RadioGraphics, Vol 15, 1457-1464, Copyright © 1995 by Radiological Society of North America
Fractal analysis of interstitial lung abnormalities in chest radiography
S Kido, J Ikezoe, H Naito, S Tamura and S Machi
Department of Radiology, Nishinomiya Municipal Central Hospital, Hyogo, Japan.
A computerized method for analyzing interstitial lung abnormalities seen 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 the processed images are then
calculated by using the box- counting algorithm. The accuracy of the
computerized method in differentiating between normal and abnormal lung
tissue was tested on digitized chest radiographs (0.175 mm pixel, 10-bit)
of 100 randomly selected patients. One hundred regions of interest (ROIs)
from radiographs of 50 patients 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 (mean, 1.67 +/- 0.10 vs 1.44 +/- 0.12, respectively; P <
.001). This result indicates that fractal analysis is useful in
distinguishing interstitial lung abnormalities from normal lung tissue on
chest radiographs.
