BREAST ULTRASONOGRAPHY - COMPUTER-AIDED DIAGNOSIS USING FUZZY INFERENCE

On the basis of detailed analysis of ultrasonographic features in 105 breast masses (55 malignant, 50 benign), a computer-aided diagnostic s ystem using fuzzy inference has been developed. Ultrasonographic featu res of a mass for the input data included shape, border, halo (boundar y echoes), internal, echoes, posterior echoes, and edge shadows (bilat eral shadows). The probability of malignancy was described by an actua l number ranging from 0.0 to 1.0. The algorithm of inference was const ructed, and a sensitivity of 94.5% and specificity of 76.0% for cancer diagnosis were obtained.