Штучна інтелектуальна підтримка для виявлення захворювань на зображеннях з бездротової капсульної ендоскопії товстої кишки людини

Abstract

In the work the chosen algorithms of disease recognition in endoscopy images were described and compared for theirs efficiency. The algorithms were estimated with regard to utility for application in computer system's support for digestive system’s diagnostics. Estimations were achieved in an advanced testing environment, which was built with use of the large collection of endoscopy movies received from Medical University in Gdańsk. For classification of the endoscopy images the neural networks and SVM classifiers were used. Efficiency of classifiers was also compared. To achieve the best scores of efficiency in disease recognition, all of the algorithms' input parameters were optimized. In the summary scores of tests and the bests of algorithms were described.