Dual-stream disentangled model for microvascular extraction in five datasets from multiple OCTA instruments
IntroductionOptical Coherence Tomography Angiography (OCTA) is a cutting-edge imaging technique that captures retinal capillaries at micrometer resolution using optical instrument. Accurate segmentation of retinal vasculature is essential for eye related diseases measurement and diagnosis. However,...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmed.2025.1542737/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832582982699843584 |
|---|---|
| author | Xiaoyang Hu Xiaoyang Hu Jinkui Hao Quanyong Yi Yitian Zhao Jiong Zhang |
| author_facet | Xiaoyang Hu Xiaoyang Hu Jinkui Hao Quanyong Yi Yitian Zhao Jiong Zhang |
| author_sort | Xiaoyang Hu |
| collection | DOAJ |
| description | IntroductionOptical Coherence Tomography Angiography (OCTA) is a cutting-edge imaging technique that captures retinal capillaries at micrometer resolution using optical instrument. Accurate segmentation of retinal vasculature is essential for eye related diseases measurement and diagnosis. However, noise and artifacts from different imaging instruments can interfere with segmentation, and most existing deep learning models struggle with segmenting small vessels and capturing low-dimensional structural information. These challenges typically results in less precise segmentation performance.MethodsTherefore, we propose a novel and robust Dual-stream Disentangled Network (D2Net) for retinal OCTA microvascular segmentation. Specifically, the D2Net includes a dual-stream encoder that separately learns image artifacts and latent vascular features. By introducing vascular structure as a prior constraint and constructing auxiliary information, the network achieves disentangled representation learning, effectively minimizing the interference of noise and artifacts. The introduced vascular structure prior includes low-dimensional neighborhood energy from the Distance Correlation Energy (DCE) module, which helps to better perceive the structural information of continuous vessels.Results and discussionTo precisely evaluate our method on small vessels, we delicately establish OCTA microvascular labels by performing comprehensive and detailed annotations on the FOCA dataset, which includes data collected from different instruments, and evaluated the proposed D2Net effectively mitigates the challenges of microvasculature region recognition caused by noise and artifacts. The method achieves more refined segmentation performance. In addition, we validated the performance of D2Net on four OCTA datasets (OCTA-500, ROSE-O, ROSE-Z, and ROSE-H) acquired using different instruments, demonstrating its robustness and generalization capabilities in retinal vessel segmentation compared to other state-of-the-art methods. |
| format | Article |
| id | doaj-art-e72bf6f811c64326b108f641cf74bc24 |
| institution | Kabale University |
| issn | 2296-858X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Medicine |
| spelling | doaj-art-e72bf6f811c64326b108f641cf74bc242025-01-29T06:45:31ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2025-01-011210.3389/fmed.2025.15427371542737Dual-stream disentangled model for microvascular extraction in five datasets from multiple OCTA instrumentsXiaoyang Hu0Xiaoyang Hu1Jinkui Hao2Quanyong Yi3Yitian Zhao4Jiong Zhang5Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, ChinaLaboratory of Advanced Theranostic Materials and Technology, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, ChinaLaboratory of Advanced Theranostic Materials and Technology, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, ChinaNingbo Eye Hospital, Wenzhou Medical University, Ningbo, ChinaLaboratory of Advanced Theranostic Materials and Technology, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, ChinaLaboratory of Advanced Theranostic Materials and Technology, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, ChinaIntroductionOptical Coherence Tomography Angiography (OCTA) is a cutting-edge imaging technique that captures retinal capillaries at micrometer resolution using optical instrument. Accurate segmentation of retinal vasculature is essential for eye related diseases measurement and diagnosis. However, noise and artifacts from different imaging instruments can interfere with segmentation, and most existing deep learning models struggle with segmenting small vessels and capturing low-dimensional structural information. These challenges typically results in less precise segmentation performance.MethodsTherefore, we propose a novel and robust Dual-stream Disentangled Network (D2Net) for retinal OCTA microvascular segmentation. Specifically, the D2Net includes a dual-stream encoder that separately learns image artifacts and latent vascular features. By introducing vascular structure as a prior constraint and constructing auxiliary information, the network achieves disentangled representation learning, effectively minimizing the interference of noise and artifacts. The introduced vascular structure prior includes low-dimensional neighborhood energy from the Distance Correlation Energy (DCE) module, which helps to better perceive the structural information of continuous vessels.Results and discussionTo precisely evaluate our method on small vessels, we delicately establish OCTA microvascular labels by performing comprehensive and detailed annotations on the FOCA dataset, which includes data collected from different instruments, and evaluated the proposed D2Net effectively mitigates the challenges of microvasculature region recognition caused by noise and artifacts. The method achieves more refined segmentation performance. In addition, we validated the performance of D2Net on four OCTA datasets (OCTA-500, ROSE-O, ROSE-Z, and ROSE-H) acquired using different instruments, demonstrating its robustness and generalization capabilities in retinal vessel segmentation compared to other state-of-the-art methods.https://www.frontiersin.org/articles/10.3389/fmed.2025.1542737/fullOCTAcross-instrumentsmicrovascular segmentationvessel measurementsdisentanglement |
| spellingShingle | Xiaoyang Hu Xiaoyang Hu Jinkui Hao Quanyong Yi Yitian Zhao Jiong Zhang Dual-stream disentangled model for microvascular extraction in five datasets from multiple OCTA instruments Frontiers in Medicine OCTA cross-instruments microvascular segmentation vessel measurements disentanglement |
| title | Dual-stream disentangled model for microvascular extraction in five datasets from multiple OCTA instruments |
| title_full | Dual-stream disentangled model for microvascular extraction in five datasets from multiple OCTA instruments |
| title_fullStr | Dual-stream disentangled model for microvascular extraction in five datasets from multiple OCTA instruments |
| title_full_unstemmed | Dual-stream disentangled model for microvascular extraction in five datasets from multiple OCTA instruments |
| title_short | Dual-stream disentangled model for microvascular extraction in five datasets from multiple OCTA instruments |
| title_sort | dual stream disentangled model for microvascular extraction in five datasets from multiple octa instruments |
| topic | OCTA cross-instruments microvascular segmentation vessel measurements disentanglement |
| url | https://www.frontiersin.org/articles/10.3389/fmed.2025.1542737/full |
| work_keys_str_mv | AT xiaoyanghu dualstreamdisentangledmodelformicrovascularextractioninfivedatasetsfrommultipleoctainstruments AT xiaoyanghu dualstreamdisentangledmodelformicrovascularextractioninfivedatasetsfrommultipleoctainstruments AT jinkuihao dualstreamdisentangledmodelformicrovascularextractioninfivedatasetsfrommultipleoctainstruments AT quanyongyi dualstreamdisentangledmodelformicrovascularextractioninfivedatasetsfrommultipleoctainstruments AT yitianzhao dualstreamdisentangledmodelformicrovascularextractioninfivedatasetsfrommultipleoctainstruments AT jiongzhang dualstreamdisentangledmodelformicrovascularextractioninfivedatasetsfrommultipleoctainstruments |