Research and Development of the Method for Automating the Diagnostic Analysis of Human Fundus Images Produced by Optical Coherent Tomography Angiography
- 1 September 2022
- journal article
- research article
- Published by Pleiades Publishing Ltd in Pattern Recognition and Image Analysis
- Vol. 32 (3) , 533-544
Abstract
This article presents the results of the joint work of specialists in the field of image analysis and ophthalmologists on the task of analyzing images obtained by the method of optical coherence tomography angiography. A descriptive algorithmic scheme for analyzing images obtained using optical coherence tomography angiography is built to automate the detection of pathological changes in the morphometric characteristics of the fundus. The algorithmic scheme is based on the methods of image processing, analysis, and recognition. The previously developed feature space is supplemented and modified, based on which it is possible to identify pathological changes in the structure of the choroid plexuses of the human retina. It was possible to improve the accuracy of classifying images of healthy and pathological eyes, as well as significantly increasing the accuracy of classification of borderline cases. Software is created that makes it possible to accurately carry out differential diagnostics of the normal state of vessels from the pathological one in the offline mode, which increases its diagnostic value. It is planned to achieve higher classification accuracy results for all three cases.Keywords
This publication has 26 references indexed in Scilit:
- Quantitative assessment of the retinal microvasculature using optical coherence tomography angiographyJournal of Biomedical Optics, 2016
- Volume-Rendered Optical Coherence Tomography of Diabetic Retinopathy Pilot StudyAmerican Journal of Ophthalmology, 2015
- On basic problems of image recognition in neurosciences and heuristic methods for their solutionPattern Recognition and Image Analysis, 2015
- Diabetic retinopathyThe Lancet, 2010
- Retinal vessel extraction by matched filter with first-order derivative of GaussianComputers in Biology and Medicine, 2010
- Elements of the information technology of cytological specimen analysis: Taxonomy and factor analysisPattern Recognition and Image Analysis, 2006
- A model based method for retinal blood vessel detectionComputers in Biology and Medicine, 2004
- The internist's role in managing diabetic retinopathy: screening for early detection.Cleveland Clinic Journal of Medicine, 2004
- Adaptive document image binarizationPattern Recognition, 2000
- A Threshold Selection Method from Gray-Level HistogramsIEEE Transactions on Systems, Man, and Cybernetics, 1979