Multi scale multi attention network for blood vessel segmentation in fundus images
Abstract Precise segmentation of retinal vasculature is crucial for the early detection, diagnosis, and treatment of vision-threatening ailments. However, this task is challenging due to limited contextual information, variations in vessel thicknesses, the complexity of vessel structures, and the po...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2025-01-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-024-84255-w |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
_version_ | 1832571811229859840 |
---|---|
author | Giri Babu Kande Madhusudana Rao Nalluri R. Manikandan Jaehyuk Cho Sathishkumar Veerappampalayam Easwaramoorthy |
author_facet | Giri Babu Kande Madhusudana Rao Nalluri R. Manikandan Jaehyuk Cho Sathishkumar Veerappampalayam Easwaramoorthy |
author_sort | Giri Babu Kande |
collection | DOAJ |
description | Abstract Precise segmentation of retinal vasculature is crucial for the early detection, diagnosis, and treatment of vision-threatening ailments. However, this task is challenging due to limited contextual information, variations in vessel thicknesses, the complexity of vessel structures, and the potential for confusion with lesions. In this paper, we introduce a novel approach, the MSMA Net model, which overcomes these challenges by replacing traditional convolution blocks and skip connections with an improved multi-scale squeeze and excitation block (MSSE Block) and Bottleneck residual paths (B-Res paths) with spatial attention blocks (SAB). Our experimental findings on publicly available datasets of fundus images, specifically DRIVE, STARE, CHASE_DB1, HRF and DR HAGIS consistently demonstrate that our approach outperforms other segmentation techniques, achieving higher accuracy, sensitivity, Dice score, and area under the receiver operator characteristic (AUC) in the segmentation of blood vessels with different thicknesses, even in situations involving diverse contextual information, the presence of coexisting lesions, and intricate vessel morphologies. |
format | Article |
id | doaj-art-a50da136ff454f559b1862119f71d766 |
institution | Kabale University |
issn | 2045-2322 |
language | English |
publishDate | 2025-01-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Scientific Reports |
spelling | doaj-art-a50da136ff454f559b1862119f71d7662025-02-02T12:18:55ZengNature PortfolioScientific Reports2045-23222025-01-0115112110.1038/s41598-024-84255-wMulti scale multi attention network for blood vessel segmentation in fundus imagesGiri Babu Kande0Madhusudana Rao Nalluri1R. Manikandan2Jaehyuk Cho3Sathishkumar Veerappampalayam Easwaramoorthy4Vasireddy Venkatadri Institute of TechnologySchool of Computing, Amrita Vishwa VidyapeethamSchool of Computing, SASTRA Deemed UniversityDepartment of Software Engineering & Division of Electronics and Information Engineering, Jeonbuk National UniversityDepartment of Data Science and Artificial Intelligence, Sunway UniversityAbstract Precise segmentation of retinal vasculature is crucial for the early detection, diagnosis, and treatment of vision-threatening ailments. However, this task is challenging due to limited contextual information, variations in vessel thicknesses, the complexity of vessel structures, and the potential for confusion with lesions. In this paper, we introduce a novel approach, the MSMA Net model, which overcomes these challenges by replacing traditional convolution blocks and skip connections with an improved multi-scale squeeze and excitation block (MSSE Block) and Bottleneck residual paths (B-Res paths) with spatial attention blocks (SAB). Our experimental findings on publicly available datasets of fundus images, specifically DRIVE, STARE, CHASE_DB1, HRF and DR HAGIS consistently demonstrate that our approach outperforms other segmentation techniques, achieving higher accuracy, sensitivity, Dice score, and area under the receiver operator characteristic (AUC) in the segmentation of blood vessels with different thicknesses, even in situations involving diverse contextual information, the presence of coexisting lesions, and intricate vessel morphologies.https://doi.org/10.1038/s41598-024-84255-w |
spellingShingle | Giri Babu Kande Madhusudana Rao Nalluri R. Manikandan Jaehyuk Cho Sathishkumar Veerappampalayam Easwaramoorthy Multi scale multi attention network for blood vessel segmentation in fundus images Scientific Reports |
title | Multi scale multi attention network for blood vessel segmentation in fundus images |
title_full | Multi scale multi attention network for blood vessel segmentation in fundus images |
title_fullStr | Multi scale multi attention network for blood vessel segmentation in fundus images |
title_full_unstemmed | Multi scale multi attention network for blood vessel segmentation in fundus images |
title_short | Multi scale multi attention network for blood vessel segmentation in fundus images |
title_sort | multi scale multi attention network for blood vessel segmentation in fundus images |
url | https://doi.org/10.1038/s41598-024-84255-w |
work_keys_str_mv | AT giribabukande multiscalemultiattentionnetworkforbloodvesselsegmentationinfundusimages AT madhusudanaraonalluri multiscalemultiattentionnetworkforbloodvesselsegmentationinfundusimages AT rmanikandan multiscalemultiattentionnetworkforbloodvesselsegmentationinfundusimages AT jaehyukcho multiscalemultiattentionnetworkforbloodvesselsegmentationinfundusimages AT sathishkumarveerappampalayameaswaramoorthy multiscalemultiattentionnetworkforbloodvesselsegmentationinfundusimages |