Discordant vascular parameter measurements in diabetic and non-diabetic eyes detected by different optical coherence tomography angiography devices

Differential Capillary and Large Vessel Analysis Improves OCTA Classification of Diabetic Retinopathy

Purpose

This study aimed to investigate the impact of distinctive capillary-large vessel (CLV) analysis in optical coherence tomography angiography (OCTA) on the classification performance of diabetic retinopathy (DR).

Methods

This multicenter study analyzed 212 OCTA images from 146 patients, including 28 controls, 36 diabetic patients without DR (NoDR), 31 with mild non-proliferative DR (NPDR), 28 with moderate NPDR, and 23 with severe NPDR. Quantitative features were derived from the whole image as well as the parafovea and perifovea regions. A support vector machine classifier was employed for DR classification. The accuracy and area under the receiver operating characteristic curve were used to evaluate the classification performance, utilizing features derived from the whole image and specific regions, both before and after CLV analysis.

Results

Differential CLV analysis significantly improved OCTA classification of DR. In binary classifications, accuracy improved by 11.81%, rising from 77.45% to 89.26%, when utilizing whole image features. For multiclass classifications, accuracy increased by 7.55%, from 78.68% to 86.23%. Incorporating features from the whole image, parafovea, and perifovea further improved binary classification accuracy from 83.07% to 93.80%, and multiclass accuracy from 82.64% to 87.92%.

Conclusions

This study demonstrated that feature changes in capillaries are more sensitive during DR progression, and CLV analysis can significantly improve DR classification performance by extracting features that are specific to large vessels and capillaries in OCTA. Incorporating regional features further improves DR classification accuracy. Differential CLV analysis promises better disease screening, diagnosis, and treatment outcome assessment.

Optical coherence tomography angiography in diabetic retinopathy: A major review

Diabetic retinopathy (DR) is characterized by retinal vasculopathy and is a leading cause of visual impairment. Optical coherence tomography angiography (OCTA) is an innovative imaging technology that can detect various pathologies and quantifiable changes in retinal microvasculature. We briefly describe its functional principles and advantages over fluorescein angiography and perform a comprehensive review on its clinical applications in the screening or management of people with prediabetes, diabetes without clinical retinopathy (NDR), nonproliferative DR (NPDR), proliferative DR (PDR), and diabetic macular edema (DME). OCTA reveals early microvascular alterations in prediabetic and NDR eyes, which may coexist with sub-clinical neuroretinal dysfunction. Its applications in NPDR include measuring ischemia, detecting retinal neovascularization, and timing of early treatment through predicting the risk of retinopathy worsening or development of DME. In PDR, OCTA helps characterize the flow within neovascular complexes and evaluate their progression or regression in response to treatment. In eyes with DME, OCTA perfusion parameters may be of predictive value regarding the visual and anatomical gains associated with treatment. We further discussed the limitations of OCTA and the benefits of its incorporation into an updated DR severity scale.

Qualitative and quantitative comparison of two semi-manual retinal vascular density analyzing methods on optical coherence tomography angiography images of healthy individuals

The aim of this study was to evaluate qualitative and quantitative differences in vascular density analysis of an established and a novel alternative for post-processing on optical coherence tomography angiography (OCTA) images in healthy individuals. OCTA examinations of 38 subjects were performed. After extracting the images, two semi-manual post-processing techniques, the already established Mexican hat filtering (MHF) and an alternative, the Shanbhag thresholding (ST) were applied. We assessed Vessel Density (VD), Skeleton Density (SkD) and Vessel Diameter Index (VDI). We analyzed the results in order to establish similarities or potentially relevant differences. Regarding SkD and VD, MHF generally gave higher values than ST. Simultaneously, mean values were also predominantly higher by MHF; however, standard deviations (SD) were higher by ST (range [mean ± SD]: 0.054 ± 0.038 to 0.134 ± 0.01 and 0.134 ± 0.095 to 0.362 ± 0.028 vs 0.012 ± 0.014 to 0.087 ± 0.03 and 0.039 ± 0.047 to 0.4 ± 0.095 for SkD and VD with MHF vs SkD and VD with ST, respectively). Values of VDI were considerably higher with ST than with MHF, while standard deviation was still significantly higher with ST (range [mean ± SD]: 2.459 ± 0.144 to 2.71 ± 0.084 and 2.983 ± 0.929 to 5.19 ± 1.064 for VDI with MHF and ST, respectively). The noise level reduction of the two methods were almost identical (noise levels: 65.8% with MHT and 65.24% with ST). Using MHF, the vascular network gets more fragmented by an average of 40% compared to ST. Both methods allow the segmentation of the vascular network and the examination of vascular density parameters, but they produce largely inconsistent results. To determine if these inconsistent results are clinically meaningful, and which method is more suitable for clinical use, our results provide further evidence that detailed understanding of the image analysis method is essential for reliable decision making for patients with retinal pathology. For longitudinal monitoring, use of the same image processing method is recommended.

Addressing inter-device variations in optical coherence tomography angiography: will image-to-image translation systems help?

BACKGROUND

Optical coherence tomography angiography (OCTA) is an innovative technology providing visual and quantitative data on retinal microvasculature in a non-invasive manner.

MAIN BODY

Due to variations in the technical specifications of different OCTA devices, there are significant inter-device differences in OCTA data, which can limit their comparability and generalizability. These variations can also result in a domain shift problem that may interfere with applicability of machine learning models on data obtained from different OCTA machines. One possible approach to address this issue may be unsupervised deep image-to-image translation leveraging systems such as Cycle-Consistent Generative Adversarial Networks (Cycle-GANs) and Denoising Diffusion Probabilistic Models (DDPMs). Through training on unpaired images from different device domains, Cycle-GANs and DDPMs may enable cross-domain translation of images. They have been successfully applied in various medical imaging tasks, including segmentation, denoising, and cross-modality image-to-image translation. In this commentary, we briefly describe how Cycle-GANs and DDPMs operate, and review the recent experiments with these models on medical and ocular imaging data. We then discuss the benefits of applying such techniques for inter-device translation of OCTA data and the potential challenges ahead.

CONCLUSION

Retinal imaging technologies and deep learning-based domain adaptation techniques are rapidly evolving. We suggest exploring the potential of image-to-image translation methods in improving the comparability of OCTA data from different centers or devices. This may facilitate more efficient analysis of heterogeneous data and broader applicability of machine learning models trained on limited datasets in this field.

Clinical Observation of Macular Superficial Capillary Plexus and Ganglion Cell Complex in Patients with Parkinson's Disease

INTRODUCTION

We investigated macular superficial capillary plexus (SCP) density and the thicknesses of the ganglion cell complex (GCC) in patients with Parkinson's disease (PD) and correlated them. We also observed the correlations between SCP density and clinical parameters of PD patients. The retina might be a novel biomarker of PD and will be useful in the future for the early diagnosis of PD and detecting disease progression.

METHODS

Seventy-four participants (38 patients with PD and 36 healthy controls) were recruited at the Affiliated Hospital of Xuzhou Medical University between January 2022 and June 2022 in this study. The macular SCP densities was measured by optical coherence tomography angiography (OCTA), and the GCC thickness was measured by optical coherence tomography (OCT). The parameters were compared between PD patients and healthy controls. The correlation between SCP and clinical parameters was tested.

RESULTS

Compared with the control group, PD patients showed reduced SCP densities in all areas of the macular region (parafovea-temporal: t = 3.053, p = 0.003; parafovea-superior: t = 3.680, p = 0.001; parafovea-nasal: t = 4.643, p < 0.001; parafovea-inferior: t = 2.254, p = 0.027; perifovea-temporal: t = 3.798, p < 0.001; perifovea-superior: t = 3.014, p = 0.004; perifovea-nasal: t = 2.948, p = 0.004; perifovea-inferior: t = 3.337, p = 0.021). The average GCC thickness in the PD patients was significantly reduced (t = 2.365, p = 0.021). There were positive correlations between the average GCC thickness and the SCP densities in most of the areas of the macular regions in PD patients (parafovea-temporal: r = 0.325, p = 0.005; parafovea-superior: r = 0.295, p = 0.011; parafovea-nasal: r = 0.335, p = 0.003; perifovea-superior: r = 0.362, p = 0.002; perifovea-nasal: r = 0.290, p = 0.012; perifovea-inferior: r = 0.333, p = 0.004). We found significant correlations between SCP densities and Hoehn and Yahr (H and Y) scales, UPDRS III scores, and MMSE scores. No significant correlation was observed between SCP density and PD disease duration (all p > 0.05).

CONCLUSIONS

We demonstrated that the macular SCP density was decreased, and the average GCC thickness was reduced in PD patients. The correlation between SCP density damage and GCC thinning also suggested that the retinal microvascular damage may be associated with retinal structural degeneration in PD patients. OCTA and OCT may be considered objective biomarkers for detecting microvascular impairment and neuronal damage in the early stages of PD in the future.

Differential effects of high-intensity interval training (HIIT) on choriocapillaris perfusion in healthy adults and patients with type 1 diabetes mellitus (T1DM)

PURPOSE

To investigate the effects of a four-week high-intensity interval training (HIIT) on choriocapillaris (CC) perfusion in young healthy adults and type 1 diabetes mellitus (T1DM) patients.

METHODS

Data of two HIIT studies with baseline to follow-up comparison were retrospectively analysed. Twenty healthy participants and twenty T1DM patients without clinical signs of diabetic retinopathy were included. All participants had performed a four-week all-out HIIT protocol with a total of 8 training sessions. Changes in physical fitness were assessed using power output at the individual aerobic lactate threshold (IANT). Optical coherence tomography angiography (OCTA) imaging was performed at baseline and follow-up. CC images were analysed for number, size and total area of flow deficits (FD), mean signal intensity, signal intensity standard deviation and kurtosis of signal intensity distribution.

RESULTS

At baseline, CC OCTA revealed a lower and more heterogeneous intensity signal in T1DM eyes (mean intensity signal and standard deviation of signal intensity, p < 0.001). Percent of CC FD area was greater in T1DM eyes (p < 0.001). While T1DM patients showed greater improvement of exercise capacity at IANT than healthy controls (group×time p = 0.0403), CC FD area and standard deviation of intensity increased in healthy controls but not in T1DM patients (group×time p ≤ 0.029). Moreover, linear regression slopes of FD region distribution differed significantly at baseline and follow-up (p = 0.0002) in healthy individuals but not in T1DM patients.

CONCLUSIONS

Effects of regular physical exercise performed as HIIT on CC perfusion were only seen in healthy participants, not in T1DM patients suggesting impaired CC adaptation in T1DM.