Automated Detection and Classification of Mass from Breast Ultrasound Images

This paper introduces a computer aided diagnosis (CAD) technique for segmentation of mass in breast ultrasound (BUS) images followed by an efficient classification of the image into benign or malignant one. The presence of speckle noise, low contrast and blurred boundary of mass in a BUS image makes it challenging to determine the mass, which is the region of interest (ROI) in the current work. Detecting an accurate ROI in turn results in efficient feature extraction and classification. In current work, image enhancement and speckle noise reduction are implemented for preprocessing in a simple but efficient way through filtering techniques. The results of the preprocessing stage are as effective as those obtained using traditional speckle reduction anisotropic diffusion (SRAD) algorithm. ROI is then accurately determined on preprocessed image by employing local region based active contour method. BUS images are classified through textural, morphological and histogram oriented feature metrics in this work. The obtained features are dimensionally reduced using principal component analysis (PCA) and classified through support vector machine (SVM) method. The proposed method is tested on several images and found to be very effective having an accuracy of 95.7% with very high specificity and positive predictive value (PPV).