Labeling of MR brain images using Boolean neural network

Abstract

Presents a knowledge-based approach for labeling two-dimensional (2-D) magnetic resonance (MR) brain images using the Boolean neural network (BNN), which has binary inputs and outputs, integer weights, fast learning and classification, and guaranteed convergence. The approach consists of two components: a BNN clustering algorithm and a constraint satisfying Boolean neural network (CSBNN) labeling procedure. The BNN clustering algorithm is developed to initially segment an image into a number of regions. Then the segmented regions are labeled with the CSBNN, which is a modified version of BNN. The CSBNN uses a knowledge base that contains information on image-feature space and tissue models as constraints. The method is tested using sets of MR brain images. The regions of the different brain tissues are satisfactorily segmented and labeled. A comparison with the Hopfield neural network and the traditional simulated annealing method for image labeling is provided. The comparison results show that the CSBNN approach offers a fast, feasible, and reliable alternative to the existing techniques for medical image labeling.

Two-step verification of brain tumor segmentation using watershed-matching algorithm

“…But it only takes into consideration the image intensity, thereby not producing adequate outputs in noisy images. Many efforts have explored artificial neural network (ANN) [ 7 ]. Edge-based segmentation techniques cannot work well due to having inherent speckle noise and texture characteristics.…”

Gray Matter Segmentation of Brain MRI Using Hybrid Enhanced Independent Component Analysis in Noisy and Noise Free Environment

“…[9] Image intensities are segregated using the watershed approach and used those intensity level as a seed to perform region growing along with image entropy is used to perform the medical segmentation of different tissues, The supervised segmentation method is used to make brain tissue classification using TRIOA by proposing with integrating SVM, ICA and Fisher's Linear Discriminant Analysis [18]. [15] Boolean neural network is used to perform segmentation, constraint satisfying Boolean neural network used to label. [26] Segmented the tissues using Self-organized maps and used learning vector quantization for fine-tuning to perform the segmentation of the MRI using stationary wavelet transform (SWT).…”