Brain tumor segmentation is routinely needed in diagnostic radiology. Automatic volume estimation has been used for diagnosis improvement and treatment process. This article presents a new approach for tumor volume estimation, using a variational level set method. The new adapted representation of intensity allows the method to be efficient in the region of interest identification, regardless the shape, size, and location of the tumor. For the estimation of an optimal bounding box, a fuzzy preference optimization model is used. The proposed approach is suitable for the zero level set initialization as well as for the reduction of the processing area, which ultimately speeds up the curve evolution. Moreover, tumor contours are determined using the hybrid level set technique, which combines the gradient and local phase information as an edge indicator term. Such an approach is robust to attenuation and intensity inhomogeneity. The proposed method is evaluated using a set of real and synthetic images. Our method achieved a performance of 96% accuracy, with an average execution time of 4.75 seconds. The proposed method is fast, accurate, and does not require training data or prior knowledge. With such experimental results, our approach outperforms 18 state-of-the-art methods.
Developing a computer aided diagnosis system (CAD) is an extremelychallenging task. One of the major goals of CAD is to help the radiologist to makegood decisions by detecting and analyzing characteristics of benign and malignant lesions. In this context, we present accurate and automatic method that, detect and extract malignancy descriptors of breast and meningioma brain tumor.Our applied an algorithm that uses enhancement image based on homomorphicfiltering and adaptive histogram equalization technique. This work was proposedby Zhang Chaofu et al. [3]. A region of interest is determinated using K meansclustering. And then, we employed basically wavelet transform to extract pertinent features for meningioma tumor, geometric and texture characteristics forbreast tumor in order to classify malignancy lesion.
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.