Zhiyong Zhou

Robust Non-Rigid Point Set Registration Using Student's-t Mixture Model

The Students-t mixture model, which is heavily tailed and more robust than the Gaussian mixture model, has recently received great attention on image processing. In this paper, we propose a robust non-rigid point set registration algorithm using the Students-t mixture model. Specifically, first, we consider the alignment of two point sets as a probability density estimation problem and treat one point set as Students-t mixture model centroids. Then, we fit the Students-t mixture model centroids to the other point set which is treated as data. Finally, we get the closed-form solutions of registration parameters, leading to a computationally efficient registration algorithm. The proposed algorithm is especially effective for addressing the non-rigid point set registration problem when significant amounts of noise and outliers are present. Moreover, less registration parameters have to be set manually for our algorithm compared to the popular coherent points drift (CPD) algorithm. We have compared our algorithm with other state-of-the-art registration algorithms on both 2D and 3D data with noise and outliers, where our non-rigid registration algorithm showed accurate results and outperformed the other algorithms.

Direct point-based registration for precise non-rigid surface matching using Student’s-t mixture model

Abstract One of the main challenges in the non-rigid surface matching is to match complex surfaces with absence of salient landmarks (marker-less) and salient structures (structure-less). We propose an accurate non-rigid surface registration method, called DSMM, to match complex surfaces based on a dense point-to-point correspondence alignment. The key idea of our approach is to model the correspondences on surfaces by using Student’s-t mixture model and represent local spatial structures via Dirichlet distribution and the directional springs. Firstly, we formulate the problem of alignment of two point sets as a probability density estimate, modeling one set as Student’s-t mixture model centroids, and the other one as observation data. We subsequently incorporate spatial representations of vertices on the surfaces into the prior probability of the finite Student’s-t mixture model by exploiting the Dirichlet distribution and Dirichlet law. We later explicitly add an additional structure regularization to get an approximate isometric and near-conformal transformation. Finally, we obtain closed-form solutions of registration parameters using Expectation Maximization (EM) framework, leading to a computationally efficient registration method. We compare DSMM with other state-of-the-art direct point-based non-rigid surface matching methods based on finite mixture models on artificial shapes with large deformation and real complex shapes from various segmented brain structures. DSMM demonstrates its statistical accuracy and robustness, outperforming the competing

A multilevel-ROI-features-based machine learning method for detection of morphometric biomarkers in Parkinson’s disease

Machine learning methods have been widely used in recent years for detection of neuroimaging biomarkers in regions of interest (ROIs) and assisting diagnosis of neurodegenerative diseases. The innovation of this study is to use multilevel-ROI-features-based machine learning method to detect sensitive morphometric biomarkers in Parkinsons disease (PD). Specifically, the low-level ROI features (gray matter volume, cortical thickness, etc.) and high-level correlative features (connectivity between ROIs) are integrated to construct the multilevel ROI features. Filter- and wrapper- based feature selection method and multi-kernel support vector machine (SVM) are used in the classification algorithm. T1-weighted brain magnetic resonance (MR) images of 69 PD patients and 103 normal controls from the Parkinsons Progression Markers Initiative (PPMI) dataset are included in the study. The machine learning method performs well in classification between PD patients and normal controls with an accuracy of 85.78%, a specificity of 87.79%, and a sensitivity of 87.64%. The most sensitive biomarkers between PD patients and normal controls are mainly distributed in frontal lobe, parental lobe, limbic lobe, temporal lobe, and central region. The classification performance of our method with multilevel ROI features is significantly improved comparing with other classification methods using single-level features. The proposed method shows promising identification ability for detecting morphometric biomarkers in PD, thus confirming the potentiality of our method in assisting diagnosis of the disease.

Examining Brain Morphometry Associated with Self-Esteem in Young Adults Using Multilevel-ROI-Features-Based Classification Method

Purpose: This study is to exam self-esteem related brain morphometry on brain magnetic resonance (MR) images using multilevel-features-based classification method. Method: The multilevel region of interest (ROI) features consist of two types of features: (i) ROI features, which include gray matter volume, white matter volume, cerebrospinal fluid volume, cortical thickness, and cortical surface area, and (ii) similarity features, which are based on similarity calculation of cortical thickness between ROIs. For each feature type, a hybrid feature selection method, comprising of filter-based and wrapper-based algorithms, is used to select the most discriminating features. ROI features and similarity features are integrated by using multi-kernel support vector machines (SVMs) with appropriate weighting factor. Results: The classification performance is improved by using multilevel ROI features with an accuracy of 96.66%, a specificity of 96.62%, and a sensitivity of 95.67%. The most discriminating ROI features that are related to self-esteem spread over occipital lobe, frontal lobe, parietal lobe, limbic lobe, temporal lobe, and central region, mainly involving white matter and cortical thickness. The most discriminating similarity features are distributed in both the right and left hemisphere, including frontal lobe, occipital lobe, limbic lobe, parietal lobe, and central region, which conveys information of structural connections between different brain regions. Conclusion: By using ROI features and similarity features to exam self-esteem related brain morphometry, this paper provides a pilot evidence that self-esteem is linked to specific ROIs and structural connections between different brain regions.

Accurate and Robust Non-rigid Point Set Registration using Student’s-t Mixture Model with Prior Probability Modeling

A new accurate and robust non-rigid point set registration method, named DSMM, is proposed for non-rigid point set registration in the presence of significant amounts of missing correspondences and outliers. The key idea of this algorithm is to consider the relationship between the point sets as random variables and model the prior probabilities via Dirichlet distribution. We assign the various prior probabilities of each point to its correspondences in the Student’s-t mixture model. We later incorporate the local spatial representation of the point sets by representing the posterior probabilities in a linear smoothing filter and get closed-form mixture proportions, leading to a computationally efficient registration algorithm comparing to other Student’s-t mixture model based methods. Finally, by introducing the hidden random variables in the Bayesian framework, we propose a general mixture model family for generalizing the mixture-model-based point set registration, where the existing methods can be considered as members of the proposed family. We evaluate DSMM and other state-of-the-art finite mixture models based point set registration algorithms on both artificial point set and various 2D and 3D point sets, where DSMM demonstrates its statistical accuracy and robustness, outperforming the competing algorithms.

A real-time wireless wearable electroencephalography system based on Support Vector Machine for encephalopathy daily monitoring

Wearable electroencephalography systems of out-of-hospital can both provide complementary recordings and offer several benefits over long-term monitoring. However, several limitations were present in these new-born systems, for example, uncomfortable for wearing, inconvenient for retrieving the recordings by patients themselves, unable to timely provide accurate classification, and early warning information. Therefore, we proposed a wireless wearable electroencephalography system for encephalopathy daily monitoring, named as Brain-Health, which focused on the following three points: (a) the monitoring device integrated with electroencephalography acquisition sensors, signal processing chip, and Bluetooth, attached to a sport hat or elastic headband; (b) the mobile terminal with dedicated application, which is not only for continuous recording and displaying electroencephalography signal but also for early warning in real time; and (c) the encephalopathy’s classification algorithm based on intelligent Support Vector Machine, which is used in a new application of wearable electroencephalography for encephalopathy daily monitoring. The results showed a high mean accuracy of 91.79% and 93.89% in two types of classification for encephalopathy. In conclusion, good performance of our Brain-Health system indicated the feasibility and effectiveness for encephalopathy daily monitoring and patients’ health self-management.

Combining SENSE and reduced field-of-view for high-resolution diffusion weighted magnetic resonance imaging

BackgroundIn diffusion-weighted magnetic resonance imaging (DWI) using single-shot echo planar imaging (ss-EPI), both reduced field-of-view (FOV) excitation and sensitivity encoding (SENSE) alone can increase in-plane resolution to some degree. However, when the two techniques are combined to further increase resolution without pronounced geometric distortion, the resulted images are often corrupted by high level of noise and artifact due to the numerical restriction in SENSE. Hence, this study is aimed to provide a reconstruction method to deal with this problem.MethodsThe proposed reconstruction method was developed and implemented to deal with the high level of noise and artifact in the combination of reduced FOV imaging and traditional SENSE, in which all the imaging data were considered jointly by incorporating the motion induced phase variations among excitations. The in vivo human spine diffusion images from ten subjects were acquired at 1.5xa0T and reconstructed using the proposed method, and compared with SENSE magnitude average results for a range of reduction factors in reduced FOV. These images were evaluated by two radiologists using visual scores (considering distortion, noise and artifact levels) from 1 to 10.ResultsThe proposed method was able to reconstruct images with greatly reduced noise and artifact compared to SENSE magnitude average. The mean g-factors were maintained close to 1 along with enhanced signal-to-noise ratio efficiency. The image quality scores of the proposed method were significantly higher (Pu2009<u20090.01) than SENSE magnitude average for all the evaluated reduction factors.ConclusionThe proposed method can improve the combination of SENSE and reduced FOV for high-resolution ss-EPI DWI with reduced noise and artifact.

Vessel segmentation using prior shape based on tensor analysis for inhomogeneous intensity and weak-edge images

Blood vessel segmentation is a key component for various clinical applications. In this paper, we present a novel method for vessel segmentation by using a prior shape based on tensor analysis and then incorporate it in a level-set-based segmentation method. We firstly introduce the prior shape via tensor analysis, which formulates the fractional anisotropy and anisotropic character of the mechanical tensor. Comparing to conventional statistical prior shape models, the main advantage of the proposed prior shape is that it directly derives from the given clinical images via tensor analysis, instead of statistical shape from a training sample set, leading to a simple and practice method for complex vascular structures. We subsequently explicitly incorporate the prior shape in our hybrid energy function, which enforces the segmentation depending on the joint influence of the region-homogeneity, gradient (edge), and the proposed prior shape. We validate our method both on the synthetic images and multimodal clinical images, which shows that our method outperforms the competing methods.

Examining population differences in cerebral morphometry between Chinese and Indian undergraduate students

The aim of this study is to examine potential population differences in brain morphometry using magnetic resonance imaging (MRI). Thirty-six Chinese and thirty-two Indian undergraduate students are included in this study. All images are processed using BrainLab toolbox to obtain the morphometric values of gray matter volume, cortical thickness, and cortical surface area in each region of interest (ROI). We use ROI-based analysis to investigate ethnic differences using the three types of measurements. Cerebral variations of the brain between Chinese and Indian groups are mostly distributed in the frontal lobe, temporal lobe, and occipital lobe. Subgroup analysis reveals sex differences between the two groups. Our study demonstrates population-related differences in brain morphometry (gray matter volume, cortical thickness, and cortical surface area) between Chinese and Indian undergraduates.

Computer aided analysis of cognitive disorder in patients with Parkinsonism using machine learning method with multilevel ROI-based features

This paper proposes to use multilevel ROI-based features and machine learning method to improve the accuracy of qualitative recognition of mild cognitive disorder in parkinsonism. 77 Parkinsons patients and 32 normal controls with neuropsychological assessments and structural magnetic resonance images from the Parkinsons Progression Markers Initiative dataset are tested. Specifically, the BrainLab software is used to process images and measure volume of gray matter, thickness of the cortex, and surface area of the cortex at each region of interest (ROI). We utilize t-test, support vector machine (SVM), and minimum redundancy and maximum relevance (mRMR) methods conjunctively to select features and get the optimal features and the classifier. The experimental results reveal that our method with multilevel ROI-based features gives significant improvement of the classification performance compared with other methods using single-level ROI-based features (i.e., using only volume of gray matter, thickness of cortex, or surface area of cortex).