Mohammed Goryawala

A NEW PARAMETRIC FEATURE DESCRIPTOR FOR THE CLASSIFICATION OF EPILEPTIC AND CONTROL EEG RECORDS IN PEDIATRIC POPULATION

This study evaluates the sensitivity, specificity and accuracy in associating scalp EEG to either control or epileptic patients by means of artificial neural networks (ANNs) and support vector machines (SVMs). A confluence of frequency and temporal parameters are extracted from the EEG to serve as input features to well-configured ANN and SVM networks. Through these classification results, we thus can infer the occurrence of high-risk (epileptic) as well as low risk (control) patients for potential follow up procedures.

A 3-D Liver Segmentation Method with Parallel Computing for Selective Internal Radiation Therapy

This study describes a new 3-D liver segmentation method in support of the selective internal radiation treatment as a treatment for liver tumors. This 3-D segmentation is based on coupling a modified k-means segmentation method with a special localized contouring algorithm. In the segmentation process, five separate regions are identified on the computerized tomography image frames. The merit of the proposed method lays in its potential to provide fast and accurate liver segmentation and 3-D rendering as well as in delineating tumor region(s), all with minimal user interaction. Leveraging of multicore platforms is shown to speed up the processing of medical images considerably, making this method more suitable in clinical settings. Experiments were performed to assess the effect of parallelization using up to 442 slices. Empirical results, using a single workstation, show a reduction in processing time from 4.5 h to almost 1 h for a 78% gain. Most important is the accuracy achieved in estimating the volumes of the liver and tumor region(s), yielding an average error of less than 2% in volume estimation over volumes generated on the basis of the current manually guided segmentation processes. Results were assessed using the analysis of variance statistical analysis.

An optimal decisional space for the classification of alzheimer's disease and mild cognitive impairment

This paper proposes to combine MRI data with a neuropsychological test, mini-mental state examination (MMSE), as input to a multi-dimensional space for the classification of Alzheimers disease (AD) and its prodromal stages-mild cognitive impairment (MCI) including amnestic MCI (aMCI) and nonamnestic MCI (naMCI). The decisional space is constructed using those features deemed statistically significant through an elaborate feature selection and ranking mechanism. FreeSurfer was used to calculate 55 volumetric variables, which were then adjusted for intracranial volume, age and education. The classification results obtained using support vector machines are based on twofold cross validation of 50 independent and randomized runs. The study included 59 AD, 67 aMCI, 56 naMCI, and 127 cognitively normal (CN) subjects. The study shows that MMSE scores contain the most discriminative power of AD, aMCI, and naMCI. For AD versus CN, the two most discriminative volumetric variables (right hippocampus and left inferior lateral ventricle), when combined with MMSE scores, provided an average accuracy of 92.4% (sensitivity: 84.0%; specificity: 96.1%). MMSE scores are found to improve all classifications with accuracy increments of 8.2% and 12% for aMCI versus CN and naMCI versus CN, respectively. Results also show that brain atrophy is almost evenly seen on both sides of the brain for AD subjects, which is different from right-side dominance for aMCI and left-side dominance for naMCI. Furthermore, hippocampal atrophy is seen to be the most significant for aMCI, while Accumbens area and ventricle are most significant for naMCI.

Thermal Imaging as a Biometrics Approach to Facial Signature Authentication

A new thermal imaging framework with unique feature extraction and similarity measurements for face recognition is presented. The research premise is to design specialized algorithms that would extract vasculature information, create a thermal facial signature, and identify the individual. The proposed algorithm is fully integrated and consolidates the critical steps of feature extraction through the use of morphological operators, registration using the Linear Image Registration Tool, and matching through unique similarity measures designed for this task. The novel approach at developing a thermal signature template using four images taken at various instants of time ensured that unforeseen changes in the vasculature over time did not affect the biometric matching process as the authentication process relied only on consistent thermal features. Thirteen subjects were used for testing the developed technique on an in-house thermal imaging system. The matching using the similarity measures showed an average accuracy of 88.46% for skeletonized signatures and 90.39% for anisotropically diffused signatures. The highly accurate results obtained in the matching process clearly demonstrate the ability of the thermal infrared system to extend in application to other thermal-imaging-based systems. Empirical results applying this approach to an existing database of thermal images prove this assertion.

Scalp EEG brain functional connectivity networks in pediatric epilepsy

This study establishes a new data-driven approach to brain functional connectivity networks using scalp EEG recordings for classifying pediatric subjects with epilepsy from pediatric controls. Graph theory is explored on the functional connectivity networks of individuals where three different sets of topological features were defined and extracted for a thorough assessment of the two groups. The raters opinion on the diagnosis could also be taken into consideration when deploying the general linear model (GLM) for feature selection in order to optimize classification. Results demonstrate the existence of statistically significant (p<0.05) changes in the functional connectivity of patients with epilepsy compared to those of control subjects. Furthermore, clustering results demonstrate the ability to discriminate pediatric epilepsy patients from control subjects with an initial accuracy of 87.5%, prior to initiating the feature selection process and without taking into consideration the clinical raters opinion. Otherwise, leave-one-out cross validation (LOOCV) showed a significant increase in the classification accuracy to 96.87% in epilepsy diagnosis.

Computer-assisted quantification of lung tumors in respiratory gated PET/CT images: phantom study

A computer-aided method was developed to automatically localize tumors in lung PET images of discrete bins within the breathing cycle, followed by an algorithm that registers all the information of a complete respiratory cycle into a single reference bin. Four registration/integration algorithms: Centroid Based, Intensity Based, Rigid Body, and Optical Flow registration were compared as well as two registration schemes: Direct scheme and Successive scheme. Validation was demonstrated by conducting experiments with the computerized 4D NCAT phantom and with a dynamic lung–chest phantom imaged using a GE PET/CT System. Iterations were conducted on different size simulated tumors. Static tumors without respiratory motion were used as gold standard; quantitative results were compared with respect to tumor activity concentration, cross-correlation coefficient, relative noise level, and computation time. After motion correction, the best compromise between short PET scan time and reduced image noise can be achieved, while quantification and clinical analysis become faster and more precise.

Significance of Normalization on Anatomical MRI Measures in Predicting Alzheimer’s Disease

This study establishes a new approach for combining neuroimaging and neuropsychological measures for an optimal decisional space to classify subjects with Alzheimers disease (AD). This approach relies on a multivariate feature selection method with different MRI normalization techniques. Subcortical volume, cortical thickness, and surface area measures are obtained using MRIs from 189 participants (129 normal controls and 60 AD patients). Statistically significant variables were selected for each combination model to construct a multidimensional space for classification. Different normalization approaches were explored to gauge the effect on classification performance using a support vector machine classifier. Results indicate that the Mini-mental state examination (MMSE) measure is most discriminative among single-measure models, while subcortical volume combined with MMSE is the most effective multivariate model for AD classification. The study demonstrates that subcortical volumes need not be normalized, whereas cortical thickness should be normalized either by intracranial volume or mean thickness, and surface area is a weak indicator of AD with and without normalization. On the significant brain regions, a nearly perfect symmetry is observed for subcortical volumes and cortical thickness, and a significant reduction in thickness is particularly seen in the temporal lobe, which is associated with brain deficits characterizing AD.

Inclusion of neuropsychological scores in atrophy models improves diagnostic classification of alzheimer’s disease and mild cognitive impairment

Brain atrophy in mild cognitive impairment (MCI) and Alzheimers disease (AD) are difficult to demarcate to assess the progression of AD. This study presents a statistical framework on the basis of MRI volumes and neuropsychological scores. A feature selection technique using backward stepwise linear regression together with linear discriminant analysis is designed to classify cognitive normal (CN) subjects, early MCI (EMCI), late MCI (LMCI), and AD subjects in an exhaustive two-group classification process. Results show a dominance of the neuropsychological parameters like MMSE and RAVLT. Cortical volumetric measures of the temporal, parietal, and cingulate regions are found to be significant classification factors. Moreover, an asymmetrical distribution of the volumetric measures across hemispheres is seen for CN versus EMCI and EMCI versus AD, showing dominance of the right hemisphere; whereas CN versus LMCI and EMCI versus LMCI show dominance of the left hemisphere. A 2-fold cross-validation showed an average accuracy of 93.9%, 90.8%, and 94.5%, for the CN versus AD, CN versus LMCI, and EMCI versus AD, respectively. The accuracy for groups that are difficult to differentiate like EMCI versus LMCI was 73.6%. With the inclusion of the neuropsychological scores, a significant improvement (24.59%) was obtained over using MRI measures alone.

An algorithm for PET tumor volume and activity quantification: Without specifying camera's point spread function (PSF)

PURPOSE The authors have developed an algorithm for segmentation and removal of the partial volume effect (PVE) of tumors in positron emission tomography (PET) images. The algorithm accurately measures functional volume (FV) and activity concentration (AC) of tumors independent of the cameras full width half maximum (FWHM). METHODS A novel iterative histogram thresholding (HT) algorithm is developed to segment the tumors in PET images, which have low resolution and suffer from inherent noise in the image. The algorithm is initiated by manually drawing a region of interest (ROI). The segmented tumors are subjected to the iterative deconvolution thresholding segmentation (IDTS) algorithm, where the Van-Citterts method of deconvolution is used for correcting PVE. The IDTS algorithm is fully automated and accurately measures the FV and AC, and stops once it reaches convergence. The convergence criteria or stopping conditions are developed in such a way that the algorithm does not rely on estimating the FWHM of the point spread function (PSF) to perform the deconvolution process. The algorithm described here was tested in phantom studies, where hollow spheres (0.5-16 ml) were used to represent tumors with a homogeneous activity distribution, and an irregular shaped volume was used to represent a tumor with a heterogeneous activity distribution. The phantom studies were performed with different signal to background ratios (SBR) and with different acquisition times (1 min, 3 min, and 5 min). The parameters in the algorithm were also changed (FWHM and matrix size of the Gaussian function) to check the accuracy of the algorithm. Simulated data were also used to test the algorithm with tumors having heterogeneous activity distribution. RESULTS The results show that changing the size and shape of the ROI during initiation of the algorithm had no significant impact on the FV. An average FV overestimation of 30% and an average AC underestimation of 35% were observed for the smallest tumor (0.5 ml) over the entire range of noise and SBR level. The difference in average FV and AC estimations from the actual volumes were less than 5% as the tumor size increased to 16 ml. For tumors with heterogeneous activity profile, the overall volume error was less than 10%. The average overestimation of FV was less than 10% and classification error was around 11%. CONCLUSIONS The algorithm developed herein was extensively tested and is not dependent on accurately quantifying the cameras PSF. This feature demonstrates the robustness of the algorithm and enables it to be applied on a wide range of noise and SBR within an image. The ultimate goal of the algorithm is to be able to be operated independent of the camera type used and the reconstruction algorithm deployed.PURPOSE The authors have developed an algorithm for segmentation and removal of the partial volume effect (PVE) of tumors in positron emission tomography (PET) images. The algorithm accurately measures functional volume (FV) and activity concentration (AC) of tumors independent of the cameras full width half maximum (FWHM). METHODS A novel iterative histogram thresholding (HT) algorithm is developed to segment the tumors in PET images, which have low resolution and suffer from inherent noise in the image. The algorithm is initiated by manually drawing a region of interest (ROI). The segmented tumors are subjected to the iterative deconvolution thresholding segmentation (IDTS) algorithm, where the Van-Citterts method of deconvolution is used for correcting PVE. The IDTS algorithm is fully automated and accurately measures the FV and AC, and stops once it reaches convergence. The convergence criteria or stopping conditions are developed in such a way that the algorithm does not rely on estimating the FWHM of the point spread function (PSF) to perform the deconvolution process. The algorithm described here was tested in phantom studies, where hollow spheres (0.5-16 ml) were used to represent tumors with a homogeneous activity distribution, and an irregular shaped volume was used to represent a tumor with a heterogeneous activity distribution. The phantom studies were performed with different signal to background ratios (SBR) and with different acquisition times (1 min, 3 min, and 5 min). The parameters in the algorithm were also changed (FWHM and matrix size of the Gaussian function) to check the accuracy of the algorithm. Simulated data were also used to test the algorithm with tumors having heterogeneous activity distribution. RESULTS The results show that changing the size and shape of the ROI during initiation of the algorithm had no significant impact on the FV. An average FV overestimation of 30% and an average AC underestimation of 35% were observed for the smallest tumor (0.5 ml) over the entire range of noise and SBR level. The difference in average FV and AC estimations from the actual volumes were less than 5% as the tumor size increased to 16 ml. For tumors with heterogeneous activity profile, the overall volume error was less than 10%. The average overestimation of FV was less than 10% and classification error was around 11%. CONCLUSIONS The algorithm developed herein was extensively tested and is not dependent on accurately quantifying the cameras PSF. This feature demonstrates the robustness of the algorithm and enables it to be applied on a wide range of noise and SBR within an image. The ultimate goal of the algorithm is to be able to be operated independent of the camera type used and the reconstruction algorithm deployed.

A practical guideline for intracranial volume estimation in patients with Alzheimer's disease

BackgroundIntracranial volume (ICV) is an important normalization measure used in morphometric analyses to correct for head size in studies of Alzheimer Disease (AD). Inaccurate ICV estimation could introduce bias in the outcome. The current study provides a decision aid in defining protocols for ICV estimation in patients with Alzheimer disease in terms of sampling frequencies that can be optimally used on the volumetric MRI data, and the type of software most suitable for use in estimating the ICV measure.MethodsTwo groups of 22 subjects are considered, including adult controls (AC) and patients with Alzheimer Disease (AD). Reference measurements were calculated for each subject by manually tracing intracranial cavity by the means of visual inspection. The reliability of reference measurements were assured through intra- and inter- variation analyses. Three publicly well-known software packages (Freesurfer, FSL, and SPM) were examined in their ability to automatically estimate ICV across the groups.ResultsAnalysis of the results supported the significant effect of estimation method, gender, cognitive condition of the subject and the interaction among method and cognitive condition factors in the measured ICV. Results on sub-sampling studies with a 95% confidence showed that in order to keep the accuracy of the interleaved slice sampling protocol above 99%, the sampling period cannot exceed 20 millimeters for AC and 15 millimeters for AD. Freesurfer showed promising estimates for both adult groups. However SPM showed more consistency in its ICV estimation over the different phases of the study.ConclusionsThis study emphasized the importance in selecting the appropriate protocol, the choice of the sampling period in the manual estimation of ICV and selection of suitable software for the automated estimation of ICV. The current study serves as an initial framework for establishing an appropriate protocol in both manual and automatic ICV estimations with different subject populations.