Impact of eye fundus image preprocessing on key objects segmentation for glaucoma identification

The pathological changes in the eye fundus image, especially around Optic Disc (OD) and Optic Cup (OC) may indicate eye diseases such as glaucoma. Therefore, accurate OD and OC segmentation is essential. The variety in images caused by different eye fundus cameras makes the complexity for the exist...

Full description

Saved in:
Bibliographic Details
Main Authors: Sandra Virbukaitė, Jolita Bernatavičienė
Format: Article
Language:English
Published: Vilnius University Press 2023-11-01
Series:Nonlinear Analysis
Subjects:
Online Access:https://www.journals.vu.lt/nonlinear-analysis/article/view/33669
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850253699619749888
author Sandra Virbukaitė
Jolita Bernatavičienė
author_facet Sandra Virbukaitė
Jolita Bernatavičienė
author_sort Sandra Virbukaitė
collection DOAJ
description The pathological changes in the eye fundus image, especially around Optic Disc (OD) and Optic Cup (OC) may indicate eye diseases such as glaucoma. Therefore, accurate OD and OC segmentation is essential. The variety in images caused by different eye fundus cameras makes the complexity for the existing deep learning (DL) networks in OD and OC segmentation. In most research cases, experiments were conducted on individual data sets only and the results were obtained for that specific data sample. Our future goal is to develop a DL method that segments OD and OC in any kind of eye fundus image but the application of the mixed training data strategy is in the initiation stage and the image preprocessing is not discussed. Therefore, the aim of this paper is to evaluate the mage preprocessing impact on OD and OC segmentation in different eye fundus images aligned by size. We adopted a mixed training data strategy by combining images of DRISHTI-GS, REFUGE, and RIM-ONE datasets, and applied image resizing incorporating various interpolation methods, namely bilinear, nearest neighbor, and bicubic for image resolution alignment. The impact of image preprocessing on OD and OC segmentation was evaluated using three convolutional neural networks Attention U-Net, Residual Attention U-Net (RAUNET), and U-Net++. The experimental results show that the most accurate segmentation is achieved by resizing images to a size of 512 x 512 px and applying bicubic interpolation. The highest Dice of 0.979 for OD and 0.877 for OC are achieved on  RISHTI-GS test dataset, 0.973 for OD and 0.874 for OC on the REFUGE test dataset, 0.977 for OD and 0:855 for OC on RIM-ONE test dataset. Anova and Levene’s tests with statistically significant evidence at α = 0.05 show that the chosen size in image resizing has impact on the OD and OC segmentation results, meanwhile, the interpolation method does influent OC segmentation only.
format Article
id doaj-art-5d97c327e8734d019a1eaea5101cf3ac
institution OA Journals
issn 1392-5113
2335-8963
language English
publishDate 2023-11-01
publisher Vilnius University Press
record_format Article
series Nonlinear Analysis
spelling doaj-art-5d97c327e8734d019a1eaea5101cf3ac2025-08-20T01:57:19ZengVilnius University PressNonlinear Analysis1392-51132335-89632023-11-0129110.15388/namc.2024.29.33669Impact of eye fundus image preprocessing on key objects segmentation for glaucoma identificationSandra Virbukaitė0https://orcid.org/0000-0002-8758-8294Jolita Bernatavičienė1https://orcid.org/0000-0001-5435-8348Vilnius UniversityVilnius University The pathological changes in the eye fundus image, especially around Optic Disc (OD) and Optic Cup (OC) may indicate eye diseases such as glaucoma. Therefore, accurate OD and OC segmentation is essential. The variety in images caused by different eye fundus cameras makes the complexity for the existing deep learning (DL) networks in OD and OC segmentation. In most research cases, experiments were conducted on individual data sets only and the results were obtained for that specific data sample. Our future goal is to develop a DL method that segments OD and OC in any kind of eye fundus image but the application of the mixed training data strategy is in the initiation stage and the image preprocessing is not discussed. Therefore, the aim of this paper is to evaluate the mage preprocessing impact on OD and OC segmentation in different eye fundus images aligned by size. We adopted a mixed training data strategy by combining images of DRISHTI-GS, REFUGE, and RIM-ONE datasets, and applied image resizing incorporating various interpolation methods, namely bilinear, nearest neighbor, and bicubic for image resolution alignment. The impact of image preprocessing on OD and OC segmentation was evaluated using three convolutional neural networks Attention U-Net, Residual Attention U-Net (RAUNET), and U-Net++. The experimental results show that the most accurate segmentation is achieved by resizing images to a size of 512 x 512 px and applying bicubic interpolation. The highest Dice of 0.979 for OD and 0.877 for OC are achieved on  RISHTI-GS test dataset, 0.973 for OD and 0.874 for OC on the REFUGE test dataset, 0.977 for OD and 0:855 for OC on RIM-ONE test dataset. Anova and Levene’s tests with statistically significant evidence at α = 0.05 show that the chosen size in image resizing has impact on the OD and OC segmentation results, meanwhile, the interpolation method does influent OC segmentation only. https://www.journals.vu.lt/nonlinear-analysis/article/view/33669image preprocessingoptic disc segmentationoptic cup segmentationeye fundus imagesdeep neural network
spellingShingle Sandra Virbukaitė
Jolita Bernatavičienė
Impact of eye fundus image preprocessing on key objects segmentation for glaucoma identification
Nonlinear Analysis
image preprocessing
optic disc segmentation
optic cup segmentation
eye fundus images
deep neural network
title Impact of eye fundus image preprocessing on key objects segmentation for glaucoma identification
title_full Impact of eye fundus image preprocessing on key objects segmentation for glaucoma identification
title_fullStr Impact of eye fundus image preprocessing on key objects segmentation for glaucoma identification
title_full_unstemmed Impact of eye fundus image preprocessing on key objects segmentation for glaucoma identification
title_short Impact of eye fundus image preprocessing on key objects segmentation for glaucoma identification
title_sort impact of eye fundus image preprocessing on key objects segmentation for glaucoma identification
topic image preprocessing
optic disc segmentation
optic cup segmentation
eye fundus images
deep neural network
url https://www.journals.vu.lt/nonlinear-analysis/article/view/33669
work_keys_str_mv AT sandravirbukaite impactofeyefundusimagepreprocessingonkeyobjectssegmentationforglaucomaidentification
AT jolitabernataviciene impactofeyefundusimagepreprocessingonkeyobjectssegmentationforglaucomaidentification