Breast cancer is the second leading cause of death for women all over the world. Since the causernof breast cancer remains unknown, early detection and diagnosis is the key for control. In thatrnregard, Breast Ultrasound Imaging (BUS) has become important modality for breast cancerrndetection due to its noninvasive, cost effective nature and suitability for screening and diagnosingrnin low resource settings. rnUltrasound imaging is one of the most frequently used diagnosis tools to detect and classifyrnabnormalities in breast. A known drawback of the technology is that it has high amount of specklernnoise which results in poor image quality. This makes it difficult to use the imaging technologyrnfor accurate detection of malignant tumors. The procedure is traditionally carried out by visualrnassessment of the images which is often a time taking process prone to observer variability issues.rnIn this regard, computer aided detection techniques have been developed in various literaturesrnshowing promises with their merits and demerits. Nevertheless, image based accurate detection ofrnbreast cancer is still a topic of interest with many ongoing researches in the area. rnIn the current work, S-transform based breast cancer detection and classification method isrndeveloped. The proposed system consists of four stages: preprocessing, segmentation, featurernextraction and classification. Image enhancement and speckle noise reduction were implementedrnduring preprocessing. Region of interest (ROI) is then accurately determined on preprocessedrnimages by employing canny edge detection. The ultrasound images were then classified based onrndifferent features like mean, variance, standard deviation (STD), entropy and contrast metrics. Thernresults of the classification stage were compared against available ground truth images acquiredrnfrom research image database. Accordingly, the classification procedure implemented usingrnartificial neural network offered 90% detection accuracy.