Identification of pathological changes in the lungs using an analysis of radiological reports and tomographic images

Abstract

This article discusses an idea of a joint analysis of medical images and texts aimed at improving the quality of automated diagnosis of emphysema. We compare the quality of image classification with and without taking into account the localization of the pathology mentioned in radiological reports. The study was carried out on sets of real images of computed tomography of the lungs obtained in clinical studies at Samara State Medical University. It was established that the use of information on the localization of pathology contained in radiological reports leads to an increase in the F-score for the detection from 0.55 to 0.73.

Keywords

• image processing
• tomographic image processing
• image analysis
• haralick’s features
• image classification
• radiological report
• natural language processing