Medinoid: Computer-Aided Diagnosis and Localization of Glaucoma Using Deep Learning <sup>†</sup>
Glaucoma is a leading eye disease, causing vision loss by gradually affecting peripheral vision if left untreated. Current diagnosis of glaucoma is performed by ophthalmologists, human experts who typically need to analyze different types of medical images generated by different types of medical equ...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/9/15/3064 |
| _version_ | 1818251291903655936 |
|---|---|
| author | Mijung Kim Jong Chul Han Seung Hyup Hyun Olivier Janssens Sofie Van Hoecke Changwon Kee Wesley De Neve |
| author_facet | Mijung Kim Jong Chul Han Seung Hyup Hyun Olivier Janssens Sofie Van Hoecke Changwon Kee Wesley De Neve |
| author_sort | Mijung Kim |
| collection | DOAJ |
| description | Glaucoma is a leading eye disease, causing vision loss by gradually affecting peripheral vision if left untreated. Current diagnosis of glaucoma is performed by ophthalmologists, human experts who typically need to analyze different types of medical images generated by different types of medical equipment: fundus, Retinal Nerve Fiber Layer (RNFL), Optical Coherence Tomography (OCT) disc, OCT macula, perimetry, and/or perimetry deviation. Capturing and analyzing these medical images is labor intensive and time consuming. In this paper, we present a novel approach for glaucoma diagnosis and localization, only relying on fundus images that are analyzed by making use of state-of-the-art deep learning techniques. Specifically, our approach towards glaucoma diagnosis and localization leverages Convolutional Neural Networks (CNNs) and Gradient-weighted Class Activation Mapping (Grad-CAM), respectively. We built and evaluated different predictive models using a large set of fundus images, collected and labeled by ophthalmologists at Samsung Medical Center (SMC). Our experimental results demonstrate that our most effective predictive model is able to achieve a high diagnosis accuracy of 96%, as well as a high sensitivity of 96% and a high specificity of 100% for Dataset-Optic Disc (OD), a set of center-cropped fundus images highlighting the optic disc. Furthermore, we present Medinoid, a publicly-available prototype web application for computer-aided diagnosis and localization of glaucoma, integrating our most effective predictive model in its back-end. |
| first_indexed | 2024-12-12T16:05:57Z |
| format | Article |
| id | doaj.art-41d242ac87234d8badeba57d1c2a9194 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-12T16:05:57Z |
| publishDate | 2019-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-41d242ac87234d8badeba57d1c2a91942022-12-22T00:19:17ZengMDPI AGApplied Sciences2076-34172019-07-01915306410.3390/app9153064app9153064Medinoid: Computer-Aided Diagnosis and Localization of Glaucoma Using Deep Learning <sup>†</sup>Mijung Kim0Jong Chul Han1Seung Hyup Hyun2Olivier Janssens3Sofie Van Hoecke4Changwon Kee5Wesley De Neve6Center for Biotech Data Science, Ghent University Global Campus, Incheon 21985, KoreaDepartment of Ophthalmology, Samsung Medical Center, Seoul 06351, KoreaSungkyunkwan University School of Medicine, Seoul 06351, KoreaIDLab, ELIS, Ghent University, 9000 Gent, BelgiumIDLab, ELIS, Ghent University, 9000 Gent, BelgiumDepartment of Ophthalmology, Samsung Medical Center, Seoul 06351, KoreaCenter for Biotech Data Science, Ghent University Global Campus, Incheon 21985, KoreaGlaucoma is a leading eye disease, causing vision loss by gradually affecting peripheral vision if left untreated. Current diagnosis of glaucoma is performed by ophthalmologists, human experts who typically need to analyze different types of medical images generated by different types of medical equipment: fundus, Retinal Nerve Fiber Layer (RNFL), Optical Coherence Tomography (OCT) disc, OCT macula, perimetry, and/or perimetry deviation. Capturing and analyzing these medical images is labor intensive and time consuming. In this paper, we present a novel approach for glaucoma diagnosis and localization, only relying on fundus images that are analyzed by making use of state-of-the-art deep learning techniques. Specifically, our approach towards glaucoma diagnosis and localization leverages Convolutional Neural Networks (CNNs) and Gradient-weighted Class Activation Mapping (Grad-CAM), respectively. We built and evaluated different predictive models using a large set of fundus images, collected and labeled by ophthalmologists at Samsung Medical Center (SMC). Our experimental results demonstrate that our most effective predictive model is able to achieve a high diagnosis accuracy of 96%, as well as a high sensitivity of 96% and a high specificity of 100% for Dataset-Optic Disc (OD), a set of center-cropped fundus images highlighting the optic disc. Furthermore, we present Medinoid, a publicly-available prototype web application for computer-aided diagnosis and localization of glaucoma, integrating our most effective predictive model in its back-end.https://www.mdpi.com/2076-3417/9/15/3064CADdeep learningfundus imagingglaucomaweb application |
| spellingShingle | Mijung Kim Jong Chul Han Seung Hyup Hyun Olivier Janssens Sofie Van Hoecke Changwon Kee Wesley De Neve Medinoid: Computer-Aided Diagnosis and Localization of Glaucoma Using Deep Learning <sup>†</sup> Applied Sciences CAD deep learning fundus imaging glaucoma web application |
| title | Medinoid: Computer-Aided Diagnosis and Localization of Glaucoma Using Deep Learning <sup>†</sup> |
| title_full | Medinoid: Computer-Aided Diagnosis and Localization of Glaucoma Using Deep Learning <sup>†</sup> |
| title_fullStr | Medinoid: Computer-Aided Diagnosis and Localization of Glaucoma Using Deep Learning <sup>†</sup> |
| title_full_unstemmed | Medinoid: Computer-Aided Diagnosis and Localization of Glaucoma Using Deep Learning <sup>†</sup> |
| title_short | Medinoid: Computer-Aided Diagnosis and Localization of Glaucoma Using Deep Learning <sup>†</sup> |
| title_sort | medinoid computer aided diagnosis and localization of glaucoma using deep learning sup † sup |
| topic | CAD deep learning fundus imaging glaucoma web application |
| url | https://www.mdpi.com/2076-3417/9/15/3064 |
| work_keys_str_mv | AT mijungkim medinoidcomputeraideddiagnosisandlocalizationofglaucomausingdeeplearningsupsup AT jongchulhan medinoidcomputeraideddiagnosisandlocalizationofglaucomausingdeeplearningsupsup AT seunghyuphyun medinoidcomputeraideddiagnosisandlocalizationofglaucomausingdeeplearningsupsup AT olivierjanssens medinoidcomputeraideddiagnosisandlocalizationofglaucomausingdeeplearningsupsup AT sofievanhoecke medinoidcomputeraideddiagnosisandlocalizationofglaucomausingdeeplearningsupsup AT changwonkee medinoidcomputeraideddiagnosisandlocalizationofglaucomausingdeeplearningsupsup AT wesleydeneve medinoidcomputeraideddiagnosisandlocalizationofglaucomausingdeeplearningsupsup |