FRACTAL ANALYSIS OF INTERSTITIAL LUNG ABNORMALITIES IN CHEST RADIOGRAPHY

A computerized method for analyzing interstitial lung abnormalities se en on chest radiographs was investigated, The method includes two main steps: (a) extraction of linear opacities on chest radiographs and (b ) calculation of the fractal dimension, Extraction of linear opacities uses the processes of four directional Laplacian-Gaussian filtering, binarization, and Linear opacity judgment, The fractal dimensions in t he processed images are then calculated by using the box-counting algo rithm. The accuracy of the computerized method in differentiating betw een normal and abnormal lung tissue was tested on digit tized chest ra diographs (0.175 mm pixel, 10-bit) of 100 randomly selected pat tients . One hundred regions of interest (ROIs) from radiographs of 50 patien ts with interstitial lung abnormalities and 100 ROIs from radiographs of 50 patients with normal lungs were analyzed. The fractal dimensions obtained from the ROIs in lungs with interstitial abnormalities were significantly higher compared with those from ROIs in normal lungs (me an, 1.67 +/- 0.10 vs 1.44 +/- 0.12, respectively; P <.001). This resul t indicates that fractal analysis is useful in distinguishing intersti tial lung abnormalities from normal lung tissue on chest radiographs.