Automatic Method for Optic Disc Segmentation Using Deep Learning on Retinal Fundus Images
Objectives The optic disc is part of the retinal fundus image structure, which influences the extraction of glaucoma features. This study proposes a method that automatically segments the optic disc area in retinal fundus images using deep learning based on a convolutional neural network (CNN). Meth...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
The Korean Society of Medical Informatics
2023-04-01
|
Series: | Healthcare Informatics Research |
Subjects: | |
Online Access: | http://e-hir.org/upload/pdf/hir-2023-29-2-145.pdf |
_version_ | 1797826276763893760 |
---|---|
author | Anindita Septiarini Hamdani Hamdani Emy Setyaningsih Eko Junirianto Fitri Utaminingrum |
author_facet | Anindita Septiarini Hamdani Hamdani Emy Setyaningsih Eko Junirianto Fitri Utaminingrum |
author_sort | Anindita Septiarini |
collection | DOAJ |
description | Objectives The optic disc is part of the retinal fundus image structure, which influences the extraction of glaucoma features. This study proposes a method that automatically segments the optic disc area in retinal fundus images using deep learning based on a convolutional neural network (CNN). Methods This study used private and public datasets containing retinal fundus images. The private dataset consisted of 350 images, while the public dataset was the Retinal Fundus Glaucoma Challenge (REFUGE). The proposed method was based on a CNN with a single-shot multibox detector (MobileNetV2) to form images of the region-of-interest (ROI) using the original image resized into 640 × 640 input data. A pre-processing sequence was then implemented, including augmentation, resizing, and normalization. Furthermore, a U-Net model was applied for optic disc segmentation with 128 × 128 input data. Results The proposed method was appropriately applied to the datasets used, as shown by the values of the F1-score, dice score, and intersection over union of 0.9880, 0.9852, and 0.9763 for the private dataset, respectively, and 0.9854, 0.9838 and 0.9712 for the REFUGE dataset. Conclusions The optic disc area produced by the proposed method was similar to that identified by an ophthalmologist. Therefore, this method can be considered for implementing automatic segmentation of the optic disc area. |
first_indexed | 2024-03-13T11:06:22Z |
format | Article |
id | doaj.art-52ab8c48a62d4c798ff38a3bf6d9438b |
institution | Directory Open Access Journal |
issn | 2093-3681 2093-369X |
language | English |
last_indexed | 2024-03-13T11:06:22Z |
publishDate | 2023-04-01 |
publisher | The Korean Society of Medical Informatics |
record_format | Article |
series | Healthcare Informatics Research |
spelling | doaj.art-52ab8c48a62d4c798ff38a3bf6d9438b2023-05-16T06:23:33ZengThe Korean Society of Medical InformaticsHealthcare Informatics Research2093-36812093-369X2023-04-0129214515110.4258/hir.2023.29.2.1451158Automatic Method for Optic Disc Segmentation Using Deep Learning on Retinal Fundus ImagesAnindita Septiarini0Hamdani Hamdani1Emy Setyaningsih2Eko Junirianto3Fitri Utaminingrum4 Department of Informatics, Faculty of Engineering, Mulawarman University, Samarinda, Indonesia Department of Informatics, Faculty of Engineering, Mulawarman University, Samarinda, Indonesia Department of Computer, System Engineering, Institut Sains & Teknologi AKPRIND, Yogyakarta, Indonesia Departmen of Information Technology, Samarinda Polytechnic of Agriculture, Samarinda, Indonesia Computer Vision Research Group, Faculty of Computer Science, Brawijaya University, Malang, IndonesiaObjectives The optic disc is part of the retinal fundus image structure, which influences the extraction of glaucoma features. This study proposes a method that automatically segments the optic disc area in retinal fundus images using deep learning based on a convolutional neural network (CNN). Methods This study used private and public datasets containing retinal fundus images. The private dataset consisted of 350 images, while the public dataset was the Retinal Fundus Glaucoma Challenge (REFUGE). The proposed method was based on a CNN with a single-shot multibox detector (MobileNetV2) to form images of the region-of-interest (ROI) using the original image resized into 640 × 640 input data. A pre-processing sequence was then implemented, including augmentation, resizing, and normalization. Furthermore, a U-Net model was applied for optic disc segmentation with 128 × 128 input data. Results The proposed method was appropriately applied to the datasets used, as shown by the values of the F1-score, dice score, and intersection over union of 0.9880, 0.9852, and 0.9763 for the private dataset, respectively, and 0.9854, 0.9838 and 0.9712 for the REFUGE dataset. Conclusions The optic disc area produced by the proposed method was similar to that identified by an ophthalmologist. Therefore, this method can be considered for implementing automatic segmentation of the optic disc area.http://e-hir.org/upload/pdf/hir-2023-29-2-145.pdfimage processingcomputer visionfundusglaucomaoptic neuropathy |
spellingShingle | Anindita Septiarini Hamdani Hamdani Emy Setyaningsih Eko Junirianto Fitri Utaminingrum Automatic Method for Optic Disc Segmentation Using Deep Learning on Retinal Fundus Images Healthcare Informatics Research image processing computer vision fundus glaucoma optic neuropathy |
title | Automatic Method for Optic Disc Segmentation Using Deep Learning on Retinal Fundus Images |
title_full | Automatic Method for Optic Disc Segmentation Using Deep Learning on Retinal Fundus Images |
title_fullStr | Automatic Method for Optic Disc Segmentation Using Deep Learning on Retinal Fundus Images |
title_full_unstemmed | Automatic Method for Optic Disc Segmentation Using Deep Learning on Retinal Fundus Images |
title_short | Automatic Method for Optic Disc Segmentation Using Deep Learning on Retinal Fundus Images |
title_sort | automatic method for optic disc segmentation using deep learning on retinal fundus images |
topic | image processing computer vision fundus glaucoma optic neuropathy |
url | http://e-hir.org/upload/pdf/hir-2023-29-2-145.pdf |
work_keys_str_mv | AT aninditaseptiarini automaticmethodforopticdiscsegmentationusingdeeplearningonretinalfundusimages AT hamdanihamdani automaticmethodforopticdiscsegmentationusingdeeplearningonretinalfundusimages AT emysetyaningsih automaticmethodforopticdiscsegmentationusingdeeplearningonretinalfundusimages AT ekojunirianto automaticmethodforopticdiscsegmentationusingdeeplearningonretinalfundusimages AT fitriutaminingrum automaticmethodforopticdiscsegmentationusingdeeplearningonretinalfundusimages |