Automated lung segmentation in digital posteroanterior and lateral chest radiographs: Applications in diagnostic radiology and nuclear medicine

Automated segmentation of anatomic regions in digital radiographs is a key element of computer-aided diagnostic (CAD) methods. Computerized methods for automatically segmenting the aerated lung fields from posteroanterior (PA) and lateral digital chest radiographs have been developed. The methods are based on gray-level thresholding techniques, including iterative global gray-level thresholding and local gray-level thresholding, thus eliminating the need for edge detection algorithms and a priori assumptions regarding the overall morphology of the lung regions. Consequently, this method is particularly applicable to the detection of abnormal asymmetry in PA radiographs, where pathological processes may produce gross alterations to the visual appearance of the radiographic lung anatomy. An anatomic region of particular interest is the costophrenic (CP) angle, which reflects the radiographic projection of the costodiaphragmatic recess. The method described lends itself to an automated analysis of the CP angle for detection of pleural effusion, for example. Another application of this method crosses into the field of nuclear medicine. Radionuclide lung scans are typically used in conjunction with conventional chest radiographs for diagnostic purposes. A fully automated method for retrospectively registering digital PA and lateral chest radiographs with the anterior, posterior, and lateral perfusion images and posterior ventilation images that constitute a lung scan examination has been developed based on the lung segmentation method for digital chest radiographs. The computerized techniques that have been developed may be incorporated into future CAD schemes and may potentially aid radiologists in the interpretation and assessment of medical images.