A method for automated analysis of abnormalities in the form of lesions and parenchymal distortions using digital images, including generating image data from respective of digital images derived from at least one selected portion of an object, for example, from mammographical digital images of the left and right breasts. The image data from each of the digital images are then correlated to produce correlated data in which normal anatomical structured background is removed. The correlated data is then searched using one or more predetermined criteria to identify in at least one of the digital images an abnormal region represented by a portion of the correlated data which meets the predetermined criteria. The location of the abnormal region is then indicated, and the indicated location is then subjected to classification processing to determine whether or not the abnormal region is benign or malignant. Classification is performed based on the degree of spiculations of the identified abnormal region. In order to enhance the process of searching for abnormal regions, in one embodiment the gray-level frequency-distributions of two or more images are matched by matching the cumulative gray-level histograms of the images in question.
Two digital radiologic images taken from different viewing directions of a same region, notably a mammogram study of the same breast, are automatically processed by a computer to identify suspect masses by producing processed mammogram images in which suspect spots, the skinline and the nipple are marked or enhanced. Candidate suspect spots are initially identified by individually processing each mammogram image separately. Then characteristics of the candidate spots identified in the mammogram images taken from different viewing directions are compared to eliminate false positives. The characteristics compared include position of the spots relative to the explicitly detected nipple, and their size, shape, brightness and brightness variance. The candidate spots are separately identified by thresholding the breast region of the mammogram at 20 or more threshold levels determined from a histogram of the image to discriminate spots, and classifying the spots by size, shape and variance in intensity of the pixels comprising the spot. Overlaps are resolved after the comparison between views.
The present invention provides a method for detecting an object. The method includes capturing a binary image of the object, and determining a projection of the binary image to a first axis. The method further includes determining a difference between a profile of a target object to the first axis and the projection at a plurality of positions along the first axis, and detecting the object by determining if the difference between the profile and the projection is less than a threshold at one of the plurality of positions.
Radiological imaging device comprising an emitter of an X-ray beam and a receiver of the X-ray beam after it has crossed an organ, the organ being capable of being placed between the receiver and a compression element, capable of being removably fixed on the device. A calculation unit includes a means for optimizing the image quality over a particular area defined by the compression element.
The invention is a novel method for automated detection of objects in images. One specific use is to detect malignant microcalcification clusters in mammograms. The method operates by forming a contour plot of the image (mammogram), the object (microcalcification) in the contour plot being comprised of a set of nested contour lines wherein the contour lines correspond to intensity levels thereby causing the object to appear as a prominent peak in relation to the local surround in the image.
A method for automated detection of abnormal anatomic regions, wherein a mammogram is digitized to produce a digital image and the digital image is processed using local edge gradient analysis and linear pattern analysis in addition to feature extraction routines to identify abnormal anatomic regions. Noise reduction filtering and pit-filling/spike-removal filtering techniques are also provided. Multiple difference imaging techniques are also used in which difference images employing different filter characteristics are obtained and processing results logically OR'ed to identify abnormal anatomic regions. In another embodiment the processing results with and without noise reduction filtering are logically AND'ed to improve detection sensitivity. Also, in another embodiment the wavelet transform is utilized in the identification and detection of abnormal regions. The wavelet transform is preferably used in conjunction with the difference imaging technique with the results of the two techniques being logically OR'ed.
