Texture analysis of tumor in lung CT data

Abstract

The aim of this work is the revelation of the possibility of the use of texture analysis methods to detection and segmentation tumor tissue in patient’s lungs and classification viable areas of tumor tissue. The main assumption includes the possibility that there are differences of textural properties between tumor and surrounding tissues and changes of these features during development and treatment of this disease. The work deals with the creation of vector of texture features which is composed of some methods of texture analysis and then processed by methods of cluster analysis in programming environment Matlab®.