Ridgelet based Feature Extraction for Breast Cancer Detection using Ultrasound Images

Breast cancer is the second most common cancer all over the world. Ultrasound imaging is an effective tool in the detection of breast cancer because of its non ionizing radiation and low cost. This paper presents the possibility of extraction of features that can effectively differentiate benign and malignant state of cancer using ultrasound images. Speckle noises in the ultrasound images are reduced by mean, median, Weiner, filtering techniques and. Statistical texture features are extracted by applying ridgelet transform. Results shows that the ridgelet based feature extraction can effectively differentiate the state of cancer.