Multiscale guided attention network for optic disc segmentation of retinal images
Optic disc (OD) segmentation from retinal images is crucial for diagnosing, assessing, and tracking the progression of several sight-threatening diseases. This paper presents a deep machine-learning method for semantically segmenting OD from retinal images. The method is named multiscale guided atte...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Computer Methods and Programs in Biomedicine Update |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666990025000047 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592798743789568 |
|---|---|
| author | A Z M Ehtesham Chowdhury Andrew Mehnert Graham Mann William H. Morgan Ferdous Sohel |
| author_facet | A Z M Ehtesham Chowdhury Andrew Mehnert Graham Mann William H. Morgan Ferdous Sohel |
| author_sort | A Z M Ehtesham Chowdhury |
| collection | DOAJ |
| description | Optic disc (OD) segmentation from retinal images is crucial for diagnosing, assessing, and tracking the progression of several sight-threatening diseases. This paper presents a deep machine-learning method for semantically segmenting OD from retinal images. The method is named multiscale guided attention network (MSGANet-OD), comprising encoders for extracting multiscale features and decoders for constructing segmentation maps from the extracted features. The decoder also includes a guided attention module that incorporates features related to structural, contextual, and illumination information to segment OD. A custom loss function is proposed to retain the optic disc's geometrical shape (i.e., elliptical) constraint and to alleviate the blood vessels' influence in the overlapping region between the OD and vessels. MSGANet-OD was trained and tested on an in-house clinical color retinal image dataset captured during ophthalmodynamometry as well as on several publicly available color fundus image datasets, e.g., DRISHTI-GS, RIM-ONE-r3, and REFUGE1. Experimental results show that MSGANet-OD achieved superior OD segmentation performance from ophthalmodynamometry images compared to widely used segmentation methods. Our method also achieved competitive results compared to state-of-the-art OD segmentation methods on public datasets. The proposed method can be used in automated systems to quantitatively assess optic nerve head abnormalities (e.g., glaucoma, optic disc neuropathy) and vascular changes in the OD region. |
| format | Article |
| id | doaj-art-8659753098f64343925a88f97356cdfe |
| institution | Kabale University |
| issn | 2666-9900 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Computer Methods and Programs in Biomedicine Update |
| spelling | doaj-art-8659753098f64343925a88f97356cdfe2025-01-21T04:13:23ZengElsevierComputer Methods and Programs in Biomedicine Update2666-99002025-01-017100180Multiscale guided attention network for optic disc segmentation of retinal imagesA Z M Ehtesham Chowdhury0Andrew Mehnert1Graham Mann2William H. Morgan3Ferdous Sohel4School of Information Technology, Murdoch University, Murdoch, WA 6150, AustraliaLions Eye Institute, Nedlands, WA 6009, Australia; Centre for Ophthalmology and Visual Science, The University of Western Australia, Crawley, WA 6009, AustraliaSchool of Information Technology, Murdoch University, Murdoch, WA 6150, AustraliaLions Eye Institute, Nedlands, WA 6009, Australia; Centre for Ophthalmology and Visual Science, The University of Western Australia, Crawley, WA 6009, AustraliaSchool of Information Technology, Murdoch University, Murdoch, WA 6150, Australia; Corresponding author at: Murdoch University, 90 South Street, Murdoch, WA 6150, Australia.Optic disc (OD) segmentation from retinal images is crucial for diagnosing, assessing, and tracking the progression of several sight-threatening diseases. This paper presents a deep machine-learning method for semantically segmenting OD from retinal images. The method is named multiscale guided attention network (MSGANet-OD), comprising encoders for extracting multiscale features and decoders for constructing segmentation maps from the extracted features. The decoder also includes a guided attention module that incorporates features related to structural, contextual, and illumination information to segment OD. A custom loss function is proposed to retain the optic disc's geometrical shape (i.e., elliptical) constraint and to alleviate the blood vessels' influence in the overlapping region between the OD and vessels. MSGANet-OD was trained and tested on an in-house clinical color retinal image dataset captured during ophthalmodynamometry as well as on several publicly available color fundus image datasets, e.g., DRISHTI-GS, RIM-ONE-r3, and REFUGE1. Experimental results show that MSGANet-OD achieved superior OD segmentation performance from ophthalmodynamometry images compared to widely used segmentation methods. Our method also achieved competitive results compared to state-of-the-art OD segmentation methods on public datasets. The proposed method can be used in automated systems to quantitatively assess optic nerve head abnormalities (e.g., glaucoma, optic disc neuropathy) and vascular changes in the OD region.http://www.sciencedirect.com/science/article/pii/S2666990025000047Deep learningGuided attentionOphthalmodynamometrySemantic segmentation |
| spellingShingle | A Z M Ehtesham Chowdhury Andrew Mehnert Graham Mann William H. Morgan Ferdous Sohel Multiscale guided attention network for optic disc segmentation of retinal images Computer Methods and Programs in Biomedicine Update Deep learning Guided attention Ophthalmodynamometry Semantic segmentation |
| title | Multiscale guided attention network for optic disc segmentation of retinal images |
| title_full | Multiscale guided attention network for optic disc segmentation of retinal images |
| title_fullStr | Multiscale guided attention network for optic disc segmentation of retinal images |
| title_full_unstemmed | Multiscale guided attention network for optic disc segmentation of retinal images |
| title_short | Multiscale guided attention network for optic disc segmentation of retinal images |
| title_sort | multiscale guided attention network for optic disc segmentation of retinal images |
| topic | Deep learning Guided attention Ophthalmodynamometry Semantic segmentation |
| url | http://www.sciencedirect.com/science/article/pii/S2666990025000047 |
| work_keys_str_mv | AT azmehteshamchowdhury multiscaleguidedattentionnetworkforopticdiscsegmentationofretinalimages AT andrewmehnert multiscaleguidedattentionnetworkforopticdiscsegmentationofretinalimages AT grahammann multiscaleguidedattentionnetworkforopticdiscsegmentationofretinalimages AT williamhmorgan multiscaleguidedattentionnetworkforopticdiscsegmentationofretinalimages AT ferdoussohel multiscaleguidedattentionnetworkforopticdiscsegmentationofretinalimages |