmologists and primary medical institution providers complete the initial screening diagnosis of patients.https://www.frontiersin.org/articles/10.3389/fncom.2023.1169464/fullmyopic maculopathyvision outlookervisual recognitionartificial intelligencedata limitations |
| spellingShingle | Cheng Wan Jiyi Fang Xiao Hua Lu Chen Lu Chen Shaochong Zhang Shaochong Zhang Weihua Yang Weihua Yang Automated detection of myopic maculopathy using five-category models based on vision outlooker for visual recognition Frontiers in Computational Neuroscience myopic maculopathy vision outlooker visual recognition artificial intelligence data limitations |
| title | Automated detection of myopic maculopathy using five-category models based on vision outlooker for visual recognition |
| title_full | Automated detection of myopic maculopathy using five-category models based on vision outlooker for visual recognition |
| title_fullStr | Automated detection of myopic maculopathy using five-category models based on vision outlooker for visual recognition |
| title_full_unstemmed | Automated detection of myopic maculopathy using five-category models based on vision outlooker for visual recognition |
| title_short | Automated detection of myopic maculopathy using five-category models based on vision outlooker for visual recognition |
| title_sort | automated detection of myopic maculopathy using five category models based on vision outlooker for visual recognition |
| topic | myopic maculopathy vision outlooker visual recognition artificial intelligence data limitations |
| url | https://www.frontiersin.org/articles/10.3389/fncom.2023.1169464/full |
| work_keys_str_mv | AT chengwan automateddetectionofmyopicmaculopathyusingfivecategorymodelsbasedonvisionoutlookerforvisualrecognition AT jiyifang automateddetectionofmyopicmaculopathyusingfivecategorymodelsbasedonvisionoutlookerforvisualrecognition AT xiaohua automateddetectionofmyopicmaculopathyusingfivecategorymodelsbasedonvisionoutlookerforvisualrecognition AT luchen automateddetectionofmyopicmaculopathyusingfivecategorymodelsbasedonvisionoutlookerforvisualrecognition AT luchen automateddetectionofmyopicmaculopathyusingfivecategorymodelsbasedonvisionoutlookerforvisualrecognition AT shaochongzhang automateddetectionofmyopicmaculopathyusingfivecategorymodelsbasedonvisionoutlookerforvisualrecognition AT shaochongzhang automateddetectionofmyopicmaculopathyusingfivecategorymodelsbasedonvisionoutlookerforvisualrecognition AT weihuayang automateddetectionofmyopicmaculopathyusingfivecategorymodelsbasedonvisionoutlookerforvisualrecognition AT weihuayang automateddetectionofmyopicmaculopathyusingfivecategorymodelsbasedonvisionoutlookerforvisualrecognition |