ABSTRACT
Purpose: To evaluate the diagnostic accuracy of machine learning (ML) techniques applied to radiomic features extracted from OCT and OCT angiography (OCTA) images for diabetes mellitus (DM), diabetic retinopathy (DR), and referable DR (R-DR) diagnosis. Design: Cross-sectional analysis of a retinal image dataset from a previous prospective OCTA study (ClinicalTrials.govNCT03422965). Participants: Patients with type 1 DM and controls included in the progenitor study. Methods: Radiomic features were extracted from fundus retinographies, OCT, and OCTA images in each study eye. Logistic regression, linear discriminant analysis, support vector classifier (SVC)-linear, SVC-radial basis function, and random forest models were created to evaluate their diagnostic accuracy for DM, DR, and R-DR diagnosis in all image types. Main Outcome Measures: Area under the receiver operating characteristic curve (AUC) mean and standard deviation for each ML model and each individual and combined image types. Results: A dataset of 726 eyes (439 individuals) were included. For DM diagnosis, the greatest AUC was observed for OCT (0.82, 0.03). For DR detection, the greatest AUC was observed for OCTA (0.77, 0.03), especially in the 3 × 3 mm superficial capillary plexus OCTA scan (0.76, 0.04). For R-DR diagnosis, the greatest AUC was observed for OCTA (0.87, 0.12) and the deep capillary plexus OCTA scan (0.86, 0.08). The addition of clinical variables (age, sex, etc.) improved most models AUC for DM, DR and R-DR diagnosis. The performance of the models was similar in unilateral and bilateral eyes image datasets. Conclusions: Radiomics extracted from OCT and OCTA images allow identification of patients with DM, DR, and R-DR using standard ML classifiers. OCT was the best test for DM diagnosis, OCTA for DR and R-DR diagnosis and the addition of clinical variables improved most models. This pioneer study demonstrates that radiomics-based ML techniques applied to OCT and OCTA images may be an option for DR screening in patients with type 1 DM. Financial Disclosures: Proprietary or commercial disclosure may be found after the references.
ABSTRACT
The purpose of this study was to evaluate specifically the relationship between glycated haemoglobin (HbA1c) levels and retinal optical coherence tomography (OCT) and OCT angiography (OCTA) parameters in type 1 Diabetes Mellitus (DM). A total of 478 type 1 DM patients and 115 controls were included in a prospective OCTA trial (ClinicalTrials.gov NCT03422965). Subgroup analysis was performed for controls, no diabetic retinopathy (DM-no DR) and DR patients (DM-DR), and HbA1c levels. OCT and OCTA measurements were compared with HbA1c levels (current and previous 5 years). DM-no DR patients with HbA1c levels >7.5% showed lower VD than DM-DR and controls (20.16 vs. 20.22 vs. 20.71, p < 0.05), and showed a significant correlation between HbA1c levels and FAZc (p = 0.04), after adjusting for age, gender, signal strength index, axial length, and DM disease duration. DM-DR patients with HbA1c > 7.5% presented greater CRT than DM-no DR and controls (270.8 vs. 260 vs. 251.1, p < 0.05) and showed a significant correlation between HbA1c and CRT (p = 0.03). In conclusion, greater levels of HbA1c are associated with OCTA changes in DM-no DR patients, and with structural OCT changes in DM-DR patients. The combination of OCTA and OCT measurements and HbA1c levels may be helpful to identify patients at risk of progression to greater stages of the diabetic microvascular disease.
ABSTRACT
The purpose of this study is to investigate potential associations between optical coherence tomography angiography (OCTA) parameters and diabetic kidney disease (DKD) categories in type 1 diabetes mellitus (T1DM) patients and controls. A complete ocular and systemic examination, including OCTA imaging tests and bloods, was performed. OCTA parameters included vessel density (VD), perfusion density (PD), foveal avascular zone area (FAZa), perimeter (FAZp) and circularity (FAZc) in the superficial vascular plexus, and DKD categories were defined according to glomerular filtration rate (GFR), albumin-creatinine ratio (ACR) and KDIGO prognosis risk classifications. A total of 425 individuals (1 eye/1 patient) were included. Reduced VD and FAZc were associated with greater categories of GFR (p = 0.002, p = 0.04), ACR (p = 0.003, p = 0.005) and KDIGO risk prognosis classifications (p = 0.002, p = 0.005). FAZc was significantly reduced in greater KDIGO prognosis risk categories (low risk vs. moderate risk, 0.65 ± 0.09 vs. 0.60 ± 0.07, p < 0.05). VD and FAZc presented the best diagnostic performance in ROCs. In conclusion, OCTA parameters, such as VD and FAZc, are able to detect different GFR, ACR, and KDIGO categories in T1DM patients and controls in a non-invasive, objective quantitative way. FAZc is able to discriminate within T1DM patients those with greater DKD categories and greater risk of DKD progression.
ABSTRACT
Purpose: The purpose of this study was to evaluate specifically in type 1 diabetes mellitus (DM) individuals the relationship between perifoveal superficial capillary plexus (SCP) parameters assessed by optical coherence tomography angiography (OCTA) and diabetic retinopathy (DR) grade. Methods: Cross-sectional analysis of a large scale prospective OCTA trial cohort (ClinicalTrials.gov NCT03422965). A total of 1186 eyes (593 individuals), 956 type 1 DM eyes (478 patients), and 230 control eyes (115 healthy volunteers) were included in this study. DR stage was graded according to the International Classification. OCTA imaging was performed with a commercially available device (Cirrus HD-OCT). Vessel density (VD), perfusion density (PD), and foveal avascular zone (FAZ) area, perimeter and circularity measurements were quantified in the SCP and receiver operating characteristic (ROC) curves were constructed for each OCTA parameter. Results: VD and PD (in both 3 × 3 and 6 × 6 mm captures) were inversely associated with DR stage (P < 0.001 in all cases) in a multiple regression analysis after controlling by age, gender, signal strength index, axial length, and DM duration. Greater FAZ area and perimeter and conversely lower circularity measurements were observed as DR severity increased in both scanning protocols (P < 0.05 in all cases). Conclusions: In type 1 DM individuals, OCTA provides an objective, continuous, and reliable method for accurate quantification of VD, PD, and FAZ parameters in the SCP, which ultimately correlate with DR stages. Translational Relevance: Objective OCTA measurements of the retinal microvasculature could substitute the clinical DR classification in patients with type 1 DM, identify patients at risk of DR progression, and inform treatment decisions to modify the evolution of the disease.
Subject(s)
Diabetes Mellitus, Type 1 , Diabetic Retinopathy , Cross-Sectional Studies , Diabetes Mellitus, Type 1/complications , Diabetic Retinopathy/diagnosis , Fluorescein Angiography , Humans , Prospective Studies , Retinal Vessels/diagnostic imaging , Tomography, Optical CoherenceABSTRACT
BACKGROUND: Diabetic retinopathy (DR) is the leading cause of blindness in type 1 Diabetes Mellitus (DM) patients, as a consequence of impaired blood flow in the retina. Optical coherence tomography angiography (OCTA) is a newly developed, non-invasive, retinal imaging technique that permits adequate delineation of the perifoveal vascular network. It allows the detection of paramacular areas of capillary non perfusion and/or enlargement of the foveal avascular zone (FAZ), representing an excellent tool for assessment of DR. The relationship of these microvascular changes with systemic factors such as metabolic control or duration of the disease still needs to be elucidated. METHODS: Prospective, consecutive, large-scale OCTA study. A complete ocular examination including a comprehensive series of OCTA images of different scan sizes captured with 2 OCT devices (Cirrus HD-OCT, Carl Zeiss Meditec, Dublin, CA, USA, and Triton Deep Range Imaging OCT, Topcon Corp, Topcon, Japan) will be obtained as part of the yearly routine follow up visits in type 1 DM patients seen in the Diabetes Unit of the Endocrinology department which give written informed consent to participate in the project. The aim of this study is to investigate the relationship between OCTA-derived parameters and systemic factors, as metabolic control (Hb1Ac, lipid profile, cholesterol, etc), and other relevant clinical factors as demographics or duration of the disease. DISCUSSION: This study is directed to investigate the relationship between the status of the perifoveal vascular network and systemic markers of the disease, and in particular to study whether these changes reflect those occurring elsewhere in the body affected by diabetic microvascular disease, as the kidneys or the brain. If these relationships were demonstrated, early detection of these microvascular changes by OCTA could lead to modifications in the pharmacological management of type 1 diabetic patients, as a way to reduce the risk of future complications in both the eye and other organs. TRIAL REGISTRATION: ClinicalTrials.gov, trial number NCT03422965.
