Early diabetic retinopathy diagnosis based on local retinal blood vessel analysis in optical coherence tomography angiography (OCTA) images

Eladawi, Nabila; Elmogy, Mohammed; Khalifa, Fahmi; Ghazal, Mohammed; Ghazi, Nicola G.; Aboelfetouh, Ahmed; Riad, A. M.; Sandhu, Harpal S.; Schaal, Shlomit; El-Baz, Ayman

doi:10.1002/mp.13142

Cited by 41 publications

(20 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We plan to use greater levels of information from these OCT-As such as by using deep or intermediate capillary plexi. Previous articles 8 suggest that level of information can be improved by accessing these deep capillary plexi, and we also plan to use new imaging scanners presenting larger areas for analysis. Additional patient metadata such as recent specific symptoms and details of race and sex might further increase the power of the classification algorithms and provide more assurance on external validity.…”

Section: Discussionmentioning

confidence: 99%

“…They found that superficial plexus vessel density had the highest area under the receiver operating characteristic (ROC) curve (area under curve [AUC]) of 0.893, compared with features such as foveal avascular zone (FAZ) area (0.472) and vessel density in the deep plexus (0.703). More recent studies by Eladawi et al 8 have progressed to demonstrate the ability to distinguish normal patients from those who were diabetic with retinopathy (DR) by combining OCT-A features using a machine learning algorithm.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Differentiation of Diabetic Status Using Statistical and Machine Learning Techniques on Optical Coherence Tomography Angiography Images

Aslam

Hoyle

Puri

et al. 2020

Trans. Vis. Sci. Tech.

View full text Add to dashboard Cite

Purpose To investigate the potential of statistical and machine learning approaches to determine the diabetic status of patients from optical coherence tomography angiography (OCT-A) images. Methods This was a retrospective cross-sectional observational study based at Manchester Royal Eye Hospital, United Kingdom. OCT-A scans were sequentially selected from one eye of each of 182 patients who were either not diabetic, diabetic without retinopathy, or diabetic with retinopathy requiring hospital follow-up. Eligible images were analyzed by expert purpose-built automated algorithms to calculate clinically relevant outcome measures. These were used in turn as inputs to machine learning and statistical procedures to derive algorithms to perform clinically relevant classifications of patient images into the clinical groups. Receiver operating characteristic curves for the classifiers were evaluated and predictive accuracy assessed using area under curve (AUC). Results For distinguishing diabetic patients from those without diabetes, the Random Forest classifier provided the highest AUC (0.8). For distinguishing diabetic patients with significant retinopathy from those with no retinopathy, the highest AUC was represented by logistic regression (0.91). Conclusions The study demonstrates the potential of novel techniques using automated analysis of OCT-A scans to diagnose patients with diabetes, or when diabetic status is known, to automatically determine those that require hospital input. Translational Relevance This work advances the concept of a rapid and noninvasive clinical screening tool using OCT-A to determine a patient's diabetic status.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Differentiation of Diabetic Status Using Statistical and Machine Learning Techniques on Optical Coherence Tomography Angiography Images

Aslam

Hoyle

Puri

et al. 2020

Trans. Vis. Sci. Tech.

View full text Add to dashboard Cite

show abstract

“…Most studies use their own quantification algorithm, where the vessel detections vary from using global thresholding [11], binarization and skeletonization [12], to more complex filtering and thresholding approaches [3,14]. More advanced methods include local fractal dimension [9], and a probabilistic model utilizing the 3D spatial information from both the superficial and the deep layer [8]. Some OCTA devices provide proprietary software for extracting vessel densities, e.g.…”

Section: Related Workmentioning

confidence: 99%

“…Larger vessels are defined as vessels of twice (or more) the radius of the capillaries. Similarly to the study by Eladawi et al [8], manual annotations are produced and used as ground truth (GT). Two images acquired as described in section 3.1 were annotated manually by AMEE.…”

Section: Dictionary-based Segmentationmentioning

confidence: 99%

Automated Quantification of Retinal Microvasculature from OCT Angiography Using Dictionary-Based Vessel Segmentation

Engberg

Erichsen

Sander

et al. 2020

Communications in Computer and Information Science

View full text Add to dashboard Cite

Investigations in how the retinal microvasculature correlates with ophthalmological conditions necessitate a method for measuring the microvasculature. Optical coherence tomography angiography (OCTA) depicts the superficial and the deep layer of the retina, but quantification of the microvascular network is still needed. Here, we propose an automatic quantitative analysis of the retinal microvasculature. We use a dictionary-based segmentation to detect larger vessels and capillaries in the retina and we extract features such as densities and vessel radius. The method is validated on repeated OCTA scans from healthy subjects, and we observe high intraclass correlation coe cients and high agreement in a Bland-Altman analysis. The quantification method is also applied to pre-and postoperative scans of cataract patients. Here, we observe a higher variation between the measurements, which can be explained by the greater variation in scan quality. Statistical tests of both the healthy subjects and cataract patients show that our method is able to di↵erentiate subjects based on the extracted microvascular features.

show abstract

“…To date, this complementary technique has been used in the evaluation of common and also infrequent ophthalmologic diseases such as diabetic retinopathy [25][26][27][28][29][30][31][32][33][34][35]; congenital and acquired retinopathies [36]; preretinal, intraretinal, and subretinal neovascularization [37][38][39][40][41][42][43][44][45][46][47]; retinal venous occlusions [48][49][50][51]; retinal artery occlusions [52]; macular teleangiectasia [53][54][55][56][57]; senile macular degenerations [58][59][60]; glaucoma [60][61][62][63][64][65][66][67]; uveitis [68][69][70][71]; and optic neuropathies…”

Section: Introductionmentioning

confidence: 99%

OCT Angiography: A Technique for the Assessment of Retinal and Optic Nerve Diseases in the Pediatric Population

et al. 2018

View full text Add to dashboard Cite

Optical coherence tomography angiography (OCT-A) is a novel, rapidly evolving, non-invasive imaging technique that allows images of the retinal vasculature to be obtained in a few seconds. Blood vessels of different retinal vascular plexuses and the foveal avascular zone (FAZ) can be examined without the administration of any contrast or dye. Due to these characteristics, OCT-A could be an excellent complementary test to study retinal vascularization in children. Until now, most of the studies with OCT-A have been conducted in adults and only a few have been carried out in children. In this review, we describe the principles and advantages of OCT-A over traditional imaging methods and provide a summary of the OCT-A findings in retinopathy of prematurity and other retinal and optic disc pathologies in children. In view of the promising results from studies, the advantages of a relatively rapid and non-invasive method to assess the retinal vasculature makes OCT-A a tool of which applications in the field of pediatric ophthalmology will be expanded in the near future for patient diagnosis and follow-up in every day clinical practice.

show abstract

Early diabetic retinopathy diagnosis based on local retinal blood vessel analysis in optical coherence tomography angiography (OCTA) images

Abstract: We developed a new DR-CAD system that is capable of diagnosing DR in its early stage. The proposed system is based on extracting three different features from the segmented OCTA images, which reflect the changes in the retinal vasculature network.

Cited by 41 publications

References 51 publications

Differentiation of Diabetic Status Using Statistical and Machine Learning Techniques on Optical Coherence Tomography Angiography Images

Differentiation of Diabetic Status Using Statistical and Machine Learning Techniques on Optical Coherence Tomography Angiography Images

Automated Quantification of Retinal Microvasculature from OCT Angiography Using Dictionary-Based Vessel Segmentation

OCT Angiography: A Technique for the Assessment of Retinal and Optic Nerve Diseases in the Pediatric Population

Contact Info

Product

Resources

About