Agreement study between color and IR retinal images based on retinal vasculature morphological parameters

Comparing Common Retinal Vessel Caliber Measurement Software with an Automatic Deep Learning System

PURPOSE

To compare the Retina-based Microvascular Health Assessment System (RMHAS) with Integrative Vessel Analysis (IVAN) for retinal vessel caliber measurement.

METHODS

Eligible fundus photographs from the Lingtou Eye Cohort Study were obtained alongside their corresponding participant data. Vascular diameter was automatically measured using IVAN and RMHAS software, and intersoftware variations were assessed by intra-class correlation coefficients (ICC), and 95% confidence intervals (CIs). Scatterplots and Bland-Altman plots assessed the agreement between programs, and a Pearson's correlation test assessed the strength of associations between systemic variables and retinal calibers. An algorithm was proposed to convert measurements between software for interchangeability.

RESULTS

ICCs between IVAN and RMHAS were moderate for CRAE and AVR (ICC; 95%CI)(0.62; 0.60 to 0.63 and 0.42; 0.40 to 0.44 respectively) and excellent for CRVE (0.76; 0.75 to 0.77). When comparing retinal vascular calibre measurements between tools, mean differences (MD, 95% confidence intervals) in CRAE, CRVE, and AVR were 22.34 (-7.29 to 51.97 µm),-7.01 (-37.68 to 23.67 µm), and 0.12 (-0.02 to 0.26 µm), respectively. The correlation of systemic parameters with CRAE/CRVE was poor and the correlation of CRAE with age, sex, systolic blood pressure, and CRVE with age, sex, and serum glucose were significantly different between IVAN and RMHAS (p < 0.05).

CONCLUSIONS

CRAE and AVR correlated moderately between retinal measurement software systems while CRVE correlated well. Further studies confirming this agreeability and interchangeability in large-scale datasets are needed before softwares are deemed comparable in clinical practice.

A narrative review of retinal vascular parameters and the applications (Part I): Measuring methods

The retina is often used to evaluate the vascular health status of eyes and the whole body directly and noninvasively in vivo. Retinal vascular parameters included caliber, tortuosity and fractal dimension. These variables represent the density or geometric characteristics of the vascular network apart from reflecting structural changes in the retinal vessel system. Currently, these parameters are often used as indicators of retinal disease, cardiovascular and cerebrovascular disease. Advanced digital fundus photography apparatus and computer-assisted analysis techniques combined with artificial intelligence, make the quantitative calculation of these parameters easier, objective, and labor-saving.

The big warp: Registration of disparate retinal imaging modalities and an example overlay of ultrawide-field photos and en-face OCTA images

PURPOSE

To develop an algorithm and scripts to combine disparate multimodal imaging modalities and show its use by overlaying en-face optical coherence tomography angiography (OCTA) images and Optos ultra-widefield (UWF) retinal images using the Fiji (ImageJ) plugin BigWarp.

METHODS

Optos UWF images and Heidelberg en-face OCTA images were collected from various patients as part of their routine care. En-face OCTA images were generated and ten (10) images at varying retinal depths were exported. The Fiji plugin BigWarp was used to transform the Optos UWF image onto the en-face OCTA image using matching reference points in the retinal vasculature surrounding the macula. The images were then overlayed and stacked to create a series of ten combined Optos UWF and en-face OCTA images of increasing retinal depths. The first algorithm was modified to include two scripts that automatically aligned all the en-face OCTA images.

RESULTS

The Optos UWF image could easily be transformed to the en-face OCTA images using BigWarp with common vessel branch point landmarks in the vasculature. The resulting warped Optos image was then successfully superimposed onto the ten Optos UWF images. The scripts more easily allowed for automatic overlay of the images.

CONCLUSIONS

Optos UWF images can be successfully superimposed onto en-face OCTA images using freely available software that has been applied to ocular use. This synthesis of multimodal imaging may increase their potential diagnostic value. Script A is publicly available at https://doi.org/10.6084/m9.figshare.16879591.v1 and Script B is available at https://doi.org/10.6084/m9.figshare.17330048.

Ganglion cell layer analysis with deep learning in glaucoma diagnosis

OBJECTIVE

To determine and compare the diagnostic precision in glaucoma of two deep learning models using infrared images of the optic nerve, eye fundus, and the ganglion cell layer (GCL).

METHODS

We have selected a sample of normal and glaucoma patients. Three infrared images were registered with a spectral-domain optical coherence tomography (SD-OCT). The first corresponds to the confocal scan image of the fundus, the second is a cut-out of the first centered on the optic nerve, and the third was the SD-OCT image of the GCL. Our deep learning models are developed on the MatLab platform with the ResNet50 and VGG19 pre-trained neural networks.

RESULTS

498 eyes of 298 patients were collected. Of the 498 eyes, 312 are glaucoma and 186 are normal. In the test, the precision of the models was 96% (ResNet50) and 96% (VGG19) for the GCL images, 90% (ResNet50) and 90% (VGG19) for the optic nerve images and 82% (ResNet50) and 84% (VGG19) for the fundus images. The ROC area in the test was 0.96 (ResNet50) and 0.97 (VGG19) for the GCL images, 0.87 (ResNet50) and 0.88 (VGG19) for the optic nerve images, and 0.79 (ResNet50) and 0.81 (VGG19) for the fundus images.

CONCLUSIONS

Both deep learning models, applied to the GCL images, achieve high diagnostic precision, sensitivity and specificity in the diagnosis of glaucoma.

Diagnosis of chronic stage of hypertensive retinopathy based on spectral domain optical coherence tomography

Hypertensive retinopathy refers to the retinal vascular changes associated with systemic arterial hypertension. Hypertensive retinopathy can be divided into chronic and acute phases. A cross-sectional study was performed to explore a method of measurement in the diameters of retinal vessels for diagnosis of chronic hypertensive retinopathy based on spectral domain optical coherence tomography (SD-OCT). The central retinal artery diameter (CRAD), the central retinal vein diameter (CRVD), and the artery-to-vein ratio (AVR) were measured. A total of 119 subjects with 119 eyes were included in this study, in which 56 subjects with 56 eyes were included in hypertensive group and 63 subjects with 63 eyes were included in normotensive group. There were significant differences between the two groups in the CRAD (t = -2.14, P = .04) and the AVR (t = -2.59, P = .01). The cutoff point of 0.75 was determined by receiver operating characteristic (ROC) curve (area under the curve, AUC 0.786; 95% confidence interval, 95% CI 0.70-0.87). Multivariate logistic regression analysis showed the probability of AVR below to 0.75 was more in patients with high systolic blood pressure (odds ratio OR 4.39; P = .048), more in male (OR 4.15; P = .004) and more in smokers (OR 5.80; P = .01). Bland-Altman plots showed small mean bias between the measurements of the two technicians in the CRAD, the CRVD, and the AVR. In summary, application of SD-OCT is an accurate, reproducible, convenient method for measuring the diameters of retinal vessels. It is valuable for the diagnosis of chronic stage of hypertensive retinopathy.