Vascular changes precede tomographic changes in diabetic eyes without retinopathy and improve artificial intelligence diagnostics

Govindaswamy, Nivedhitha; Ratra, Dhanashree; Dalan, Daleena; Doralli, Subashchandra; Tirumalai, Anirudha A.; Nagarajan, Rajesh; Mochi, Thirumalesh B; Shetty, Nitin; Roy, Abhijit Sinha

doi:10.1002/jbio.202000107

Cited by 8 publications

(10 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Optical coherence tomography angiography (OCTA) has rapidly proved itself to be a reliable, fast and noninvasive method for screening of changes in the retinal vasculature. [ 4 5 ] Additionally, it can quantify the changes making it easy to compare between patients.…”

mentioning

confidence: 99%

Quantitative analysis of retinal microvascular changes in prediabetic and diabetic patients

Ratra

Dalan²,

Prakash³

et al. 2021

Indian J Ophthalmol

Self Cite

View full text Add to dashboard Cite

Purpose: To evaluate and correlate retinal microvascular changes in prediabetic and diabetic patients with functional and systemic parameters. Methods: Optical coherence tomography angiography (OCTA) was performed on all subjects after medical evaluation and laboratory investigations for blood sugar, glycosylated hemoglobin, and others. Automated quantification of vascular indices of the superficial plexus were analyzed. Results: Hundred and eleven persons (222 eyes) were grouped into prediabetic (PDM) (60 eyes), diabetic without retinopathy (NDR) (56 eyes), diabetic with retinopathy (DR) (66 eyes), and healthy controls (CTR) (40 eyes). The superficial retinal capillary plexus showed no significant changes in the prediabetic and NDR groups; however, central foveal thickness (CFT) was significantly reduced in PDM ( P = 0.04). The circularity of the foveal avascular zone (FAZ) ( P = 0.03) and the vessel density (VD) ( P = 0.01) showed significant reduction from PDM to NDR. All vascular parameters were significantly reduced in DR and correlated with disease severity. The CFT correlated significantly with FAZ area. The VD and perfusion density were seen to correlate significantly with HbA1c and contrast sensitivity. The visual acuity was significantly correlated with the FAZ. Logistic regression revealed VD [OR 20.42 (7.9–53)] and FAZ perimeter [OR 9.8 (4.2–23.2)] as the strongest predictors of DR. Conclusion: The changes in OCTA can help predict onset of DR. FAZ changes are seen in early stages and are correlated well with systemic parameters, making it an easy target to monitor and screen for severity of DR. Significant reduction in the CFT in PDM suggests that neuronal damage precedes vascular changes.

show abstract

mentioning

confidence: 99%

Quantitative analysis of retinal microvascular changes in prediabetic and diabetic patients

Ratra

Dalan²,

Prakash³

et al. 2021

Indian J Ophthalmol

Self Cite

View full text Add to dashboard Cite

show abstract

“…Thus, some authors use artificial intelligence (AI), including deep learning (DL), to evaluate OCTA images; this is a machine learning technique which learns representations of data based on computational models with more efficient and precise results, and has already been applied to other ocular conditions [ 138 ]. In fact, the combination of AI models using OCT, OCTA and multimodal images appears to be more precise to detect changes in diabetic patients than the OCT AI model [ 139 ].…”

Section: Resultsmentioning

confidence: 99%

“…Le et al’s DL classifier differentiated among healthy, no DR, and DR eyes with 83.76% sensitivity, 90.82% specificity, and an 87.27% accuracy [ 146 ] and Heisler et al achieved an accuracy of between 90% and 92% [ 147 ]. Other DL techniques have shown an AUC of 0.91 to differentiate diabetic patients without DR from those with DR and an AUC of 0.8 to diagnose DR from non-diabetic patients [ 139 ]. This AUC was increased up to 92.33% in the DL model of Alam et al to distinguish controls from DR [ 148 ].…”

Section: Resultsmentioning

confidence: 99%

Optical Coherence Tomography Angiography in Diabetic Patients: A Systematic Review

et al. 2021

View full text Add to dashboard Cite

Background: Diabetic retinopathy (DR) is the leading cause of legal blindness in the working population in developed countries. Optical coherence tomography (OCT) angiography (OCTA) has risen as an essential tool in the diagnosis and control of diabetic patients, with and without DR, allowing visualisation of the retinal and choroidal microvasculature, their qualitative and quantitative changes, the progression of vascular disease, quantification of ischaemic areas, and the detection of preclinical changes. The aim of this article is to analyse the current applications of OCTA and provide an updated overview of them in the evaluation of DR. Methods: A systematic literature search was performed in PubMed and Embase, including the keywords “OCTA” OR “OCT angiography” OR “optical coherence tomography angiography” AND “diabetes” OR “diabetes mellitus” OR “diabetic retinopathy” OR “diabetic maculopathy” OR “diabetic macular oedema” OR “diabetic macular ischaemia”. Of the 1456 studies initially identified, 107 studies were screened after duplication, and those articles that did not meet the selection criteria were removed. Finally, after looking for missing data, we included 135 studies in this review. Results: We present the common and distinctive findings in the analysed papers after the literature search including the diagnostic use of OCTA in diabetes mellitus (DM) patients. We describe previous findings in retinal vascularization, including microaneurysms, foveal avascular zone (FAZ) changes in both size and morphology, changes in vascular perfusion, the appearance of retinal microvascular abnormalities or new vessels, and diabetic macular oedema (DME) and the use of deep learning technology applied to this disease. Conclusion: OCTA findings enable the diagnosis and follow-up of DM patients, including those with no detectable lesions with other devices. The evaluation of retinal and choroidal plexuses using OCTA is a fundamental tool for the diagnosis and prognosis of DR.

show abstract

“…Optical coherence tomography (OCT) has been widely used for classifying retina diseases, such as age‐related macular degeneration (AMD) and diabetic macular edema (DME), which may cause vision loss without timely and effective treatment in early stage [1, 2]. Exiting manual identification of retinopathies from OCT images is unrealistic, considering the huge number of OCT images generated daily and the requirement of highly experienced ophthalmologists, especially for developing countries.…”

Section: Introductionmentioning

confidence: 99%

Cross‐domain retinopathy classification with optical coherence tomography images via a novel deep domain adaptation method

Luo

Hou

et al. 2021

Journal of Biophotonics

View full text Add to dashboard Cite

Deep learning based retinopathy classification with optical coherence tomography (OCT) images has recently attracted great attention. However, existing deep learning methods fail to work well when training and testing datasets are different due to the general issue of domain shift between datasets caused by different collection devices, subjects, imaging parameters, etc. To address this practical and challenging issue, we propose a novel deep domain adaptation (DDA) method to train a model on a labeled dataset and adapt it to an unlabelled dataset (collected under different conditions). It consists of two modules for domain alignment, that is, adversarial learning and entropy minimization. We conduct extensive experiments on three public datasets to evaluate the performance of the proposed method. The results indicate that there are large domain shifts between datasets, resulting a poor performance for conventional deep learning methods. The proposed DDA method can significantly outperform existing methods for retinopathy classification with OCT images. It achieves retinopathy classification accuracies of 0.915, 0.959 and 0.990 under three cross‐domain (cross‐dataset) scenarios. Moreover, it obtains a comparable performance with human experts on a dataset where no labeled data in this dataset have been used to train the proposed DDA method. We have also visualized the learnt features by using the t‐distributed stochastic neighbor embedding (t‐SNE) technique. The results demonstrate that the proposed method can learn discriminative features for retinopathy classification.

show abstract

Vascular changes precede tomographic changes in diabetic eyes without retinopathy and improve artificial intelligence diagnostics

Cited by 8 publications

References 36 publications

Quantitative analysis of retinal microvascular changes in prediabetic and diabetic patients

Quantitative analysis of retinal microvascular changes in prediabetic and diabetic patients

Optical Coherence Tomography Angiography in Diabetic Patients: A Systematic Review

Cross‐domain retinopathy classification with optical coherence tomography images via a novel deep domain adaptation method

Contact Info

Product

Resources

About