Computer-Aided Diagnosis System for Variance Estimation of 3D Ultrasonography Based on Gabor Filter

With the development of the times, people's lifestyle and eating habits are changed a lot. Worldwide, breast cancer is the second most common type of cancer after lung cancer and the fifth most common cause of cancer death. Diagnostic ultrasound (US) of breast cancer is currently the major clinical detection method. However, ultrasound imaging usually contains a large number of noises and speckles. That will impact greatly on diagnosis by physicians. Therefore, we proposed a method to enhance the computer-aided diagnosis (CAD) of the breast cancer tumors and to reduce detection time and error rate. Experimental investigations demonstrated that the texture variance of 3D ultrasound were effective and useful for differential diagnosis of breast tumors. Texture extraction with proposed method can find malignant more accurate than auto-correlation.