LUVS-Net: A Lightweight U-Net Vessel Segmentor for Retinal Vasculature Detection in Fundus Images
This paper presents LUVS-Net, which is a lightweight convolutional network for retinal vessel segmentation in fundus images that is designed for resource-constrained devices that are typically unable to meet the computational requirements of large neural networks. The computational challenges arise...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-04-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/12/8/1786 |
_version_ | 1797605741264109568 |
---|---|
author | Muhammad Talha Islam Haroon Ahmed Khan Khuram Naveed Ali Nauman Sardar Muhammad Gulfam Sung Won Kim |
author_facet | Muhammad Talha Islam Haroon Ahmed Khan Khuram Naveed Ali Nauman Sardar Muhammad Gulfam Sung Won Kim |
author_sort | Muhammad Talha Islam |
collection | DOAJ |
description | This paper presents LUVS-Net, which is a lightweight convolutional network for retinal vessel segmentation in fundus images that is designed for resource-constrained devices that are typically unable to meet the computational requirements of large neural networks. The computational challenges arise due to low-quality retinal images, wide variance in image acquisition conditions and disparities in intensity. Consequently, the training of existing segmentation methods requires a multitude of trainable parameters for the training of networks, resulting in computational complexity. The proposed Lightweight U-Net for Vessel Segmentation Network (LUVS-Net) can achieve high segmentation performance with only a few trainable parameters. This network uses an encoder–decoder framework in which edge data are transposed from the first layers of the encoder to the last layer of the decoder, massively improving the convergence latency. Additionally, LUVS-Net’s design allows for a dual-stream information flow both inside as well as outside of the encoder–decoder pair. The network width is enhanced using group convolutions, which allow the network to learn a larger number of low- and intermediate-level features. Spatial information loss is minimized using skip connections, and class imbalances are mitigated using dice loss for pixel-wise classification. The performance of the proposed network is evaluated on the publicly available retinal blood vessel datasets DRIVE, CHASE_DB1 and STARE. LUVS-Net proves to be quite competitive, outperforming alternative state-of-the-art segmentation methods and achieving comparable accuracy using trainable parameters that are reduced by two to three orders of magnitude compared with those of comparative state-of-the-art methods. |
first_indexed | 2024-03-11T05:05:22Z |
format | Article |
id | doaj.art-bf1794d876fd44ee8970978222bc0b9a |
institution | Directory Open Access Journal |
issn | 2079-9292 |
language | English |
last_indexed | 2024-03-11T05:05:22Z |
publishDate | 2023-04-01 |
publisher | MDPI AG |
record_format | Article |
series | Electronics |
spelling | doaj.art-bf1794d876fd44ee8970978222bc0b9a2023-11-17T19:00:53ZengMDPI AGElectronics2079-92922023-04-01128178610.3390/electronics12081786LUVS-Net: A Lightweight U-Net Vessel Segmentor for Retinal Vasculature Detection in Fundus ImagesMuhammad Talha Islam0Haroon Ahmed Khan1Khuram Naveed2Ali Nauman3Sardar Muhammad Gulfam4Sung Won Kim5Department of Computer Science, COMSATS University Islamabad (CUI), Islamabad 45550, PakistanDepartment of Electrical and Computer Engineering, COMSATS University Islamabad (CUI), Islamabad 45550, PakistanDepartment of Electrical and Computer Engineering, COMSATS University Islamabad (CUI), Islamabad 45550, PakistanDepartment of Information and Communication Engineering, Yeungnam University, Gyeongsan-si 38541, Republic of KoreaDepartment of Electrical and Computer Engineering, Abbottabad Campus, COMSATS University Islamabad (CUI), Abbottabad 22060, PakistanDepartment of Information and Communication Engineering, Yeungnam University, Gyeongsan-si 38541, Republic of KoreaThis paper presents LUVS-Net, which is a lightweight convolutional network for retinal vessel segmentation in fundus images that is designed for resource-constrained devices that are typically unable to meet the computational requirements of large neural networks. The computational challenges arise due to low-quality retinal images, wide variance in image acquisition conditions and disparities in intensity. Consequently, the training of existing segmentation methods requires a multitude of trainable parameters for the training of networks, resulting in computational complexity. The proposed Lightweight U-Net for Vessel Segmentation Network (LUVS-Net) can achieve high segmentation performance with only a few trainable parameters. This network uses an encoder–decoder framework in which edge data are transposed from the first layers of the encoder to the last layer of the decoder, massively improving the convergence latency. Additionally, LUVS-Net’s design allows for a dual-stream information flow both inside as well as outside of the encoder–decoder pair. The network width is enhanced using group convolutions, which allow the network to learn a larger number of low- and intermediate-level features. Spatial information loss is minimized using skip connections, and class imbalances are mitigated using dice loss for pixel-wise classification. The performance of the proposed network is evaluated on the publicly available retinal blood vessel datasets DRIVE, CHASE_DB1 and STARE. LUVS-Net proves to be quite competitive, outperforming alternative state-of-the-art segmentation methods and achieving comparable accuracy using trainable parameters that are reduced by two to three orders of magnitude compared with those of comparative state-of-the-art methods.https://www.mdpi.com/2079-9292/12/8/1786convolutional neural networkCHASEDRIVEdeep learningimage segmentationmedical images |
spellingShingle | Muhammad Talha Islam Haroon Ahmed Khan Khuram Naveed Ali Nauman Sardar Muhammad Gulfam Sung Won Kim LUVS-Net: A Lightweight U-Net Vessel Segmentor for Retinal Vasculature Detection in Fundus Images Electronics convolutional neural network CHASE DRIVE deep learning image segmentation medical images |
title | LUVS-Net: A Lightweight U-Net Vessel Segmentor for Retinal Vasculature Detection in Fundus Images |
title_full | LUVS-Net: A Lightweight U-Net Vessel Segmentor for Retinal Vasculature Detection in Fundus Images |
title_fullStr | LUVS-Net: A Lightweight U-Net Vessel Segmentor for Retinal Vasculature Detection in Fundus Images |
title_full_unstemmed | LUVS-Net: A Lightweight U-Net Vessel Segmentor for Retinal Vasculature Detection in Fundus Images |
title_short | LUVS-Net: A Lightweight U-Net Vessel Segmentor for Retinal Vasculature Detection in Fundus Images |
title_sort | luvs net a lightweight u net vessel segmentor for retinal vasculature detection in fundus images |
topic | convolutional neural network CHASE DRIVE deep learning image segmentation medical images |
url | https://www.mdpi.com/2079-9292/12/8/1786 |
work_keys_str_mv | AT muhammadtalhaislam luvsnetalightweightunetvesselsegmentorforretinalvasculaturedetectioninfundusimages AT haroonahmedkhan luvsnetalightweightunetvesselsegmentorforretinalvasculaturedetectioninfundusimages AT khuramnaveed luvsnetalightweightunetvesselsegmentorforretinalvasculaturedetectioninfundusimages AT alinauman luvsnetalightweightunetvesselsegmentorforretinalvasculaturedetectioninfundusimages AT sardarmuhammadgulfam luvsnetalightweightunetvesselsegmentorforretinalvasculaturedetectioninfundusimages AT sungwonkim luvsnetalightweightunetvesselsegmentorforretinalvasculaturedetectioninfundusimages |