Optical coherence tomography angiography and microvascular changes in diabetic retinopathy: a systematic review

Johannesen, Sunniva Kruse; Viken, Julie Nilssen; Vergmann, Anna Stage; Grauslund, Jakob

doi:10.1111/aos.13859

Cited by 66 publications

(56 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We found a significant positive correlation between the FAZ area and BCVA (LogMAR) in DR patients; larger FAZ areas were correlated with poorer BCVA (P<0.001). These results concur with previous research by Balaratnasingam et al, who also demonstrated a significant correlation between the FAZ area and BCVA in patients with DR. 16 Our results are also in agreement with a study by Johannesen et al, 17 who stated that the FAZ area was larger in patients with NPDR and PDR in comparison to the healthy control group. The association between DR progression and increased FAZ area may reflect the increased amount of non-perfused areas.…”

Section: Discussionsupporting

confidence: 93%

<p>Correlations Between Optical Coherence Tomography Angiography Parameters and the Visual Acuity in Patients with Diabetic Retinopathy</p>

Abdelshafy

2020

OPTH

View full text Add to dashboard Cite

The aim of this study was to assess the correlation between different optical coherence tomography angiography (OCTA) parameters and the best corrected visual acuity (BCVA) in patients with diabetic retinopathy (DR). Patients and Methods: Sixty eyes of 60 participants were included in this prospective study: 40 diabetic patients [20 with non-proliferative diabetic retinopathy (NPDR group), 20 with proliferative diabetic retinopathy (PDR group)] and 20 age-and gender-matched normal healthy subjects (control group). After full ophthalmological examination and fundus fluorescein angiography, OCTA was performed for all participants. Quantitative OCTA parameters, such as the foveal avascular zone (FAZ) area, the superficial capillary plexus vessel density (%) (SCP-VD) and the deep capillary plexus vessel density (%) (DCP-VD) in, whole and parafoveal areas were measured. Correlations between BCVA and OCTA parameters were analyzed. Results: There were no statistically significant differences between groups regarding age, gender, refraction, macular thickness or intraocular pressure. The median (IQR) FAZ area was 0.42 (0.39-0.46) mm 2 in the NPDR group, 0.54 (0.45-0.65) mm 2 in the PDR group and 0.24 (0.21-0.26) mm 2 in the control group (P<0.001). The FAZ area increased with increasing severity of DR. SCP-VD and DCP-VD showed significant differences between groups (P<0.001). Vessel density (VD) was decreased in both DCP and SCP as DR progressed. There was a significant positive correlation between BCVA (LogMAR) and FAZ area. There were significant negative correlations between BCVA (LogMAR) and VD in both SCP and DCP. Stepwise multiple linear regression analysis demonstrated that SCP-VD in the whole area and DCP-VD in the parafoveal area were the best predictive factors for BCVA in the NPDR and PDR groups. Conclusion: With progression of DR, the VD decreased and the FAZ area increased, and both parameters were correlated with poor visual acuity. OCTA is a non-invasive tool which can be used to detect diabetic macular ischemia and help in the prediction of visual prognosis.

show abstract

Section: Discussionsupporting

confidence: 93%

<p>Correlations Between Optical Coherence Tomography Angiography Parameters and the Visual Acuity in Patients with Diabetic Retinopathy</p>

Abdelshafy

2020

OPTH

View full text Add to dashboard Cite

show abstract

“…There exists strong evidence in the literature that hand-crafted features extracted from OCT and OCTA images are able to differentiate between grades of DR. [34][35][36] One study 37 that looked at combining handcrafted features from both the superficial and deep plexus resulted in an overall accuracy, sensitivity, and specificity of 94.3, 97.9, and 87.0, when classifying between controls and mild DR patients. This paper extracts parameters for the vessel density, blood vessel caliber, and width of the FAZ and used an SVM for the classifier.…”

Section: It Is Shown Inmentioning

confidence: 99%

Ensemble Deep Learning for Diabetic Retinopathy Detection Using Optical Coherence Tomography Angiography

Heisler

Karst

et al. 2020

Trans. Vis. Sci. Tech.

View full text Add to dashboard Cite

To evaluate the role of ensemble learning techniques with deep learning in classifying diabetic retinopathy (DR) in optical coherence tomography angiography (OCTA) images and their corresponding co-registered structural images. Methods: A total of 463 volumes from 380 eyes were acquired using the 3 × 3-mm OCTA protocol on the Zeiss Plex Elite system. Enface images of the superficial and deep capillary plexus were exported from both the optical coherence tomography and OCTA data. Component neural networks were constructed using single data-types and fine-tuned using VGG19, ResNet50, and DenseNet architectures pretrained on ImageNet weights. These networks were then ensembled using majority soft voting and stacking techniques. Results were compared with a classifier using manually engineered features. Class activation maps (CAMs) were created using the original CAM algorithm and Grad-CAM. Results: The networks trained with the VGG19 architecture outperformed the networks trained on deeper architectures. Ensemble networks constructed using the four finetuned VGG19 architectures achieved accuracies of 0.92 and 0.90 for the majority soft voting and stacking methods respectively. Both ensemble methods outperformed the highest single data-type network and the network trained on hand-crafted features. Grad-CAM was shown to more accurately highlight areas of disease. Conclusions: Ensemble learning increases the predictive accuracy of CNNs for classifying referable DR on OCTA datasets. Translational Relevance: Because the diagnostic accuracy of OCTA images is shown to be greater than the manually extracted features currently used in the literature, the proposed methods may be beneficial toward developing clinically valuable solutions for DR diagnoses.

show abstract

“…There is high interest to use results from quantitative OCTA parameters as endpoints in clinical studies [25][26][27]. For this purpose, OCTA metrics need to be both repeatable and reproducible.…”

Section: Quantification Of Octa Datamentioning

confidence: 99%

OCT Angiography (OCTA) in Retinal Diagnostics

Rocholz

Corvi

Weichsel

et al. 2019

High Resolution Imaging in Microscopy and Ophthalmology

View full text Add to dashboard Cite

Optical coherence tomography angiography and microvascular changes in diabetic retinopathy: a systematic review

Cited by 66 publications

References 35 publications

<p>Correlations Between Optical Coherence Tomography Angiography Parameters and the Visual Acuity in Patients with Diabetic Retinopathy</p>

<p>Correlations Between Optical Coherence Tomography Angiography Parameters and the Visual Acuity in Patients with Diabetic Retinopathy</p>

Ensemble Deep Learning for Diabetic Retinopathy Detection Using Optical Coherence Tomography Angiography

OCT Angiography (OCTA) in Retinal Diagnostics

Contact Info

Product

Resources

About