Discrimination of Diabetic Retinopathy From Optical Coherence Tomography Angiography Images Using Machine Learning Methods

• Published in: IEEE access Vol. 9; pp. 51689 - 51694
• Main Authors: Liu, Zhiping, Wang, Chen, Cai, Xiaodong, Jiang, Hong, Wang, Jianhua
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Algorithms; Angiography; Datasets; Diabetes; Diabetic retinopathy; Diagnostic systems; Discrete Wavelet Transform; Discrete wavelet transforms; Eye (anatomy); Feature extraction; Image classification; logistic regression; logistic regression regularized with the elastic net penalty; Logistics; Machine learning; Medical imaging; Optical Coherence Tomography; Retina; Retinopathy; Sensitivity; support vector machine; Support vector machines; Wavelet transforms
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2021.3056430

The goal was to discriminate between diabetic retinopathy (DR) and healthy controls (HC) by evaluating Optical coherence tomography angiography (OCTA) images from <inline-formula> <tex-math notation="LaTeX">3\times 3 </tex-math></inline-formula> mm scans with the assistance of different machine learning models. The OCTA angiography dataset of superficial vascular plexus (SVP), deep vascular plexus (DVP), and retinal vascular network (RVN) were acquired from 19 DR (38 eyes) patients and 25 HC (44 eyes). A discrete wavelet transform was applied to extract texture features from each image. Four machine learning models, including logistic regression (LR), logistic regression regularized with the elastic net penalty (LR-EN), support vector machine (SVM), and the gradient boosting tree named XGBoost, were used to classify wavelet features between groups. The area under the receiver operating characteristics curve (AUC), sensitivity, specificity, and diagnostic accuracy of the classifiers were obtained. The OCTA image dataset included 114 and 132 images from DR and HC subjects, respectively. LR-EN and LR using all three images, SVP, DVP, and RVN, provided the highest sensitivity of 0.84 and specificity of 0.80, the best diagnostic accuracy of 0.82, and an AUC of 0.83 and 0.84, respectively, which were slightly lower than that of LR using one image SVP (0.85) or two images DVP and SVP (0.85). The LR-EN and LR classification algorithms had the high sensitivity, specificity, and diagnostic accuracy in identifying DR, which may be promising in facilitating the early diagnosis of DR.