Comprehensive Evaluation of OCT-based Automated Segmentation of Retinal Layer, Fluid and Hyper-Reflective Foci: Impact on Clinical Assessment of Diabetic Retinopathy Severity
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915384932696064 |
|---|---|
| author | Chen, S. Ma, D. Raviselvan, M. Sundaramoorthy, S. Popuri, K. Ju, M. J. Sarunic, M. V. Ratra, D. Beg, M. F. |
| author_facet | Chen, S. Ma, D. Raviselvan, M. Sundaramoorthy, S. Popuri, K. Ju, M. J. Sarunic, M. V. Ratra, D. Beg, M. F. |
| contents | Diabetic retinopathy (DR) is a leading cause of vision loss, requiring early and accurate assessment to prevent irreversible damage. Spectral Domain Optical Coherence Tomography (SD-OCT) enables high-resolution retinal imaging, but automated segmentation performance varies, especially in cases with complex fluid and hyperreflective foci (HRF) patterns. This study proposes an active-learning-based deep learning pipeline for automated segmentation of retinal layers, fluid, and HRF, using four state-of-the-art models: U-Net, SegFormer, SwinUNETR, and VM-UNet, trained on expert-annotated SD-OCT volumes. Segmentation accuracy was evaluated with five-fold cross-validation, and retinal thickness was quantified using a K-nearest neighbors algorithm and visualized with Early Treatment Diabetic Retinopathy Study (ETDRS) maps. SwinUNETR achieved the highest overall accuracy (DSC = 0.7719; NSD = 0.8149), while VM-UNet excelled in specific layers. Structural differences were observed between non-proliferative and proliferative DR, with layer-specific thickening correlating with visual acuity impairment. The proposed framework enables robust, clinically relevant DR assessment while reducing the need for manual annotation, supporting improved disease monitoring and treatment planning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_01248 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Comprehensive Evaluation of OCT-based Automated Segmentation of Retinal Layer, Fluid and Hyper-Reflective Foci: Impact on Clinical Assessment of Diabetic Retinopathy Severity Chen, S. Ma, D. Raviselvan, M. Sundaramoorthy, S. Popuri, K. Ju, M. J. Sarunic, M. V. Ratra, D. Beg, M. F. Image and Video Processing Computer Vision and Pattern Recognition Machine Learning Tissues and Organs Diabetic retinopathy (DR) is a leading cause of vision loss, requiring early and accurate assessment to prevent irreversible damage. Spectral Domain Optical Coherence Tomography (SD-OCT) enables high-resolution retinal imaging, but automated segmentation performance varies, especially in cases with complex fluid and hyperreflective foci (HRF) patterns. This study proposes an active-learning-based deep learning pipeline for automated segmentation of retinal layers, fluid, and HRF, using four state-of-the-art models: U-Net, SegFormer, SwinUNETR, and VM-UNet, trained on expert-annotated SD-OCT volumes. Segmentation accuracy was evaluated with five-fold cross-validation, and retinal thickness was quantified using a K-nearest neighbors algorithm and visualized with Early Treatment Diabetic Retinopathy Study (ETDRS) maps. SwinUNETR achieved the highest overall accuracy (DSC = 0.7719; NSD = 0.8149), while VM-UNet excelled in specific layers. Structural differences were observed between non-proliferative and proliferative DR, with layer-specific thickening correlating with visual acuity impairment. The proposed framework enables robust, clinically relevant DR assessment while reducing the need for manual annotation, supporting improved disease monitoring and treatment planning. |
| title | Comprehensive Evaluation of OCT-based Automated Segmentation of Retinal Layer, Fluid and Hyper-Reflective Foci: Impact on Clinical Assessment of Diabetic Retinopathy Severity |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Machine Learning Tissues and Organs |
| url | https://arxiv.org/abs/2503.01248 |