Architectural distortion is an important ultrasonographic indicator of breast cancer. However, it is\ndifficult for clinicians to determine whether a given lesion is malignant because such distortions\ncan be subtle in ultra sonographic images. In this paper, we report on a study to develop a computerized\nscheme for the histological classification of masses with architectural distortions as a differential\ndiagnosis aid. Our database consisted of 72 ultra sonographic images obtained from 47\npatients whose masses had architectural distortions. This included 51 malignant (35 invasive and\n16 noninvasive carcinomas) and 21 benign masses. In the proposed method, the location of the\nmasses and the area occupied by them were first determined by an experienced clinician. Fourteen\nobjective features concerning masses with architectural distortions were then extracted automatically\nby taking into account subjective features commonly used by experienced clinicians to\ndescribe such masses. The k-nearest neighbors (k-NN) rule was finally used to distinguish three\nhistological classifications. The proposed method yielded classification accuracy values of 91.4%\n(32/35) for invasive carcinoma, 75.0% (12/16) for noninvasive carcinoma, and 85.7% (18/21) for\nbenign mass, respectively. The sensitivity and specificity values were 92.2% (47/51) and 85.7%\n(18/21), respectively. The positive predictive values (PPV) were 88.9% (32/36) for invasive carcinoma\nand 85.7% (12/14) for noninvasive carcinoma whereas the negative predictive values\n(NPV) were 81.8% (18/22) for benign mass. Thus, the proposed method can help the differential\ndiagnosis of masses with architectural distortions in ultrasonographic images.
Loading....