Detecting brain structural changes as biomarker from magnetic resonance images using a local feature based SVM approach

Artificial intelligence in psychiatry research, diagnosis, and therapy

Psychiatric disorders are now responsible for the largest proportion of the global burden of disease, and even more challenges have been seen during the COVID-19 pandemic. Artificial intelligence (AI) is commonly used to facilitate the early detection of disease, understand disease progression, and discover new treatments in the fields of both physical and mental health. The present review provides a broad overview of AI methodology and its applications in data acquisition and processing, feature extraction and characterization, psychiatric disorder classification, potential biomarker detection, real-time monitoring, and interventions in psychiatric disorders. We also comprehensively summarize AI applications with regard to the early warning, diagnosis, prognosis, and treatment of specific psychiatric disorders, including depression, schizophrenia, autism spectrum disorder, attention-deficit/hyperactivity disorder, addiction, sleep disorders, and Alzheimer's disease. The advantages and disadvantages of AI in psychiatry are clarified. We foresee a new wave of research opportunities to facilitate and improve AI technology and its long-term implications in psychiatry during and after the COVID-19 era.

Sampling inequalities affect generalization of neuroimaging-based diagnostic classifiers in psychiatry

BACKGROUND

The development of machine learning models for aiding in the diagnosis of mental disorder is recognized as a significant breakthrough in the field of psychiatry. However, clinical practice of such models remains a challenge, with poor generalizability being a major limitation.

METHODS

Here, we conducted a pre-registered meta-research assessment on neuroimaging-based models in the psychiatric literature, quantitatively examining global and regional sampling issues over recent decades, from a view that has been relatively underexplored. A total of 476 studies (n = 118,137) were included in the current assessment. Based on these findings, we built a comprehensive 5-star rating system to quantitatively evaluate the quality of existing machine learning models for psychiatric diagnoses.

RESULTS

A global sampling inequality in these models was revealed quantitatively (sampling Gini coefficient (G) = 0.81, p < .01), varying across different countries (regions) (e.g., China, G = 0.47; the USA, G = 0.58; Germany, G = 0.78; the UK, G = 0.87). Furthermore, the severity of this sampling inequality was significantly predicted by national economic levels (β =  - 2.75, p < .001, R²_adj = 0.40; r =  - .84, 95% CI: - .41 to - .97), and was plausibly predictable for model performance, with higher sampling inequality for reporting higher classification accuracy. Further analyses showed that lack of independent testing (84.24% of models, 95% CI: 81.0-87.5%), improper cross-validation (51.68% of models, 95% CI: 47.2-56.2%), and poor technical transparency (87.8% of models, 95% CI: 84.9-90.8%)/availability (80.88% of models, 95% CI: 77.3-84.4%) are prevailing in current diagnostic classifiers despite improvements over time. Relating to these observations, model performances were found decreased in studies with independent cross-country sampling validations (all p < .001, BF₁₀ > 15). In light of this, we proposed a purpose-built quantitative assessment checklist, which demonstrated that the overall ratings of these models increased by publication year but were negatively associated with model performance.

CONCLUSIONS

Together, improving sampling economic equality and hence the quality of machine learning models may be a crucial facet to plausibly translating neuroimaging-based diagnostic classifiers into clinical practice.

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis: A Systematic Review

IMPORTANCE

Neuroimaging-based artificial intelligence (AI) diagnostic models have proliferated in psychiatry. However, their clinical applicability and reporting quality (ie, feasibility) for clinical practice have not been systematically evaluated.

OBJECTIVE

To systematically assess the risk of bias (ROB) and reporting quality of neuroimaging-based AI models for psychiatric diagnosis.

EVIDENCE REVIEW

PubMed was searched for peer-reviewed, full-length articles published between January 1, 1990, and March 16, 2022. Studies aimed at developing or validating neuroimaging-based AI models for clinical diagnosis of psychiatric disorders were included. Reference lists were further searched for suitable original studies. Data extraction followed the CHARMS (Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies) and PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses) guidelines. A closed-loop cross-sequential design was used for quality control. The PROBAST (Prediction Model Risk of Bias Assessment Tool) and modified CLEAR (Checklist for Evaluation of Image-Based Artificial Intelligence Reports) benchmarks were used to systematically evaluate ROB and reporting quality.

FINDINGS

A total of 517 studies presenting 555 AI models were included and evaluated. Of these models, 461 (83.1%; 95% CI, 80.0%-86.2%) were rated as having a high overall ROB based on the PROBAST. The ROB was particular high in the analysis domain, including inadequate sample size (398 of 555 models [71.7%; 95% CI, 68.0%-75.6%]), poor model performance examination (with 100% of models lacking calibration examination), and lack of handling data complexity (550 of 555 models [99.1%; 95% CI, 98.3%-99.9%]). None of the AI models was perceived to be applicable to clinical practices. Overall reporting completeness (ie, number of reported items/number of total items) for the AI models was 61.2% (95% CI, 60.6%-61.8%), and the completeness was poorest for the technical assessment domain with 39.9% (95% CI, 38.8%-41.1%).

CONCLUSIONS AND RELEVANCE

This systematic review found that the clinical applicability and feasibility of neuroimaging-based AI models for psychiatric diagnosis were challenged by a high ROB and poor reporting quality. Particularly in the analysis domain, ROB in AI diagnostic models should be addressed before clinical application.

Magnetic resonance imaging image analysis of the therapeutic effect and neuroprotective effect of deep brain stimulation in Parkinson's disease based on a deep learning algorithm

In order to study the therapeutic neuroprotective effect of deep brain stimulation (DBS) in Parkinson's disease (PD), based on the deep learning algorithm, this study combines with magnetic resonance imaging (MRI) image analysis technology to study the clinical efficacy of DBS in the surgical treatment of PD and the neuroprotective and neurological recovery effects after surgery. Establish a deep learning algorithm model based on MRI image analysis technology, comparison of UPDRS motor status assessment and the improvement of daily life ability before and after DBS surgery, evaluate the accuracy rate and the detection speed of the model. The models constructed in this study have an accuracy rate of more than 90% in the PD detection test, and the detection speed of the algorithm model under the condition of big data is between 60 and 200 ms. DBS significantly improve a series of clinical symptoms in patients with PD. The deep learning algorithm model based on MRI image analysis technology in this paper has a certain effect. DBS operation can improve the symptoms of PD, and has the effect of neuroprotection and neurological recovery.

Classification of Parkinson's disease using a region-of-interest- and resting-state functional magnetic resonance imaging-based radiomics approach

To investigate the value of combining amplitude of low-frequency fluctuations-based radiomics and the support vector machine classifier method in distinguishing patients with Parkinson's disease from healthy controls. A total of 123 patients with Parkinson's disease and 90 healthy controls from three centers with functional and structural MRI images were included in this study. We extracted radiomics features using the Brainnetome 246 atlas from the mean amplitude of low-frequency fluctuations maps. Two-sample t-tests and recursive feature elimination combined with support vector machine method were applied for feature selection and dimensionality reduction. We used support vector machine classifier to construct model and identify the discriminative features. The automated anatomical labeling 90 atlas and fivefold cross-validation were used to evaluate the robustness and generalization of the classifier. We found our model obtained a high classification performance with an accuracy of 78.07%, and AUC, sensitivity, and specificity of 0.8597, 78.80%, and 76.08%, respectively. We detected 7 discriminative brain subregions. The fivefold cross-validation and automated anatomical labeling 90 atlas also got high classification accuracy, and we found Brainnetome 246 atlas achieved a higher classification performance than the automated anatomical labeling 90 atlas both with tenfold and fivefold cross-validation. Our findings may help the early diagnosis of Parkinson's disease and provide support for research on Parkinson's disease mechanisms and clinical evaluation.

Detection and Grading of Gliomas Using a Novel Two-Phase Machine Learning Method Based on MRI Images

The early detection and grading of gliomas is important for treatment decision and assessment of prognosis. Over the last decade numerous automated computer analysis tools have been proposed, which can potentially lead to more reliable and reproducible brain tumor diagnostic procedures. In this paper, we used the gradient-based features extracted from structural magnetic resonance imaging (sMRI) images to depict the subtle changes within brains of patients with gliomas. Based on the gradient features, we proposed a novel two-phase classification framework for detection and grading of gliomas. In the first phase, the probability of each local feature being related to different types (e.g., diseased or healthy for detection, benign or malignant for grading) was calculated. Then the high-level feature representing the whole MRI image was generated by concatenating the membership probability of each local feature. In the second phase, the supervised classification algorithm was used to train a classifier based on the high-level features and patient labels of the training subjects. We applied this framework on the brain imaging data collected from Zhongnan Hospital of Wuhan University for glioma detection, and the public TCIA datasets including glioblastomas (WHO IV) and low-grade gliomas (WHO II and III) data for glioma grading. The experimental results showed that the gradient-based classification framework could be a promising tool for automatic diagnosis of brain tumors.

Application of Functional Magnetic Resonance Imaging in the Diagnosis of Parkinson's Disease: A Histogram Analysis

This study aimed to investigate the value of amplitude of low-frequency fluctuation (ALFF)-based histogram analysis in the diagnosis of Parkinson's disease (PD) and to investigate the regions of the most important discriminative features and their contribution to classification discrimination. Patients with PD (n = 59) and healthy controls (HCs; n = 41) were identified and divided into a primary set (80 cases, including 48 patients with PD and 32 HCs) and a validation set (20 cases, including 11 patients with PD and nine HCs). The Automated Anatomical Labeling (AAL) 116 atlas was used to extract the histogram features of the regions of interest in the brain. Machine learning methods were used in the primary set for data dimensionality reduction, feature selection, model construction, and model performance evaluation. The model performance was further validated in the validation set. After feature data dimension reduction and feature selection, 23 of a total of 1,276 features were entered in the model. The brain regions of the selected features included the frontal, temporal, parietal, occipital, and limbic lobes, as well as the cerebellum and the thalamus. In the primary set, the area under the curve (AUC) of the model was 0.974, the sensitivity was 93.8%, the specificity was 90.6%, and the accuracy was 93.8%. In the validation set, the AUC, sensitivity, specificity, and accuracy were 0.980, 90.9%, 88.9%, and 90.0%, respectively. ALFF-based histogram analysis can be used to classify patients with PD and HCs and to effectively identify abnormal brain function regions in PD patients.

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.

Multivariate radiomics models based on 18F-FDG hybrid PET/MRI for distinguishing between Parkinson's disease and multiple system atrophy

PURPOSE

To construct multivariate radiomics models using hybrid ¹⁸F-FDG PET/MRI for distinguishing between Parkinson's disease (PD) and multiple system atrophy (MSA).

METHODS

Ninety patients (60 with PD and 30 with MSA) were randomized to training and test sets in a 7:3 ratio. All patients underwent ¹⁸F-fluorodeoxyglucose (¹⁸F-FDG) PET/MRI to simultaneously obtain metabolic images (¹⁸F-FDG), structural MRI images (T1-weighted imaging (T1WI), T2-weighted imaging (T2WI) and T2-weighted fluid-attenuated inversion recovery (T2/FLAIR)) and functional MRI images (susceptibility-weighted imaging (SWI) and apparent diffusion coefficient). Using PET and five MRI sequences, we extracted 1172 radiomics features from the putamina and caudate nuclei. The radiomics signatures were constructed with the least absolute shrinkage and selection operator algorithm in the training set, with progressive optimization through single-sequence and double-sequence radiomics models. Multivariable logistic regression analysis was used to develop a clinical-radiomics model, combining the optimal multi-sequence radiomics signature with clinical characteristics and SUV values. The diagnostic performance of the models was assessed by receiver operating characteristic and decision curve analysis (DCA).

RESULTS

The radiomics signatures showed favourable diagnostic efficacy. The optimal model comprised structural (T1WI), functional (SWI) and metabolic (¹⁸F-FDG) sequences (Radscore_{FDG_T1WI_SWI}) with the area under curves (AUCs) of the training and test sets of 0.971 and 0.957, respectively. The integrated model, incorporating Radscore_{FDG_T1WI_SWI}, three clinical symptoms (disease duration, dysarthria and autonomic failure) and SUV_max, demonstrated satisfactory calibration and discrimination in the training and test sets (0.993 and 0.994, respectively). DCA indicated the highest clinical benefit of the clinical-radiomics integrated model.

CONCLUSIONS

The radiomics signature with metabolic, structural and functional information provided by hybrid ¹⁸F-FDG PET/MRI may achieve promising diagnostic efficacy for distinguishing between PD and MSA. The clinical-radiomics integrated model performed best.

Alzheimer's diagnosis using deep learning in segmenting and classifying 3D brain MR images

BACKGROUND AND OBJECTIVES

Dementia is one of the brain diseases with serious symptoms such as memory loss, and thinking problems. According to the World Alzheimer Report 2016, in the world, there are 47 million people having dementia and it can be 131 million by 2050. There is no standard method to diagnose dementia, and consequently unable to access the treatment effectively. Hence, the computational diagnosis of the disease from brain Magnetic Resonance Image (MRI) scans plays an important role in supporting the early diagnosis. Alzheimer's Disease (AD), a common type of Dementia, includes problems related to disorientation, mood swings, not managing self-care, and behavioral issues. In this article, we present a new computational method to diagnosis Alzheimer's disease from 3D brain MR images.

METHODS

An efficient approach to diagnosis Alzheimer's disease from brain MRI scans is proposed comprising two phases: I) segmentation and II) classification, both based on deep learning. After the brain tissues are segmented by a model that combines Gaussian Mixture Model (GMM) and Convolutional Neural Network (CNN), a new model combining Extreme Gradient Boosting (XGBoost) and Support Vector Machine (SVM) is used to classify Alzheimer's disease based on the segmented tissues.

RESULTS

We present two evaluations for segmentation and classification. For comparison, the new method was evaluated using the AD-86 and AD-126 datasets leading to Dice 0.96 for segmentation in both datasets and accuracies 0.88, and 0.80 for classification, respectively.

CONCLUSION

Deep learning gives prominent results for segmentation and feature extraction in medical image processing. The combination of XGboost and SVM improves the results obtained.

Will machine learning applied to neuroimaging in bipolar disorder help the clinician? A critical review and methodological suggestions

OBJECTIVES

The existence of anatomofunctional brain abnormalities in bipolar disorder (BD) is now well established by magnetic resonance imaging (MRI) studies. To create diagnostic and prognostic tools, as well as identifying biologically valid subtypes of BD, research has recently turned towards the use of machine learning (ML) techniques. We assessed both supervised ML and unsupervised ML studies in BD to evaluate their robustness, reproducibility and the potential need for improvement.

METHOD

We systematically searched for studies using ML algorithms based on MRI data of patients with BD until February 2019.

RESULT

We identified 47 studies, 45 using supervised ML techniques and 2 including unsupervised ML analyses. Among supervised studies, 43 focused on diagnostic classification. The reported accuracies for classification of BD ranged between (a) 57% and 100%, for BD vs healthy controls; (b) 49.5% and 93.1% for BD vs patients with major depressive disorder; and (c) 50% and 96.2% for BD vs patients with schizophrenia. Reported accuracies for discriminating subjects genetically at risk for BD (either from control or from patients with BD) ranged between 64.3% and 88.93%.

CONCLUSIONS

Although there are strong methodological limitations in previous studies and an important need for replication in large multicentric samples, the conclusions of our review bring hope of future computer-aided diagnosis of BD and pave the way for other applications, such as treatment response prediction. To reinforce the reliability of future results we provide methodological suggestions for good practice in conducting and reporting MRI-based ML studies in BD.

The Development of a Practical Artificial Intelligence Tool for Diagnosing and Evaluating Autism Spectrum Disorder: Multicenter Study

Background

Autism spectrum disorder (ASD) is a complex neurodevelopmental disorder with an unknown etiology. Early diagnosis and intervention are key to improving outcomes for patients with ASD. Structural magnetic resonance imaging (sMRI) has been widely used in clinics to facilitate the diagnosis of brain diseases such as brain tumors. However, sMRI is less frequently used to investigate neurological and psychiatric disorders, such as ASD, owing to the subtle, if any, anatomical changes of the brain.

Objective

This study aimed to investigate the possibility of identifying structural patterns in the brain of patients with ASD as potential biomarkers in the diagnosis and evaluation of ASD in clinics.

Methods

We developed a novel 2-level histogram-based morphometry (HBM) classification framework in which an algorithm based on a 3D version of the histogram of oriented gradients (HOG) was used to extract features from sMRI data. We applied this framework to distinguish patients with ASD from healthy controls using 4 datasets from the second edition of the Autism Brain Imaging Data Exchange, including the ETH Zürich (ETH), NYU Langone Medical Center: Sample 1, Oregon Health and Science University, and Stanford University (SU) sites. We used a stratified 10-fold cross-validation method to evaluate the model performance, and we applied the Naive Bayes approach to identify the predictive ASD-related brain regions based on classification contributions of each HOG feature.

Results

On the basis of the 3D HOG feature extraction method, our proposed HBM framework achieved an area under the curve (AUC) of >0.75 in each dataset, with the highest AUC of 0.849 in the ETH site. We compared the 3D HOG algorithm with the original 2D HOG algorithm, which showed an accuracy improvement of >4% in each dataset, with the highest improvement of 14% (6/42) in the SU site. A comparison of the 3D HOG algorithm with the scale-invariant feature transform algorithm showed an AUC improvement of >18% in each dataset. Furthermore, we identified ASD-related brain regions based on the sMRI images. Some of these regions (eg, frontal gyrus, temporal gyrus, cingulate gyrus, postcentral gyrus, precuneus, caudate, and hippocampus) are known to be implicated in ASD in prior neuroimaging literature. We also identified less well-known regions that may play unrecognized roles in ASD and be worth further investigation.

Conclusions

Our research suggested that it is possible to identify neuroimaging biomarkers that can distinguish patients with ASD from healthy controls based on the more cost-effective sMRI images of the brain. We also demonstrated the potential of applying data-driven artificial intelligence technology in the clinical setting of neurological and psychiatric disorders, which usually harbor subtle anatomical changes in the brain that are often invisible to the human eye.

A proof of concept machine learning analysis using multimodal neuroimaging and neurocognitive measures as predictive biomarker in bipolar disorder

BACKGROUND

Concomitant use of complementary, multimodal imaging measures and neurocognitive measures is reported to have higher accuracy as a biomarker in Alzheimer's dementia. However, such an approach has not been examined to differentiate healthy individuals from Bipolar disorder. In this study, we examined the utility of support vector machine (SVM) technique to differentiate bipolar disorder patients and healthy using structural, functional and diffusion tensor images of brain and neurocognitive measures.

METHODS

30 patients with Bipolar disorder-I and 30 age, sex matched individuals participated in the study. Structural MRI, resting state functional MRI and diffusion tensor images were obtained using a 1.5 T scanner. All participants were administered neuropsychological tests to measure executive functions. SVM, a supervised machine learning technique was applied to differentiate patients and healthy individuals with k-fold cross validation over 10 trials.

RESULTS

The composite marker consisting of both neuroimaging and neuropsychological measures, had an accuracy of 87.60 %, sensitivity of 82.3 % and specificity of 92.7 %. The performance of composite marker was better compared to that of individual markers on classificatory.

CONCLUSIONS

We were able to achieve a high accuracy for machine learning technique in distinguishing BD from HV using a combination of multimodal neuroimaging and neurocognitive measures. Findings of this proof of concept study, if replicated in larger samples, could have potential clinical applications.

An empirical assessment of appearance descriptors applied to MRI for automated diagnosis of TLE and MCI

OBJECTIVE

Differential diagnosis of mild cognitive impairment MCI and temporal lobe epilepsy TLE is a debated issue, specifically because these conditions may coincide in the elderly population. We evaluate automated differential diagnosis based on characteristics derived from structural brain MRI of different brain regions.

METHODS

In 22 healthy controls, 19 patients with MCI, and 17 patients with TLE we used scale invariant feature transform (SIFT), local binary patterns (LBP), and wavelet-based features and investigate their predictive performance for MCI and TLE.

RESULTS

The classification based on SIFT features resulted in an accuracy of 81% of MCI vs. TLE and reasonable generalizability. Local binary patterns yielded satisfactory diagnostic performance with up to 94.74% sensitivity and 88.24% specificity in the right Thalamus for the distinction of MCI vs. TLE, but with limited generalizable. Wavelet features yielded similar results as LPB with 94.74% sensitivity and 82.35% specificity but generalize better.

SIGNIFICANCE

Features beyond volume analysis are a valid approach when applied to specific regions of the brain. Most significant information could be extracted from the thalamus, frontal gyri, and temporal regions, among others. These results suggest that analysis of changes of the central nervous system should not be limited to the most typical regions of interest such as the hippocampus and parahippocampal areas. Region-independent approaches can add considerable information for diagnosis. We emphasize the need to characterize generalizability in future studies, as our results demonstrate that not doing so can lead to overestimation of classification results.

LIMITATIONS

The data used within this study allows for separation of MCI and TLE subjects using a simple age threshold. While we present a strong indication that the presented method is age-invariant and therefore agnostic to this situation, new data would be needed for a rigorous empirical assessment of this findings.

Machine-learning identifies Parkinson's disease patients based on resting-state between-network functional connectivity

OBJECTIVE

Evaluation of a data-driven, model-based classification approach to discriminate idiopathic Parkinson's disease (PD) patients from healthy controls (HC) based on between-network connectivity in whole-brain resting-state functional MRI (rs-fMRI).

METHODS

Whole-brain rs-fMRI (EPI, TR = 2.2 s, TE = 30 ms, flip angle = 90°. resolution = 3.1 × 3.1 × 3.1 mm, acquisition time ≈ 11 min) was assessed in 42 PD patients (medical OFF) and 47 HC matched for age and gender. Between-network connectivity based on full and L2-regularized partial correlation measures were computed for each subject based on canonical functional network architectures of two cohorts at different levels of granularity (Human Connectome Project: 15/25/50/100/200 networks; 1000BRAINS: 15/25/50/70 networks). A Boosted Logistic Regression model was trained on the correlation matrices using a nested cross-validation (CV) with 10 outer and 10 inner folds for an unbiased performance estimate, treating the canonical functional network architecture and the type of correlation as hyperparameters. The number of boosting iterations was fixed at 100. The model with the highest mean accuracy over the inner folds was trained using an non-nested 10-fold 20-repeats CV over the whole dataset to determine feature importance.

RESULTS

Over the outer folds the mean accuracy was found to be 76.2% (median 77.8%, SD 18.2, IQR 69.4 - 87.1%). Mean sensitivity was 81% (median 80%, SD 21.1, IQR 75 - 100%) and mean specificity was 72.7% (median 75%, SD 20.4, IQR 66.7 - 80%). The 1000BRAINS 50-network-parcellation, using full correlations, performed best over the inner folds. The top features predominantly included sensorimotor as well as sensory networks.

CONCLUSION

A rs-fMRI whole-brain-connectivity, data-driven, model-based approach to discriminate PD patients from healthy controls shows a very good accuracy and a high sensitivity. Given the high sensitivity of the approach, it may be of use in a screening setting.

ADVANCES IN KNOWLEDGE

Resting-state functional MRI could prove to be a valuable, non-invasive neuroimaging biomarker for neurodegenerative diseases. The current model-based, data-driven approach on whole-brain between-network connectivity to discriminate Parkinson's disease patients from healthy controls shows promising results with a very good accuracy and a very high sensitivity.

Image Based Brain Segmentation: From Multi-Atlas Fusion to Deep Learning

Background:

This review aims to identify the development of the algorithms for brain tissue and structure segmentation in MRI images.

Discussion:

Starting from the results of the Grand Challenges on brain tissue and structure segmentation held in Medical Image Computing and Computer-Assisted Intervention (MICCAI), this review analyses the development of the algorithms and discusses the tendency from multi-atlas label fusion to deep learning. The intrinsic characteristics of the winners’ algorithms on the Grand Challenges from the year 2012 to 2018 are analyzed and the results are compared carefully.

Conclusion:

Although deep learning has got higher rankings in the challenge, it has not yet met the expectations in terms of accuracy. More effective and specialized work should be done in the future.

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.

Mining EEG with SVM for Understanding Cognitive Underpinnings of Math Problem Solving Strategies

We have developed a new methodology for examining and extracting patterns from brain electric activity by using data mining and machine learning techniques. Data was collected from experiments focused on the study of cognitive processes that might evoke different specific strategies in the resolution of math problems. A binary classification problem was constructed using correlations and phase synchronization between different electroencephalographic channels as characteristics and, as labels or classes, the math performances of individuals participating in specially designed experiments. The proposed methodology is based on using well-established procedures of feature selection, which were used to determine a suitable brain functional network size related to math problem solving strategies and also to discover the most relevant links in this network without including noisy connections or excluding significant connections.

The impact of machine learning techniques in the study of bipolar disorder: A systematic review

Machine learning techniques provide new methods to predict diagnosis and clinical outcomes at an individual level. We aim to review the existing literature on the use of machine learning techniques in the assessment of subjects with bipolar disorder. We systematically searched PubMed, Embase and Web of Science for articles published in any language up to January 2017. We found 757 abstracts and included 51 studies in our review. Most of the included studies used multiple levels of biological data to distinguish the diagnosis of bipolar disorder from other psychiatric disorders or healthy controls. We also found studies that assessed the prediction of clinical outcomes and studies using unsupervised machine learning to build more consistent clinical phenotypes of bipolar disorder. We concluded that given the clinical heterogeneity of samples of patients with BD, machine learning techniques may provide clinicians and researchers with important insights in fields such as diagnosis, personalized treatment and prognosis orientation.

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

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

Classification of brain disease in magnetic resonance images using two-stage local feature fusion

BACKGROUND

Many classification methods have been proposed based on magnetic resonance images. Most methods rely on measures such as volume, the cerebral cortical thickness and grey matter density. These measures are susceptible to the performance of registration and limited in representation of anatomical structure. This paper proposes a two-stage local feature fusion method, in which deformable registration is not desired and anatomical information is represented from moderate scale.

METHODS

Keypoints are firstly extracted from scale-space to represent anatomical structure. Then, two kinds of local features are calculated around the keypoints, one for correspondence and the other for representation. Scores are assigned for keypoints to quantify their effect in classification. The sum of scores for all effective keypoints is used to determine which group the test subject belongs to.

RESULTS

We apply this method to magnetic resonance images of Alzheimer's disease and Parkinson's disease. The advantage of local feature in correspondence and representation contributes to the final classification. With the help of local feature (Scale Invariant Feature Transform, SIFT) in correspondence, the performance becomes better. Local feature (Histogram of Oriented Gradient, HOG) extracted from 16×16 cell block obtains better results compared with 4×4 and 8×8 cell block.

DISCUSSION

This paper presents a method which combines the effect of SIFT descriptor in correspondence and the representation ability of HOG descriptor in anatomical structure. This method has the potential in distinguishing patients with brain disease from controls.

Single subject prediction of brain disorders in neuroimaging: Promises and pitfalls

Neuroimaging-based single subject prediction of brain disorders has gained increasing attention in recent years. Using a variety of neuroimaging modalities such as structural, functional and diffusion MRI, along with machine learning techniques, hundreds of studies have been carried out for accurate classification of patients with heterogeneous mental and neurodegenerative disorders such as schizophrenia and Alzheimer's disease. More than 500 studies have been published during the past quarter century on single subject prediction focused on a multiple brain disorders. In the first part of this study, we provide a survey of more than 200 reports in this field with a focus on schizophrenia, mild cognitive impairment (MCI), Alzheimer's disease (AD), depressive disorders, autism spectrum disease (ASD) and attention-deficit hyperactivity disorder (ADHD). Detailed information about those studies such as sample size, type and number of extracted features and reported accuracy are summarized and discussed. To our knowledge, this is by far the most comprehensive review of neuroimaging-based single subject prediction of brain disorders. In the second part, we present our opinion on major pitfalls of those studies from a machine learning point of view. Common biases are discussed and suggestions are provided. Moreover, emerging trends such as decentralized data sharing, multimodal brain imaging, differential diagnosis, disease subtype classification and deep learning are also discussed. Based on this survey, there is extensive evidence showing the great potential of neuroimaging data for single subject prediction of various disorders. However, the main bottleneck of this exciting field is still the limited sample size, which could be potentially addressed by modern data sharing models such as the ones discussed in this paper. Emerging big data technologies and advanced data-intensive machine learning methodologies such as deep learning have coincided with an increasing need for accurate, robust and generalizable single subject prediction of brain disorders during an exciting time. In this report, we survey the past and offer some opinions regarding the road ahead.

Classification of brain disease from magnetic resonance images based on multi-level brain partitions

In this paper, we present a classification method based on the multi-level brain partitions. Bag-of-visual-words model is used. Firstly, the representative SIFT features are extracted from brain template as the basic visual words. Secondly, individual MR images are described using the basic visual words and support vector machine classifiers are trained for different brain partitions respectively. Thirdly, the final classification is derived from the combination of multiple classifiers. We apply this method to MR images of Alzheimer's disease and Parkinson's disease. The results demonstrate that the multi-level partitions favors the classification accuracy of brain disease from MR images.

Probability distribution function-based classification of structural MRI for the detection of Alzheimer's disease

High-dimensional classification methods have been a major target of machine learning for the automatic classification of patients who suffer from Alzheimer's disease (AD). One major issue of automatic classification is the feature-selection method from high-dimensional data. In this paper, a novel approach for statistical feature reduction and selection in high-dimensional magnetic resonance imaging (MRI) data based on the probability distribution function (PDF) is introduced. To develop an automatic computer-aided diagnosis (CAD) technique, this research explores the statistical patterns extracted from structural MRI (sMRI) data on four systematic levels. First, global and local differences of gray matter in patients with AD compared to healthy controls (HCs) using the voxel-based morphometric (VBM) technique with 3-Tesla 3D T1-weighted MRI are investigated. Second, feature extraction based on the voxel clusters detected by VBM on sMRI and voxel values as volume of interest (VOI) is used. Third, a novel statistical feature-selection process is employed, utilizing the PDF of the VOI to represent statistical patterns of the respective high-dimensional sMRI sample. Finally, the proposed feature-selection method for early detection of AD with support vector machine (SVM) classifiers compared to other standard feature selection methods, such as partial least squares (PLS) techniques, is assessed. The performance of the proposed technique is evaluated using 130 AD and 130 HC MRI data from the ADNI dataset with 10-fold cross validation(1). The results show that the PDF-based feature selection approach is a reliable technique that is highly competitive with respect to the state-of-the-art techniques in classifying AD from high-dimensional sMRI samples.

Combined analysis of sMRI and fMRI imaging data provides accurate disease markers for hearing impairment

In this research, we developed a robust two-layer classifier that can accurately classify normal hearing (NH) from hearing impaired (HI) infants with congenital sensori-neural hearing loss (SNHL) based on their Magnetic Resonance (MR) images. Unlike traditional methods that examine the intensity of each single voxel, we extracted high-level features to characterize the structural MR images (sMRI) and functional MR images (fMRI). The Scale Invariant Feature Transform (SIFT) algorithm was employed to detect and describe the local features in sMRI. For fMRI, we constructed contrast maps and detected the most activated/de-activated regions in each individual. Based on those salient regions occurring across individuals, the bag-of-words strategy was introduced to vectorize the contrast maps. We then used a two-layer model to integrate these two types of features together. With the leave-one-out cross-validation approach, this integrated model achieved an AUC score of 0.90. Additionally, our algorithm highlighted several important brain regions that differentiated between NH and HI children. Some of these regions, e.g. planum temporale and angular gyrus, were well known auditory and visual language association regions. Others, e.g. the anterior cingulate cortex (ACC), were not necessarily expected to play a role in differentiating HI from NH children and provided a new understanding of brain function and of the disorder itself. These important brain regions provided clues about neuroimaging markers that may be relevant to the future use of functional neuroimaging to guide predictions about speech and language outcomes in HI infants who receive a cochlear implant. This type of prognostic information could be extremely useful and is currently not available to clinicians by any other means.

•

We probe brain structural and functional changes in hearing impaired (HI) infants.

•

We build a robust two-layer classifier that integrates sMRI and fMRI data.

•

This integrated model accurately separates HI from normal infants (AUC 0.9).

•

Our method detects important brain regions different between HI and normal infants.

•

Our method can include diverse types of data and be applied to other diseases.