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).
Abstract:Full movement of the vocal cords is necessary for life sustaining functions. To enable correct diagnosis of reduced vocal cord motion and thereby potentially enhance treatment outcomes, it is proposed to objectively determine the degree of vocal cord paralysis in contrast to the current clinical practice of subjective evaluation. Our study shows that quantitative assessment can be achieved using optical flow based motion estimation of the opening and closing movements of the vocal cords. The novelty of the proposed method lies in the automatic processing of fibre-optic endoscopy videos to derive an objective measure for the degree of paralysis, without the need for high-end data acquisition systems such as high speed cameras or stroboscopy. Initial studies with three video samples yield promising results and encourage further investigation of vocal cord paralysis using this technique.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.