A Novel Network for Choroidal Segmentation Based on Enhanced Boundary Information

Due to the inherent imaging characteristics of Optical Coherence Tomography (OCT), the contrast between the choroid and sclera is low, presenting significant challenges in choroidal segmentation, such as subchoroidal boundary blurring and difficulty in accurate boundary delineation. To address these...

Full description

Saved in:
Bibliographic Details
Main Authors: Wenbo Huang, Chaofan Qu, Yang Yan
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10829938/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850094140148154368
author Wenbo Huang
Chaofan Qu
Yang Yan
author_facet Wenbo Huang
Chaofan Qu
Yang Yan
author_sort Wenbo Huang
collection DOAJ
description Due to the inherent imaging characteristics of Optical Coherence Tomography (OCT), the contrast between the choroid and sclera is low, presenting significant challenges in choroidal segmentation, such as subchoroidal boundary blurring and difficulty in accurate boundary delineation. To address these issues, this paper proposes an automatic choroid segmentation network, termed Boundary Enhancement Net (BENet), which enhances boundary information to facilitate precise recognition and achieve end-to-end automatic segmentation. BENet is constructed on the TransUnet backbone and integrates a boundary enhancement module, leveraging a multi-branch architecture and dilated convolutions to capture features across multiple scales. The attention mechanism is incorporated to dynamically highlight critical features, thus improving the model’s capacity to represent boundary details. Furthermore, the channel enhancement mechanism further refines the expression of salient channel futures, while the adaptive activation function improves the sensitivity of the network to boundary futures. A custom loss function, specifically designed to replace the conventional Mean Squared Error (MSE) loss, is utilized to optimize network parameters, leading to further improvements in segmentation performance. The BENet architecture achieved a Dice coefficient of 95.24%, a Hausdorff distance of 2.68, and an accuracy of 99.12%. Compared to the original TransUnet, BENet demonstrated an increase of nearly 5% in the Dice coefficient and 0.85% in accuracy. Ablation studies and results from multiple medical image datasets validate that BENet consistently delivers precise segmentation outcomes. The boundary enhancement module effectively improves the accuracy of choroidal segmentation, while the custom loss function optimizes network performance, increasing both stability and generalization capabilities. Moreover, the modular design of the boundary enhancement module ensures its portability across different segmentation tasks, making it a versatile component for integration into existing frameworks.
format Article
id doaj-art-e8955b8cc7e94bde88fadd2d684e8e80
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-e8955b8cc7e94bde88fadd2d684e8e802025-08-20T02:41:43ZengIEEEIEEE Access2169-35362025-01-01137027703910.1109/ACCESS.2025.352665710829938A Novel Network for Choroidal Segmentation Based on Enhanced Boundary InformationWenbo Huang0https://orcid.org/0000-0001-5509-7979Chaofan Qu1https://orcid.org/0009-0001-8289-2553Yang Yan2https://orcid.org/0000-0002-8227-7630School of Computer Science and Technology, Changchun Normal University, Erdao, Changchun, Jilin, ChinaSchool of Computer Science and Technology, Changchun Normal University, Erdao, Changchun, Jilin, ChinaSchool of Computer Science and Technology, Changchun Normal University, Erdao, Changchun, Jilin, ChinaDue to the inherent imaging characteristics of Optical Coherence Tomography (OCT), the contrast between the choroid and sclera is low, presenting significant challenges in choroidal segmentation, such as subchoroidal boundary blurring and difficulty in accurate boundary delineation. To address these issues, this paper proposes an automatic choroid segmentation network, termed Boundary Enhancement Net (BENet), which enhances boundary information to facilitate precise recognition and achieve end-to-end automatic segmentation. BENet is constructed on the TransUnet backbone and integrates a boundary enhancement module, leveraging a multi-branch architecture and dilated convolutions to capture features across multiple scales. The attention mechanism is incorporated to dynamically highlight critical features, thus improving the model’s capacity to represent boundary details. Furthermore, the channel enhancement mechanism further refines the expression of salient channel futures, while the adaptive activation function improves the sensitivity of the network to boundary futures. A custom loss function, specifically designed to replace the conventional Mean Squared Error (MSE) loss, is utilized to optimize network parameters, leading to further improvements in segmentation performance. The BENet architecture achieved a Dice coefficient of 95.24%, a Hausdorff distance of 2.68, and an accuracy of 99.12%. Compared to the original TransUnet, BENet demonstrated an increase of nearly 5% in the Dice coefficient and 0.85% in accuracy. Ablation studies and results from multiple medical image datasets validate that BENet consistently delivers precise segmentation outcomes. The boundary enhancement module effectively improves the accuracy of choroidal segmentation, while the custom loss function optimizes network performance, increasing both stability and generalization capabilities. Moreover, the modular design of the boundary enhancement module ensures its portability across different segmentation tasks, making it a versatile component for integration into existing frameworks.https://ieeexplore.ieee.org/document/10829938/Choroid segmentationTransUnetboundary enhancementadaptive activationdeep learning
spellingShingle Wenbo Huang
Chaofan Qu
Yang Yan
A Novel Network for Choroidal Segmentation Based on Enhanced Boundary Information
IEEE Access
Choroid segmentation
TransUnet
boundary enhancement
adaptive activation
deep learning
title A Novel Network for Choroidal Segmentation Based on Enhanced Boundary Information
title_full A Novel Network for Choroidal Segmentation Based on Enhanced Boundary Information
title_fullStr A Novel Network for Choroidal Segmentation Based on Enhanced Boundary Information
title_full_unstemmed A Novel Network for Choroidal Segmentation Based on Enhanced Boundary Information
title_short A Novel Network for Choroidal Segmentation Based on Enhanced Boundary Information
title_sort novel network for choroidal segmentation based on enhanced boundary information
topic Choroid segmentation
TransUnet
boundary enhancement
adaptive activation
deep learning
url https://ieeexplore.ieee.org/document/10829938/
work_keys_str_mv AT wenbohuang anovelnetworkforchoroidalsegmentationbasedonenhancedboundaryinformation
AT chaofanqu anovelnetworkforchoroidalsegmentationbasedonenhancedboundaryinformation
AT yangyan anovelnetworkforchoroidalsegmentationbasedonenhancedboundaryinformation
AT wenbohuang novelnetworkforchoroidalsegmentationbasedonenhancedboundaryinformation
AT chaofanqu novelnetworkforchoroidalsegmentationbasedonenhancedboundaryinformation
AT yangyan novelnetworkforchoroidalsegmentationbasedonenhancedboundaryinformation