Application of a deep learning system in glaucoma screening and further classification with colour fundus photographs: a case control study
Abstract Background To verify efficacy of automatic screening and classification of glaucoma with deep learning system. Methods A cross-sectional, retrospective study in a tertiary referral hospital. Patients with healthy optic disc, high-tension, or normal-tension glaucoma were enrolled. Complicate...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-12-01
|
| Series: | BMC Ophthalmology |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12886-022-02730-2 |
| _version_ | 1797980309892890624 |
|---|---|
| author | Kuo-Hsuan Hung Yu-Ching Kao Yu-Hsuan Tang Yi-Ting Chen Chuen-Heng Wang Yu-Chen Wang Oscar Kuang-Sheng Lee |
| author_facet | Kuo-Hsuan Hung Yu-Ching Kao Yu-Hsuan Tang Yi-Ting Chen Chuen-Heng Wang Yu-Chen Wang Oscar Kuang-Sheng Lee |
| author_sort | Kuo-Hsuan Hung |
| collection | DOAJ |
| description | Abstract Background To verify efficacy of automatic screening and classification of glaucoma with deep learning system. Methods A cross-sectional, retrospective study in a tertiary referral hospital. Patients with healthy optic disc, high-tension, or normal-tension glaucoma were enrolled. Complicated non-glaucomatous optic neuropathy was excluded. Colour and red-free fundus images were collected for development of DLS and comparison of their efficacy. The convolutional neural network with the pre-trained EfficientNet-b0 model was selected for machine learning. Glaucoma screening (Binary) and ternary classification with or without additional demographics (age, gender, high myopia) were evaluated, followed by creating confusion matrix and heatmaps. Area under receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and F1 score were viewed as main outcome measures. Results Two hundred and twenty-two cases (421 eyes) were enrolled, with 1851 images in total (1207 normal and 644 glaucomatous disc). Train set and test set were comprised of 1539 and 312 images, respectively. If demographics were not provided, AUC, accuracy, precision, sensitivity, F1 score, and specificity of our deep learning system in eye-based glaucoma screening were 0.98, 0.91, 0.86, 0.86, 0.86, and 0.94 in test set. Same outcome measures in eye-based ternary classification without demographic data were 0.94, 0.87, 0.87, 0.87, 0.87, and 0.94 in our test set, respectively. Adding demographics has no significant impact on efficacy, but establishing a linkage between eyes and images is helpful for a better performance. Confusion matrix and heatmaps suggested that retinal lesions and quality of photographs could affect classification. Colour fundus images play a major role in glaucoma classification, compared to red-free fundus images. Conclusions Promising results with high AUC and specificity were shown in distinguishing normal optic nerve from glaucomatous fundus images and doing further classification. |
| first_indexed | 2024-04-11T05:52:32Z |
| format | Article |
| id | doaj.art-c7ce4bc65a0b404ebe5d671662811dfa |
| institution | Directory Open Access Journal |
| issn | 1471-2415 |
| language | English |
| last_indexed | 2024-04-11T05:52:32Z |
| publishDate | 2022-12-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Ophthalmology |
| spelling | doaj.art-c7ce4bc65a0b404ebe5d671662811dfa2022-12-22T04:42:01ZengBMCBMC Ophthalmology1471-24152022-12-0122111210.1186/s12886-022-02730-2Application of a deep learning system in glaucoma screening and further classification with colour fundus photographs: a case control studyKuo-Hsuan Hung0Yu-Ching Kao1Yu-Hsuan Tang2Yi-Ting Chen3Chuen-Heng Wang4Yu-Chen Wang5Oscar Kuang-Sheng Lee6Department of Ophthalmology, Chang-Gung Memorial HospitalMuen Biomedical and Optoelectronics Technologies Inc.Institute of Clinical Medicine, National Yang Ming Chiao Tung UniversityMuen Biomedical and Optoelectronics Technologies Inc.Muen Biomedical and Optoelectronics Technologies Inc.Muen Biomedical and Optoelectronics Technologies Inc.Institute of Clinical Medicine, National Yang Ming Chiao Tung UniversityAbstract Background To verify efficacy of automatic screening and classification of glaucoma with deep learning system. Methods A cross-sectional, retrospective study in a tertiary referral hospital. Patients with healthy optic disc, high-tension, or normal-tension glaucoma were enrolled. Complicated non-glaucomatous optic neuropathy was excluded. Colour and red-free fundus images were collected for development of DLS and comparison of their efficacy. The convolutional neural network with the pre-trained EfficientNet-b0 model was selected for machine learning. Glaucoma screening (Binary) and ternary classification with or without additional demographics (age, gender, high myopia) were evaluated, followed by creating confusion matrix and heatmaps. Area under receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and F1 score were viewed as main outcome measures. Results Two hundred and twenty-two cases (421 eyes) were enrolled, with 1851 images in total (1207 normal and 644 glaucomatous disc). Train set and test set were comprised of 1539 and 312 images, respectively. If demographics were not provided, AUC, accuracy, precision, sensitivity, F1 score, and specificity of our deep learning system in eye-based glaucoma screening were 0.98, 0.91, 0.86, 0.86, 0.86, and 0.94 in test set. Same outcome measures in eye-based ternary classification without demographic data were 0.94, 0.87, 0.87, 0.87, 0.87, and 0.94 in our test set, respectively. Adding demographics has no significant impact on efficacy, but establishing a linkage between eyes and images is helpful for a better performance. Confusion matrix and heatmaps suggested that retinal lesions and quality of photographs could affect classification. Colour fundus images play a major role in glaucoma classification, compared to red-free fundus images. Conclusions Promising results with high AUC and specificity were shown in distinguishing normal optic nerve from glaucomatous fundus images and doing further classification.https://doi.org/10.1186/s12886-022-02730-2Glaucoma screening and classificationDeep learning systemNormal- tension glaucomaColour fundus photographHigh myopia |
| spellingShingle | Kuo-Hsuan Hung Yu-Ching Kao Yu-Hsuan Tang Yi-Ting Chen Chuen-Heng Wang Yu-Chen Wang Oscar Kuang-Sheng Lee Application of a deep learning system in glaucoma screening and further classification with colour fundus photographs: a case control study BMC Ophthalmology Glaucoma screening and classification Deep learning system Normal- tension glaucoma Colour fundus photograph High myopia |
| title | Application of a deep learning system in glaucoma screening and further classification with colour fundus photographs: a case control study |
| title_full | Application of a deep learning system in glaucoma screening and further classification with colour fundus photographs: a case control study |
| title_fullStr | Application of a deep learning system in glaucoma screening and further classification with colour fundus photographs: a case control study |
| title_full_unstemmed | Application of a deep learning system in glaucoma screening and further classification with colour fundus photographs: a case control study |
| title_short | Application of a deep learning system in glaucoma screening and further classification with colour fundus photographs: a case control study |
| title_sort | application of a deep learning system in glaucoma screening and further classification with colour fundus photographs a case control study |
| topic | Glaucoma screening and classification Deep learning system Normal- tension glaucoma Colour fundus photograph High myopia |
| url | https://doi.org/10.1186/s12886-022-02730-2 |
| work_keys_str_mv | AT kuohsuanhung applicationofadeeplearningsysteminglaucomascreeningandfurtherclassificationwithcolourfundusphotographsacasecontrolstudy AT yuchingkao applicationofadeeplearningsysteminglaucomascreeningandfurtherclassificationwithcolourfundusphotographsacasecontrolstudy AT yuhsuantang applicationofadeeplearningsysteminglaucomascreeningandfurtherclassificationwithcolourfundusphotographsacasecontrolstudy AT yitingchen applicationofadeeplearningsysteminglaucomascreeningandfurtherclassificationwithcolourfundusphotographsacasecontrolstudy AT chuenhengwang applicationofadeeplearningsysteminglaucomascreeningandfurtherclassificationwithcolourfundusphotographsacasecontrolstudy AT yuchenwang applicationofadeeplearningsysteminglaucomascreeningandfurtherclassificationwithcolourfundusphotographsacasecontrolstudy AT oscarkuangshenglee applicationofadeeplearningsysteminglaucomascreeningandfurtherclassificationwithcolourfundusphotographsacasecontrolstudy |