LiViT-Net: A U-Net-like, lightweight Transformer network for retinal vessel segmentation
The intricate task of precisely segmenting retinal vessels from images, which is critical for diagnosing various eye diseases, presents significant challenges for models due to factors such as scale variation, complex anatomical patterns, low contrast, and limitations in training data. Building on t...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2024-12-01
|
Series: | Computational and Structural Biotechnology Journal |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2001037024000564 |
_version_ | 1797243006369136640 |
---|---|
author | Le Tong Tianjiu Li Qian Zhang Qin Zhang Renchaoli Zhu Wei Du Pengwei Hu |
author_facet | Le Tong Tianjiu Li Qian Zhang Qin Zhang Renchaoli Zhu Wei Du Pengwei Hu |
author_sort | Le Tong |
collection | DOAJ |
description | The intricate task of precisely segmenting retinal vessels from images, which is critical for diagnosing various eye diseases, presents significant challenges for models due to factors such as scale variation, complex anatomical patterns, low contrast, and limitations in training data. Building on these challenges, we offer novel contributions spanning model architecture, loss function design, robustness, and real-time efficacy. To comprehensively address these challenges, a new U-Net-like, lightweight Transformer network for retinal vessel segmentation is presented. By integrating MobileViT+ and a novel local representation in the encoder, our design emphasizes lightweight processing while capturing intricate image structures, enhancing vessel edge precision. A novel joint loss is designed, leveraging the characteristics of weighted cross-entropy and Dice loss to effectively guide the model through the task's challenges, such as foreground-background imbalance and intricate vascular structures. Exhaustive experiments were performed on three prominent retinal image databases. The results underscore the robustness and generalizability of the proposed LiViT-Net, which outperforms other methods in complex scenarios, especially in intricate environments with fine vessels or vessel edges. Importantly, optimized for efficiency, LiViT-Net excels on devices with constrained computational power, as evidenced by its fast performance. To demonstrate the model proposed in this study, a freely accessible and interactive website was established (https://hz-t3.matpool.com:28765?token=aQjYR4hqMI), revealing real-time performance with no login requirements. |
first_indexed | 2024-04-24T18:48:15Z |
format | Article |
id | doaj.art-24ff6196ab994c96a17a781d636d7ab0 |
institution | Directory Open Access Journal |
issn | 2001-0370 |
language | English |
last_indexed | 2024-04-24T18:48:15Z |
publishDate | 2024-12-01 |
publisher | Elsevier |
record_format | Article |
series | Computational and Structural Biotechnology Journal |
spelling | doaj.art-24ff6196ab994c96a17a781d636d7ab02024-03-27T04:51:47ZengElsevierComputational and Structural Biotechnology Journal2001-03702024-12-0124213224LiViT-Net: A U-Net-like, lightweight Transformer network for retinal vessel segmentationLe Tong0Tianjiu Li1Qian Zhang2Qin Zhang3Renchaoli Zhu4Wei Du5Pengwei Hu6The College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, No. 100 Haisi Road, Shanghai, 201418, ChinaThe College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, No. 100 Haisi Road, Shanghai, 201418, ChinaThe College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, No. 100 Haisi Road, Shanghai, 201418, China; Corresponding authors.Ophthalmology Department, Jing'an District Central Hospital, No. 259, Xikang Road, Shanghai, 200040, China; Corresponding authors.The College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, No. 100 Haisi Road, Shanghai, 201418, ChinaLaboratory of Smart Manufacturing in Energy Chemical Process, East China University of Science and Technology, No. 130 Meilong Road, Shanghai, 200237, ChinaThe Xinjiang Technical Institute of Physics and Chemistry, Chinese Academy of Sciences, 40-1 South Beijing Road, Urumqi, 830011, ChinaThe intricate task of precisely segmenting retinal vessels from images, which is critical for diagnosing various eye diseases, presents significant challenges for models due to factors such as scale variation, complex anatomical patterns, low contrast, and limitations in training data. Building on these challenges, we offer novel contributions spanning model architecture, loss function design, robustness, and real-time efficacy. To comprehensively address these challenges, a new U-Net-like, lightweight Transformer network for retinal vessel segmentation is presented. By integrating MobileViT+ and a novel local representation in the encoder, our design emphasizes lightweight processing while capturing intricate image structures, enhancing vessel edge precision. A novel joint loss is designed, leveraging the characteristics of weighted cross-entropy and Dice loss to effectively guide the model through the task's challenges, such as foreground-background imbalance and intricate vascular structures. Exhaustive experiments were performed on three prominent retinal image databases. The results underscore the robustness and generalizability of the proposed LiViT-Net, which outperforms other methods in complex scenarios, especially in intricate environments with fine vessels or vessel edges. Importantly, optimized for efficiency, LiViT-Net excels on devices with constrained computational power, as evidenced by its fast performance. To demonstrate the model proposed in this study, a freely accessible and interactive website was established (https://hz-t3.matpool.com:28765?token=aQjYR4hqMI), revealing real-time performance with no login requirements.http://www.sciencedirect.com/science/article/pii/S2001037024000564Retinal vessel segmentationTransformerLightweightJoint loss |
spellingShingle | Le Tong Tianjiu Li Qian Zhang Qin Zhang Renchaoli Zhu Wei Du Pengwei Hu LiViT-Net: A U-Net-like, lightweight Transformer network for retinal vessel segmentation Computational and Structural Biotechnology Journal Retinal vessel segmentation Transformer Lightweight Joint loss |
title | LiViT-Net: A U-Net-like, lightweight Transformer network for retinal vessel segmentation |
title_full | LiViT-Net: A U-Net-like, lightweight Transformer network for retinal vessel segmentation |
title_fullStr | LiViT-Net: A U-Net-like, lightweight Transformer network for retinal vessel segmentation |
title_full_unstemmed | LiViT-Net: A U-Net-like, lightweight Transformer network for retinal vessel segmentation |
title_short | LiViT-Net: A U-Net-like, lightweight Transformer network for retinal vessel segmentation |
title_sort | livit net a u net like lightweight transformer network for retinal vessel segmentation |
topic | Retinal vessel segmentation Transformer Lightweight Joint loss |
url | http://www.sciencedirect.com/science/article/pii/S2001037024000564 |
work_keys_str_mv | AT letong livitnetaunetlikelightweighttransformernetworkforretinalvesselsegmentation AT tianjiuli livitnetaunetlikelightweighttransformernetworkforretinalvesselsegmentation AT qianzhang livitnetaunetlikelightweighttransformernetworkforretinalvesselsegmentation AT qinzhang livitnetaunetlikelightweighttransformernetworkforretinalvesselsegmentation AT renchaolizhu livitnetaunetlikelightweighttransformernetworkforretinalvesselsegmentation AT weidu livitnetaunetlikelightweighttransformernetworkforretinalvesselsegmentation AT pengweihu livitnetaunetlikelightweighttransformernetworkforretinalvesselsegmentation |