Ayman El-Baz

Precise segmentation of multimodal images

We propose new techniques for unsupervised segmentation of multimodal grayscale images such that each region-of-interest relates to a single dominant mode of the empirical marginal probability distribution of grey levels. We follow the most conventional approaches in that initial images and desired maps of regions are described by a joint Markov-Gibbs random field (MGRF) model of independent image signals and interdependent region labels. However, our focus is on more accurate model identification. To better specify region borders, each empirical distribution of image signals is precisely approximated by a linear combination of Gaussians (LCG) with positive and negative components. We modify an expectation-maximization (EM) algorithm to deal with the LCGs and also propose a novel EM-based sequential technique to get a close initial LCG approximation with which the modified EM algorithm should start. The proposed technique identifies individual LCG models in a mixed empirical distribution, including the number of positive and negative Gaussians. Initial segmentation based on the LCG models is then iteratively refined by using the MGRF with analytically estimated potentials. The convergence of the overall segmentation algorithm at each stage is discussed. Experiments show that the developed techniques segment different types of complex multimodal medical images more accurately than other known algorithms.

Computer-Aided Diagnosis Systems for Lung Cancer: Challenges and Methodologies

This paper overviews one of the most important, interesting, and challenging problems in oncology, the problem of lung cancer diagnosis. Developing an effective computer-aided diagnosis (CAD) system for lung cancer is of great clinical importance and can increase the patients chance of survival. For this reason, CAD systems for lung cancer have been investigated in a huge number of research studies. A typical CAD system for lung cancer diagnosis is composed of four main processing steps: segmentation of the lung fields, detection of nodules inside the lung fields, segmentation of the detected nodules, and diagnosis of the nodules as benign or malignant. This paper overviews the current state-of-the-art techniques that have been developed to implement each of these CAD processing steps. For each technique, various aspects of technical issues, implemented methodologies, training and testing databases, and validation methods, as well as achieved performances, are described. In addition, the paper addresses several challenges that researchers face in each implementation step and outlines the strengths and drawbacks of the existing approaches for lung cancer CAD systems.

A unified framework for MAP estimation in remote sensing image segmentation

A complete framework is proposed for applying the maximum a posteriori (MAP) estimation principle in remote sensing image segmentation. The MAP principle provides an estimate for the segmented image by maximizing the posterior probabilities of the classes defined in the image. The posterior probability can be represented as the product of the class conditional probability (CCP) and the class prior probability (CPP). In this paper, novel supervised algorithms for the CCP and the CPP estimations are proposed which are appropriate for remote sensing images where the estimation process might to be done in high-dimensional spaces. For the CCP, a supervised algorithm which uses the support vector machines (SVM) density estimation approach is proposed. This algorithm uses a novel learning procedure, derived from the main field theory, which avoids the (hard) quadratic optimization problem arising from the traditional formulation of the SVM density estimation. For the CPP estimation, Markov random field (MRF) is a common choice which incorporates contextual and geometrical information in the estimation process. Instead of using predefined values for the parameters of the MRF, an analytical algorithm is proposed which automatically identifies the values of the MRF parameters. The proposed framework is built in an iterative setup which refines the estimated image to get the optimum solution. Experiments using both synthetic and real remote sensing data (multispectral and hyperspectral) show the powerful performance of the proposed framework. The results show that the proposed density estimation algorithm outperforms other algorithms for remote sensing data over a wide range of spectral dimensions. The MRF modeling raises the segmentation accuracy by up to 10% in remote sensing images.

MRBrainS challenge: online evaluation framework for brain image segmentation in 3T MRI scans

Many methods have been proposed for tissue segmentation in brain MRI scans. The multitude of methods proposed complicates the choice of one method above others. We have therefore established the MRBrainS online evaluation framework for evaluating (semi)automatic algorithms that segment gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) on 3T brain MRI scans of elderly subjects (65–80 y). Participants apply their algorithms to the provided data, after which their results are evaluated and ranked. Full manual segmentations of GM, WM, and CSF are available for all scans and used as the reference standard. Five datasets are provided for training and fifteen for testing. The evaluated methods are ranked based on their overall performance to segment GM, WM, and CSF and evaluated using three evaluation metrics (Dice, H95, and AVD) and the results are published on the MRBrainS13 website. We present the results of eleven segmentation algorithms that participated in the MRBrainS13 challenge workshop at MICCAI, where the framework was launched, and three commonly used freeware packages: FreeSurfer, FSL, and SPM. The MRBrainS evaluation framework provides an objective and direct comparison of all evaluated algorithms and can aid in selecting the best performing method for the segmentation goal at hand.

EM Based Approximation of Empirical Distributions with Linear Combinations of Discrete Gaussians

We propose novel expectation maximization (EM) based algorithms for accurate approximation of an empirical probability distribution of discrete scalar data. The algorithms refine our previous ones in that they approximate the empirical distribution with a linear combination of discrete Gaussians (LCDG). The use of the DGs results in closer approximation and considerably better convergence to a local likelihood maximum compared to previously involved conventional continuous Gaussian densities. Experiments in segmenting multimodal medical images show the proposed algorithms produce more adequate region borders.

Models and methods for analyzing DCE‐MRI: A review

PURPOSE To present a review of most commonly used techniques to analyze dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI), discusses their strengths and weaknesses, and outlines recent clinical applications of findings from these approaches. METHODS DCE-MRI allows for noninvasive quantitative analysis of contrast agent (CA) transient in soft tissues. Thus, it is an important and well-established tool to reveal microvasculature and perfusion in various clinical applications. In the last three decades, a host of nonparametric and parametric models and methods have been developed in order to quantify the CAs perfusion into tissue and estimate perfusion-related parameters (indexes) from signal- or concentration-time curves. These indexes are widely used in various clinical applications for the detection, characterization, and therapy monitoring of different diseases. RESULTS Promising theoretical findings and experimental results for the reviewed models and techniques in a variety of clinical applications suggest that DCE-MRI is a clinically relevant imaging modality, which can be used for early diagnosis of different diseases, such as breast and prostate cancer, renal rejection, and liver tumors. CONCLUSIONS Both nonparametric and parametric approaches for DCE-MRI analysis possess the ability to quantify tissue perfusion.

Focal cortical dysplasias in autism spectrum disorders

BackgroundPrevious reports indicate the presence of histological abnormalities in the brains of individuals with autism spectrum disorders (ASD) suggestive of a dysplastic process. In this study we identified areas of abnormal cortical thinning within the cerebral cortex of ASD individuals and examined the same for neuronal morphometric abnormalities by using computerized image analysis.ResultsThe study analyzed celloidin-embedded and Nissl-stained serial full coronal brain sections of 7 autistic (ADI-R diagnosed) and 7 age/sex-matched neurotypicals. Sections were scanned and manually segmented before implementing an algorithm using Laplace’s equation to measure cortical width. Identified areas were then subjected to analysis for neuronal morphometry. Results of our study indicate the presence within our ASD population of circumscribed foci of diminished cortical width that varied among affected individuals both in terms of location and overall size with the frontal lobes being particularly involved. Spatial statistic indicated a reduction in size of neurons within affected areas. Granulometry confirmed the presence of smaller pyramidal cells and suggested a concomitant reduction in the total number of interneurons.ConclusionsThe neuropathology is consistent with a diagnosis of focal cortical dysplasia (FCD). Results from the medical literature (e.g., heterotopias) and our own study suggest that the genesis of this cortical malformation seemingly resides in the heterochronic divisions of periventricular germinal cells. The end result is that during corticogenesis radially migrating neuroblasts (future pyramidal cells) are desynchronized in their development from those that follow a tangential route (interneurons). The possible presence of a pathological mechanism in common among different conditions expressing an autism-like phenotype argue in favor of considering ASD a “sequence” rather than a syndrome. Focal cortical dysplasias in ASD may serve to explain the high prevalence of seizures and sensory abnormalities in this patient population.

Reduced Gyral Window and Corpus Callosum Size in Autism: Possible Macroscopic Correlates of a Minicolumnopathy

Minicolumnar changes that generalize throughout a significant portion of the cortex have macroscopic structural correlates that may be visualized with modern structural neuroimaging techniques. In magnetic resonance images (MRIs) of fourteen autistic patients and 28 controls, the present study found macroscopic morphological correlates to recent neuropathological findings suggesting a minicolumnopathy in autism. Autistic patients manifested a significant reduction in the aperture for afferent/efferent cortical connections, i.e., gyral window. Furthermore, the size of the gyral window directly correlated to the size of the corpus callosum. A reduced gyral window constrains the possible size of projection fibers and biases connectivity towards shorter corticocortical fibers at the expense of longer association/commisural fibers. The findings may help explain abnormalities in motor skill development, differences in postnatal brain growth, and the regression of acquired functions observed in some autistic patients.

A Topographic Study of Minicolumnar Core Width by Lamina Comparison between Autistic Subjects and Controls: Possible Minicolumnar Disruption due to an Anatomical Element In‐Common to Multiple Laminae

Radial cell minicolumns are basic cytoarchitectonic motifs of the mammalian neocortex. Recent studies reveal that autism is associated with a “minicolumnopathy” defined by decreased columnar width and both a diminished and disrupted peripheral neuropil compartment. This study further characterizes this cortical deficit by comparing minicolumnar widths across layers. Brains from seven autistic patients and an equal number of age‐matched controls were celloidin embedded, serially sectioned at 200 µm and Nissl stained with gallocyanin. Photomicrograph mosaics of the cortex were analyzed with computerized imaging methods to determine minicolumnar width at nine separate neocortical areas: Brodmann Areas (BA) 3b, 4, 9, 10, 11, 17, 24, 43 and 44. Each area was assessed at supragranular, granular and infragranular levels. Autistic subjects had smaller minicolumns whose dimensions varied according to neocortical area. The greatest difference between autistic and control groups was observed in area 44. The interaction of diagnosis × cortical area × lamina (F16,316 = 1.33; P = 0.175) was not significant. Diminished minicolumnar width across deep and superficial neocortical layers most probably reflects involvement of shared constituents among the different layers. In this article we discuss the possible role of double bouquet and pyramidal cells in the translaminar minicolumnar width narrowing observed in autistic subjects.

Low-Frequency Repetitive Transcranial Magnetic Stimulation (rTMS) Affects Event-Related Potential Measures of Novelty Processing in Autism

In our previous study on individuals with autism spectrum disorder (ASD) (Sokhadze et al., Appl Psychophysiol Biofeedback 34:37–51, 2009a) we reported abnormalities in the attention-orienting frontal event-related potentials (ERP) and the sustained-attention centro-parietal ERPs in a visual oddball experiment. These results suggest that individuals with autism over-process information needed for the successful differentiation of target and novel stimuli. In the present study we examine the effects of low-frequency, repetitive Transcranial Magnetic Stimulation (rTMS) on novelty processing as well as behavior and social functioning in 13 individuals with ASD. Our hypothesis was that low-frequency rTMS application to dorsolateral prefrontal cortex (DLFPC) would result in an alteration of the cortical excitatory/inhibitory balance through the activation of inhibitory GABAergic double bouquet interneurons. We expected to find post-TMS differences in amplitude and latency of early and late ERP components. The results of our current study validate the use of low-frequency rTMS as a modulatory tool that altered the disrupted ratio of cortical excitation to inhibition in autism. After rTMS the parieto-occipital P50 amplitude decreased to novel distracters but not to targets; also the amplitude and latency to targets increased for the frontal P50 while decreasing to non-target stimuli. Low-frequency rTMS minimized early cortical responses to irrelevant stimuli and increased responses to relevant stimuli. Improved selectivity in early cortical responses lead to better stimulus differentiation at later-stage responses as was made evident by our P3b and P3a component findings. These results indicate a significant change in early, middle-latency and late ERP components at the frontal, centro-parietal, and parieto-occipital regions of interest in response to target and distracter stimuli as a result of rTMS treatment. Overall, our preliminary results show that rTMS may prove to be an important research tool or treatment modality in addressing the stimulus hypersensitivity characteristic of autism spectrum disorders.