Deep learning for artery–vein classification in optical coherence tomography angiography

Le, David; Abtahi, Mansour; Adejumo, Tobiloba; Ebrahimi, Behrouz; Son, Taeyoon; Yao, Xincheng

doi:10.1177/15353702231181182

Cited by 7 publications

(2 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent studies in deep learning OCTA have primarily been focused on the classification of eye diseases such as diabetic retinopathy 16 – 18 , age-related macular degeneration 19 – 21 , and glaucoma 22 – 24 . Other applications include improving the image quality of OCTA 25 , 26 and artery–vein segmentation 27 – 31 . Recently, deep learning has also been explored for OCTA construction 32 – 35 .…”

Section: Introductionmentioning

confidence: 99%

Deep learning-based optical coherence tomography angiography image construction using spatial vascular connectivity network

Le,

Son,

Kim

et al. 2024

Commun Eng

Self Cite

View full text Add to dashboard Cite

Optical coherence tomography angiography (OCTA) provides unrivaled capability for depth-resolved visualization of retinal vasculature at the microcapillary level resolution. For OCTA image construction, repeated OCT scans from one location are required to identify blood vessels with active blood flow. The requirement for multi-scan-volumetric OCT can reduce OCTA imaging speed, which will induce eye movements and limit the image field-of-view. In principle, the blood flow should also affect the reflectance brightness profile along the vessel direction in a single-scan-volumetric OCT. Here we report a spatial vascular connectivity network (SVC-Net) for deep learning OCTA construction from single-scan-volumetric OCT. We quantitatively determine the optimal number of neighboring B-scans as image input, we compare the effects of neighboring B-scans to single B-scan input models, and we explore different loss functions for optimization of SVC-Net. This approach can improve the clinical implementation of OCTA by improving transverse image resolution or increasing the field-of-view.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep learning-based optical coherence tomography angiography image construction using spatial vascular connectivity network

Le,

Son,

Kim

et al. 2024

Commun Eng

Self Cite

View full text Add to dashboard Cite

show abstract

“…It has shown significant advancements in various medical imaging applications. 20 – 24 Previous ROP classification studies mainly focused on direct use of color fundus images, 25 – 29 with a limited exploration of the green channel. 30 , 31 The potential of the red channel for deep learning ROP classification remains unexplored.…”

Section: Introductionmentioning

confidence: 99%

Assessing spectral effectiveness in color fundus photography for deep learning classification of retinopathy of prematurity

Ebrahimi,

Le,

Abtahi

et al. 2024

J. Biomed. Opt.

Self Cite

View full text Add to dashboard Cite

Retinopathy of prematurity (ROP) poses a significant global threat to childhood vision, necessitating effective screening strategies. This study addresses the impact of color channels in fundus imaging on ROP diagnosis, emphasizing the efficacy and safety of utilizing longer wavelengths, such as red or green for enhanced depth information and improved diagnostic capabilities.Aim: This study aims to assess the spectral effectiveness in color fundus photography for the deep learning classification of ROP.Approach: A convolutional neural network end-to-end classifier was utilized for deep learning classification of normal, stage 1, stage 2, and stage 3 ROP fundus images. The classification performances with individual-color-channel inputs, i.e., red, green, and blue, and multi-color-channel fusion architectures, including early-fusion, intermediate-fusion, and late-fusion, were quantitatively compared.Results: For individual-color-channel inputs, similar performance was observed for green channel (88.00% accuracy, 76.00% sensitivity, and 92.00% specificity) and red channel (87.25% accuracy, 74.50% sensitivity, and 91.50% specificity), which is substantially outperforming the blue channel (78.25% accuracy, 56.50% sensitivity, and 85.50% specificity). For multi-color-channel fusion options, the early-fusion and intermediate-fusion architecture showed almost the same performance when compared to the green/red channel input, and they outperformed the late-fusion architecture.Conclusions: This study reveals that the classification of ROP stages can be effectively achieved using either the green or red image alone. This finding enables the exclusion of blue images, acknowledged for their increased susceptibility to light toxicity.

show abstract

Evaluating color efficacy in fundus photography for artificial intelligence classification of retinopathy of prematurity

Ebrahimi,

Le,

Abtahi

et al. 2024

Ophthalmic Technologies XXXIV

Self Cite

View full text Add to dashboard Cite

This study investigates the efficacy of the red, green, and blue channels in color fundus photography on the deep learning classification of retinopathy of prematurity (ROP). We used a total of 200 color fundus images from four ROP stages and applied the transfer learning for deep learning classification. To enhance visibility, contrast limiting adaptive histogram equalization (CLAHE) was utilized. Multi-color-channel fusion approach was tested to determine its effect on ROP classification. For individual channel classification, the green channel demonstrated the best results, with an accuracy of 80.5%, sensitivity of 61%, and specificity of 87%. Multi-color-channel fusion provided slightly better performance than green channel with an accuracy of 81%, sensitivity of 62%, and specificity of 87.33%. After CLAHE, the red-only, green-only, and RGB-fusion showed comparable performance, with accuracies of 83.5%, 84%, and 84.25, sensitivities of 67%, 68% and 68.5%, and specificities of 89%, 89.33% and 89.50%, respectively. This observation suggests that the red channel after contrast enhancement can provide sufficient information for ROP stage classification.

show abstract

Deep learning for artery–vein classification in optical coherence tomography angiography

Cited by 7 publications

References 39 publications

Deep learning-based optical coherence tomography angiography image construction using spatial vascular connectivity network

Deep learning-based optical coherence tomography angiography image construction using spatial vascular connectivity network

Assessing spectral effectiveness in color fundus photography for deep learning classification of retinopathy of prematurity

Evaluating color efficacy in fundus photography for artificial intelligence classification of retinopathy of prematurity

Contact Info

Product

Resources

About