Nigel John

Hidden Markov models-based 3D MRI brain segmentation

Abstract This paper introduces a 3D MRI segmentation algorithm based on Hidden Markov Models (HMMs). The mathematical models for the HMM that forms the basis of the segmentation algorithm for both the continuous and discrete cases are developed and contrasted with Hidden Markov Random Field in terms of complexity and extensibility to larger fields. The presented algorithm clearly demonstrates the capacity of HMM to tackle multi-dimensional classification problems. The HMM-based segmentation algorithm was evaluated through application to simulated brain images from the McConnell Brain Imaging Centre, Montreal Neurological Institute, McGill University as well as real brain images from the Internet Brain Segmentation Repository (IBSR), Harvard University. The HMM model exhibited high accuracy in segmenting the simulated brain data and an even higher accuracy when compared to other techniques applied to the IBSR 3D MRI data sets. The achieved accuracy of the segmentation results is attributed to the HMM foundation and the utilization of the 3D model of the data. The IBSR 3D MRI data sets encompass various levels of difficulty and artifacts that were chosen to pose a wide range of challenges, which required handling of sudden intensity variations and the need for global intensity level correction and 3D anisotropic filtering. During segmentation, each class of MR tissue was assigned to a separate HMM and all of the models were trained using the discriminative MCE training algorithm. The results were numerically assessed and compared to those reported using other techniques applied to the same data sets, including manual segmentations establishing the ground truth for real MR brain data. The results obtained using the HMM-based algorithm were the closest to the manual segmentation ground truth in terms of an objective measure of overlap compared to other methods.

Histogram-based gravitational optimization algorithm on single MR modality for automatic brain lesion detection and segmentation

Magnetic resonance imaging (MRI) is a very effective medical imaging technique for the clinical diagnosis and monitoring of neurological disorders. Because of intensity similarities between brain lesions and normal tissues, multispectral MRI modalities are usually applied for brain lesion detection. However, the time and cost restrictions for collecting multi-spectral MRI, and the issue of possible errors from registering multiple MR images necessitate developing an automatic lesion detection approach that can detect lesions using a single anatomical MRI modality. In this paper, an automatic algorithm for brain stroke and tumor lesion detection and segmentation using single-spectral MRI is presented. The proposed algorithm, called histogram-based gravitational optimization algorithm (HGOA), is a novel intensity-based segmentation technique, which applies enhanced gravitational optimization algorithm on histogram analysis results. The mathematical descriptions as well as the convergence criteria of the developed optimization algorithm are presented in detail. Using this algorithm, brain is segmented into different number of regions, which will be labeled as lesion or healthy. Here, the ischemic stroke lesions and tumor lesions are segmented with 91.5% and 88.1% accuracy, respectively.

An Artificial Immune-Activated Neural Network Applied to Brain 3D MRI Segmentation

In this paper, a new neural network model inspired by the biological immune system functions is presented. The model, termed Artificial Immune-Activated Neural Network (AIANN), extracts classification knowledge from a training data set, which is then used to classify input patterns or vectors. The AIANN is based on a neuron activation function whose behavior is conceptually modeled after the chemical bonds between the receptors and epitopes in the biological immune system. The bonding is controlled through an energy measure to ensure accurate recognition. The AIANN model was applied to the segmentation of 3-dimensional magnetic resonance imaging (MRI) data of the brain and a contextual basis was developed for the segmentation problem. Evaluation of the segmentation results was performed using both real MRI data obtained from the Center for Morphometric Analysis at Massachusetts General Hospital and simulated MRI data generated using the McGill University BrainWeb MRI simulator. Experimental results demonstrated that the AIANN model attained higher average results than those obtained using published methods for real MRI data and simulated MRI data, especially at low levels of noise.

Multi-Sectional Views Textural Based SVM for MS Lesion Segmentation in Multi-Channels MRIs

In this paper, a new technique is proposed for automatic segmentation of multiple sclerosis (MS) lesions from brain magnetic resonance imaging (MRI) data. The technique uses a trained support vector machine (SVM) to discriminate between the blocks in regions of MS lesions and the blocks in non-MS lesion regions mainly based on the textural features with aid of the other features. The classification is done on each of the axial, sagittal and coronal sectional brain view independently and the resultant segmentations are aggregated to provide more accurate output segmentation. The main contribution of the proposed technique described in this paper is the use of textural features to detect MS lesions in a fully automated approach that does not rely on manually delineating the MS lesions. In addition, the technique introduces the concept of the multi-sectional view segmentation to produce verified segmentation. The proposed textural-based SVM technique was evaluated using three simulated datasets and more than fifty real MRI datasets. The results were compared with state of the art methods. The obtained results indicate that the proposed method would be viable for use in clinical practice for the detection of MS lesions in MRI.

Multivariate Statistical Model for 3D Image Segmentation with Application to Medical Images

In this article we describe a statistical model that was developed to segment brain magnetic resonance images. The statistical segmentation algorithm was applied after a pre-processing stage involving the use of a 3D anisotropic filter along with histogram equalization techniques. The segmentation algorithm makes use of prior knowledge and a probability-based multivariate model designed to semi-automate the process of segmentation. The algorithm was applied to images obtained from the Center for Morphometric Analysis at Massachusetts General Hospital as part of the Internet Brain Segmentation Repository (IBSR). The developed algorithm showed improved accuracy over the k-means, adaptive Maximum Apriori Probability (MAP), biased MAP, and other algorithms. Experimental results showing the segmentation and the results of comparisons with other algorithms are provided. Results are based on an overlap criterion against expertly segmented images from the IBSR. The algorithm produced average results of approximately 80% overlap with the expertly segmented images (compared with 85% for manual segmentation and 55% for other algorithms).

Co-segmentation of MR and MR spectroscopy imaging using hidden markov models

A Hidden Markov Models based technique is introduced for co-segmentation of MRI and MRSI data of the brain. The technique demonstrates the ability of Hidden Markov Models to handle the co-analysis of MRI and MRSI for the purpose of improving the accuracy of MRI segmentation as well as the quantification of brain metabolites. For that purpose, two HMM-based schemes are presented; one that relies on parallel HMMs for separately analyzing MRI and MRSI data and the other utilizes combined feature vectors of MRI and MRSI data. The co-segmentation of MRI and MRSI data using HMMs is evaluated using simulated MRI brain data (from the McConnell Brain Imaging Centre, Montreal Neurological Institute of McGill University) and simulated MRSI data. Experimental results demonstrate that the co-segmentation of brain MRI and MRSI data based on HMMs exhibited higher accuracy, in terms of the Dice similarity coefficient, than only using brain MRI data. The technique involving parallel HMMs that separately analyze brain MRI and MRSI data and then combine the segmentation results demonstrated better accuracy and faster segmentation times compared to the co-analysis of combined MRI and MRSI data of the brain.

MS Lesions Detection in MRI Using Grouping Artificial Immune Networks

A dual-channel 3D MRI segmentation technique based on grouping artificial immune networks (GAIN) is introduced to detect MS lesion in MR images. The technique demonstrates the ability of artificial immune networks to handle MS lesions detection in T1- and T2-weighted brain MRI. The GAIN-based MRI segmentation technique was evaluated using simulated MS brain images from the McConnell Brain Imaging Centre, Montreal Neurological Institute of McGill University. 3D anisotropic filtering is used to handle noise artifacts in the simulated 3D MRI data sets. Experimental results demonstrated that dual channel MS segmentation approach exhibited high accuracy in segmenting the simulated MS brain data and an even higher accuracy when compared to techniques based on single channel 3D MRI data sets in terms of the Dice coefficient, an objective measure of overlap.

Module Extraction for Efficient Object Queries over Ontologies with Large ABoxes.

The extraction of logically-independent fragments out of an ontology ABox can be useful for solving the tractability problem of querying ontologies with large ABoxes. In this paper, we propose a formal definition of an ABox module, such that it guarantees complete preservation of facts about a given set of individuals, and thus can be reasoned independently w.r.t. the ontology TBox. With ABox modules of this type, isolated or distributed (parallel) ABox reasoning becomes feasible, and more efficient data retrieval from ontology ABoxes can be attained. To compute such an ABox module, we present a theoretical approach and also an approximation for SHIQ ontologies. Evaluation of the module approximation on different types of ontologies shows that, on average, extracted ABox modules are significantly smaller than the entire ABox, and the time for ontology reasoning based on ABox modules can be improved significantly.

Automatic Facial Expression Recognition Using Modified Wavelet-Based Salient Points and Gabor-Wavelet Filters

In this paper, we present an automated approach for recognizing seven facial expressions including the neutral expression. The approach is based upon efficient feature extraction, feature compression, and an artificial neural network (ANN) classification. In the proposed method, the basic components of face, eyes, eyebrow, and mouth, are first segmented from the whole face using modified Wavelet based salient points. Then, the features of the eye and the mouth are extracted using Gabor-wavelet filters. Afterwards, the dimension of the features is reduced using principal component analysis (PCA). Finally a multi layer perceptron neural network is used to classify the facial expressions. The simulated results show high recognition rate as well as the low computational complexity that makes the proposed algorithm remarkable for accurate and fast facial expression recognition.

Automatic segmentation of MR brain images

An automatic image segmentation for MR brain images based on the gray level characteristics of the images is developed. The method analyses a sequence of MR brain images to provide region information as well as boundary data for classification and eventual creation of 3D models. The system incorporates global information from the image set through an analysis of the statistics of the cooccurrence matrices. Local consistency is then applied with the use of a relaxation algorithm on individual images. The cooccurrence matrices provide conditional probabilities for the classification of pixels into specific regions or boundaries based on the matrix distribution. A constrained stochastic relaxation is then used to refine the probabilistic labels using local image information. Results of the technique are presented for MR brain images.