Alzheimer's disease(AD) is being the burden of society and family. Applying computing-aided strategies to reveal its pathology is one of the research highlights. Plasma neurofilament light (NFL) is an emerging noninvasive and economic biomarker for AD molecular pathology. It is valuable to reveal the correlations between the plasma NFL levels and neurodegeneration, especially hippcampal deformations at the preclinical stage. The negative correlation between plasma NFL levels and hippocampal volumes has been documented. However, the relationship between the plasma NFL levels and the hippocampal morphometry details at the preclinical stage is still elusive. This study seeks to demonstrate the capacity of our proposed surface-based hippocampal morphometry system to discern the plasma NFL positive (NFL+>41.9 pg/L) level and plasma NFL negative (NFL-<41.9pg/L) level and illustrate its superiority to the hippocampal volume measurement by drawing the cohort of 154 CU middle aged and elderly adults. We also apply this morphometry measure and a proposed sparse coding based classification algorithm to classify CU individuals with NFL+ and NFL- levels. Experimental results show that the proposed hippocampal morphometry system offers stronger statistical power to discriminate CU subjects with NFL+ and NFL- levels, comparing with the hippocampal volume measure. Furthermore, this system can discriminate plasma NFL levels in CU individuals (Accuracy=0.86). Both the group level and individual level analysis results indicate that the association between plasma NFL levels and the hippocampal shapes can be mapped at the preclinical stage.

Dynamic PET imaging provides superior physiological information than conventional static PET imaging. However, the dynamic information is gained at the cost of a long scanning protocol; this limits the clinical application of dynamic PET imaging. We developed a modified Logan reference plot model to shorten the acquisition procedure in dynamic PET imaging by omitting the early-time information necessary for the conventional reference Logan model. The proposed model is accurate theoretically, but the straightforward approach raises the sampling problem in implementation and results in noisy parametric images. We then designed a self-supervised convolutional neural network to increase the noise performance of parametric imaging, with dynamic images of only a single subject for training. The proposed method was validated via simulated and real dynamic [Formula: see text]-fallypride PET data. Results showed that it accurately estimated the distribution volume ratio (DVR) in dynamic PET with a shortened scanning protocol, e.g., 20 minutes, where the estimations were comparable with those obtained from a standard dynamic PET study of 120 minutes of acquisition. Further comparisons illustrated that our method outperformed the shortened Logan model implemented with Gaussian filtering, regularization, BM4D and the 4D deep image prior methods in terms of the trade-off between bias and variance. Since the proposed method uses data acquired in a short period of time upon the equilibrium, it has the potential to add clinical values by providing both DVR and Standard Uptake Value (SUV) simultaneously. It thus promotes clinical applications of dynamic PET studies when neuronal receptor functions are studied.

To quantitatively determining the temporal ordering of abnormal age onsets (AAO) among various biomarkers for Alzheimer's disease (AD), we introduced a computational Monte-Carlo simulation (CMCS) to statistically examine such ordering of an AAO pair or over all AAOs. The CMCS 1) simulates longitudinal data, estimates AAO for each iteration, and finally assesses the type-I error of an AAO pair or all AAO ordering. Using hippocampus volume (VHC), cerebral glucose hypometabolic convergence index (HCI), plasma neurofilament light (NfL), mini-mental state exam (MMSE), the auditory verbal learning test-long term memory (AVLT-LTM), short term memory (AVLT-STM) and clinical-dementia rating sum of box scale (CDR-SOB) from 382 mild cognitive impairment converters and non-converters, the CMCS estimated type-I error for the earlier AAO of VHC, AVLT_STM and AVLT_LTM each than MMSE was significant (pHC≤ AVLT_STM ≤ AVLT_LTM < HCI ≤ MMSE ≤ CDR-SOB ≤ NfL was p = 0.012. These findings showed that our CMCS is capable of providing statistical inferences for quantifying AAO ordering which has important implications in advancing our understanding of AD.

Many real-world applications have to tackle the Positive-Unlabeled (PU) learning problem, i.e., learning binary classifiers from a large amount of unlabeled data and a few labeled positive examples. While current state-of-the-art methods employ importance reweighting to design various biased or unbiased risk estimators, they completely ignored the learning capability of the model itself, which could provide reliable supervision. This motivates us to propose a novel Self-PU learning framework, which seamlessly integrates PU learning and self-training. Self-PU highlights three “self”-oriented building blocks: a self-paced training algorithm that adaptively discovers and augments confident positive/negative examples as the training proceeds; a self-reweighted, instance-aware loss; and a self-distillation scheme that introduces teacher-students learning as an effective regularization for PU learning. We demonstrate the state-of-the-art performance of Self-PU on common PU learning benchmarks (MNIST and CIFAR10), which compare favorably against the latest competitors. Moreover, we study a real-world application of PU learning, i.e., classifying brain images of Alzheimer’s Disease. Self-PU obtains significantly improved results on the renowned Alzheimer’s Disease Neuroimaging Initiative (ADNI) database over existing methods.

The alterations of brain structures and functions have been considered closely correlated to the change of cognitive performance due to neurodegenerative diseases such as Alzheimer's disease. In this paper, we introduce a variational framework to compute the optimal transformation (OT) in 3D space and propose a univariate neuroimaging index based on OT to measure such alterations. We compute the OT from each image to a template and measure the Wasserstein distance between them. By comparing the distances from all the images to the common template, we obtain a concise and informative index for each image. Our framework makes use of the Newton's method, which reduces the computational cost and enables itself to be applicable to large-scale datasets. The proposed work is a generic approach and thus may be applicable to various volumetric brain images, including structural magnetic resonance (sMR) and fluorodeoxyglucose positron emission tomography (FDG-PET) images. In the classification between Alzheimer's disease patients and healthy controls, our method achieves an accuracy of 82:30% on the Alzheimers Disease Neuroimaging Initiative (ADNI) baseline sMRI dataset and outperforms several other indices. On FDG-PET dataset, we boost the accuracy to 88:37% by leveraging pairwise Wasserstein distances. In a longitudinal study, we obtain a 5% significance with p-value = 1:13 ×105 in a t-test on FDG-PET. The results demonstrate a great potential of the proposed index for neuroimage analysis and the precision medicine research.

Structure learning of Bayesian Networks (BNs) is an important topic in machine learning. Driven by modern applications in genetics and brain sciences, accurate and efficient learning of large-scale BN structures from high-dimensional data becomes a challenging problem. To tackle this challenge, we propose a Sparse Bayesian Network (SBN) structure learning algorithm that employs a novel formulation involving one L1-norm penalty term to impose sparsity and another penalty term to ensure that the learned BN is a Directed Acyclic Graph--a required property of BNs. Through both theoretical analysis and extensive experiments on 11 moderate and large benchmark networks with various sample sizes, we show that SBN leads to improved learning accuracy, scalability, and efficiency as compared with 10 existing popular BN learning algorithms. We apply SBN to a real-world application of brain connectivity modeling for Alzheimer's disease (AD) and reveal findings that could lead to advancements in AD research.

Given a single index, the receiver operational characteristic (ROC) curve analysis is routinely utilized for characterizing performances in distinguishing two conditions/groups in terms of sensitivity and specificity. Given the availability of multiple data sources (referred to as multi-indices), such as multimodal neuroimaging data sets, cognitive tests, and clinical ratings and genomic data in Alzheimer’s disease (AD) studies, the single-index-based ROC underutilizes all available information. For a long time, a number of algorithmic/analytic approaches combining multiple indices have been widely used to simultaneously incorporate multiple sources. In this study, we propose an alternative for combining multiple indices using logical operations, such as “AND,” “OR,” and “at least n” (where n is an integer), to construct multivariate ROC (multiV-ROC) and characterize the sensitivity and specificity statistically associated with the use of multiple indices. With and without the “leave-one-out” cross-validation, we used two data sets from AD studies to showcase the potentially increased sensitivity/specificity of the multiV-ROC in comparison to the single-index ROC and linear discriminant analysis (an analytic way of combining multi-indices). We conclude that, for the data sets we investigated, the proposed multiV-ROC approach is capable of providing a natural and practical alternative with improved classification accuracy as compared to univariate ROC and linear discriminant analysis.

Independent component analysis (ICA) has been widely applied to the analysis of fMRI data. Accurate estimation of the number of independent components (ICs) in fMRI data is critical to reduce over/underfitting. Various methods based on information theoretic criteria (ITC) have been used to estimate the intrinsic dimension of fMRI data. An important assumption of ITC is that the noise is purely white. However, this assumption is often violated by the existence of temporally correlated noise in fMRI data. In this study, we introduced a filtering method into the order selection to remove the autocorrelation from the colored noise by using the whitening filter proposed by Prudon and Weisskoff. Results of the simulated data show that the filtering method has strong robustness to noise and significantly improves the accuracy of order selection from data with colored noise. Moreover, the multifiltering method proposed by us was applied to real fMRI data to improve the performance of ITC. Results of the real fMRI data show that the proposed method can alleviate the overestimation due to the autocorrelation of colored noise. We further compared the stability of IC estimates of real fMRI data at order estimated by minimum description length criterion based on the filtered and unfiltered data by using the software package ICASSO. Results show that ICA yields more stable IC estimates using the reduced order by filtering.

Recent studies have shown that Alzheimer's disease (AD) is related to alteration in brain connectivity networks. One type of connectivity, called effective connectivity, defined as the directional relationship between brain regions, is essential to brain function. However, there have been few studies on modeling the effective connectivity of AD and characterizing its difference from normal controls (NC). In this paper, we investigate the sparse Bayesian Network (BN) for effective connectivity modeling. Specifically, we propose a novel formulation for the structure learning of BNs, which involves one L1-norm penalty term to impose sparsity and another penalty to ensure the learned BN to be a directed acyclic graph - a required property of BNs. We show, through both theoretical analysis and extensive experiments on eleven moderate and large benchmark networks with various sample sizes, that the proposed method has much improved learning accuracy and scalability compared with ten competing algorithms. We apply the proposed method to FDG-PET images of 42 AD and 67 NC subjects, and identify the effective connectivity models for AD and NC, respectively. Our study reveals that the effective connectivity of AD is different from that of NC in many ways, including the global-scale effective connectivity, intra-lobe, interlobe, and inter-hemispheric effective connectivity distributions, as well as the effective connectivity associated with specific brain regions. These findings are consistent with known pathology and clinical progression of AD, and will contribute to AD knowledge discovery.

Diagnosis of Alzheimer's disease (AD) at the early stage of the disease development is of great clinical importance. Current clinical assessment that relies primarily on cognitive measures proves low sensitivity and specificity. The fast growing neuroimaging techniques hold great promise. Research so far has focused on single neuroimaging modalities. However, as different modalities provide complementary measures for the same disease pathology, fusion of multi-modality data may increase the statistical power in identification of disease-related brain regions. This is especially true for early AD, at which stage the disease-related regions are most likely to be weak-effect regions that are difficult to be detected from a single modality alone. We propose a sparse composite linear discriminant analysis model (SCLDA) for identification of disease-related brain regions of early AD from multi-modality data. SCLDA uses a novel formulation that decomposes each LDA parameter into a product of a common parameter shared by all the modalities and a parameter specific to each modality, which enables joint analysis of all the modalities and borrowing strength from one another. We prove that this formulation is equivalent to a penalized likelihood with non-convex regularization, which can be solved by the DC ((difference of convex functions) programming. We show that in using the DC programming, the property of the non-convex regularization in terms of preserving weak-effect features can be nicely revealed. We perform extensive simulations to show that SCLDA outperforms existing competing algorithms on feature selection, especially on the ability for identifying weak-effect features. We apply SCLDA to the Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET) images of 49 AD patients and 67 normal controls (NC). Our study identifies disease-related brain regions consistent with findings in the AD literature.

Effective diagnosis of Alzheimer's disease (AD), the most common type of dementia in elderly patients, is of primary importance in biomedical research. Recent studies have demonstrated that AD is closely related to the structure change of the brain network, i.e., the connectivity among different brain regions. The connectivity patterns will provide useful imaging-based biomarkers to distinguish Normal Controls (NC), patients with Mild Cognitive Impairment (MCI), and patients with AD. In this paper, we investigate the sparse inverse covariance estimation technique for identifying the connectivity among different brain regions. In particular, a novel algorithm based on the block coordinate descent approach is proposed for the direct estimation of the inverse covariance matrix. One appealing feature of the proposed algorithm is that it allows the user feedback (e.g., prior domain knowledge) to be incorporated into the estimation process, while the connectivity patterns can be discovered automatically. We apply the proposed algorithm to a collection of FDG-PET images from 232 NC, MCI, and AD subjects. Our experimental results demonstrate that the proposed algorithm is promising in revealing the brain region connectivity differences among these groups.

Recent advances in neuroimaging techniques provide great potentials for effective diagnosis of Alzheimer’s disease (AD), the most common form of dementia. Previous studies have shown that AD is closely related to alternation in the functional brain network, i.e., the functional connectivity among different brain regions. In this paper, we consider the problem of learning functional brain connectivity from neuroimaging, which holds great promise for identifying image-based markers used to distinguish Normal Controls (NC), patients with Mild Cognitive Impairment (MCI), and patients with AD. More specifically, we study sparse inverse covariance estimation (SICE), also known as exploratory Gaussian graphical models, for brain connectivity modeling. In particular, we apply SICE to learn and analyze functional brain connectivity patterns from different subject groups, based on a key property of SICE, called the “monotone property” we established in this paper. Our experimental results on neuroimaging PET data of 42 AD, 116 MCI, and 67 NC subjects reveal several interesting connectivity patterns consistent with literature findings, and also some new patterns that can help the knowledge discovery of AD.

Effective diagnosis of Alzheimer's disease (AD) is of primary importance in biomedical research. Recent studies have demonstrated that neuroimaging parameters are sensitive and consistent measures of AD. In addition, genetic and demographic information have also been successfully used for detecting the onset and progression of AD. The research so far has mainly focused on studying one type of data source only. It is expected that the integration of heterogeneous data (neuroimages, demographic, and genetic measures) will improve the prediction accuracy and enhance knowledge discovery from the data, such as the detection of biomarkers. In this paper, we propose to integrate heterogeneous data for AD prediction based on a kernel method. We further extend the kernel framework for selecting features (biomarkers) from heterogeneous data sources. The proposed method is applied to a collection of MRI data from 59 normal healthy controls and 59 AD patients. The MRI data are pre-processed using tensor factorization. In this study, we treat the complementary voxel-based data and region of interest (ROI) data from MRI as two data sources, and attempt to integrate the complementary information by the proposed method. Experimental results show that the integration of multiple data sources leads to a considerable improvement in the prediction accuracy. Results also show that the proposed algorithm identifies biomarkers that play more significant roles than others in AD diagnosis.

Optimal sampling schedule (OSS) design for both image-derived input and output functions in tracer kinetic modeling with positron emission tomography (PET) is investigated. This problem is very important in noninvasive PET dynamic cardiac studies where both the input function, i.e., the plasma time-activity curve (PTAC), and the output function, i.e., the tissue time-activity curve (TTAC), are obtained simultaneously from the same sequence of PET images. The integral PET measurement is used in this study. The spillover correction for the cross contaminations in cardiac studies is incorporated into the OSS design procedure. A new target function based on the D-optimal criterion involving both the input and output sensitivity functions is proposed. The fluorodeoxyglucose (FDG) model and a six-parameter PTAC model are used to illustrate the simultaneous OSS design for both the PTAC and TTAC. An OSS design consisting of six different scanning intervals is derived. Computer simulations are performed based on the estimated parameters from real studies to evaluate the effectiveness of the OSS. The double modeling approach is used in parameter estimation to simultaneously estimate the parameters involved. The results have shown that, for a wide range of parameter variations, the OSS is as effective as a conventional sampling schedule (CSS) and comparable parameter estimates can be obtained. Compared with the use of the CSS, the use of the OSS leads to an approximately 70% reduction in the storage space and data processing time.

In this paper, we developed and tested strategies for estimating myocardial blood flow (MBF) and generating MBF parametric images using positron emission tomography (PET), N-13 ammonia, and the generalized linear least square (GLLS) method. GLLS was generalized to the general linear compartment model, modified for the correction of spillover, validated using simulated N-13 ammonia data, and examined using PET data from several patient studies. In comparison to the standard model-fitting procedure, the GLLS method provided similar accuracy and superior computational speed.

Advanced medical imaging requires storage of large quantities of digitized clinical data. These data must be stored in such a way that their retrieval does not impair the clinician's ability to make a diagnosis. In this paper, we propose the theory and algorithm for near (or diagnostically) lossless dynamic image data compression. Taking advantage of domain-specific knowledge related to medical imaging, the medical practice and the dynamic imaging modality, a compression ratio greater than 80:1 is achieved. The high compression ratios are achieved by the proposed compression algorithm through three stages: 1) addressing temporal redundancies in the data through application of image optimal sampling, 2) addressing spatial redundancies in the data through cluster analysis, and 3) efficient coding of image data using standard still-image compression techniques. To illustrate the practicality of the proposed compression algorithm, a simulated positron emission tomography (PET) study using the fluoro-deoxy-glucose (FDG) tracer is presented. Realistic dynamic image data are generated by "virtual scanning" of a simulated brain phantom as a real PET scanner. These data are processed using the conventional [8] and proposed algorithms as well as the techniques for storage and analysis. The resulting parametric images obtained from the conventional and proposed approaches are subsequently compared to evaluate the proposed compression algorithm. As a result of this study, storage space for dynamic image data is able to be reduced by more than 95%, without loss in diagnostic quality. Therefore, the proposed theory and algorithm are expected to be very useful in medical image database management and telecommunication.

An optimal image sampling schedule for tracer dynamic studies with positron emission tomography (PET) is proposed. This schedule incorporates the characteristics of PET measurement and uses a new cost function and the D-optimal criterion. A detailed case study of the estimation of the local cerebral metabolic rate of glucose (LCMRGLc) using the tracer fluorodeoxyglucose (FDG) and the four-parameter FDG model is presented. As the sampling schedule designed requires only four dynamic images, the storage space and data processing time are greatly reduced, while the precision of the parameter estimates is almost the same as that achieved with a commonly used schedule. The effects of intersubject and intrasubject parameter variations on parameter estimation with the use of this optimal sampling schedule are investigated by computer simulation. The simulation results show that the estimation of parameters is sufficiently robust with respect to these intersubject and intrasubject variations. The optimal sampling schedule is quite suitable therefore for PET regional parameter estimation, as well as for image-wide parameter estimation, for different subjects.

Measurement of the local cerebral metabolic rate of glucose (LCMRGlc) and the individual rate constant parameters of the [(18 )F]2-fluoro-2-deoxy-D-glucose (FDG) model can provide a clearer understanding and insight to the physiological processes in the human brain, and a quicker and more accurate means of diagnosis in clinical applications. A systematic study using simulated and clinical tissue time activity data is presented to evaluate several existing and newly developed major algorithms used for determining LCMRGlc and the individual rate constants from positron emission tomography dynamic data. The computational and statistical properties of the autoradiographic approach, weighted and unweighted nonlinear least squares methods, Patlak graphic approach, weighted integration method, linear least squares and generalized linear least squares methods are investigated and discussed in this paper.