Breast image classification using machine learning techniques

Among all the common forms of cancer, breast cancer is the most prevalent one. Statistics show that breast cancer causes the second highest mortality in women worldwide. Accurate classification of the breast cancer is of high importance for the proper diagnosis. The survival rate of breast cancer affected people is greatly increased if the cancer is detected early. Ultrasound, MRI or CT imaging techniques are used to capture the current condition of the breast. Digital signal processing, along with modern computer aided techniques are used to analyse these images, and proper diagnosis of the images can save the diagnoses time of the doctor. For the correct classification of the images, Feature detection and extraction of the features play a vital role. Various feature detection techniques are available, But for this thesis we will use the wavelet transform to perform feature detection. The features extracted from the images using the wavelet transform will be utilised for classification purposes. For the classification task we will use a support vector machine.