Application of Machine Learning to Arterial Spin Labeling in Mild Cognitive Impairment and Alzheimer Disease

Effects of the Fasting-Postprandial State on Arterial Spin Labeling MRI-Based Cerebral Perfusion Quantification in Alzheimer's Disease

BACKGROUND

The fasting-postprandial state remains an underrecognized confounding factor for quantifying cerebral blood flow (CBF) in the cognitive assessment and differential diagnosis of Alzheimer's disease (AD).

PURPOSE

To investigate the effects of fasting-postprandial state on arterial spin labeling (ASL)-based CBF in AD patients.

STUDY TYPE

Prospective.

SUBJECTS

Ninety-two subjects (mean age = 62.5 ± 6.4 years; females 29.3%), including 30 with AD, 32 with mild cognitive impairment (MCI), and 30 healthy controls (HCs). Differential diagnostic models were developed with a 4:1 training to testing set ratio.

FIELD STRENGTH/SEQUENCE

3-T, T1-weighted imaging using gradient echo and pseudocontinuous ASL imaging using turbo spin echo.

ASSESSMENT

Two ASL scans were acquired to quantify fasting state and postprandial state regional CBFs based on an automated anatomical labeling atlas. Two-way ANOVA was used to assess the effects of fasting/postprandial state and disease state (AD, MCI, and HC) on regional CBF. Pearson's correlation analysis was conducted between regional CBF and cognitive scores (Mini-Mental State Examination [MMSE] and Montreal Cognitive Assessment [MoCA]). The diagnostic performances of the fasting state, postprandial state, and mixed state (random mixing of the fasting and postprandial state CBF) in differential diagnosis of AD were conducted using support vector machine and logistic regression models.

STATISTICAL TESTS

Two-way ANOVA, Pearson's correlation, and area under the curve (AUC) of diagnostic model were performed. P values <0.05 indicated statistical significance.

RESULTS

Fasting-state CBF was correlated with cognitive scores in more brain regions (17 vs. 4 [MMSE] and 15 vs. 9 [MoCA]) and had higher absolute correlation coefficients than postprandial-state CBF. In the differential diagnosis of AD patients from MCI patients and HCs, fasting-state CBF outperformed mixed-state CBF, which itself outperformed postprandial-state CBF.

DATA CONCLUSION

Compared with postprandial CBF, fasting-state CBF performed better in terms of cognitive score correlations and in differentiating AD patients from MCI patients and HCs.

EVIDENCE LEVEL

2 TECHNICAL EFFICACY: Stage 3.

Intracerebral hemodynamic abnormalities in patients with Parkinson's disease: Comparison between multi-delay arterial spin labelling and conventional single-delay arterial spin labelling

PURPOSE

The purpose of this study was to analyze the intracerebral abnormalities of hemodynamics in patients with Parkinson's disease (PD) through arterial spin labelling (ASL) technique with multi-delay ASL (MDASL) and conventional single-delay ASL (SDASL) protocols and to verify the potential clinical application of these features for the diagnosis of PD.

MATERIALS AND METHODS

Perfusion data of the brain obtained using MDASL and SDASL in patients with PD were compared to those obtained in healthy control (HC) subjects. Intergroup comparisons of z-scored cerebral blood flow (zCBF), arterial transit time (zATT) and cerebral blood volume (zCBV) were performed via voxel-based analysis. Performance of these perfusion metrics were estimated using area under the receiver operating characteristic curve (AUC) and compared using Delong test.

RESULTS

A total of 47 patients with PD (29 men; 18 women; mean age, 69.0 ± 7.6 (standard deviation, [SD]) years; range: 50.0-84.0 years) and 50 HC subjects (28 men; 22 women; mean age, 70.1 ± 6.2 [SD] years; range: 50.0-93.0 years) were included. Relative to the uncorrected-zCBF map, the corrected-zCBF map further refined the distributed brain regions in the PD group versus the HC group, manifested as the extension of motor-related regions (PFWE < 0.001). Compared to the HC subjects, patients with PD had elevated zATT and zCBV in the right putamen, a shortened zATT in the superior frontal gyrus, and specific zCBV variations in the left precuneus and the right supplementary motor area (PFWE < 0.001). The corrected-zCBF (AUC, 0.90; 95% confidence interval [CI]: 0.84-0.96) showed better classification performance than uncorrected-zCBF (AUC, 0.84; 95% CI: 0.75-0.92) (P = 0.035). zCBV achieved an AUC of 0.89 (95% CI: 0.82-0.96) and zATT achieved an AUC of 0.66 (95% CI: 0.55-0.77). The integration model of hemodynamic features from MDASL provided improved performance (AUC, 0.97; 95% CI: 0.95-0.98) for the diagnosis of PD by comparison with each perfusion model (P < 0.001).

CONCLUSION

ASL identifies impaired hemodynamics in patients with PD including regional abnormalities of CBF, CBV and ATT, which can better be mapped with MDASL compared to SDASL. These findings provide complementary depictions of perfusion abnormalities in patients with PD and highlight the clinical feasibility of MDASL.

The correlation between changes in gray matter microstructure and cerebral blood flow in Alzheimer's disease

Objective

To investigate the relationship between changes in cerebral blood flow (CBF) and gray matter (GM) microstructure in Alzheimer's disease (AD) and mild cognitive impairment (MCI).

Methods

A recruited cohort of 23 AD patients, 40 MCI patients, and 37 normal controls (NCs) underwent diffusional kurtosis imaging (DKI) for microstructure evaluation and pseudo-continuous arterial spin labeling (pCASL) for CBF assessment. We investigated the differences in diffusion- and perfusion-related parameters across the three groups, including CBF, mean diffusivity (MD), mean kurtosis (MK), and fractional anisotropy (FA). These quantitative parameters were compared using volume-based analyses for the deep GM and surface-based analyses for the cortical GM. The correlation between CBF, diffusion parameters, and cognitive scores was assessed using Spearman coefficients, respectively. The diagnostic performance of different parameters was investigated with k-nearest neighbor (KNN) analysis, using fivefold cross-validation to generate the mean accuracy (mAcc), mean precision (mPre), and mean area under the curve (mAuc).

Results

In the cortical GM, CBF reduction primarily occurred in the parietal and temporal lobes. Microstructural abnormalities were predominantly noted in the parietal, temporal, and frontal lobes. In the deep GM, more regions showed DKI and CBF parametric changes at the MCI stage. MD showed most of the significant abnormalities among all the DKI metrics. The MD, FA, MK, and CBF values of many GM regions were significantly correlated with cognitive scores. In the whole sample, the MD, FA, and MK were associated with CBF in most evaluated regions, with lower CBF values associated with higher MD, lower FA, or lower MK values in the left occipital lobe, left frontal lobe, and right parietal lobe. CBF values performed best (mAuc = 0.876) for distinguishing the MCI from the NC group. Last, MD values performed best (mAuc = 0.939) for distinguishing the AD from the NC group.

Conclusion

Gray matter microstructure and CBF are closely related in AD. Increased MD, decreased FA, and MK are accompanied by decreased blood perfusion throughout the AD course. Furthermore, CBF values are valuable for the predictive diagnosis of MCI and AD. GM microstructural changes are promising as novel neuroimaging biomarkers of AD.

Biomarkers of diagnosis, prognosis, pathogenesis, response to therapy: Convergence or divergence? Lessons from Alzheimer's disease and synucleinopathies

Alzheimer's disease (AD) is the most common disorder associated with cognitive impairment. Recent observations emphasize the pathogenic role of multiple factors inside and outside the central nervous system, supporting the notion that AD is a syndrome of many etiologies rather than a "heterogeneous" but ultimately unifying disease entity. Moreover, the defining pathology of amyloid and tau coexists with many others, such as α-synuclein, TDP-43, and others, as a rule, not an exception. Thus, an effort to shift our AD paradigm as an amyloidopathy must be reconsidered. Along with amyloid accumulation in its insoluble state, β-amyloid is becoming depleted in its soluble, normal states, as a result of biological, toxic, and infectious triggers, requiring a shift from convergence to divergence in our approach to neurodegeneration. These aspects are reflected-in vivo-by biomarkers, which have become increasingly strategic in dementia. Similarly, synucleinopathies are primarily characterized by abnormal deposition of misfolded α-synuclein in neurons and glial cells and, in the process, depleting the levels of the normal, soluble α-synuclein that the brain needs for many physiological functions. The soluble to insoluble conversion also affects other normal brain proteins, such as TDP-43 and tau, accumulating in their insoluble states in both AD and dementia with Lewy bodies (DLB). The two diseases have been distinguished by the differential burden and distribution of insoluble proteins, with neocortical phosphorylated tau deposition more typical of AD and neocortical α-synuclein deposition peculiar to DLB. We propose a reappraisal of the diagnostic approach to cognitive impairment from convergence (based on clinicopathologic criteria) to divergence (based on what differs across individuals affected) as a necessary step for the launch of precision medicine.

MRI assessment of cerebral perfusion in clinical trials

Neurodegenerative mechanisms affect the brain through a variety of processes that are reflected as changes in brain structure and physiology. Although some biomarkers for these changes are well established, others are at different stages of development for use in clinical trials. One of the most challenging biomarkers to harmonize for clinical trials is cerebral blood flow (CBF). There are several magnetic resonance imaging (MRI) methods for quantifying CBF without the use of contrast agents, in particular arterial spin labeling (ASL) perfusion MRI, which has been increasingly applied in clinical trials. In this review, we present ASL MRI techniques, including strategies for implementation across multiple imaging centers, levels of confidence in assessing disease progression and treatment effects, and details of image analysis.

Classification of severe obstructive sleep apnea with cognitive impairment using degree centrality: A machine learning analysis

In this study, we aimed to use voxel-level degree centrality (DC) features in combination with machine learning methods to distinguish obstructive sleep apnea (OSA) patients with and without mild cognitive impairment (MCI). Ninety-nine OSA patients were recruited for rs-MRI scanning, including 51 MCI patients and 48 participants with no mild cognitive impairment. Based on the Automated Anatomical Labeling (AAL) brain atlas, the DC features of all participants were calculated and extracted. Ten DC features were screened out by deleting variables with high pin-correlation and minimum absolute contraction and performing selective operator lasso regression. Finally, three machine learning methods were used to establish classification models. The support vector machine method had the best classification efficiency (AUC = 0.78), followed by random forest (AUC = 0.71) and logistic regression (AUC = 0.77). These findings demonstrate an effective machine learning approach for differentiating OSA patients with and without MCI and provide potential neuroimaging evidence for cognitive impairment caused by OSA.

Alzheimer's Disease Diagnosis and Biomarker Analysis Using Resting-State Functional MRI Functional Brain Network With Multi-Measures Features and Hippocampal Subfield and Amygdala Volume of Structural MRI

Accurate diagnosis of the initial phase of Alzheimer's disease (AD) is essential and crucial. The objective of this research was to employ efficient biomarkers for the diagnostic analysis and classification of AD based on combining structural MRI (sMRI) and resting-state functional MRI (rs-fMRI). So far, several anatomical MRI imaging markers for AD diagnosis have been identified. The use of cortical and subcortical volumes, the hippocampus, and amygdala volume, as well as genetic patterns, has proven to be beneficial in distinguishing patients with AD from the healthy population. The fMRI time series data have the potential for specific numerical information as well as dynamic temporal information. Voxel and graphical analyses have gained popularity for analyzing neurodegenerative diseases, such as Alzheimer's and its prodromal phase, mild cognitive impairment (MCI). So far, these approaches have been utilized separately for the diagnosis of AD. In recent studies, the classification of cases of MCI into those that are not converted for a certain period as stable MCI (MCIs) and those that converted to AD as MCIc has been less commonly reported with inconsistent results. In this study, we verified and validated the potency of a proposed diagnostic framework to identify AD and differentiate MCIs from MCIc by utilizing the efficient biomarkers obtained from sMRI, along with functional brain networks of the frequency range .01-.027 at the resting state and the voxel-based features. The latter mainly included default mode networks (amplitude of low-frequency fluctuation [ALFF], fractional ALFF [ALFF], and regional homogeneity [ReHo]), degree centrality (DC), and salience networks (SN). Pearson's correlation coefficient for measuring fMRI functional networks has proven to be an efficient means for disease diagnosis. We applied the graph theory to calculate nodal features (nodal degree [ND], nodal path length [NL], and between centrality [BC]) as a graphical feature and analyzed the connectivity link between different brain regions. We extracted three-dimensional (3D) patterns to calculate regional coherence and then implement a univariate statistical t-test to access a 3D mask that preserves voxels showing significant changes. Similarly, from sMRI, we calculated the hippocampal subfield and amygdala nuclei volume using Freesurfer (version 6). Finally, we implemented and compared the different feature selection algorithms to integrate the structural features, brain networks, and voxel features to optimize the diagnostic identifications of AD using support vector machine (SVM) classifiers. We also compared the performance of SVM with Random Forest (RF) classifiers. The obtained results demonstrated the potency of our framework, wherein a combination of the hippocampal subfield, the amygdala volume, and brain networks with multiple measures of rs-fMRI could significantly enhance the accuracy of other approaches in diagnosing AD. The accuracy obtained by the proposed method was reported for binary classification. More importantly, the classification results of the less commonly reported MCIs vs. MCIc improved significantly. However, this research involved only the AD Neuroimaging Initiative (ADNI) cohort to focus on the diagnosis of AD advancement by integrating sMRI and fMRI. Hence, the study's primary disadvantage is its small sample size. In this case, the dataset we utilized did not fully reflect the whole population. As a result, we cannot guarantee that our findings will be applicable to other populations.

Artificial intelligence in brain MRI analysis of Alzheimer's disease over the past 12 years: A systematic review

INTRODUCTION

Multiple structural brain changes in Alzheimer's disease (AD) and mild cognitive impairment (MCI) have been revealed on magnetic resonance imaging (MRI). There is a fast-growing effort in applying artificial intelligence (AI) to analyze these data. Here, we review and evaluate the AI studies in brain MRI analysis with synthesis.

METHODS

A systematic review of the literature, spanning the years from 2009 to 2020, was completed using the PubMed database. AI studies using MRI imaging to investigate normal aging, mild cognitive impairment, and AD-dementia were retrieved for review. Bias assessment was completed using the PROBAST criteria.

RESULTS

97 relevant studies were included in the review. The studies were typically focused on the classification of AD, MCI, and normal aging (71% of the reported studies) and the prediction of MCI conversion to AD (25%). The best performance was achieved by using the deep learning-based convolution neural network algorithms (weighted average accuracy 89%), in contrast to 76-86% using Logistic Regression, Support Vector Machines, and other AI methods.

DISCUSSION

The synthesized evidence is paramount to developing sophisticated AI approaches to reliably capture and quantify multiple subtle MRI changes in the whole brain that exemplify the complexity and heterogeneity of AD and brain aging.

Voxel-based morphometry and a deep learning model for the diagnosis of early Alzheimer's disease based on cerebral gray matter changes

This study aimed to analyse cerebral grey matter changes in mild cognitive impairment (MCI) using voxel-based morphometry and to diagnose early Alzheimer's disease using deep learning methods based on convolutional neural networks (CNNs) evaluating these changes. Participants (111 MCI, 73 normal cognition) underwent 3-T structural magnetic resonance imaging. The obtained images were assessed using voxel-based morphometry, including extraction of cerebral grey matter, analyses of statistical differences, and correlation analyses between cerebral grey matter and clinical cognitive scores in MCI. The CNN-based deep learning method was used to extract features of cerebral grey matter images. Compared to subjects with normal cognition, participants with MCI had grey matter atrophy mainly in the entorhinal cortex, frontal cortex, and bilateral frontotemporal lobes (p < 0.0001). This atrophy was significantly correlated with the decline in cognitive scores (p < 0.01). The accuracy, sensitivity, and specificity of the CNN model for identifying participants with MCI were 80.9%, 88.9%, and 75%, respectively. The area under the curve of the model was 0.891. These findings demonstrate that research based on brain morphology can provide an effective way for the clinical, non-invasive, objective evaluation and identification of early Alzheimer's disease.

Machine-Learning-Based Disease Diagnosis: A Comprehensive Review

Globally, there is a substantial unmet need to diagnose various diseases effectively. The complexity of the different disease mechanisms and underlying symptoms of the patient population presents massive challenges in developing the early diagnosis tool and effective treatment. Machine learning (ML), an area of artificial intelligence (AI), enables researchers, physicians, and patients to solve some of these issues. Based on relevant research, this review explains how machine learning (ML) is being used to help in the early identification of numerous diseases. Initially, a bibliometric analysis of the publication is carried out using data from the Scopus and Web of Science (WOS) databases. The bibliometric study of 1216 publications was undertaken to determine the most prolific authors, nations, organizations, and most cited articles. The review then summarizes the most recent trends and approaches in machine-learning-based disease diagnosis (MLBDD), considering the following factors: algorithm, disease types, data type, application, and evaluation metrics. Finally, in this paper, we highlight key results and provides insight into future trends and opportunities in the MLBDD area.

Classification of Alzheimer’s Disease and Mild-Cognitive Impairment Base on High-Order Dynamic Functional Connectivity at Different Frequency Band

Functional brain connectivity networks obtained from resting-state functional magnetic resonance imaging (rs-fMRI) have been extensively utilized for the diagnosis of Alzheimer’s disease (AD). However, the traditional correlation analysis technique only explores the pairwise relation, which may not be suitable for revealing sufficient and proper functional connectivity links among brain regions. Additionally, previous literature typically focuses on only lower-order dynamics, without considering higher-order dynamic networks properties, and they particularly focus on single frequency range time series of rs-fMRI. To solve these problems, in this article, a new diagnosis scheme is proposed by constructing a high-order dynamic functional network at different frequency level time series (full-band (0.01–0.08 Hz); slow-4 (0.027–0.08 Hz); and slow-5 (0.01–0.027 Hz)) data obtained from rs-fMRI to build the functional brain network for all brain regions. Especially, to tune the precise analysis of the regularized parameters in the Support Vector Machine (SVM), a nested leave-one-out cross-validation (LOOCV) technique is adopted. Finally, the SVM classifier is trained to classify AD from HC based on these higher-order dynamic functional brain networks at different frequency ranges. The experiment results illustrate that for all bands with a LOOCV classification accuracy of 94.10% with a 90.95% of sensitivity, and a 96.75% of specificity outperforms the individual networks. Utilization of the given technique for the identification of AD from HC compete for the most state-of-the-art technology in terms of the diagnosis accuracy. Additionally, results obtained for the all-band shows performance further suggest that our proposed scheme has a high-rate accuracy. These results have validated the effectiveness of the proposed methods for clinical value to the identification of AD.

The State of Machine Learning in Spine Surgery: A Systematic Review

STUDY DESIGN

This was a systematic review of existing literature.

OBJECTIVE

The objective of this study was to evaluate the current state-of-the-art trends and utilization of machine learning in the field of spine surgery.

SUMMARY OF BACKGROUND DATA

The past decade has seen a rise in the clinical use of machine learning in many fields including diagnostic radiology and oncology. While studies have been performed that specifically pertain to spinal surgery, there have been relatively few aggregate reviews of the existing scientific literature as applied to clinical spine surgery.

METHODS

This study utilized Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology to review the scientific literature from 2009 to 2019 with syntax specific for machine learning and spine surgery applications. Specific data was extracted from the available literature including algorithm application, algorithms tested, database type and size, algorithm training method, and outcome of interest.

RESULTS

A total of 44 studies met inclusion criteria, of which the majority were level III evidence. Studies were grouped into 4 general types: diagnostic tools, clinical outcome prediction, surgical assessment tools, and decision support tools. Across studies, a wide swath of algorithms were used, which were trained across multiple disparate databases. There were no studies identified that assessed the ethical implementation or patient perceptions of machine learning in clinical care.

CONCLUSIONS

The results reveal the broad range of clinical applications and methods used to create machine learning algorithms for use in the field of spine surgery. Notable disparities exist in algorithm choice, database characteristics, and training methods. Ongoing research is needed to make machine learning operational on a large scale.

A diagnostic index based on quantitative susceptibility mapping and voxel-based morphometry may improve early diagnosis of Alzheimer's disease

OBJECTIVES

Voxel-based morphometry (VBM) is widely used to quantify the progression of Alzheimer's disease (AD), but improvement is still needed for accurate early diagnosis. We evaluated the feasibility of a novel diagnosis index for early diagnosis of AD based on quantitative susceptibility mapping (QSM) and VBM.

METHODS

Thirty-seven patients with AD, 24 patients with mild cognitive impairment (MCI) due to AD, and 36 cognitively normal (NC) subjects from four centers were included. A hybrid sequence was performed by using 3-T MRI with a 3D multi-echo GRE sequence to obtain both a T1-weighted image for VBM and phase images for QSM. The index was calculated from specific voxels in QSM and VBM images by using a linear support vector machine. The method of voxel extraction was optimized to maximize diagnostic accuracy, and the optimized index was compared with the conventional VBM-based index using receiver operating characteristic analysis.

RESULTS

The index was optimal when voxels were extracted as increased susceptibility (AD > NC) in the parietal lobe and decreased gray matter volume (AD < NC) in the limbic system. The optimized proposed index showed excellent performance for discrimination between AD and NC (AUC = 0.94, p = 1.1 × 10^-10) and good performance for MCI and NC (AUC = 0.87, p = 1.8 × 10^-6), but poor performance for AD and MCI (AUC = 0.68, p = 0.018). Compared with the conventional index, AUCs were improved for all cases, especially for MCI and NC (p < 0.05).

CONCLUSIONS

In this preliminary study, the proposed index based on QSM and VBM improved the diagnostic performance between MCI and NC groups compared with the VBM-based index.

KEY POINTS

• We developed a novel diagnostic index for Alzheimer's disease based on quantitative susceptibility mapping (QSM) and voxel-based morphometry (VBM). • QSM and VBM images can be acquired simultaneously in a single sequence with little increasing scan time. • In this preliminary study, the proposed diagnostic index improved the discriminative performance between mild cognitive impairment and normal control groups compared with the conventional VBM-based index.

Connectivity and variability of related cognitive subregions lead to different stages of progression toward Alzheimer's disease

Single modality MRI data is not enough to depict and discern the cause of the underlying brain pathology of Alzheimer's disease (AD). Most existing studies do not perform well with multi-group classification. To reveal the structural, functional connectivity and functional topological relationships among different stages of mild cognitive impairment (MCI) and AD, a novel method was proposed in this paper for the analysis of regional importance with an improved deep learning model. Obvious drift of related cognitive regions can be observed in the prefrontal lobe and surrounding the cingulate area in the right hemisphere when comparing AD and healthy controls (HC) based on absolute weights in the classification mode. Alterations of these regions being responsible for cognitive impairment have been previously reported. Different parcellation atlases of the human cerebral cortex were compared, and the fine-grained multimodal parcellation HCPMMP performed the best with 180 cortical areas per hemisphere. In multi-group classification, the highest accuracy achieved was 96.86% with the utilization of structural and functional topological modalities as input to the training model. Weights in the trained model with perfect discriminating ability quantify the importance of each cortical region. This is the first time such a phenomenon is discovered and weights in cortical areas are precisely described in AD and its prodromal stages to the best of our knowledge. Our findings can establish other study models to differentiate the patterns in various diseases with cognitive impairments and help to identify the underlying pathology.

Prediction of Alzheimer's Disease Progression Based on Magnetic Resonance Imaging

The neuroimaging method of multimodal magnetic resonance imaging (MRI) can identify the changes in brain structure and function caused by Alzheimer's disease (AD) at different stages, and it is a practical method to study the mechanism of AD progression. This paper reviews the studies of methods and biomarkers for predicting AD progression based on multimodal MRI. First, different approaches for predicting AD progression are analyzed and summarized, including machine learning, deep learning, regression, and other MRI analysis methods. Then, the effective biomarkers of AD progression under structural magnetic resonance imaging, diffusion tensor imaging, functional magnetic resonance imaging, and arterial spin labeling modes of MRI are summarized. It is believed that the brain changes shown on MRI may be related to the cognitive decline in different prodrome stages of AD, which is conducive to the further realization of early intervention and prevention of AD. Finally, the deficiencies of the existing studies are analyzed in terms of data set size, data heterogeneity, processing methods, and research depth. More importantly, future research directions are proposed, including enriching data sets, simplifying biomarkers, utilizing multimodal magnetic resonance, etc. In the future, the study of AD progression by multimodal MRI will still be a challenge but also a significant research hotspot.

Machine learning methods for predicting progression from mild cognitive impairment to Alzheimer's disease dementia: a systematic review

BACKGROUND

An increase in lifespan in our society is a double-edged sword that entails a growing number of patients with neurocognitive disorders, Alzheimer's disease being the most prevalent. Advances in medical imaging and computational power enable new methods for the early detection of neurocognitive disorders with the goal of preventing or reducing cognitive decline. Computer-aided image analysis and early detection of changes in cognition is a promising approach for patients with mild cognitive impairment, sometimes a prodromal stage of Alzheimer's disease dementia.

METHODS

We conducted a systematic review following PRISMA guidelines of studies where machine learning was applied to neuroimaging data in order to predict whether patients with mild cognitive impairment might develop Alzheimer's disease dementia or remain stable. After removing duplicates, we screened 452 studies and selected 116 for qualitative analysis.

RESULTS

Most studies used magnetic resonance image (MRI) and positron emission tomography (PET) data but also magnetoencephalography. The datasets were mainly extracted from the Alzheimer's disease neuroimaging initiative (ADNI) database with some exceptions. Regarding the algorithms used, the most common was support vector machine with a mean accuracy of 75.4%, but convolutional neural networks achieved a higher mean accuracy of 78.5%. Studies combining MRI and PET achieved overall better classification accuracy than studies that only used one neuroimaging technique. In general, the more complex models such as those based on deep learning, combined with multimodal and multidimensional data (neuroimaging, clinical, cognitive, genetic, and behavioral) achieved the best performance.

CONCLUSIONS

Although the performance of the different methods still has room for improvement, the results are promising and this methodology has a great potential as a support tool for clinicians and healthcare professionals.

Quantitative Study of the Changes in Cerebral Blood Flow and Iron Deposition During Progression of Alzheimer's Disease

BACKGROUND

Advanced Alzheimer's disease (AD) has no effective treatment, and identifying early diagnosis markers can provide a time window for treatment.

OBJECTIVE

To quantify the changes in cerebral blood flow (CBF) and iron deposition during progression of AD.

METHODS

94 subjects underwent brain imaging on a 3.0-T MRI scanner with techniques of three-dimensional arterial spin labeling (3D-ASL) and quantitative susceptibility mapping (QSM). The subjects included 22 patients with probable AD, 22 patients with mild cognitive impairment (MCI), 25 patients with subjective cognitive decline (SCD), and 25 normal controls (NC). The CBF and QSM values were obtained using a standardized brain region method based on the Brainnetome Atlas. The differences in CBF and QSM values were analyzed between and within groups using variance analysis and correlation analysis.

RESULTS

CBF and QSM identified several abnormal brain regions of interest (ROIs) at different stages of AD (p < 0.05). Regionally, the CBF values in several ROIs of the AD and MCI subjects were lower than for NC subjects (p < 0.001). Higher QSM values were observed in the globus pallidus. The CBF and QSM values in multiple ROI were negatively correlated, while the putamen was the common ROI of the three study groups (p < 0.05). The CBF and QSM values in hippocampus were cross-correlated with scale scores during the progression of AD (p < 0.05).

CONCLUSION

Iron deposition in the basal ganglia and reduction in blood perfusion in multiple regions existed during the progression of AD. The QSM values in putamen can be used as an imaging biomarker for early diagnosis of AD.

Diagnostic Value of the Fimbriae Distribution Pattern in Localization of Urinary Tract Infection

Urinary tract infections (UTIs) are one of the most common infectious diseases. UTIs are mainly caused by uropathogenic Escherichia coli (UPEC), and are either upper or lower according to the infection site. Fimbriae are necessary for UPEC to adhere to the host uroepithelium, and are abundant and diverse in UPEC strains. Although great progress has been made in determining the roles of different types of fimbriae in UPEC colonization, the contributions of multiple fimbriae to site-specific attachment also need to be considered. Therefore, the distribution patterns of 22 fimbrial genes in 90 UPEC strains from patients diagnosed with upper or lower UTIs were analyzed using PCR. The distribution patterns correlated with the infection sites, an XGBoost model with a mean accuracy of 83.33% and a mean area under the curve (AUC) of the receiver operating characteristic (ROC) of 0.92 demonstrated that fimbrial gene distribution patterns could predict the localization of upper and lower UTIs.

Modeling autosomal dominant Alzheimer's disease with machine learning

INTRODUCTION

Machine learning models were used to discover novel disease trajectories for autosomal dominant Alzheimer's disease.

METHODS

Longitudinal structural magnetic resonance imaging, amyloid positron emission tomography (PET), and fluorodeoxyglucose PET were acquired in 131 mutation carriers and 74 non-carriers from the Dominantly Inherited Alzheimer Network; the groups were matched for age, education, sex, and apolipoprotein ε4 (APOE ε4). A deep neural network was trained to predict disease progression for each modality. Relief algorithms identified the strongest predictors of mutation status.

RESULTS

The Relief algorithm identified the caudate, cingulate, and precuneus as the strongest predictors among all modalities. The model yielded accurate results for predicting future Pittsburgh compound B (R2  = 0.95), fluorodeoxyglucose (R2  = 0.93), and atrophy (R2  = 0.95) in mutation carriers compared to non-carriers.

DISCUSSION

Results suggest a sigmoidal trajectory for amyloid, a biphasic response for metabolism, and a gradual decrease in volume, with disease progression primarily in subcortical, middle frontal, and posterior parietal regions.

Predicting future cognitive decline with hyperbolic stochastic coding

Hyperbolic geometry has been successfully applied in modeling brain cortical and subcortical surfaces with general topological structures. However, such approaches, similar to other surface-based brain morphology analysis methods, usually generate high dimensional features. It limits their statistical power in cognitive decline prediction research, especially in datasets with limited subject numbers. To address the above limitation, we propose a novel framework termed as hyperbolic stochastic coding (HSC). We first compute diffeomorphic maps between general topological surfaces by mapping them to a canonical hyperbolic parameter space with consistent boundary conditions and extracts critical shape features. Secondly, in the hyperbolic parameter space, we introduce a farthest point sampling with breadth-first search method to obtain ring-shaped patches. Thirdly, stochastic coordinate coding and max-pooling algorithms are adopted for feature dimension reduction. We further validate the proposed system by comparing its classification accuracy with some other methods on two brain imaging datasets for Alzheimer's disease (AD) progression studies. Our preliminary experimental results show that our algorithm achieves superior results on various classification tasks. Our work may enrich surface-based brain imaging research tools and potentially result in a diagnostic and prognostic indicator to be useful in individualized treatment strategies.

Early diagnosis of Alzheimer's disease on ADNI data using novel longitudinal score based on functional principal component analysis

Methods: Alzheimer's disease (AD) is a worldwide prevalent age-related neurodegenerative disease with no available cure yet. Early prognosis is therefore crucial for planning proper clinical intervention. It is especially true for people diagnosed with mild cognitive impairment, to whom the prediction of whether and when the future disease onset would happen is particularly valuable. However, such prognostic prediction has been proven to be challenging, and previous studies have only achieved limited success. Approach: In this study, we seek to extract the principal component of the longitudinal disease progression trajectory in the early stage of AD, measured as the magnetic resonance imaging (MRI)-derived structural volume, to predict the onset of AD for mild cognitive impaired patients two years ahead. Results: Cross-validation results of LASSO regression using the longitudinal functional principal component (FPC) features show significant improved predictive power compared to training using the baseline volume 12 months before AD conversion [area under the receiver operating characteristic curve (AUC) of 0.802 versus 0.732] and 24 months before AD conversion (AUC of 0.816 versus 0.717). Conclusions: We present a framework using the FPCA to extract features from MRI-derived information collected from multiple timepoints. The results of our study demonstrate the advantageous predictive power of the population-based longitudinal features to predict the disease onset compared with using only cross-sectional data-based on volumetric features extracted from a single timepoint, demonstrating the improved prediction power using FPC-derived longitudinal features.

Test-Retest Variability of Relative Tracer Delivery Rate as Measured by [11C]PiB

Purpose

Moderate-to-high correlations have been reported between the [¹¹C]PiB PET-derived relative tracer delivery rate R₁ and relative CBF as measured using [¹⁵O]H₂O PET, supporting its use as a proxy of relative CBF. As longitudinal PET studies become more common for measuring treatment efficacy or disease progression, it is important to know the intrinsic variability of R₁. The purpose of the present study was to determine this through a retrospective data analysis.

Procedures

Test-retest data belonging to twelve participants, who underwent two 90 min [¹¹C]PiB PET scans, were retrospectively included. The voxel-based implementation of the two-step simplified reference tissue model with cerebellar grey matter as reference tissue was used to compute R₁ images. Next, test-retest variability was calculated, and test and retest R₁ measures were compared using linear mixed effect models and a Bland-Altman analysis.

Results

Test-retest variability was low across regions (max. 5.8 %), and test and retest measures showed high, significant correlations (R²=0.92, slope=0.98) and a negligible bias (0.69±3.07 %).

Conclusions

In conclusion, the high precision of [¹¹C]PiB R₁ suggests suitable applicability for cross-sectional and longitudinal studies.

Perspectives on Virtual (Remote) Clinical Trials as the "New Normal" to Accelerate Drug Development

Although the digital revolution has transformed many areas of human endeavor, pharmaceutical drug development has been relatively slow to embrace the emerging technologies to enhance efficiency and optimize value in clinical trials. The topic has garnered even greater attention in the face of the coronavirus disease 2019 (COVID-19) outbreak, which has caused unprecedented disruption in the conduct of clinical trials and presented considerable challenges and opportunities for clinical trialists and data analysts. In this paper, we highlight the potential opportunity with virtual or digital clinical trials as viable options to enhance efficiency in drug development and, more importantly, in offering diverse patients easier and attractive means to participate in clinical trials. Special reference is made to the implication of artificial intelligence and machine-learning tools in trial execution and data acquisition, processing, and analysis in a virtual trial setting. Issues of patient safety, measurement validity, and data integrity are reviewed, and considerations are put forth with reference to the mitigation of underlying regulatory and operational barriers.

Parametric imaging of dual-time window [18F]flutemetamol and [18F]florbetaben studies

Optimal pharmacokinetic models for quantifying amyloid beta (Aβ) burden using both [¹⁸F]flutemetamol and [¹⁸F]florbetaben scans have previously been identified at a region of interest (ROI) level. The purpose of this study was to determine optimal quantitative methods for parametric analyses of [¹⁸F]flutemetamol and [¹⁸F]florbetaben scans. Forty-six participants were scanned on a PET/MR scanner using a dual-time window protocol and either [¹⁸F]flutemetamol (N=24) or [¹⁸F]florbetaben (N=22). The following parametric approaches were used to derive DVR estimates: reference Logan (RLogan), receptor parametric mapping (RPM), two-step simplified reference tissue model (SRTM2) and multilinear reference tissue models (MRTM0, MRTM1, MRTM2), all with cerebellar grey matter as reference tissue. In addition, a standardized uptake value ratio (SUVR) was calculated for the 90-110 min post injection interval. All parametric images were assessed visually. Regional outcome measures were compared with those from a validated ROI method, i.e. DVR derived using RLogan. Visually, RPM, and SRTM2 performed best across tracers and, in addition to SUVR, provided highest AUC values for differentiating between Aβ-positive vs Aβ-negative scans ([¹⁸F]flutemetamol: range AUC=0.96-0.97 [¹⁸F]florbetaben: range AUC=0.83-0.85). Outcome parameters of most methods were highly correlated with the reference method (R²≥0.87), while lowest correlation were observed for MRTM2 (R²=0.71-0.80). Furthermore, bias was low (≤5%) and independent of underlying amyloid burden for MRTM0 and MRTM1. The optimal parametric method differed per evaluated aspect; however, the best compromise across aspects was found for MRTM0 followed by SRTM2, for both tracers. SRTM2 is the preferred method for parametric imaging because, in addition to its good performance, it has the advantage of providing a measure of relative perfusion (R₁), which is useful for measuring disease progression.

Machine learning for predictive data analytics in medicine: A review illustrated by cardiovascular and nuclear medicine examples

The evidence-based medicine allows the physician to evaluate the risk-benefit ratio of a treatment through setting and data. Risk-based choices can be done by the doctor using different information. With the emergence of new technologies, a large amount of data is recorded offering interesting perspectives with machine learning for predictive data analytics. Machine learning is an ensemble of methods that process data to model a learning problem. Supervised machine learning algorithms consist in using annotated data to construct the model. This category allows to solve prediction data analytics problems. In this paper, we detail the use of supervised machine learning algorithms for predictive data analytics problems in medicine. In the medical field, data can be split into two categories: medical images and other data. For brevity, our review deals with any kind of medical data excluding images. In this article, we offer a discussion around four supervised machine learning approaches: information-based, similarity-based, probability-based and error-based approaches. Each method is illustrated with detailed cardiovascular and nuclear medicine examples. Our review shows that model ensemble (ME) and support vector machine (SVM) methods are the most popular. SVM, ME and artificial neural networks often lead to better results than those given by other algorithms. In the coming years, more studies, more data, more tools and more methods will, for sure, be proposed.

Using machine learning to quantify structural MRI neurodegeneration patterns of Alzheimer's disease into dementia score: Independent validation on 8,834 images from ADNI, AIBL, OASIS, and MIRIAD databases

Biomarkers for dementia of Alzheimer's type (DAT) are sought to facilitate accurate prediction of the disease onset, ideally predating the onset of cognitive deterioration. T1-weighted magnetic resonance imaging (MRI) is a commonly used neuroimaging modality for measuring brain structure in vivo, potentially providing information enabling the design of biomarkers for DAT. We propose a novel biomarker using structural MRI volume-based features to compute a similarity score for the individual's structural patterns relative to those observed in the DAT group. We employed ensemble-learning framework that combines structural features in most discriminative ROIs to create an aggregate measure of neurodegeneration in the brain. This classifier is trained on 423 stable normal control (NC) and 330 DAT subjects, where clinical diagnosis is likely to have the highest certainty. Independent validation on 8,834 unseen images from ADNI, AIBL, OASIS, and MIRIAD Alzheimer's disease (AD) databases showed promising potential to predict the development of DAT depending on the time-to-conversion (TTC). Classification performance on stable versus progressive mild cognitive impairment (MCI) groups achieved an AUC of 0.81 for TTC of 6 months and 0.73 for TTC of up to 7 years, achieving state-of-the-art results. The output score, indicating similarity to patterns seen in DAT, provides an intuitive measure of how closely the individual's brain features resemble the DAT group. This score can be used for assessing the presence of AD structural atrophy patterns in normal aging and MCI stages, as well as monitoring the progression of the individual's brain along with the disease course.

Effect of post-labeling delay on regional cerebral blood flow in arterial spin-labeling MR imaging

BACKGROUND

Investigating the effect of post-labeling delay (PLD) on regional cerebral blood flow (CBF) in adults and optimizing the PLD for arterial spin-labeling (ASL) magnetic resonance (MR) imaging are important.

METHODS

Pseudo-continuous ASL imaging with a three PLDs protocol was performed in 90 healthy adult volunteers from January 2018 to February 2019. Healthy subjects were divided into youth group (mean age, 30.63 years; age range, 20-44 years), middle-aged group (mean age, 52.16 years; age range 45-59 years) and elderly group (mean age, 66.07 years; age range, 60-77 years). After preprocessing, analyses of variance (ANOVA) and volume-of-interest (VOI) were conducted to compare the CBF in each brain region. According to the trends of CBF changing with PLD and the results of ANOVA, we optimized the PLD for ASL imaging in different brain regions and age groups.

RESULTS

The CBF values of 87 VOIs [global gray matter (global GM) and other 86 VOIs] for each subject were obtained. Young people had less statistically significant VOIs than middle-aged and elderly people [Numbers of VOIs which had statistical significance (P < .05) in the analysis of ANOVA: 42 (youth group), 79 (middle-aged group), and 71 (elderly group)]. In youth group, the deep GM, occipital lobe and temporal lobe were more affected by PLDs than limbic system, frontal lobe and parietal lobe [VOIs with statistical significance (P < .05)/total VOIs: 8/8 (deep GM) > 8/12 (occipital lobe) > (8/14) (temporal lobe) > 5/12 (limbic system) > 11/28 (frontal lobe) > (2/12) parietal lobe]. In middle-aged group, the limbic system, deep GM and temporal lobe were more affected by PLDs than parietal lobe, frontal lobe and occipital lobe [VOIs with statistical significance (P < 0.05)/total VOIs: 12/12 (limbic system) = 8/8 (deep GM) > (13/14) (temporal lobe) > (11/12) parietal lobe > 25/28 (frontal lobe) > 9/12 (occipital lobe)]. In elderly group, the temporal lobe, parietal lobe, and frontal lobe were more affected by PLDs than occipital lobe, limbic system, and deep GM [VOIs with statistical significance (P < .05)/total VOIs: 14/14 (temporal lobe) > 12/12 (parietal lobe) > 22/28 (frontal lobe) > 9/12 (occipital lobe) > 8/12 (limbic system) > 5/8 (deep GM)]. The optimal PLD for most VOIs in youth group was 1525 ms. However, for middle-aged and elderly group, the optimal PLD for most VOIs was 2525 ms.

CONCLUSION

Young people are less affected by PLDs than middle-aged and elderly people. The middle-aged people are most affected by PLDs. In addition, the spatial distributions of PLD effect were different among the three age groups. Optimizing the PLD for ASL imaging according to age and brain regions can obtain more accurate and reliable CBF values.

Classifying intracranial stenosis disease severity from functional MRI data using machine learning

Translation of many non-invasive hemodynamic MRI methods to cerebrovascular disease patients has been hampered by well-known artifacts associated with delayed blood arrival times and reduced microvascular compliance. Using machine learning and support vector machine (SVM) algorithms, we investigated whether arrival time-related artifacts in these methods could be exploited as novel contrast sources to discriminate angiographically confirmed stenotic flow territories. Intracranial steno-occlusive moyamoya patients (n = 53; age = 45 ± 14.2 years; sex = 43 F) underwent (i) catheter angiography, (ii) anatomical MRI, (iii) cerebral blood flow (CBF)-weighted arterial spin labeling, and (iv) cerebrovascular reactivity (CVR)-weighted hypercapnic blood-oxygenation-level-dependent MRI. Mean, standard deviation (std), and 99th percentile of CBF, CVR, CVR_Delay, and CVR_Max were calculated in major anterior and posterior flow territories perfused by vessels with vs. without stenosis (≥70%) confirmed by catheter angiography. These and demographic variables were input into SVMs to evaluate discriminatory capacity for stenotic flow territories using k-fold cross-validation and receiver-operating-characteristic-area-under-the-curve to quantify variable combination relevance. Anterior circulation CBF-std, attributable to heterogeneous endovascular signal and prolonged arterial transit times, was the best performing single variable and CVR_Delay-mean and CBF-std, both reflective of delayed vascular compliance, were a high-performing two-variable combination (specificity = 0.67; sensitivity = 0.75). Findings highlight the relevance of hemodynamic imaging and machine learning for identifying cerebrovascular impairment.

Support vector machine-based multivariate pattern classification of methamphetamine dependence using arterial spin labeling

Arterial spin labeling (ASL) magnetic resonance imaging has been widely applied to identify cerebral blood flow (CBF) abnormalities in a number of brain disorders. To evaluate its significance in detecting methamphetamine (MA) dependence, this study used a multivariate pattern classification algorithm, ie, a support vector machine (SVM), to construct classifiers for discriminating MA-dependent subjects from normal controls. Forty-five MA-dependent subjects, 45 normal controls, and 36 heroin-dependent subjects were enrolled. Classifiers trained with ASL-CBF data from the left or right cerebrum showed significant hemispheric asymmetry in their cross-validated prediction performance (P < 0.001 for accuracy, sensitivity, specificity, kappa, and area under the curve [AUC] of the receiver operating characteristics [ROC] curve). A classifier trained with ASL-CBF data from all cerebral regions (bilateral hemispheres and corpus callosum) was able to differentiate MA-dependent subjects from normal controls with a cross-validated prediction accuracy, sensitivity, specificity, kappa, and AUC of 89%, 94%, 84%, 0.78, and 0.95, respectively. The discrimination map extracted from this classifier covered multiple brain circuits that either constitute a network related to drug abuse and addiction or could be impaired in MA-dependence. The cerebral regions contribute most to classification include occipital lobe, insular cortex, postcentral gyrus, corpus callosum, and inferior frontal cortex. This classifier was also specific to MA-dependence rather than substance use disorders in general (ie, 55.56% accuracy for heroin dependence). These results support the future utilization of ASL with an SVM-based classifier for the diagnosis of MA-dependence and could help improve the understanding of MA-related neuropathology.

Prediction and Classification of Alzheimer's Disease Based on Combined Features From Apolipoprotein-E Genotype, Cerebrospinal Fluid, MR, and FDG-PET Imaging Biomarkers

Alzheimer's disease (AD), including its mild cognitive impairment (MCI) phase that may or may not progress into the AD, is the most ordinary form of dementia. It is extremely important to correctly identify patients during the MCI stage because this is the phase where AD may or may not develop. Thus, it is crucial to predict outcomes during this phase. Thus far, many researchers have worked on only using a single modality of a biomarker for the diagnosis of AD or MCI. Although recent studies show that a combination of one or more different biomarkers may provide complementary information for the diagnosis, it also increases the classification accuracy distinguishing between different groups. In this paper, we propose a novel machine learning-based framework to discriminate subjects with AD or MCI utilizing a combination of four different biomarkers: fluorodeoxyglucose positron emission tomography (FDG-PET), structural magnetic resonance imaging (sMRI), cerebrospinal fluid (CSF) protein levels, and Apolipoprotein-E (APOE) genotype. The Alzheimer's Disease Neuroimaging Initiative (ADNI) baseline dataset was used in this study. In total, there were 158 subjects for whom all four modalities of biomarker were available. Of the 158 subjects, 38 subjects were in the AD group, 82 subjects were in MCI groups (including 46 in MCIc [MCI converted; conversion to AD within 24 months of time period], and 36 in MCIs [MCI stable; no conversion to AD within 24 months of time period]), and the remaining 38 subjects were in the healthy control (HC) group. For each image, we extracted 246 regions of interest (as features) using the Brainnetome template image and NiftyReg toolbox, and later we combined these features with three CSF and two APOE genotype features obtained from the ADNI website for each subject using early fusion technique. Here, a different kernel-based multiclass support vector machine (SVM) classifier with a grid-search method was applied. Before passing the obtained features to the classifier, we have used truncated singular value decomposition (Truncated SVD) dimensionality reduction technique to reduce high dimensional features into a lower-dimensional feature. As a result, our combined method achieved an area under the receiver operating characteristic (AU-ROC) curve of 98.33, 93.59, 96.83, 94.64, 96.43, and 95.24% for AD vs. HC, MCIs vs. MCIc, AD vs. MCIs, AD vs. MCIc, HC vs. MCIc, and HC vs. MCIs subjects which are high relative to single modality results and other state-of-the-art approaches. Moreover, combined multimodal methods have improved the classification performance over the unimodal classification.

Classification of Alzheimer's Disease with and without Imagery using Gradient Boosted Machines and ResNet-50

Background. Alzheimer’s is a disease for which there is no cure. Diagnosing Alzheimer’s disease (AD) early facilitates family planning and cost control. The purpose of this study is to predict the presence of AD using socio-demographic, clinical, and magnetic resonance imaging (MRI) data. Early detection of AD enables family planning and may reduce costs by delaying long-term care. Accurate, non-imagery methods also reduce patient costs. The Open Access Series of Imaging Studies (OASIS-1) cross-sectional MRI data were analyzed. A gradient boosted machine (GBM) predicted the presence of AD as a function of gender, age, education, socioeconomic status (SES), and a mini-mental state exam (MMSE). A residual network with 50 layers (ResNet-50) predicted the clinical dementia rating (CDR) presence and severity from MRI’s (multi-class classification). The GBM achieved a mean 91.3% prediction accuracy (10-fold stratified cross validation) for dichotomous CDR using socio-demographic and MMSE variables. MMSE was the most important feature. ResNet-50 using image generation techniques based on an 80% training set resulted in 98.99% three class prediction accuracy on 4139 images (20% validation set) at Epoch 133 and nearly perfect multi-class predication accuracy on the training set (99.34%). Machine learning methods classify AD with high accuracy. GBM models may help provide initial detection based on non-imagery analysis, while ResNet-50 network models might help identify AD patients automatically prior to provider review.

A clinically-translatable machine learning algorithm for the prediction of Alzheimer's disease conversion: further evidence of its accuracy via a transfer learning approach

BACKGROUND

In a previous study, we developed a highly performant and clinically-translatable machine learning algorithm for a prediction of three-year conversion to Alzheimer's disease (AD) in subjects with Mild Cognitive Impairment (MCI) and Pre-mild Cognitive Impairment. Further tests are necessary to demonstrate its accuracy when applied to subjects not used in the original training process. In this study, we aimed to provide preliminary evidence of this via a transfer learning approach.

METHODS

We initially employed the same baseline information (i.e. clinical and neuropsychological test scores, cardiovascular risk indexes, and a visual rating scale for brain atrophy) and the same machine learning technique (support vector machine with radial-basis function kernel) used in our previous study to retrain the algorithm to discriminate between participants with AD (n = 75) and normal cognition (n = 197). Then, the algorithm was applied to perform the original task of predicting the three-year conversion to AD in the sample of 61 MCI subjects that we used in the previous study.

RESULTS

Even after the retraining, the algorithm demonstrated a significant predictive performance in the MCI sample (AUC = 0.821, 95% CI bootstrap = 0.705-0.912, best balanced accuracy = 0.779, sensitivity = 0.852, specificity = 0.706).

CONCLUSIONS

These results provide a first indirect evidence that our original algorithm can also perform relevant generalized predictions when applied to new MCI individuals. This motivates future efforts to bring the algorithm to sufficient levels of optimization and trustworthiness that will allow its application in both clinical and research settings.

Quantitative assessment of field strength, total intracranial volume, sex, and age effects on the goodness of harmonization for volumetric analysis on the ADNI database

When analyzing large multicenter databases, the effects of multiple confounding covariates increase the variability in the data and may reduce the ability to detect changes due to the actual effect of interest, for example, changes due to disease. Efficient ways to evaluate the effect of covariates toward the data harmonization are therefore important. In this article, we showcase techniques to assess the "goodness of harmonization" of covariates. We analyze 7,656 MR images in the multisite, multiscanner Alzheimer's Disease Neuroimaging Initiative (ADNI) database. We present a comparison of three methods for estimating total intracranial volume to assess their robustness and correct the brain structure volumes using the residual method and the proportional (normalization by division) method. We then evaluated the distribution of brain structure volumes over the entire ADNI database before and after accounting for multiple covariates such as total intracranial volume, scanner field strength, sex, and age using two techniques: (a) Zscapes, a panoramic visualization technique to analyze the entire database and (b) empirical cumulative distributions functions. The results from this study highlight the importance of assessing the goodness of data harmonization as a necessary preprocessing step when pooling large data set with multiple covariates, prior to further statistical data analysis.

Study the Longitudinal in vivo and Cross-Sectional ex vivo Brain Volume Difference for Disease Progression and Treatment Effect on Mouse Model of Tauopathy Using Automated MRI Structural Parcellation

Brain volume measurements extracted from structural MRI data sets are a widely accepted neuroimaging biomarker to study mouse models of neurodegeneration. Whether to acquire and analyze data in vivo or ex vivo is a crucial decision during the phase of experimental designs, as well as data analysis. In this work, we extracted the brain structures for both longitudinal in vivo and single-time-point ex vivo MRI acquired from the same animals using accurate automatic multi-atlas structural parcellation, and compared the corresponding statistical and classification analysis. We found that most gray matter structures volumes decrease from in vivo to ex vivo, while most white matter structures volume increase. The level of structural volume change also varies between different genetic strains and treatment. In addition, we showed superior statistical and classification power of ex vivo data compared to the in vivo data, even after resampled to the same level of resolution. We further demonstrated that the classification power of the in vivo data can be improved by incorporating longitudinal information, which is not possible for ex vivo data. In conclusion, this paper demonstrates the tissue-specific changes, as well as the difference in statistical and classification power, between the volumetric analysis based on the in vivo and ex vivo structural MRI data. Our results emphasize the importance of longitudinal analysis for in vivo data analysis.

Deep Learning in Radiology

As radiology is inherently a data-driven specialty, it is especially conducive to utilizing data processing techniques. One such technique, deep learning (DL), has become a remarkably powerful tool for image processing in recent years. In this work, the Association of University Radiologists Radiology Research Alliance Task Force on Deep Learning provides an overview of DL for the radiologist. This article aims to present an overview of DL in a manner that is understandable to radiologists; to examine past, present, and future applications; as well as to evaluate how radiologists may benefit from this remarkable new tool. We describe several areas within radiology in which DL techniques are having the most significant impact: lesion or disease detection, classification, quantification, and segmentation. The legal and ethical hurdles to implementation are also discussed. By taking advantage of this powerful tool, radiologists can become increasingly more accurate in their interpretations with fewer errors and spend more time to focus on patient care.

Machine learning identified an Alzheimer's disease-related FDG-PET pattern which is also expressed in Lewy body dementia and Parkinson's disease dementia

Utilizing the publicly available neuroimaging database enabled by Alzheimer's disease Neuroimaging Initiative (ADNI; http://adni.loni.usc.edu/ ), we have compared the performance of automated classification algorithms that differentiate AD vs. normal subjects using Positron Emission Tomography (PET) with fluorodeoxyglucose (FDG). General linear model, scaled subprofile modeling and support vector machines were examined. Among the tested classification methods, support vector machine with Iterative Single Data Algorithm produced the best performance, i.e., sensitivity (0.84) × specificity (0.95), by 10-fold cross-validation. We have applied the same classification algorithm to four different datasets from ADNI, Health Science Centre (Winnipeg, Canada), Dong-A University Hospital (Busan, S. Korea) and Asan Medical Centre (Seoul, S. Korea). Our data analyses confirmed that the support vector machine with Iterative Single Data Algorithm showed the best performance in prediction of future development of AD from the prodromal stage (mild cognitive impairment), and that it was also sensitive to other types of dementia such as Parkinson's Disease Dementia and Dementia with Lewy Bodies, and that perfusion imaging using single photon emission computed tomography may achieve a similar accuracy to that of FDG-PET.

Multiparametric ultrasomics of significant liver fibrosis: A machine learning-based analysis

Objective

To assess significant liver fibrosis by multiparametric ultrasomics data using machine learning.

Materials and Methods

This prospective study consisted of 144 patients with chronic hepatitis B. Ultrasomics—high-throughput quantitative data from ultrasound imaging of liver fibrosis—were generated using conventional radiomics, original radiofrequency (ORF) and contrast-enhanced micro-flow (CEMF) features. Three categories of features were explored using pairwise correlation and hierarchical clustering. Features were selected using diagnostic tests for fibrosis, activity and steatosis stage, with the histopathological results as the reference. The fibrosis staging performance of ultrasomics models with combinations of the selected features was evaluated with machine-learning algorithms by calculating the area under the receiver-operator characteristic curve (AUC).

Results

ORF and CEMF features had better predictive power than conventional radiomics for liver fibrosis stage (both p < 0.01). CEMF features exhibited the highest diagnostic value for activity stage (both p < 0.05), and ORF had the best diagnostic value for steatosis stage (both p < 0.01). The machine-learning classifiers of adaptive boosting, random forest and support vector machine were found to be optimal algorithms with better (all mean AUCs = 0.85) and more stable performance (coefficient of variation = 0.01–0.02) for fibrosis staging than decision tree, logistic regression and neural network (mean AUC = 0.61–0.72, CV = 0.07–0.08). The multiparametric ultrasomics model achieved much better performance (mean AUC values of 0.78–0.85) than the features from a single modality in discriminating significant fibrosis (≥ F2).

Conclusion

Machine-learning-based analysis of multiparametric ultrasomics can help improve the discrimination of significant fibrosis compared with mono or dual modalities.

Key Points

• Multiparametric ultrasomics has achieved much better performance in the discrimination of significant fibrosis (≥ F2) than the single modality of conventional radiomics, original radiofrequency and contrast-enhanced micro-flow.

• Adaptive boosting, random forest and support vector machine are the optimal algorithms for machine learning.

Electronic supplementary material

The online version of this article (10.1007/s00330-018-5680-z) contains supplementary material, which is available to authorized users.

Estradiol Protects White Matter of Male C57BL6J Mice against Experimental Chronic Cerebral Hypoperfusion

BACKGROUND AND PURPOSE

Estradiol is a sex steroid hormone known to protect the brain against damage related to transient and global cerebral ischemia. In the present study, we leverage an experimental murine model of bilateral carotid artery stenosis (BCAS) to examine the putative effects of estradiol therapy on chronic cerebral hypoperfusion. We hypothesize that long-term estradiol therapy protects against white matter injury and declarative memory deficits associated with chronic cerebral hypoperfusion.

METHODS

Adult male C57BL/6J mice underwent either surgical BCAS or sham procedures. Two days after surgery, the mice were given oral estradiol (Sham+E, BCAS+E) or placebo (Sham+P, BCAS+P) treatments daily for 31-34 days. All mice underwent Novel Object Recognition (NOR) testing 31-34 days after the start of oral treatments. Following sacrifice, blood was collected and brains fixed, sliced, and prepared for histological examination of white matter injury and extracellular signal-regulated kinase (ERK) expression.

RESULTS

Animals receiving long-term oral estradiol therapy (BCAS-E2 and Sham-E2) had higher plasma estradiol levels than those receiving placebo treatment (BCAS-P and Sham-P). BCAS-E2 mice demonstrated less white matter injury (Klüver-Barrera staining) and performed better on the NOR task compared to BCAS-P mice. ERK expression in the brain was increased in the BCAS compared to sham cohorts. Among the BCAS mice, the BCAS-E2 cohort had a greater number of ERK + cells.

CONCLUSION

This study demonstrates a potentially protective role for oral estradiol therapy in the setting of white matter injury and declarative memory deficits secondary to murine chronic cerebral hypoperfusion.

Prediction of Incipient Alzheimer's Disease Dementia in Patients with Mild Cognitive Impairment

BACKGROUND

Mild cognitive impairment (MCI) is a transitional stage from normal aging to Alzheimer's disease (AD) dementia. It is extremely important to develop criteria that can be used to separate the MCI subjects at imminent risk of conversion to Alzheimer-type dementia from those who would remain stable. We have developed an automatic algorithm for computing a novel measure of hippocampal volumetric integrity (HVI) from structural MRI scans that may be useful for this purpose.

OBJECTIVE

To determine the utility of HVI in classification between stable and progressive MCI patients using the Random Forest classification algorithm.

METHODS

We used a 16-dimensional feature space including bilateral HVI obtained from baseline and one-year follow-up structural MRI, cognitive tests, and genetic and demographic information to train a Random Forest classifier in a sample of 164 MCI subjects categorized into two groups [progressive (n = 86) or stable (n = 78)] based on future conversion (or lack thereof) of their diagnosis to probable AD.

RESULTS

The overall accuracy of classification was estimated to be 82.3% (86.0% sensitivity, 78.2% specificity). The accuracy in women (89.1%) was considerably higher than that in men (78.9%). The prediction accuracy achieved in women is the highest reported in any previous application of machine learning to AD diagnosis in MCI.

CONCLUSION

The method presented in this paper can be used to separate stable MCI patients from those who are at early stages of AD dementia with high accuracy. There may be stronger indicators of imminent AD dementia in women with MCI as compared to men.

Amsterdam Dementia Cohort: Performing Research to Optimize Care

The Alzheimer center of the VU University Medical Center opened in 2000 and was initiated to combine both patient care and research. Together, to date, all patients forming the Amsterdam Dementia Cohort number almost 6,000 individuals. In this cohort profile, we provide an overview of the results produced based on the Amsterdam Dementia Cohort. We describe the main results over the years in each of these research lines: 1) early diagnosis, 2) heterogeneity, and 3) vascular factors. Among the most important research efforts that have also impacted patients' lives and/or the research field, we count the development of novel, easy to use diagnostic measures such as visual rating scales for MRI and the Amsterdam IADL Questionnaire, insight in different subgroups of AD, and findings on incidence and clinical sequelae of microbleeds. Finally, we describe in the outlook how our research endeavors have improved the lives of our patients.

[Test-retest reliability of 3D spiral fast-spin-echo pseudo-continuous arterial spin labeling for cerebral perfusion imaging of subcortical gray matter in healthy adults]

OBJECTIVE

To evaluate the test-retest reliability of 3D spiral fast-spin-echo (FSE) pseudo-continuous arterial spin labeling (3D pc-ASL) for cerebral perfusion imaging of the subcortical gray matter in healthy adults in resting state.

METHODS

3D spiral FSE ASL and 3D T1-weighted fast spoiled gradient recalled echo (3D T1-FSPGR) sequences were used for cerebral perfusion imaging in 8 healthy adult subjects, and a repeat imaging examination was performed after one week. The subcortical gray matter structures including the putamen, globus pallidus, caudate nucleus, thalamus, amygdala and hippocampus were segmented on the brain structural 3D images to generate the cerebral blood flow (CBF) map. The CBF value was extracted based on the segmented images and the CBF maps. The reliability and reproducibility of the measurements were evaluated using the intraclass correlation coefficient (ICC) and Bland-Altman plot.

RESULTS

The mean ICC value of the subcortical gray matter structures was 0.88∓0.04 (range, 0.80-0.93). The Bland-Altman plot analysis demonstrated that the differences between the two measurements at all the points corresponding to the subcortical gray matter structures were within 95% CI of the limits of agreement.

CONCLUSION

3D spiral FSE pseudo-continuous ASL is a reliable method for assessing the perfusion of the cerebral subcortical gray matter structures.

δ scores predict mild cognitive impairment and Alzheimer's disease conversions from nondemented states

INTRODUCTION

We tested the latent variable "δ" (for "dementia")'s ability to predict conversion to "mild cognitive impairment" (MCI) and Alzheimer's disease (AD).

METHODS

An ethnicity equivalent d homolog ("dEQ") was constructed in n = 1113 Mexican- American (MA) and n = 1958 non-Hispanic white (NHW) participants in the Texas Alzheimer's Research and Care Consortium. "Normal Controls" (NC) (n = 1276) and MCI cases (n = 611) were followed annually for up to 6 years [m = 4.7(0.6)].

RESULTS

22.0% (n = 281) of NC converted to "MCI" or "AD". 17.3%( n = 106) of MCI converted to "AD." Independently of covariates, each quintile increase in the dEQ scores of NC increased the odds of conversion by 52%. Each quintile increase in the dEQ scores of MCI cases increased the odds of conversion to AD almost three-fold.

DISCUSSION

Baseline δ scores predict MCI and AD conversions from nondemented states in MA and NHW.

Cerebral Blood Flow Alterations as Assessed by 3D ASL in Cognitive Impairment in Patients with Subcortical Vascular Cognitive Impairment: A Marker for Disease Severity

Abnormal reductions in cortical cerebral blood flow (CBF) have been identified in subcortical vascular cognitive impairment (SVCI). However, little is known about the pattern of CBF reduction in relation with the degree of cognitive impairment. CBF measured with three-dimensional (3D) Arterial Spin Labeling (ASL) perfusion magnetic resonance imaging (MRI) helps detect functional changes in subjects with SVCI. We aimed to compare CBF maps in subcortical ischemic vascular disease (SIVD) subjects with and without cognitive impairment and to detect the relationship of the regions of CBF reduction in the brain with the degree of cognitive impairment according to the z-score. A total of 53 subjects with SVCI and 23 matched SIVD subjects without cognitive impairment (controls), underwent a whole-brain 3D ASL MRI in the resting state. Regional CBF (rCBF) was compared voxel wise by using an analysis of variance design in a statistical parametric mapping program, with patient age and sex as covariates. Correlations were calculated between the rCBF value in the whole brain and the z-score in the 53 subjects with SVCI. Compared with the control subjects, SVCI group demonstrated diffuse decreased CBF in the brain. Significant positive correlations were determined in the rCBF values in the left hippocampus, left superior temporal pole gyrus, right superior frontal orbital lobe, right medial frontal orbital lobe, right middle temporal lobe, left thalamus and right insula with the z-scores in SVCI group. The noninvasively quantified resting CBF demonstrated altered CBF distributions in the SVCI brain. The deficit brain perfusions in the temporal and frontal lobe, hippocampus, thalamus and insula was related to the degree of cognitive impairment. Its relationship to cognition indicates the clinical relevance of this functional marker. Thus, our results provide further evidence for the mechanisms underlying the cognitive deficit in patients with SVCI.