A computerized method and system based on quantitative analysis of geometric features of various infiltrate patterns in chest images for the detection and categorization of abnormalities related to the infiltrate patterns. Chest images are digitized and a lung texture analysis is performed on a number of small regions of interest (ROIs) in order to determine a classification of normal or abnormal of the particular patient's lungs. If the lungs are determined as being abnormal, large ROIs with a 128.times.128 matrix are selected in order to cover the detected areas of abnormality. Overall background trend correction is then performed in these large ROIs using a 2D-surface fitting technique for isolation of the fluctuating patterns of the underlying lung texture. Opacities of interstitial infiltrates are identified from two processed images which are obtained by employing thresholding with a morphological filter and a line enhancement filter. Finally, ROIs are classified into nodular, reticular and/or reticulo-nodular patterns by measurement of parameters corresponding to the type of the abnormality pattern detected.