Algorithm of segmentation of OCT macular images to analyze the results in patients with age-related macular degeneration

Ibragimova RR1, Gilmanov II2, Lopukhova EA2, Lakman IA1,2, Bilyalov AR1, Mukhamadeev TR1,3, Kutluyarov RV2, Idrisova GM1,3
About authors

1 Bashkir State Medical University, Ufa, Russia

2 Ufa State Aviation Technical University, Ufa, Russia

3 Optimedservice, Ufa, Russia

Correspondence should be addressed: Rada R. Ibragimova
Lenina, d. 3, Ufa, 450008, Russia; ur.xednay@6102adar.avomigarbi

About paper

Financing: the study was partially conducted as part of the State Assignment of the Ministry of Education and Science of the Russian Federation for the Ufa State Aviation Technical University (code of scientific assignment #FEUE-2021-0013, agreement № 075-03-2021-014) at the scientific research laboratory named ‘Sensor systems based on appliances of integrated photonics’ (sections ‘Materials and methods’, ‘Study results’, ‘Discussion of results’) and as part of the project backed by subsidies in the area of science taken from the budget of the Republic of Bashkortostan to ensure state support of scientific research conducted under the guidance of the leading scientists (НОЦ-РМГ-2021, agreement with the Ufa State Aviation Technical University) (Introduction section).

Author contribution: Ibragimova RR — review of literature, data acquisition and analysis, writing an article; Gilmanov II — development of software, searching a database, testing the existing code components; Lopukhova EA — development of software, writing an article, data acquisition and analysis; Lakman IA, Mukhamadeev TR, Kutluyarov RV — study concept and design, scientific editing; Bilyalov AR — scientific editing; Idrisova GM — data analysis, scientific editing.

Compliance with ethical standards: the study was performed in accordance with the principles of Declaration of Helsinki; all patients signed voluntary informed consent to OCT.

Received: 2022-11-03 Accepted: 2022-12-03 Published online: 2022-12-27

Age-related macular degeneration (AMD) is one of the main causes of loss of sight and hypovision in people over working age. Results of optical coherence tomography (OCT) are essential for diagnostics of the disease. Developing the recommendation system to analyze OCT images will reduce the time to process visual data and decrease the probability of errors while working as a doctor. The purpose of the study was to develop an algorithm of segmentation to analyze the results of macular OCT in patients with AMD. It allows to provide a correct prediction of an AMD stage based on the form of discovered pathologies. A program has been developed in the Python programming language using the Pytorch and TensorFlow libraries. Its quality was estimated using OCT macular images of 51 patients with early, intermediate, late AMD. A segmentation algorithm of OCT images was developed based on convolutional neural network. UNet network was selected as architecture of high-accuracy neural net. The neural net is trained on macular OCT images of 125 patients (197 eyes). The author algorithm displayed 98.1% of properly segmented areas on OCT images, which are the most essential for diagnostics and determination of an AMD stage. Weighted sensitivity and specificity of AMD stage classifier amounted to 83.8% and 84.9% respectively. The developed algorithm is promising as a recommendation system that implements the AMD classification based on data that promote taking decisions regarding the treatment strategy.

Keywords: artificial intelligence, optical coherent tomography, neural network, age-related macular degeneration, machine learning algorithm