A fast and fully automated system for glaucoma detection using color fundus photographs
Abstract This paper presents a low computationally intensive and memory efficient convolutional neural network (CNN)-based fully automated system for detection of glaucoma, a leading cause of irreversible blindness worldwide. Using color fundus photographs, the system detects glaucoma in two steps....
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-10-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-44473-0 |
| _version_ | 1827781239464001536 |
|---|---|
| author | Sajib Saha Janardhan Vignarajan Shaun Frost |
| author_facet | Sajib Saha Janardhan Vignarajan Shaun Frost |
| author_sort | Sajib Saha |
| collection | DOAJ |
| description | Abstract This paper presents a low computationally intensive and memory efficient convolutional neural network (CNN)-based fully automated system for detection of glaucoma, a leading cause of irreversible blindness worldwide. Using color fundus photographs, the system detects glaucoma in two steps. In the first step, the optic disc region is determined relying upon You Only Look Once (YOLO) CNN architecture. In the second step classification of ‘glaucomatous’ and ‘non-glaucomatous’ is performed using MobileNet architecture. A simplified version of the original YOLO net, specific to the context, is also proposed. Extensive experiments are conducted using seven state-of-the-art CNNs with varying computational intensity, namely, MobileNetV2, MobileNetV3, Custom ResNet, InceptionV3, ResNet50, 18-Layer CNN and InceptionResNetV2. A total of 6671 fundus images collected from seven publicly available glaucoma datasets are used for the experiment. The system achieves an accuracy and F1 score of 97.4% and 97.3%, with sensitivity, specificity, and AUC of respectively 97.5%, 97.2%, 99.3%. These findings are comparable with the best reported methods in the literature. With comparable or better performance, the proposed system produces significantly faster decisions and drastically minimizes the resource requirement. For example, the proposed system requires 12 times less memory in comparison to ResNes50, and produces 2 times faster decisions. With significantly less memory efficient and faster processing, the proposed system has the capability to be directly embedded into resource limited devices such as portable fundus cameras. |
| first_indexed | 2024-03-11T15:15:03Z |
| format | Article |
| id | doaj.art-ad43112ff6c446a29bc4ee465d028a1e |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-11T15:15:03Z |
| publishDate | 2023-10-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-ad43112ff6c446a29bc4ee465d028a1e2023-10-29T12:20:40ZengNature PortfolioScientific Reports2045-23222023-10-0113111110.1038/s41598-023-44473-0A fast and fully automated system for glaucoma detection using color fundus photographsSajib Saha0Janardhan Vignarajan1Shaun Frost2Australian e-Health Research Centre, Commonwealth Scientific and Industrial Research Organisation (CSIRO)Australian e-Health Research Centre, Commonwealth Scientific and Industrial Research Organisation (CSIRO)Australian e-Health Research Centre, Commonwealth Scientific and Industrial Research Organisation (CSIRO)Abstract This paper presents a low computationally intensive and memory efficient convolutional neural network (CNN)-based fully automated system for detection of glaucoma, a leading cause of irreversible blindness worldwide. Using color fundus photographs, the system detects glaucoma in two steps. In the first step, the optic disc region is determined relying upon You Only Look Once (YOLO) CNN architecture. In the second step classification of ‘glaucomatous’ and ‘non-glaucomatous’ is performed using MobileNet architecture. A simplified version of the original YOLO net, specific to the context, is also proposed. Extensive experiments are conducted using seven state-of-the-art CNNs with varying computational intensity, namely, MobileNetV2, MobileNetV3, Custom ResNet, InceptionV3, ResNet50, 18-Layer CNN and InceptionResNetV2. A total of 6671 fundus images collected from seven publicly available glaucoma datasets are used for the experiment. The system achieves an accuracy and F1 score of 97.4% and 97.3%, with sensitivity, specificity, and AUC of respectively 97.5%, 97.2%, 99.3%. These findings are comparable with the best reported methods in the literature. With comparable or better performance, the proposed system produces significantly faster decisions and drastically minimizes the resource requirement. For example, the proposed system requires 12 times less memory in comparison to ResNes50, and produces 2 times faster decisions. With significantly less memory efficient and faster processing, the proposed system has the capability to be directly embedded into resource limited devices such as portable fundus cameras.https://doi.org/10.1038/s41598-023-44473-0 |
| spellingShingle | Sajib Saha Janardhan Vignarajan Shaun Frost A fast and fully automated system for glaucoma detection using color fundus photographs Scientific Reports |
| title | A fast and fully automated system for glaucoma detection using color fundus photographs |
| title_full | A fast and fully automated system for glaucoma detection using color fundus photographs |
| title_fullStr | A fast and fully automated system for glaucoma detection using color fundus photographs |
| title_full_unstemmed | A fast and fully automated system for glaucoma detection using color fundus photographs |
| title_short | A fast and fully automated system for glaucoma detection using color fundus photographs |
| title_sort | fast and fully automated system for glaucoma detection using color fundus photographs |
| url | https://doi.org/10.1038/s41598-023-44473-0 |
| work_keys_str_mv | AT sajibsaha afastandfullyautomatedsystemforglaucomadetectionusingcolorfundusphotographs AT janardhanvignarajan afastandfullyautomatedsystemforglaucomadetectionusingcolorfundusphotographs AT shaunfrost afastandfullyautomatedsystemforglaucomadetectionusingcolorfundusphotographs AT sajibsaha fastandfullyautomatedsystemforglaucomadetectionusingcolorfundusphotographs AT janardhanvignarajan fastandfullyautomatedsystemforglaucomadetectionusingcolorfundusphotographs AT shaunfrost fastandfullyautomatedsystemforglaucomadetectionusingcolorfundusphotographs |