COMPUTERIZED SHEMES FOR DETECING AND/OR DIAGNOSING LESIONS ON ULTRASOUND IMAGES USING ANALYSIS OF LESION SHADOWS

摘要

Computerized detection and diagnostic schemes for sonographic images combine the benefits of computerized machine detection with the acquisition of non-radiographic medical images of special use for the screening of high risk, young patients who do not want the effects of ionizing characteristic of mammography. The lesion schemes employ computer-assisted interpretation of medical sonographic images, and output potential lesion sites and/or diagnosis of those lesions. More specifically, an embodiment of the computerized detection scheme involves convoluting a sonographic image with a mask of a given ROI (region of interest) size, and calculating a skewness value for each mask location, and assembling the calculated skewness values to form a skewness image. Thresholds are applied to pixels of the skewness image to determine potential shadows. (Ultrasound images show characteristic posterior acoustic behavior for different lesion types: Posterior acoustic shadowing is often observed for malignant lesions and for some benign solid masses, while posterior acoustic enhancement is often seen for cysts.) An embodiment of the diagnostic scheme (classifying a detected lesion as malignant or benign, for example) involves calculating the skewness of a shadow of a detected lesion, and comparing the calculated skewness to a threshold to arrive at a diagnosis. The detection and diagnostic schemes may also involve merging skewness values with other values determined in accordance with other analytic features, to arrive more comprehensive detection and diagnoses. The schemes are computationally efficient, allowing their use in real-time sonography.