AUTOMATED LUNG SEGMENTATION IN DIGITIZED POSTEROANTERIOR CHEST RADIOGRAPHS

Rationale and Objectives. The authors developed and tested a gray-leve l thresholding-based approach to automated lung segmentation in digiti zed posteroanterior chest radiographs. Materials and Methods. Gray-lev el histogram analysis was initially performed to establish a range of thresholds for use during an iterative global gray-level thresholding technique. Local gray-level threshold analysis was then performed on t he output of global thresholding. The resulting contours ware subjecte d to several smoothing processes, including a rolling-ball technique. The final contours closely approximated the boundaries of the aerated lung regions. The method was applied to a database of 600 posteroanter ior chest images. Radiologists rated the accuracy and completeness of the contours with a five-point scale. Results. Results of the subjecti ve rating evaluation indicated that this method was accurate, with 79% Of the assigned ratings reflecting moderately or highly accurate segm entation and only 8% of the ratings indicating moderately or highly in accurate segmentation. Conclusion. This gray-level thresholding-based approach provides accurate automated lung segmentation in digital post eroanterior chest radiographs.