Improved method for automatic identification of lung regions on chest radiographs

Rationale and Objectives. The authors performed this study to evaluate an a lgorithm developed to help identify lungs on chest radiographs. Materials and Methods. Forty clinical posteroanterior chest radiographs obt ained in adult patients were digitized to 12-bit gray-scale resolution. In the proposed algorithm, the authors simplified the current approach of edge detection with derivatives by using only the first derivative of the horiz ontal and/or vertical image profiles. In addition to the derivative method, pattern classification and image feature analysis were used to determine t he region of interest and lung boundaries. Instead of using the traditional curve-fitting method to delineate the lung, the authors applied an iterati ve contour-smoothing algorithm to each of the four detected boundary segmen ts (costal, mediastinal, lung apex, and hemidiaphragm edges) to form a smoo th lung boundary. Results. The algorithm had an average accuracy of 96.0% for the right lung and 95.2% for the left lung and was especially useful in the delineation of hemidiaphragm edges. In addition, it took about 0.775 second per image to identify the lung boundaries, which is much faster than that of other algor ithms noted in the literature. Conclusion. The computer-generated segmentation results can be used directl y in the detection and compensation of rib structures and in lungs nodule d etection.