Abstract: A method and system for automated analysis of digital radiographic images in which regions-of-interest (ROI's) are first determined, and subsequently analyzed for abnormalities. To locate the ROI's, the outer ribcage and midline boundary locations of the chest image are determined from the digital image data. Vertical profiles are then selected and background trend is then removed from each vertical profile. A shift-variant sinusoidal function is fitted to each vertical profile and ROI's are selected based on the fitted functions. The non-uniform background trend is removed from the original image data of each selected ROI to obtain corrected data. The power spectrum of the lung texture is obtained from the 2D Fourier transform of the corrected data and is filtered by the human visual response.

Abstract: A method and system for automated classification of distinction between normal lungs and abnormal lungs with interstitial disease, based on the analysis of predetermined physical texture measures and also on a data base for normal lungs of these texture measures. The texture measures selected are the RMS variation, R, and the first moment of power spectrum, M, for lung texture. These two texture measures are normalized by using the data base for normal lungs. A single texture index is determined from the two normalized texture measures by taking into account the distribution (or the data base) of texture measures obtained from abnormal lungs, in order to facilitate the automated classification of normal and abnormal lungs. A threshold texture index is then chosen for initial selection of "abnormal" regions of interest (ROIs), which contain a large texture index above the threshold level.