APPLICATION OF NEURAL NETWORKS FOR DIFFERENTIAL DIAGNOSIS OF PULMONARY PATHOLOGIES BASED ON X-RAY IMAGES
S.M. Borzov1, A.V. Karpov2, O.I. Potaturkin1, A.O. Hadziev2
1Institute of Automation and Electrometry, Siberian Branch, Russian Academy of Sciences, Novosibirsk, Russia
2Federal State Budgetary Institution "Novosibirsk Tuberculosis Research Institute", Ministry of Health of the Russian Federation, Novosibirsk, Russia
Keywords: digital image processing, classification, neural network technologies, intelligent systems, diagnostics of lung diseases
Abstract
The goal is to study the possibility of creating intelligent automated systems for differential diagnosis of pulmonary diseases based on the identification of pathological structures in X-ray images of thoracic cavity organs using neural network technologies. A brief analysis of modern diagnostic techniques is presented, and a description of the proposed algorithm for determining the type of lung tissue pathologies used in the visual analysis of X-ray images and based on the identification of the main radiological syndromes, as well as on the evaluation of the quantitative characteristics of differential X-ray diagnostics, is given. By the example of classification of radiographs of healthy and tuberculosis patients, the effectiveness of using neural network technologies in the computer diagnosis of lung diseases is demonstrated. The studies are carried out using a publicly available database of X-ray images of thoracic cavity organs containing 3,500 images of healthy people and the same number of sick people images.
|
