Texture Analysis Approach to Quantify and Discriminate Normal and Pathological Human Lung CT- Images

Abstract

Pulmonary diseases are one of the most attractive area of medical research domain all over the world. Diagnosis of these diseases lack due to subjective interpretation of diagnostic images, even medication has been in effect from decades. Better diagnosis is an essential requirement before prescribing medication. As radiologists learn and differentiate various cases varies among themselves during training and routine practice. The main objective of this research work is to provide some standard pulmonary diseases diagnostic measures. Normal and pulmonary diseased Lung CT images were collected from BVH Hospital. Haralick texture parameters have been computed on the selected Regions of Interest. B11 is used for discrimination and interpretation of various pulmonary diseases. Results of this research work concludes that texture parameters have high degree of reliability to automatically discriminate similar tissue textures when regions are marked correctly