Classification of Mammographic Images Using the Joint Best Basis and the Approximate Klt

Breast cancer is currently one of the major causes of death for women in the U.S. Mammography is currently the most effective method for detection of breast cancer and early detection has proven to be an efficient tool to reduce the number of deaths. Mammography is the most demanding of all clinical imaging applications as it requires high contrast, high signal to noise ratio and resolution with minimal x-radiation. According to studies [16], 10\% to 30\% of women having breast cancer and undergoing mammography have negative mammograms, i.e. are misdiagnosed. Furthermore, only 20\%-40\% of the women who undergo biopsy have cancer. Biopsies are expensive, invasive and traumatic to the patient. The high rate of false positives motivate research aimed to enhance the mammogram images, to provide Computer Aided Diagnostics tools that can alert the radiologist to potentially malignant regions in the mammograms and to develop tools for automated classification of mammograms into benign and malignant classes (see for example [4, 8]). In this paper we present classification results of mammographic images from an early stage of malignancy using feature vectors based on wavelet packets, PCA and the Approximate Karhunen Loeve transform. We employ an innovative method that provides classification results better than the average performance of radiologists. The method was tested using database of mammograms from an early stage of malignancy. Correct detection is harder and more important at an early stage of malignancy.