Texture Features Extraction of Chest HRCT Image
Tianrui Cao, Gang Xie, Wang Fang, Chengdong Yan · 2010
Combining with signs of lung diseases in high-resolution computed tomography (HRCT) images, this paper introduced texture feature extraction into the HRCT analysis, realized texture parameter extraction of any straight line and region of interest (ROI), calculated area of lung tissue. Straight line feature curve and area of lung tissue provides visual data for the diagnosis of small airway disease. Center of ROI, mean of gray and other features of ROI provide quantitative data for the study of regional lung disease, such as tumor. In order to accurately calculate the area of lung tissue required to segment the lung tissue accurately. So this paper presented a segmentation algorithm based on the tolerance granular space model and region-growing method, segmented the lung tissue of chest HRCT accurately. The results of extensive experiments illustrate that we can extract texture parameter effectively, gain the data needed for diagnosis of lungs disease. It is the more pertinence and practicality than classical texture analysis methods.