FLA-UNet: feature-location attention U-Net for foveal avascular zone segmentation in OCTA images

IntroductionSince optical coherence tomography angiography (OCTA) is non-invasive and non-contact, it is widely used in the study of retinal disease detection. As a key indicator for retinal disease detection, accurate segmentation of foveal avascular zone (FAZ) has an important impact on clinical a...

Full description

Saved in:
Bibliographic Details
Main Authors: Wei Li, Li Cao, He Deng
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-07-01
Series:Frontiers in Artificial Intelligence
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/frai.2025.1463233/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849318302233395200
author Wei Li
Li Cao
He Deng
author_facet Wei Li
Li Cao
He Deng
author_sort Wei Li
collection DOAJ
description IntroductionSince optical coherence tomography angiography (OCTA) is non-invasive and non-contact, it is widely used in the study of retinal disease detection. As a key indicator for retinal disease detection, accurate segmentation of foveal avascular zone (FAZ) has an important impact on clinical application. Although the U-Net and its existing improvement methods have achieved good performance on FAZ segmentation, their generalization ability and segmentation accuracy can be further improved by exploring more effective improvement strategies.MethodsWe propose a novel improved method named Feature-location Attention U-Net (FLA-UNet) by introducing new designed feature-location attention blocks (FLABs) into U-Net and using a joint loss function. The FLAB consists of feature-aware blocks and location-aware blocks in parallel, and is embed into each decoder of U-Net to integrate more marginal information of FAZ and strengthen the connection between target region and boundary information. The joint loss function is composed of the cross-entropy loss (CE loss) function and the Dice coefficient loss (Dice loss) function, and by adjusting the weights of them, the performance of the network on boundary and internal segmentation can be comprehensively considered to improve its accuracy and robustness for FAZ segmentation.ResultsThe qualitative and quantitative comparative experiments on the three datasets of OCTAGON, FAZID and OCTA-500 show that, our proposed FLA-UNet achieves better segmentation quality, and is superior to other existing state-of-the-art methods in terms of the MIoU, ACC and Dice coefficient.DiscussionThe proposed FLA-UNet can effectively improve the accuracy and robustness of FAZ segmentation in OCTA images by introducing feature-location attention blocks into U-Net and using a joint loss function. This has laid a solid theoretical foundation for its application in auxiliary diagnosis of fundus diseases.
format Article
id doaj-art-ea110575cc0545708b64850e9525baa4
institution Kabale University
issn 2624-8212
language English
publishDate 2025-07-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Artificial Intelligence
spelling doaj-art-ea110575cc0545708b64850e9525baa42025-08-20T03:50:53ZengFrontiers Media S.A.Frontiers in Artificial Intelligence2624-82122025-07-01810.3389/frai.2025.14632331463233FLA-UNet: feature-location attention U-Net for foveal avascular zone segmentation in OCTA imagesWei Li0Li Cao1He Deng2School of Electrical and Electronic Engineering, Wuhan Polytechnic University, Wuhan, ChinaSchool of Electrical and Electronic Engineering, Wuhan Polytechnic University, Wuhan, ChinaSchool of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, ChinaIntroductionSince optical coherence tomography angiography (OCTA) is non-invasive and non-contact, it is widely used in the study of retinal disease detection. As a key indicator for retinal disease detection, accurate segmentation of foveal avascular zone (FAZ) has an important impact on clinical application. Although the U-Net and its existing improvement methods have achieved good performance on FAZ segmentation, their generalization ability and segmentation accuracy can be further improved by exploring more effective improvement strategies.MethodsWe propose a novel improved method named Feature-location Attention U-Net (FLA-UNet) by introducing new designed feature-location attention blocks (FLABs) into U-Net and using a joint loss function. The FLAB consists of feature-aware blocks and location-aware blocks in parallel, and is embed into each decoder of U-Net to integrate more marginal information of FAZ and strengthen the connection between target region and boundary information. The joint loss function is composed of the cross-entropy loss (CE loss) function and the Dice coefficient loss (Dice loss) function, and by adjusting the weights of them, the performance of the network on boundary and internal segmentation can be comprehensively considered to improve its accuracy and robustness for FAZ segmentation.ResultsThe qualitative and quantitative comparative experiments on the three datasets of OCTAGON, FAZID and OCTA-500 show that, our proposed FLA-UNet achieves better segmentation quality, and is superior to other existing state-of-the-art methods in terms of the MIoU, ACC and Dice coefficient.DiscussionThe proposed FLA-UNet can effectively improve the accuracy and robustness of FAZ segmentation in OCTA images by introducing feature-location attention blocks into U-Net and using a joint loss function. This has laid a solid theoretical foundation for its application in auxiliary diagnosis of fundus diseases.https://www.frontiersin.org/articles/10.3389/frai.2025.1463233/fulloptical coherence tomography angiography (OCTA)foveal avascular zone (FAZ) segmentationfeature-location attentionjoint loss functionU-Net
spellingShingle Wei Li
Li Cao
He Deng
FLA-UNet: feature-location attention U-Net for foveal avascular zone segmentation in OCTA images
Frontiers in Artificial Intelligence
optical coherence tomography angiography (OCTA)
foveal avascular zone (FAZ) segmentation
feature-location attention
joint loss function
U-Net
title FLA-UNet: feature-location attention U-Net for foveal avascular zone segmentation in OCTA images
title_full FLA-UNet: feature-location attention U-Net for foveal avascular zone segmentation in OCTA images
title_fullStr FLA-UNet: feature-location attention U-Net for foveal avascular zone segmentation in OCTA images
title_full_unstemmed FLA-UNet: feature-location attention U-Net for foveal avascular zone segmentation in OCTA images
title_short FLA-UNet: feature-location attention U-Net for foveal avascular zone segmentation in OCTA images
title_sort fla unet feature location attention u net for foveal avascular zone segmentation in octa images
topic optical coherence tomography angiography (OCTA)
foveal avascular zone (FAZ) segmentation
feature-location attention
joint loss function
U-Net
url https://www.frontiersin.org/articles/10.3389/frai.2025.1463233/full
work_keys_str_mv AT weili flaunetfeaturelocationattentionunetforfovealavascularzonesegmentationinoctaimages
AT licao flaunetfeaturelocationattentionunetforfovealavascularzonesegmentationinoctaimages
AT hedeng flaunetfeaturelocationattentionunetforfovealavascularzonesegmentationinoctaimages