Individual detection of patients with Parkinson disease using support vector machine analysis of diffusion tensor imaging data: initial results

Toward diffusion tensor imaging as a biomarker in neurodegenerative diseases: technical considerations to optimize recordings and data processing

Neuroimaging biomarkers have shown high potential to map the disease processes in the application to neurodegenerative diseases (NDD), e.g., diffusion tensor imaging (DTI). For DTI, the implementation of a standardized scanning and analysis cascade in clinical trials has potential to be further optimized. Over the last few years, various approaches to improve DTI applications to NDD have been developed. The core issue of this review was to address considerations and limitations of DTI in NDD: we discuss suggestions for improvements of DTI applications to NDD. Based on this technical approach, a set of recommendations was proposed for a standardized DTI scan protocol and an analysis cascade of DTI data pre-and postprocessing and statistical analysis. In summary, considering advantages and limitations of the DTI in NDD we suggest improvements for a standardized framework for a DTI-based protocol to be applied to future imaging studies in NDD, towards the goal to proceed to establish DTI as a biomarker in clinical trials in neurodegeneration.

Detection of mild cognitive impairment in Parkinson's disease using gradient boosting decision tree models based on multilevel DTI indices

BACKGROUND

Cognitive dysfunction is the most common non-motor symptom in Parkinson's disease (PD), and timely detection of a slight cognitive decline is crucial for early treatment and prevention of dementia. This study aimed to build a machine learning model based on intra- and/or intervoxel metrics extracted from diffusion tensor imaging (DTI) to automatically classify PD patients without dementia into mild cognitive impairment (PD-MCI) and normal cognition (PD-NC) groups.

METHODS

We enrolled PD patients without dementia (52 PD-NC and 68 PD-MCI subtypes) who were assigned to the training and test datasets in an 8:2 ratio. Four intravoxel metrics, including fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity (AD), and radial diffusivity (RD), and two novel intervoxel metrics, local diffusion homogeneity (LDH) using Spearman's rank correlation coefficient (LDHs) and Kendall's coefficient concordance (LDHk), were extracted from the DTI data. Decision tree, random forest, and eXtreme gradient boosting (XGBoost) models based on individual and combined indices were built for classification, and model performance was assessed and compared via the area under the receiver operating characteristic curve (AUC). Finally, feature importance was evaluated using SHapley Additive exPlanation (SHAP) values.

RESULTS

The XGBoost model based on a combination of the intra- and intervoxel indices achieved the best classification performance, with an accuracy of 91.67%, sensitivity of 92.86%, and AUC of 0.94 in the test dataset. SHAP analysis showed that the LDH of the brainstem and MD of the right cingulum (hippocampus) were important features.

CONCLUSIONS

More comprehensive information on white matter changes can be obtained by combining intra- and intervoxel DTI indices, improving classification accuracy. Furthermore, machine learning methods based on DTI indices can be used as alternatives for the automatic identification of PD-MCI at the individual level.

Quick computer aided differential diagnostics based on repetitive finger tapping in Parkinson’s disease and atypical parkinsonisms

Background

Parkinson's disease (PD) is the second most common neurodegenerative disorder whose prevalence rises with age, yet clinical diagnosis is still a challenging task due to similar manifestations of other neurodegenerative movement disorders. In untreated patients or those with unclear responses to medication, correct percentages of early diagnoses go as low as 26%. Technology has been used in various forms to facilitate discerning between persons with PD and healthy individuals, but much less work has been dedicated to separating PD and atypical parkinsonisms.

Methods

A wearable system was developed based on inertial sensors that capture the movements of fingers during repetitive finger tapping. A k-nearest-neighbor classifier was used on features extracted from gyroscope recordings for quick aid in differential diagnostics, discerning patients with PD, progressive supranuclear palsy (PSP), multiple system atrophy (MSA) and healthy controls (HC).

Results

The overall classification accuracy achieved was 85.18% in the multiclass setup. MSA and HC groups were the easiest to discern (100%), while PSP was the most elusive diagnosis, as some patients were incorrectly assigned to MSA and HC groups.

Conclusions

The system shows potential for use as a tool for quick diagnostic aid, and in the era of big data, offers a means of standardization of data collection that could allow scientists to aggregate multi-center data for further research.

MNC-Net: Multi-task graph structure learning based on node clustering for early Parkinson's disease diagnosis

PURPOSE

The identification of early-stage Parkinson's disease (PD) is important for the effective management of patients, affecting their treatment and prognosis. Recently, structural brain networks (SBNs) have been used to diagnose PD. However, how to mine abnormal patterns from high-dimensional SBNs has been a challenge due to the complex topology of the brain. Meanwhile, the existing prediction mechanisms of deep learning models are often complicated, and it is difficult to extract effective interpretations. In addition, most works only focus on the classification of imaging and ignore clinical scores in practical applications, which limits the ability of the model. Inspired by the regional modularity of SBNs, we adopted graph learning from the perspective of node clustering to construct an interpretable framework for PD classification.

METHODS

In this study, a multi-task graph structure learning framework based on node clustering (MNC-Net) is proposed for the early diagnosis of PD. Specifically, we modeled complex SBNs into modular graphs that facilitated the representation learning of abnormal patterns. Traditional graph neural networks are optimized through graph structure learning based on node clustering, which identifies potentially abnormal brain regions and reduces the impact of irrelevant noise. Furthermore, we employed a regression task to link clinical scores to disease classification, and incorporated latent domain information into model training through multi-task learning.

RESULTS

We validated the proposed approach on the Parkinsons Progression Markers Initiative dataset. Experimental results showed that our MNC-Net effectively separated the early-stage PD from healthy controls(HC) with an accuracy of 95.5%. The t-SNE figures have showed that our graph structure learning method can capture more efficient and discriminatory features. Furthermore, node clustering parameters were used as important weights to extract salient task-related brain regions(ROIs). These ROIs are involved in the development of mood disorders, tremors, imbalances and other symptoms, highlighting the importance of memory, language and mild motor function in early PD. In addition, statistical results from clinical scores confirmed that our model could capture abnormal connectivity that was significantly different between PD and HC. These results are consistent with previous studies, demonstrating the interpretability of our methods.

Evaluating white matter alterations in Parkinson's disease-related parkin S/N167 mutation carriers using tract-based spatial statistics

Background

Genetic susceptibility plays an important role in the pathogenesis of Parkinson’s disease (PD). parkin S/N167 mutations may increase the risk of PD and affect white matter fibers in the brain. This cross-sectional study explored the effects of gene polymorphisms on white matter fiber damage in PD.

Methods

In all, 54 cases were enrolled in the study, including PD patients carrying parkin gene S/N167 mutations (G/A), PD patients without gene S/N167 mutations (G/G), and healthy controls (HC). The whole-brain white matter fiber skeleton was analyzed using the tract-based spatial statistics (TBSS) method. Two-way analysis of variance (ANOVA) and post hoc tests were used for data analyses.

Results

Two classification methods were used; one was based on disease classification, with 26 patients in the PD group (n=12 G/G, n=14 G/A) and 28 in the HC group (n=15 G/G, n=13 G/A), and the other was based on genetic classification, with 27 patients in the G/G group and 27 in the G/A group. In the G/A group, there was a wide range of significant changes in fractional anisotropy (FA), radial diffusivity (RD), and mean diffusivity (MD) values (P<0.05). There was also a significant decrease in FA in the PD-G/A group compared with the PD-G/G and HC-G/A groups (P<0.05).

Conclusions

There were more extensive brain white matter fiber damage and changes in PD patients; the G/A polymorphism may cause more extensive brain white matter damage.

Cerebellar Microstructural Abnormalities in Parkinson's Disease: a Systematic Review of Diffusion Tensor Imaging Studies

Diffusion tensor imaging (DTI) is now having a strong momentum in research to evaluate the neural fibers of the CNS. This technique can study white matter (WM) microstructure in neurodegenerative disorders, including Parkinson's disease (PD). Previous neuroimaging studies have suggested cerebellar involvement in the pathogenesis of PD, and these cerebellum alterations can correlate with PD symptoms and stages. Using the PRISMA 2020 framework, PubMed and EMBASE were searched to retrieve relevant articles. Our search revealed 472 articles. After screening titles and abstracts, and full-text review, and implementing the inclusion criteria, 68 papers were selected for synthesis. Reviewing the selected studies revealed that the patterns of reduction in cerebellum WM integrity, assessed by fractional anisotropy, mean diffusivity, radial diffusivity, and axial diffusivity measures can differ symptoms and stages of PD. Cerebellar diffusion tensor imaging (DTI) changes in PD patients with "postural instability and gait difficulty" are significantly different from "tremor dominant" PD patients. Freezing of the gate is strongly related to cerebellar involvement depicted by DTI. The "reduced cognition," "visual disturbances," "sleep disorders," "depression," and "olfactory dysfunction" are not related to cerebellum microstructural changes on DTI, while "impulsive-compulsive behavior" can be linked to cerebellar WM alteration. Finally, higher PD stages and longer disease duration are associated with cerebellum white matter alteration depicted by DTI. Depiction of cerebellar white matter involvement in PD is feasible by DTI. There is an association with disease duration and severity and several clinical presentations with DTI findings. This clinical-imaging association may eventually improve disease management.

Significance of deep learning for Covid-19: state-of-the-art review

Purpose

The appearance of the 2019 novel coronavirus (Covid-19), for which there is no treatment or a vaccine, formed a sense of necessity for new drug discovery advances. The pandemic of NCOV-19 (novel coronavirus-19) has been engaged as a public health disaster of overall distress by the World Health Organization. Different pandemic models for NCOV-19 are being exploited by researchers all over the world to acquire experienced assessments and impose major control measures. Among the standard techniques for NCOV-19 global outbreak prediction, epidemiological and simple statistical techniques have attained more concern by researchers. Insufficiency and deficiency of health tests for identifying a solution became a major difficulty in controlling the spread of NCOV-19. To solve this problem, deep learning has emerged as a novel solution over a dozen of machine learning techniques. Deep learning has attained advanced performance in medical applications. Deep learning has the capacity of recognizing patterns in large complex datasets. They are identified as an appropriate method for analyzing affected patients of NCOV-19. Conversely, these techniques for disease recognition focus entirely on enhancing the accurateness of forecasts or classifications without the ambiguity measure in a decision. Knowing how much assurance present in a computer-based health analysis is necessary for gaining clinicians’ expectations in the technology and progress treatment consequently. Today, NCOV-19 diseases are the main healthcare confront throughout the world. Detecting NCOV-19 in X-ray images is vital for diagnosis, treatment, and evaluation. Still, analytical ambiguity in a report is a difficult yet predictable task for radiologists.

Method

In this paper, an in-depth analysis has been performed on the significance of deep learning for Covid-19 and as per the standard search database, this is the first review research work ever made concentrating particularly on Deep Learning for NCOV-19.

Conclusion

The main aim behind this research work is to inspire the research community and to innovate novel research using deep learning. Moreover, the outcome of this detailed structured review on the impact of deep learning in covid-19 analysis will be helpful for further investigations on various modalities of diseases detection, prevention and finding novel solutions.

Computer-Aided Classification Framework of Parkinsonian Disorders Using 11C-CFT PET Imaging

Purpose

To investigate the usefulness of a novel computer-aided classification framework for the differential diagnosis of parkinsonian disorders (PDs) based on ¹¹C-methyl-N-2β-carbomethoxy-3β-(4-fluorophenyl)-tropanel (¹¹C-CFT) positron emission tomography (PET) imaging.

Methods

Patients with different forms of PDs—including Parkinson's disease (PD), multiple system atrophy (MSA) and progressive supranuclear palsy (PSP)—underwent dopamine transporter (DAT) imaging with ¹¹C-CFT PET. A novel multistep computer-aided classification framework—consisting of magnetic resonance imaging (MRI)-assisted PET segmentation, feature extraction and prediction, and automatic subject classification—was developed. A random forest method was used to assess the diagnostic relevance of different regions to the classification process. Finally, the performance of the computer-aided classification system was tested using various training strategies involving patients with early and advanced disease stages.

Results

Accuracy values for identifying PD, MSA, and PSP were 85.0, 82.2, and 89.7%, respectively—with an overall accuracy of 80.4%. The caudate and putamen provided the highest diagnostic relevance to the proposed classification framework, whereas the contribution of midbrain was negligible. With the exception of sensitivity for diagnosing PSP, the strategy comprising both early and advanced disease stages performed better in terms of sensitivity, specificity, positive predictive value, and negative predictive value within each PDs subtype.

Conclusions

The proposed computer-aided classification framework based on ¹¹C-CFT PET imaging holds promise for improving the differential diagnosis of PDs.

Mining imaging and clinical data with machine learning approaches for the diagnosis and early detection of Parkinson's disease

Parkinson’s disease (PD) is a common, progressive, and currently incurable neurodegenerative movement disorder. The diagnosis of PD is challenging, especially in the differential diagnosis of parkinsonism and in early PD detection. Due to the advantages of machine learning such as learning complex data patterns and making inferences for individuals, machine-learning techniques have been increasingly applied to the diagnosis of PD, and have shown some promising results. Machine-learning-based imaging applications have made it possible to help differentiate parkinsonism and detect PD at early stages automatically in a number of neuroimaging studies. Comparative studies have shown that machine-learning-based SPECT image analysis applications in PD have outperformed conventional semi-quantitative analysis in detecting PD-associated dopaminergic degeneration, performed comparably well as experts’ visual inspection, and helped improve PD diagnostic accuracy of radiologists. Using combined multi-modal (imaging and clinical) data in these applications may further enhance PD diagnosis and early detection. To integrate machine-learning-based diagnostic applications into clinical systems, further validation and optimization of these applications are needed to make them accurate and reliable. It is anticipated that machine-learning techniques will further help improve differential diagnosis of parkinsonism and early detection of PD, which may reduce the error rate of PD diagnosis and help detect PD at pre-motor stage to make it possible for early treatments (e.g., neuroprotective treatment) to slow down PD progression, prevent severe motor symptoms from emerging, and relieve patients from suffering.

Machine Learning for the Diagnosis of Parkinson's Disease: A Review of Literature

Diagnosis of Parkinson's disease (PD) is commonly based on medical observations and assessment of clinical signs, including the characterization of a variety of motor symptoms. However, traditional diagnostic approaches may suffer from subjectivity as they rely on the evaluation of movements that are sometimes subtle to human eyes and therefore difficult to classify, leading to possible misclassification. In the meantime, early non-motor symptoms of PD may be mild and can be caused by many other conditions. Therefore, these symptoms are often overlooked, making diagnosis of PD at an early stage challenging. To address these difficulties and to refine the diagnosis and assessment procedures of PD, machine learning methods have been implemented for the classification of PD and healthy controls or patients with similar clinical presentations (e.g., movement disorders or other Parkinsonian syndromes). To provide a comprehensive overview of data modalities and machine learning methods that have been used in the diagnosis and differential diagnosis of PD, in this study, we conducted a literature review of studies published until February 14, 2020, using the PubMed and IEEE Xplore databases. A total of 209 studies were included, extracted for relevant information and presented in this review, with an investigation of their aims, sources of data, types of data, machine learning methods and associated outcomes. These studies demonstrate a high potential for adaptation of machine learning methods and novel biomarkers in clinical decision making, leading to increasingly systematic, informed diagnosis of PD.

Artificial intelligence in neurodegenerative diseases: A review of available tools with a focus on machine learning techniques

Neurodegenerative diseases have shown an increasing incidence in the older population in recent years. A significant amount of research has been conducted to characterize these diseases. Computational methods, and particularly machine learning techniques, are now very useful tools in helping and improving the diagnosis as well as the disease monitoring process. In this paper, we provide an in-depth review on existing computational approaches used in the whole neurodegenerative spectrum, namely for Alzheimer's, Parkinson's, and Huntington's Diseases, Amyotrophic Lateral Sclerosis, and Multiple System Atrophy. We propose a taxonomy of the specific clinical features, and of the existing computational methods. We provide a detailed analysis of the various modalities and decision systems employed for each disease. We identify and present the sleep disorders which are present in various diseases and which represent an important asset for onset detection. We overview the existing data set resources and evaluation metrics. Finally, we identify current remaining open challenges and discuss future perspectives.

Utility of Multi-Modal MRI for Differentiating of Parkinson's Disease and Progressive Supranuclear Palsy Using Machine Learning

Background: Patients with Parkinson's disease (PD) and progressive supranuclear palsy Richardson's syndrome (PSP-RS) often show overlapping clinical features, leading to misdiagnoses. The objective of this study was to investigate the feasibility and utility of using multi-modal MRI datasets for an automatic differentiation of PD patients, PSP-RS patients, and healthy control (HC) subjects. Material and Methods: T1-weighted, T2-weighted, and diffusion-tensor (DTI) MRI datasets from 45 PD patients, 20 PSP-RS patients, and 38 HC subjects were available for this study. Using an atlas-based approach, regional values of brain morphology (T1-weighted), brain iron metabolism (T2-weighted), and microstructural integrity (DTI) were measured and employed for feature selection and subsequent classification using combinations of various established machine learning methods. Results: The optimal machine learning model using regional morphology features only achieved a classification accuracy of 65% (67/103 correct classifications) differentiating PD patients, PSP-RS patients, and HC subjects. The optimal machine learning model using only quantitative T2 values performed slightly better and achieved an accuracy of 75.7% (78/103). The optimal classifier using DTI features alone performed considerably better with 95.1% accuracy (98/103). The optimal multi-modal classifier using all features also achieved an accuracy of 95.1% but required more features and achieved a slightly lower F1-score compared to the optimal model using DTI features alone. Conclusion: Machine learning models using multi-modal MRI perform significantly better than uni-modal machine learning models using morphological parameters based on T1-weighted MRI datasets alone or brain iron metabolism markers based on T2-weighted MRI datasets alone. However, machine learnig models using regional brain microstructural integrity metrics computed from DTI datasets perform similar to the optimal multi-modal machine learning model. Thus, given the results from this study cohort, it appears that morphology and brain iron metabolism markers may not provide additional value for classification compared to using DTI metrics alone.

Computer-assisted Parkinson's disease diagnosis using fuzzy optimum- path forest and Restricted Boltzmann Machines

Parkinson's disease (PD) is a progressive neurodegenerative illness associated with motor skill disorders, affecting thousands of people, mainly elderly, worldwide. Since its symptoms are not clear and commonly confused with other diseases, providing early diagnosis is a challenging task for traditional methods. In this context, computer-aided assistance is an alternative method for a fast and automatic diagnosis, accelerating the treatment and alleviating an excessive effort from professionals. Moreover, the most recent studies proposing a solution to this problem lack in computational efficiency, prediction power, reliability among other factors. Therefore, this work proposes a Fuzzy Optimum Path Forest for automated PD identification, which is based on fuzzy logic and graph-based framework theory. Experiments consider a dataset composed of features extracted from hand-drawn images using Restricted Boltzmann Machines, and results are compared with baseline models such as Support Vector Machines, KNN, and the standard OPF classifier. Results show that the proposed model outperforms the baselines in most cases, suggesting the Fuzzy OPF as a viable alternative to deal with PD detection problems.

Machine learning prediction of neurocognitive impairment among people with HIV using clinical and multimodal magnetic resonance imaging data

Diagnosis of HIV-associated neurocognitive impairment (NCI) continues to be a clinical challenge. The purpose of this study was to develop a prediction model for NCI among people with HIV using clinical- and magnetic resonance imaging (MRI)-derived features. The sample included 101 adults with chronic HIV disease. NCI was determined using a standardized neuropsychological testing battery comprised of seven domains. MRI features included gray matter volume from high-resolution anatomical scans and white matter integrity from diffusion-weighted imaging. Clinical features included demographics, substance use, and routine laboratory tests. Least Absolute Shrinkage and Selection Operator Logistic regression was used to perform variable selection on MRI features. These features were subsequently used to train a support vector machine (SVM) to predict NCI. Three different classification tasks were performed: one used only clinical features; a second used only selected MRI features; a third used both clinical and selected MRI features. Model performance was evaluated by area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity with a tenfold cross-validation. The SVM classifier that combined selected MRI with clinical features outperformed the model using clinical features or MRI features alone (AUC: 0.83 vs. 0.62 vs. 0.79; accuracy: 0.80 vs. 0.65 vs. 0.72; sensitivity: 0.86 vs. 0.85 vs. 0.86; specificity: 0.71 vs. 0.37 vs. 0.52). Our results provide preliminary evidence that combining clinical and MRI features can increase accuracy in predicting NCI and could be developed as a potential tool for NCI diagnosis in HIV clinical practice.

Towards accurate and unbiased imaging-based differentiation of Parkinson's disease, progressive supranuclear palsy and corticobasal syndrome

The early and accurate differential diagnosis of parkinsonian disorders is still a significant challenge for clinicians. In recent years, a number of studies have used magnetic resonance imaging data combined with machine learning and statistical classifiers to successfully differentiate between different forms of Parkinsonism. However, several questions and methodological issues remain, to minimize bias and artefact-driven classification. In this study, we compared different approaches for feature selection, as well as different magnetic resonance imaging modalities, with well-matched patient groups and tightly controlling for data quality issues related to patient motion. Our sample was drawn from a cohort of 69 healthy controls, and patients with idiopathic Parkinson’s disease (n = 35), progressive supranuclear palsy Richardson’s syndrome (n = 52) and corticobasal syndrome (n = 36). Participants underwent standardized T1-weighted and diffusion-weighted magnetic resonance imaging. Strict data quality control and group matching reduced the control and patient numbers to 43, 32, 33 and 26, respectively. We compared two different methods for feature selection and dimensionality reduction: whole-brain principal components analysis, and an anatomical region-of-interest based approach. In both cases, support vector machines were used to construct a statistical model for pairwise classification of healthy controls and patients. The accuracy of each model was estimated using a leave-two-out cross-validation approach, as well as an independent validation using a different set of subjects. Our cross-validation results suggest that using principal components analysis for feature extraction provides higher classification accuracies when compared to a region-of-interest based approach. However, the differences between the two feature extraction methods were significantly reduced when an independent sample was used for validation, suggesting that the principal components analysis approach may be more vulnerable to overfitting with cross-validation. Both T1-weighted and diffusion magnetic resonance imaging data could be used to successfully differentiate between subject groups, with neither modality outperforming the other across all pairwise comparisons in the cross-validation analysis. However, features obtained from diffusion magnetic resonance imaging data resulted in significantly higher classification accuracies when an independent validation cohort was used. Overall, our results support the use of statistical classification approaches for differential diagnosis of parkinsonian disorders. However, classification accuracy can be affected by group size, age, sex and movement artefacts. With appropriate controls and out-of-sample cross validation, diagnostic biomarker evaluation including magnetic resonance imaging based classifiers may be an important adjunct to clinical evaluation.

A Fully Automatic Framework for Parkinson's Disease Diagnosis by Multi-Modality Images

Background

Parkinson’s disease (PD) is a prevalent long-term neurodegenerative disease. Though the criteria of PD diagnosis are relatively well defined, current diagnostic procedures using medical images are labor-intensive and expertise-demanding. Hence, highly integrated automatic diagnostic algorithms are desirable.

Methods

In this work, we propose an end-to-end multi-modality diagnostic framework, including segmentation, registration, feature extraction and machine learning, to analyze the features of striatum for PD diagnosis. Multi-modality images, including T1-weighted MRI and ¹¹C-CFT PET, are integrated into the proposed framework. The reliability of this method is validated on a dataset with the paired images from 49 PD subjects and 18 Normal (NL) subjects.

Results

We obtained a promising diagnostic accuracy in the PD/NL classification task. Meanwhile, several comparative experiments were conducted to validate the performance of the proposed framework.

Conclusion

We demonstrated that (1) the automatic segmentation provides accurate results for the diagnostic framework, (2) the method combining multi-modality images generates a better prediction accuracy than the method with single-modality PET images, and (3) the volume of the striatum is proved to be irrelevant to PD diagnosis.

Use of Magnetic Resonance Imaging and Artificial Intelligence in Studies of Diagnosis of Parkinson's Disease

Parkinson's disease (PD) is a common neurodegenerative disorder. It has a delitescent onset and a slow progress. The clinical manifestations of PD in patients are highly heterogeneous. Thus, PD diagnosis process is complex and mainly depends on the professional knowledge and experience of the physician. Magnetic resonance imaging (MRI) could detect the small changes in the brain of PD patients, and quantitative analysis of brain MRI may improve the clinical diagnosis efficiency. However, due to the complexity of clinical courses in PD and the high dimensionality in multimodal MRI data, traditional mathematical analysis could not effectively extract the huge information in them. Up to now, the accuracy of PD diagnosis in large sample size is still unsatisfying. As artificial intelligence (AI) is becoming more mature, varieties of statistical models and machine learning (ML) algorithms have been used for quantitative imaging data analysis to explore a diagnostic result. This review aims to state an overview of existing research recently that used statistical ML/AI methods to perform quantitative analysis of MR image data for the study of PD diagnosis. First we review the recent research in three subareas: diagnosis, differential diagnosis, and subtyping of PD. Then we described the overall workflow from MR image to classification result. Finally, we summarized a critical assessment of the current research and provide some recommendations for likely future research developments and trends.

Disrupted structural connectivity of fronto-deep gray matter pathways in progressive supranuclear palsy

Background

Structural connectivity is a promising methodology to detect patterns of neural network dysfunction in neurodegenerative diseases. This approach has not been tested in progressive supranuclear palsy (PSP).

Objectives

The aim of this study is reconstructing the structural connectome to characterize and detect the pathways of degeneration in PSP patients compared with healthy controls and their correlation with clinical features. The second objective is to assess the potential of structural connectivity measures to distinguish between PSP patients and healthy controls at the single-subject level.

Methods

Twenty healthy controls and 19 PSP patients underwent diffusion-weighted MRI with a 3T scanner. Structural connectivity, represented by number of streamlines, was derived from probabilistic tractography. Global and local network metrics were calculated based on graph theory.

Results

Reduced numbers of streamlines were predominantly found in connections between frontal areas and deep gray matter (DGM) structures in PSP compared with controls. Significant changes in structural connectivity correlated with clinical features in PSP patients. An abnormal small-world architecture was detected in the subnetwork comprising the frontal lobe and DGM structures in PSP patients. The classification procedure achieved an overall accuracy of 82.23% with 94.74% sensitivity and 70% specificity.

Conclusion

Our findings suggest that modelling the brain as a structural connectome is a useful method to detect changes in the organization and topology of white matter tracts in PSP patients. Secondly, measures of structural connectivity have the potential to correctly discriminate between PSP patients and healthy controls.

•

Reduced structural connectivity in PSP patients compared with healthy controls

•

Connectivity reductions in fronto-DGM tracts correlate with PSPRS and FAB scores

•

PSP patients present abnormal small-world architecture in the fronto-DGM network.

Classification of degenerative parkinsonism subtypes by support-vector-machine analysis and striatal 123I-FP-CIT indices

Objectives

To provide an automated classification method for degenerative parkinsonian syndromes (PS) based on semiquantitative ¹²³I-FP-CIT SPECT striatal indices and support-vector-machine (SVM) analysis.

Methods

¹²³I-FP-CIT SPECT was performed at a single-center level on 370 individuals with PS, including 280 patients with Parkinson’s disease (PD), 21 with multiple system atrophy-parkinsonian type (MSA-P), 41 with progressive supranuclear palsy (PSP) and 28 with corticobasal syndrome (CBS) (mean age 70.3 years, 47% female, mean disease duration at scan 1.4 year), as well as 208 age- and gender-matched control subjects. Striatal volumes-of-interest (VOIs) uptake, VOIs asymmetry indices (AIs) and caudate/putamen (C/P) ratio were used as input for SVM individual classification using fivefold cross-validation.

Results

Univariate analyses showed significantly lower VOIs uptake, higher striatal AI and C/P ratio for each PS in comparison to controls (all p < 0.001). Among PS, higher degree of striatal impairment was observed in MSA-P and PSP, while CBS showed moderate uptake reduction and higher AI. Binary SVM classification showed 92.9% accuracy in distinguishing PS from controls. Classification based on each binary combination of PS ranged 62.9–83.7% accuracy with the most satisfactory results when separating CBS from the other PS. Sensitivity and specificity values were high and balanced ranging from 60 to 80% for all analyses with > 70% accuracy. Overall, striatal AI and C/P ratio on the more affected side had the highest weighting factors.

Conclusion

Semiquantitative ¹²³I-FP-CIT SPECT striatal evaluation combined with SVM represents a promising approach to disentangle PD from non-degenerative conditions and from atypical PS at the early stage.

White Matter Connectome Edge Density in Children with Autism Spectrum Disorders: Potential Imaging Biomarkers Using Machine-Learning Models

Prior neuroimaging studies have reported white matter network underconnectivity as a potential mechanism for autism spectrum disorder (ASD). In this study, we examined the structural connectome of children with ASD using edge density imaging (EDI), and then applied machine-learning algorithms to identify children with ASD based on tract-based connectivity metrics. Boys aged 8-12 years were included: 14 with ASD and 33 typically developing children. The edge density (ED) maps were computed from probabilistic streamline tractography applied to high angular resolution diffusion imaging. Tract-based spatial statistics was used for voxel-wise comparison and coregistration of ED maps in addition to conventional diffusion tensor imaging (DTI) metrics of fractional anisotropy (FA), mean diffusivity (MD), and radial diffusivity (RD). Tract-based average DTI/connectome metrics were calculated and used as input for different machine-learning models: naïve Bayes, random forest, support vector machines (SVMs), and neural networks. For these models, cross-validation was performed with stratified random sampling ( × 1,000 permutations). The average accuracy among validation samples was calculated. In voxel-wise analysis, the body and splenium of corpus callosum, bilateral superior and posterior corona radiata, and left superior longitudinal fasciculus showed significantly lower ED in children with ASD; whereas, we could not find significant difference in FA, MD, and RD maps between the two study groups. Overall, machine-learning models using tract-based ED metrics had better performance in identification of children with ASD compared with those using FA, MD, and RD. The EDI-based random forest models had greater average accuracy (75.3%), specificity (97.0%), and positive predictive value (81.5%), whereas EDI-based polynomial SVM had greater sensitivity (51.4%) and negative predictive values (77.7%). In conclusion, we found reduced density of connectome edges in the posterior white matter tracts of children with ASD, and demonstrated the feasibility of connectome-based machine-learning algorithms in identification of children with ASD.

Assessing Working Memory in Mild Cognitive Impairment with Serial Order Recall

BACKGROUND

Working memory (WM) is often assessed with serial order tests such as repeating digits backward. In prior dementia research using the Backward Digit Span Test (BDT), only aggregate test performance was examined.

OBJECTIVE

The current research tallied primacy/recency effects, out-of-sequence transposition errors, perseverations, and omissions to assess WM deficits in patients with mild cognitive impairment (MCI).

METHODS

Memory clinic patients (n = 66) were classified into three groups: single domain amnestic MCI (aMCI), combined mixed domain/dysexecutive MCI (mixed/dys MCI), and non-MCI where patients did not meet criteria for MCI. Serial order/WM ability was assessed by asking participants to repeat 7 trials of five digits backwards. Serial order position accuracy, transposition errors, perseverations, and omission errors were tallied.

RESULTS

A 3 (group)×5 (serial position) repeated measures ANOVA yielded a significant group×trial interaction. Follow-up analyses found attenuation of the recency effect for mixed/dys MCI patients. Mixed/dys MCI patients scored lower than non-MCI patients for serial position 3 (p < 0.003) serial position 4 (p < 0.002); and lower than both group for serial position 5 (recency; p < 0.002). Mixed/dys MCI patients also produced more transposition errors than both groups (p < 0.010); and more omissions (p < 0.020), and perseverations errors (p < 0.018) than non-MCI patients.

CONCLUSIONS

The attenuation of a recency effect using serial order parameters obtained from the BDT may provide a useful operational definition as well as additional diagnostic information regarding working memory deficits in MCI.

FDG-PET hypometabolism is more sensitive than MRI atrophy in Parkinson's disease: A whole-brain multimodal imaging meta-analysis

Recently, revised diagnostic criteria for Parkinson's disease (PD) were introduced (Postuma et al., 2015). Yet, except for well-established dopaminergic imaging, validated imaging biomarkers for PD are still missing, though they could improve diagnostic accuracy. We conducted systematic meta-analyses to identify PD-specific markers in whole-brain structural magnetic resonance imaging (MRI), [18F]-fluorodeoxyglucose-positron emission tomography (FDG-PET) and diffusion tensor imaging (DTI) studies. Overall, 74 studies were identified including 2323 patients and 1767 healthy controls. Studies were first grouped according to imaging modalities (MRI 50; PET 14; DTI 10) and then into subcohorts based on clinical phenotypes. To ensure reliable results, we combined established meta-analytical algorithms - anatomical likelihood estimation and seed-based D mapping - and cross-validated them in a conjunction analysis. Glucose hypometabolism was found using FDG-PET extensively in bilateral inferior parietal cortex and left caudate nucleus with both meta-analytic methods. This hypometabolism pattern was confirmed in subcohort analyses and related to cognitive deficits (inferior parietal cortex) and motor symptoms (caudate nucleus). Structural MRI showed only small focal gray matter atrophy in the middle occipital gyrus that was not confirmed in subcohort analyses. DTI revealed fractional anisotropy reductions in the cingulate bundle near the orbital and anterior cingulate gyri in PD. Our results suggest that FDG-PET reliably identifies consistent functional brain abnormalities in PD, whereas structural MRI and DTI show only focal alterations and rather inconsistent results. In conclusion, FDG-PET hypometabolism outperforms structural MRI in PD, although both imaging methods do not offer disease-specific imaging biomarkers for PD.

Survey of Image Processing Techniques for Brain Pathology Diagnosis: Challenges and Opportunities

In recent years, a number of new products introduced to the global market combine intelligent robotics, artificial intelligence and smart interfaces to provide powerful tools to support professional decision making. However, while brain disease diagnosis from the brain scan images is supported by imaging robotics, the data analysis to form a medical diagnosis is performed solely by highly trained medical professionals. Recent advances in medical imaging techniques, artificial intelligence, machine learning and computer vision present new opportunities to build intelligent decision support tools to aid the diagnostic process, increase the disease detection accuracy, reduce error, automate the monitoring of patient's recovery, and discover new knowledge about the disease cause and its treatment. This article introduces the topic of medical diagnosis of brain diseases from the MRI based images. We describe existing, multi-modal imaging techniques of the brain's soft tissue and describe in detail how are the resulting images are analyzed by a radiologist to form a diagnosis. Several comparisons between the best results of classifying natural scenes and medical image analysis illustrate the challenges of applying existing image processing techniques to the medical image analysis domain. The survey of medical image processing methods also identified several knowledge gaps, the need for automation of image processing analysis, and the identification of the brain structures in the medical images that differentiate healthy tissue from a pathology. This survey is grounded in the cases of brain tumor analysis and the traumatic brain injury diagnoses, as these two case studies illustrate the vastly different approaches needed to define, extract, and synthesize meaningful information from multiple MRI image sets for a diagnosis. Finally, the article summarizes artificial intelligence frameworks that are built as multi-stage, hybrid, hierarchical information processing work-flows and the benefits of applying these models for medical diagnosis to build intelligent physician's aids with knowledge transparency, expert knowledge embedding, and increased analytical quality.

Widespread diffusion changes differentiate Parkinson's disease and progressive supranuclear palsy

BACKGROUND

Parkinson's disease (PD) and progressive supranuclear palsy - Richardson's syndrome (PSP-RS) are often represented by similar clinical symptoms, which may challenge diagnostic accuracy. The objective of this study was to investigate and compare regional cerebral diffusion properties in PD and PSP-RS subjects and evaluate the use of these metrics for an automatic classification framework.

MATERIAL AND METHODS

Diffusion-tensor MRI datasets from 52 PD and 21 PSP-RS subjects were employed for this study. Using an atlas-based approach, regional median values of mean diffusivity (MD), fractional anisotropy (FA), radial diffusivity (RD), and axial diffusivity (AD) were measured and employed for feature selection using RELIEFF and subsequent classification using a support vector machine.

RESULTS

According to RELIEFF, the top 17 diffusion values consisting of deep gray matter structures, the brainstem, and frontal cortex were found to be especially informative for an automatic classification. A MANCOVA analysis performed on these diffusion values as dependent variables revealed that PSP-RS and PD subjects differ significantly (p < .001). Generally, PSP-RS subjects exhibit reduced FA, and increased MD, RD, and AD values in nearly all brain structures analyzed compared to PD subjects. The leave-one-out cross-validation of the support vector machine classifier revealed that the classifier can differentiate PD and PSP-RS subjects with an accuracy of 87.7%. More precisely, six PD subjects were wrongly classified as PSP-RS and three PSP-RS subjects were wrongly classified as PD.

CONCLUSION

The results of this study demonstrate that PSP-RS subjects exhibit widespread and more severe diffusion alterations compared to PD patients, which appears valuable for an automatic computer-aided diagnosis approach.

Structural Imaging in Atypical Parkinsonism

Qualitative and quantitative structural magnetic resonance imaging offer objective measures of the underlying neurodegeneration in atypical parkinsonism. Regional changes in tissue volume, signal changes and increased deposition of iron as assessed with different structural MRI techniques are surrogate markers of underlying neurodegeneration and may reflect cell loss, microglial proliferation and astroglial activation. Structural MRI has been explored as a tool to enhance diagnostic accuracy in differentiating atypical parkinsonian disorders (APDs). Moreover, the longitudinal assessment of serial structural MRI-derived parameters offers the opportunity for robust inferences regarding the progression of APDs. This review summarizes recent research findings as (1) a diagnostic tool for APDs as well as (2) as a tool to assess longitudinal changes of serial MRI-derived parameters in the different APDs.

Structural neuroimaging as clinical predictor: A review of machine learning applications

In this paper, we provide an extensive overview of machine learning techniques applied to structural magnetic resonance imaging (MRI) data to obtain clinical classifiers. We specifically address practical problems commonly encountered in the literature, with the aim of helping researchers improve the application of these techniques in future works. Additionally, we survey how these algorithms are applied to a wide range of diseases and disorders (e.g. Alzheimer's disease (AD), Parkinson's disease (PD), autism, multiple sclerosis, traumatic brain injury, etc.) in order to provide a comprehensive view of the state of the art in different fields.

Machine Learning Interface for Medical Image Analysis

TensorFlow is a second-generation open-source machine learning software library with a built-in framework for implementing neural networks in wide variety of perceptual tasks. Although TensorFlow usage is well established with computer vision datasets, the TensorFlow interface with DICOM formats for medical imaging remains to be established. Our goal is to extend the TensorFlow API to accept raw DICOM images as input; 1513 DaTscan DICOM images were obtained from the Parkinson's Progression Markers Initiative (PPMI) database. DICOM pixel intensities were extracted and shaped into tensors, or n-dimensional arrays, to populate the training, validation, and test input datasets for machine learning. A simple neural network was constructed in TensorFlow to classify images into normal or Parkinson's disease groups. Training was executed over 1000 iterations for each cross-validation set. The gradient descent optimization and Adagrad optimization algorithms were used to minimize cross-entropy between the predicted and ground-truth labels. Cross-validation was performed ten times to produce a mean accuracy of 0.938 ± 0.047 (95 % CI 0.908-0.967). The mean sensitivity was 0.974 ± 0.043 (95 % CI 0.947-1.00) and mean specificity was 0.822 ± 0.207 (95 % CI 0.694-0.950). We extended the TensorFlow API to enable DICOM compatibility in the context of DaTscan image analysis. We implemented a neural network classifier that produces diagnostic accuracies on par with excellent results from previous machine learning models. These results indicate the potential role of TensorFlow as a useful adjunct diagnostic tool in the clinical setting.

Classification of ADHD with bi-objective optimization

Attention Deficit Hyperactive Disorder (ADHD) is one of the most common diseases in school aged children. In this paper, we consider using fMRI data with classification techniques to aid the diagnosis of ADHD and propose a bi-objective ADHD classification scheme based on L₁-norm support vector machine (SVM). In our classification model, two objectives, namely, the margin of separation and the empirical error are considered at the same time. Then the normal boundary intersection (NBI) method of Das and Dennis is used to solve the bi-objective optimization problem. A representative nondominated set which reflects the entire trade-off information between the two objectives is obtained. Each representative nondominated point in the set corresponds to an efficient classifier. Finally a decision maker can choose a final efficient classifier from the set according to the performance of each classifier. Our scheme avoids the trial and error process for regularization hyper-parameter selection. Experimental results show that our bi-objective optimization classification scheme for ADHD diagnosis performs considerably better than some traditional classification methods.

Machine learning classification of first-episode schizophrenia spectrum disorders and controls using whole brain white matter fractional anisotropy

BACKGROUND

Early diagnosis of schizophrenia could improve the outcome of the illness. Unlike classical between-group comparisons, machine learning can identify subtle disease patterns on a single subject level, which could help realize the potential of MRI in establishing a psychiatric diagnosis. Machine learning has previously been predominantly tested on gray-matter structural or functional MRI data. In this paper we used a machine learning classifier to differentiate patients with a first episode of schizophrenia-spectrum disorder (FES) from healthy controls using diffusion tensor imaging.

METHODS

We applied linear support-vector machine (SVM) and traditional tract based spatial statistics between group analyses to brain fractional anisotropy (FA) data from 77 FES and 77 age and sex matched healthy controls. We also evaluated the effects of medication and symptoms on the SVM classification.

RESULTS

The SVM distinguished between patients and controls with significant accuracy of 62.34% (p = 0.005). Participants with FES showed widespread FA reductions relative to controls in a large cluster (N  = 56,647 voxels, corrected p = 0.002). The white matter regions, which contributed to the correct identification of participants with FES, overlapped with the regions, which showed lower FA in patients relative to controls. There was no association between the classification performance and medication or symptoms.

CONCLUSIONS

Our results provide a proof of concept that SVM might help differentiate FES patients early in the course of illness from healthy controls using white-matter fractional anisotropy. As there was no effect of medications or symptoms, the SVM classification seemed to be based on trait rather than state markers and appeared to capture the lower FA in FES participants relative to controls.

Differentiation of neurodegenerative parkinsonian syndromes by volumetric magnetic resonance imaging analysis and support vector machine classification

BACKGROUND

Clinical differentiation of parkinsonian syndromes is still challenging.

OBJECTIVES

A fully automated method for quantitative MRI analysis using atlas-based volumetry combined with support vector machine classification was evaluated for differentiation of parkinsonian syndromes in a multicenter study.

METHODS

Atlas-based volumetry was performed on MRI data of healthy controls (n = 73) and patients with PD (204), PSP with Richardson's syndrome phenotype (106), MSA of the cerebellar type (21), and MSA of the Parkinsonian type (60), acquired on different scanners. Volumetric results were used as input for support vector machine classification of single subjects with leave-one-out cross-validation.

RESULTS

The largest atrophy compared to controls was found for PSP with Richardson's syndrome phenotype patients in midbrain (-15%), midsagittal midbrain tegmentum plane (-20%), and superior cerebellar peduncles (-13%), for MSA of the cerebellar type in pons (-33%), cerebellum (-23%), and middle cerebellar peduncles (-36%), and for MSA of the parkinsonian type in the putamen (-23%). The majority of binary support vector machine classifications between the groups resulted in balanced accuracies of >80%. With MSA of the cerebellar and parkinsonian type combined in one group, support vector machine classification of PD, PSP and MSA achieved sensitivities of 79% to 87% and specificities of 87% to 96%. Extraction of weighting factors confirmed that midbrain, basal ganglia, and cerebellar peduncles had the largest relevance for classification.

CONCLUSIONS

Brain volumetry combined with support vector machine classification allowed for reliable automated differentiation of parkinsonian syndromes on single-patient level even for MRI acquired on different scanners. © 2016 International Parkinson and Movement Disorder Society.

Analysis of white matter characteristics with tract-based spatial statistics according to diffusion tensor imaging in early Parkinson's disease

OBJECTIVE

To analyze the microstructure of brain white matter according to diffusion tensor imaging (DTI) based on tract-based spatial statistics (TBSS) in early Parkinson's disease (PD).

MATERIALS AND METHODS

A total of 31 age- and sex-matched early PD patients and 22 healthy volunteers were recruited in the present study. DTI was performed, and the data analyzed with fsl4.0 software. The fractional anisotropy (FA) was compared between both groups with an independent t test, and the differential area was analyzed. White matter fiber tracts with significant difference in FA between the two groups were selected, and their FAs were measured. Pearson's correlation analysis was employed to analyze the unified Parkinson's disease rating scale (UPDRS) score and its association with FA of different tracts.

RESULTS

When compared with healthy volunteers, early PD patients had reduced FA in the following areas: bilateral anterior corona radiate, upper corona radiate, fasciculus arcuatus, crus anterius capsulae internae, crus posterius capsulae internae, capsula externa, posterior thalamic radiation, optic radiation, sagittal layer (including fasciculus arcuatus and inferior fronto-occipital fasciculus), crura fornicis, stria terminalis, fornix, genu, body and pad of corpus callosum, left unciform fasciculus, right cingulate bundle, right medipeduncle, and arcuate fibers in the bilateral frontal, temporal, and occipital lobes (P < 0.05). When compared with healthy volunteers, early PD patients showed abnormal FA of fasciculus in the white matter mainly in following areas: bilateral crus anterius capsulae internae, bilateral capsula externa, right anterior corona radiate, body and pad of bilateral corpus callosum, and left sagittal layer (including fasciculi longitudinalis inferior and fasciculus occipitofrontalis inferior) (P < 0.05). In addition, in early PD patients, the UPDRS score and movement score had no relationship with the FA of different fasciculi in the white matter (P > 0.05).

CONCLUSION

There is wide alteration of white matter microstructure in early PD patients, which is characterized by disruption of projection fibers in the descending pathway, limbic system-related fasciculi, corpus callosum, thalamus after radiation, posterior thalamic radiation, Gratiolet's bundle and other fasciculi in the white matter.

Multi-class parkinsonian disorders classification with quantitative MR markers and graph-based features using support vector machines

BACKGROUND AND PURPOSE

In this study we attempt to automatically classify individual patients with different parkinsonian disorders, making use of pattern recognition techniques to distinguish among several forms of parkinsonisms (multi-class classification), based on a set of binary classifiers that discriminate each disorder from all others.

METHODS

We combine diffusion tensor imaging, proton spectroscopy and morphometric-volumetric data to obtain MR quantitative markers, which are provided to support vector machines with the aim of recognizing the different parkinsonian disorders. Feature selection is used to find the most important features for classification. We also exploit a graph-based technique on the set of quantitative markers to extract additional features from the dataset, and increase classification accuracy.

RESULTS

When graph-based features are not used, the MR markers that are most frequently automatically extracted by the feature selection procedure reflect alterations in brain regions that are also usually considered to discriminate parkinsonisms in routine clinical practice. Graph-derived features typically increase the diagnostic accuracy, and reduce the number of features required.

CONCLUSIONS

The results obtained in the work demonstrate that support vector machines applied to multimodal brain MR imaging and using graph-based features represent a novel and highly accurate approach to discriminate parkinsonisms, and a useful tool to assist the diagnosis.

Automatic Classification on Multi-Modal MRI Data for Diagnosis of the Postural Instability and Gait Difficulty Subtype of Parkinson's Disease

BACKGROUND

Patients with the postural instability and gait difficulty subtype (PIGD) of Parkinson's disease (PD) are a refractory challenge in clinical practice. Despite previous attempts that have been made at studying subtype-specific brain alterations across PD population, conclusive neuroimaging biomarkers on patients with the PIGD subtype are still lacking. Machine learning-based classifications are a promising tool for differential diagnosis that effectively integrate complex and multivariate data.

OBJECTIVE

Our present study aimed to introduce the machine learning-based automatic classification for the first time to distinguish patients with the PIGD subtype from those with the non-PIGD subtype of PD at the individual level.

METHODS

Fifty-two PD patients and forty-five normal controls (NCs) were recruited and underwent multi-modal MRI scans including a set of resting-state functional, 3D T1-weighted and diffusion tensor imaging sequences. By comparing the PD patients with the NCs, features that were not conducive to the subtype-specific classification were ruled out from massive brain features. We applied a support vector machine classifier with the recursive feature elimination method to multi-modal MRI data for selecting features with the best discriminating power, and evaluated the proposed classifier with the leave-one-out cross-validation.

RESULTS

Using this classifier, we obtained satisfactory diagnostic rates (accuracy = 92.31%, specificity = 96.97%, sensitivity = 84.21% and AUCmax  = 0.9585). The diagnostic agreement evaluated by the Kappa test showed an almost perfect agreement with the existing clinical categorization (Kappa value = 0.83).

CONCLUSIONS

With these favorable results, our findings suggested the machine learning-based classification as an alternative technique to classifying clinical subtypes in PD.

Magnetic resonance imaging for the diagnosis of Parkinson's disease

The differential diagnosis of parkinsonian syndromes is considered one of the most challenging in neurology and error rates in the clinical diagnosis can be high even at specialized centres. Despite several limitations, magnetic resonance imaging (MRI) has undoubtedly enhanced the diagnostic accuracy in the differential diagnosis of neurodegenerative parkinsonism over the last three decades. This review aims to summarize research findings regarding the value of the different MRI techniques, including advanced sequences at high- and ultra-high-field MRI and modern image analysis algorithms, in the diagnostic work-up of Parkinson's disease. This includes not only the exclusion of alternative diagnoses for Parkinson's disease such as symptomatic parkinsonism and atypical parkinsonism, but also the diagnosis of early, new onset, and even prodromal Parkinson's disease.

Machine-learning classification of 22q11.2 deletion syndrome: A diffusion tensor imaging study

Chromosome 22q11.2 deletion syndrome (22q11.2DS) is a genetic neurodevelopmental syndrome that has been studied intensively in order to understand relationships between the genetic microdeletion, brain development, cognitive function, and the emergence of psychiatric symptoms. White matter microstructural abnormalities identified using diffusion tensor imaging methods have been reported to affect a variety of neuroanatomical tracts in 22q11.2DS. In the present study, we sought to combine two discovery-based approaches: (1) white matter query language was used to parcellate the brain's white matter into tracts connecting pairs of 34, bilateral cortical regions and (2) the diffusion imaging characteristics of the resulting tracts were analyzed using a machine-learning method called support vector machine in order to optimize the selection of a set of imaging features that maximally discriminated 22q11.2DS and comparison subjects. With this unique approach, we both confirmed previously-recognized 22q11.2DS-related abnormalities in the inferior longitudinal fasciculus (ILF), and identified, for the first time, 22q11.2DS-related anomalies in the middle longitudinal fascicle and the extreme capsule, which may have been overlooked in previous, hypothesis-guided studies. We further observed that, in participants with 22q11.2DS, ILF metrics were significantly associated with positive prodromal symptoms of psychosis.

Parkinson's disease: diagnostic utility of volumetric imaging

PURPOSE

This paper aims to examine the effectiveness of structural imaging as an aid in the diagnosis of Parkinson's disease (PD).

METHODS

High-resolution T ₁-weighted magnetic resonance imaging was performed in 72 patients with idiopathic PD (mean age, 61.08 years) and 73 healthy subjects (mean age, 58.96 years). The whole brain was parcellated into 95 regions of interest using composite anatomical atlases, and region volumes were calculated. Three diagnostic classifiers were constructed using binary multiple logistic regression modeling: the (i) basal ganglion prior classifier, (ii) data-driven classifier, and (iii) basal ganglion prior/data-driven hybrid classifier. Leave-one-out cross validation was used to unbiasedly evaluate the predictive accuracy of imaging features. Pearson's correlation analysis was further performed to correlate outcome measurement using the best PD classifier with disease severity.

RESULTS

Smaller volume in susceptible regions is diagnostic for Parkinson's disease. Compared with the other two classifiers, the basal ganglion prior/data-driven hybrid classifier had the highest diagnostic reliability with a sensitivity of 74%, specificity of 75%, and accuracy of 74%. Furthermore, outcome measurement using this classifier was associated with disease severity.

CONCLUSIONS

Brain structural volumetric analysis with multiple logistic regression modeling can be a complementary tool for diagnosing PD.

Candidate Biomarkers in Children with Autism Spectrum Disorder: A Review of MRI Studies

Searching for effective biomarkers is one of the most challenging tasks in the research field of Autism Spectrum Disorder (ASD). Magnetic resonance imaging (MRI) provides a non-invasive and powerful tool for investigating changes in the structure, function, maturation, connectivity, and metabolism of the brain of children with ASD. Here, we review the more recent MRI studies in young children with ASD, aiming to provide candidate biomarkers for the diagnosis of childhood ASD. The review covers structural imaging methods, diffusion tensor imaging, resting-state functional MRI, and magnetic resonance spectroscopy. Future advances in neuroimaging techniques, as well as cross-disciplinary studies and large-scale collaborations will be needed for an integrated approach linking neuroimaging, genetics, and phenotypic data to allow the discovery of new, effective biomarkers.

Discriminating among degenerative parkinsonisms using advanced (123)I-ioflupane SPECT analyses

(123)I-ioflupane single photon emission computed tomography (SPECT) is a sensitive and well established imaging tool in Parkinson's disease (PD) and atypical parkinsonian syndromes (APS), yet a discrimination between PD and APS has been considered inconsistent at least based on visual inspection or simple region of interest analyses. We here reappraise this issue by applying advanced image analysis techniques to separate PD from the various APS. This study included 392 consecutive patients with degenerative parkinsonism undergoing (123)I-ioflupane SPECT at our institution over the last decade: 306 PD, 24 multiple system atrophy (MSA), 32 progressive supranuclear palsy (PSP) and 30 corticobasal degeneration (CBD) patients. Data analysis included voxel-wise univariate statistical parametric mapping and multivariate pattern recognition using linear discriminant classifiers. MSA and PSP showed less ioflupane uptake in the head of caudate nucleus relative to PD and CBD, yet there was no difference between MSA and PSP. CBD had higher uptake in both putamen relative to PD, MSA and PSP. Classification was significant for PD versus APS (AUC 0.69, p < 0.05) and between APS subtypes (MSA vs CBD AUC 0.80, p < 0.05; MSA vs PSP AUC 0.69 p < 0.05; CBD vs PSP AUC 0.69 p < 0.05). Both striatal and extra-striatal regions contain classification information, yet the combination of both regions does not significantly improve classification accuracy. PD, MSA, PSP and CBD have distinct patterns of dopaminergic depletion on (123)I-ioflupane SPECT. The high specificity of 84-90% for PD versus APS indicates that the classifier is particularly useful for confirming APS cases.

Computer-based magnetic resonance imaging as a tool in clinical diagnosis in neurodegenerative diseases

Magnetic resonance imaging (MRI) is one of the core elements within the differential diagnostic work-up of patients with neurodegenerative diseases such as dementia syndromes, Parkinsonian syndromes, and motor neuron diseases. Currently, computerized MRI analyses are not routinely used for individual diagnosis; however, they have improved the anatomical understanding of pathomorphological alterations in various neurodegenerative diseases by quantitative comparisons between patients and controls at the group level. For multiparametric MRI protocols, including T1-weighted MRI, diffusion-weighted imaging, and intrinsic functional connectivity MRI, the potential as a surrogate marker is a subject of investigation. The additional value of MRI with respect to diagnosis at the individual level and for future disease-modifying multicentre trials remains to be defined. Here, we give an overview of recent applications of multiparametric MRI to patients with various neurodegenerative diseases. Starting from applications at the group level, continuous progress of a transfer to individual diagnostic classification is ongoing.

Machine learning on Parkinson's disease? Let's translate into clinical practice

Machine learning techniques represent the third-generation of clinical neuroimaging studies where the principal interest is not related to describe anatomical changes of a neurological disorder, but to evaluate if a multivariate approach may use these abnormalities to predict the correct classification of previously unseen clinical cohort. In the next few years, Machine learning will revolutionize clinical practice of Parkinson's disease, but enthusiasm should be turned down before removing some important barriers.

Neuroimaging of Parkinson's disease: Expanding views

Advances in molecular and structural and functional neuroimaging are rapidly expanding the complexity of neurobiological understanding of Parkinson's disease (PD). This review article begins with an introduction to PD neurobiology as a foundation for interpreting neuroimaging findings that may further lead to more integrated and comprehensive understanding of PD. Diverse areas of PD neuroimaging are then reviewed and summarized, including positron emission tomography, single photon emission computed tomography, magnetic resonance spectroscopy and imaging, transcranial sonography, magnetoencephalography, and multimodal imaging, with focus on human studies published over the last five years. These included studies on differential diagnosis, co-morbidity, genetic and prodromal PD, and treatments from L-DOPA to brain stimulation approaches, transplantation and gene therapies. Overall, neuroimaging has shown that PD is a neurodegenerative disorder involving many neurotransmitters, brain regions, structural and functional connections, and neurocognitive systems. A broad neurobiological understanding of PD will be essential for translational efforts to develop better treatments and preventive strategies. Many questions remain and we conclude with some suggestions for future directions of neuroimaging of PD.

Identification of infants at high-risk for autism spectrum disorder using multiparameter multiscale white matter connectivity networks

Autism spectrum disorder (ASD) is a wide range of disabilities that cause life-long cognitive impairment and social, communication, and behavioral challenges. Early diagnosis and medical intervention are important for improving the life quality of autistic patients. However, in the current practice, diagnosis often has to be delayed until the behavioral symptoms become evident during childhood. In this study, we demonstrate the feasibility of using machine learning techniques for identifying high-risk ASD infants at as early as six months after birth. This is based on the observation that ASD-induced abnormalities in white matter (WM) tracts and whole-brain connectivity have already started to appear within 24 months after birth. In particular, we propose a novel multikernel support vector machine classification framework by using the connectivity features gathered from WM connectivity networks, which are generated via multiscale regions of interest (ROIs) and multiple diffusion statistics such as fractional anisotropy, mean diffusivity, and average fiber length. Our proposed framework achieves an accuracy of 76% and an area of 0.80 under the receiver operating characteristic curve (AUC), in comparison to the accuracy of 70% and the AUC of 70% provided by the best single-parameter single-scale network. The improvement in accuracy is mainly due to the complementary information provided by multiparameter multiscale networks. In addition, our framework also provides the potential imaging connectomic markers and an objective means for early ASD diagnosis.

Differentiation of Parkinsonism-Predominant Multiple System Atrophy from Idiopathic Parkinson Disease Using 3T Susceptibility-Weighted MR Imaging, Focusing on Putaminal Change and Lesion Asymmetry

BACKGROUND AND PURPOSE

Asymmetric presentation of clinical feature in parkinsonism is common, but correlatable radiologic feature is not clearly defined. Our aim was to evaluate 3T susceptibility-weighted imaging findings for differentiating parkinsonism-predominant multiple system atrophy from idiopathic Parkinson disease, focusing on putaminal changes and lesion asymmetry.

MATERIALS AND METHODS

This retrospective cohort study included 27 patients with parkinsonism-predominant multiple system atrophy and 50 patients with idiopathic Parkinson disease diagnosed clinically. Twenty-seven age-matched subjects without evidence of movement disorders who underwent SWI were included as the control group. A consensus was reached by 2 radiologists who visually assessed SWI for the presence of putaminal atrophy and marked signal hypointensity on each side of the posterolateral putamen. We also quantitatively measured putaminal width and phase-shift values.

RESULTS

The mean disease duration was 4.7 years for the patients with parkinsonism-predominant multiple system atrophy and 7.8 years for the patients with idiopathic Parkinson disease. In the patients with parkinsonism-predominant multiple system atrophy, putaminal atrophy was frequently observed (14/27, 51.9%) and was most commonly found in the unilateral putamen (13/14). Marked signal hypointensity was observed in 12 patients with parkinsonism-predominant multiple system atrophy (44.4%). No patients with idiopathic Parkinson disease or healthy controls showed putaminal atrophy or marked signal hypointensity. Quantitatively measured putaminal width, phase-shift values, and the ratio of mean phase-shift values for the dominant and nondominant sides were significantly different between the parkinsonism-predominant multiple system atrophy group and the idiopathic Parkinson disease and healthy control groups (P < .001).

CONCLUSIONS

3T SWI can visualize putaminal atrophy and marked signal hypointensity in patients with parkinsonism-predominant multiple system atrophy with high specificity. Furthermore, it clearly demonstrates the dominant side of putaminal changes, which correlate with the contralateral symptomatic side of patients.