A comparison of various MRI feature types for characterizing whole brain anatomical differences using linear pattern recognition methods

Narcissus reflected: Grey and white matter features joint contribution to the default mode network in predicting narcissistic personality traits

Despite the clinical significance of narcissistic personality, its neural bases have not been clarified yet, primarily because of methodological limitations of the previous studies, such as the low sample size, the use of univariate techniques and the focus on only one brain modality. In this study, we employed for the first time a combination of unsupervised and supervised machine learning methods, to identify the joint contributions of grey matter (GM) and white matter (WM) to narcissistic personality traits (NPT). After preprocessing, the brain scans of 135 participants were decomposed into eight independent networks of covarying GM and WM via parallel ICA. Subsequently, stepwise regression and Random Forest were used to predict NPT. We hypothesized that a fronto-temporo parietal network, mainly related to the default mode network, may be involved in NPT and associated WM regions. Results demonstrated a distributed network that included GM alterations in fronto-temporal regions, the insula and the cingulate cortex, along with WM alterations in cerebellar and thalamic regions. To assess the specificity of our findings, we also examined whether the brain network predicting narcissism could also predict other personality traits (i.e., histrionic, paranoid and avoidant personalities). Notably, this network did not predict such personality traits. Additionally, a supervised machine learning model (Random Forest) was used to extract a predictive model for generalization to new cases. Results confirmed that the same network could predict new cases. These findings hold promise for advancing our understanding of personality traits and potentially uncovering brain biomarkers associated with narcissism.

Grey matter structure within the visual networks in migraine with aura: multivariate and univariate analyses

BACKGROUND

The visual cortex is involved in the generation of migraine aura. Voxel-based multivariate analyses applied to this region may provide complementary information about aura mechanisms relative to the commonly used mass-univariate analyses.

METHODS

Structural images constrained within the functional resting-state visual networks were obtained in migraine patients with (n = 50) and without (n = 50) visual aura and healthy controls (n = 50). The masked images entered a multivariate analysis in which Gaussian process classification was used to generate pairwise models. Generalizability was assessed by five-fold cross-validation and non-parametric permutation tests were used to estimate significance levels. A univariate voxel-based morphometry analysis was also performed.

RESULTS

A multivariate pattern of grey matter voxels within the ventral medial visual network contained significant information related to the diagnosis of migraine with visual aura (aura vs. healthy controls: classification accuracy = 78%, p < 0.001; area under the curve = 0.84, p < 0.001; migraine with aura vs. without aura: classification accuracy = 71%, p < 0.001; area under the curve = 0.73, p < 0.003). Furthermore, patients with visual aura exhibited increased grey matter volume in the medial occipital cortex compared to the two other groups.

CONCLUSIONS

Migraine with visual aura is characterized by multivariate and univariate patterns of grey matter changes within the medial occipital cortex that have discriminative power and may reflect pathological mechanisms.

Gaussian Process-based prediction of memory performance and biomarker status in ageing and Alzheimer's disease-A systematic model evaluation

Neuroimaging markers based on Magnetic Resonance Imaging (MRI) combined with various other measures (such as genetic covariates, biomarkers, vascular risk factors, neuropsychological tests etc.) might provide useful predictions of clinical outcomes during the progression towards Alzheimer's disease (AD). The use of multiple features in predictive frameworks for clinical outcomes has become increasingly prevalent in AD research. However, many studies do not focus on systematically and accurately evaluating combinations of multiple input features. Hence, the aim of the present work is to explore and assess optimal combinations of various features for MR-based prediction of (1) cognitive status and (2) biomarker positivity with a multi-kernel learning Gaussian process framework. The explored features and parameters included (A) combinations of brain tissues, modulation, smoothing, and image resolution; (B) incorporating demographics & clinical covariates; (C) the impact of the size of the training data set; (D) the influence of dimensionality reduction and the choice of kernel types. The approach was tested in a large German cohort including 959 subjects from the multicentric longitudinal study of cognitive impairment and dementia (DELCODE). Our evaluation suggests the best prediction of memory performance was obtained for a combination of neuroimaging markers, demographics, genetic information (ApoE4) and CSF biomarkers explaining 57% of outcome variance in out-of-sample predictions. The highest performance for Aβ42/40 status classification was achieved for a combination of demographics, ApoE4, and a memory score while usage of structural MRI further improved the classification of individual patient's pTau status.

Borderline shades: Morphometric features predict borderline personality traits but not histrionic traits

Borderline personality disorder (BPD) is one of the most diagnosed disorders in clinical settings. Besides the fully diagnosed disorder, borderline personality traits (BPT) are quite common in the general population. Prior studies have investigated the neural correlates of BPD but not of BPT. This paper investigates the neural correlates of BPT in a subclinical population using a supervised machine learning method known as Kernel Ridge Regression (KRR) to build predictive models. Additionally, we want to determine whether the same brain areas involved in BPD are also involved in subclinical BPT. Recent attempts to characterize the specific role of resting state-derived macro networks in BPD have highlighted the role of the default mode network. However, it is not known if this extends to the subclinical population. Finally, we wanted to test the hypothesis that the same circuitry that predicts BPT can also predict histrionic personality traits. Histrionic personality is sometimes considered a milder form of BPD, and making a differential diagnosis between the two may be difficult. For the first time KRR was applied to structural images of 135 individuals to predict BPT, based on the whole brain, on a circuit previously found to correctly classify BPD, and on the five macro-networks. At a whole brain level, results show that frontal and parietal regions, as well as the Heschl's area, the thalamus, the cingulum, and the insula, are able to predict borderline traits. BPT predictions increase when considering only the regions limited to the brain circuit derived from a study on BPD, confirming a certain overlap in brain structure between subclinical and clinical samples. Of all the five macro networks, only the DMN successfully predicts BPD, confirming previous observations on its role in the BPD. Histrionic traits could not be predicted by the BPT circuit. The results have implications for the diagnosis of BPD and a dimensional model of personality.

A meta-analysis and systematic review of single vs. multimodal neuroimaging techniques in the classification of psychosis

BACKGROUND

Psychotic disorders are characterized by structural and functional abnormalities in brain networks. Neuroimaging techniques map and characterize such abnormalities using unique features (e.g., structural integrity, coactivation). However, it is unclear if a specific method, or a combination of modalities, is particularly effective in identifying differences in brain networks of someone with a psychotic disorder.

METHODS

A systematic meta-analysis evaluated machine learning classification of schizophrenia spectrum disorders in comparison to healthy control participants using various neuroimaging modalities (i.e., T1-weighted imaging (T1), diffusion tensor imaging (DTI), resting state functional connectivity (rs-FC), or some combination (multimodal)). Criteria for manuscript inclusion included whole-brain analyses and cross-validation to provide a complete picture regarding the predictive ability of large-scale brain systems in psychosis. For this meta-analysis, we searched Ovid MEDLINE, PubMed, PsychInfo, Google Scholar, and Web of Science published between inception and March 13th 2023. Prediction results were averaged for studies using the same dataset, but parallel analyses were run that included studies with pooled sample across many datasets. We assessed bias through funnel plot asymmetry. A bivariate regression model determined whether differences in imaging modality, demographics, and preprocessing methods moderated classification. Separate models were run for studies with internal prediction (via cross-validation) and external prediction.

RESULTS

93 studies were identified for quantitative review (30 T1, 9 DTI, 40 rs-FC, and 14 multimodal). As a whole, all modalities reliably differentiated those with schizophrenia spectrum disorders from controls (OR = 2.64 (95%CI = 2.33 to 2.95)). However, classification was relatively similar across modalities: no differences were seen across modalities in the classification of independent internal data, and a small advantage was seen for rs-FC studies relative to T1 studies in classification in external datasets. We found large amounts of heterogeneity across results resulting in significant signs of bias in funnel plots and Egger's tests. Results remained similar, however, when studies were restricted to those with less heterogeneity, with continued small advantages for rs-FC relative to structural measures. Notably, in all cases, no significant differences were seen between multimodal and unimodal approaches, with rs-FC and unimodal studies reporting largely overlapping classification performance. Differences in demographics and analysis or denoising were not associated with changes in classification scores.

CONCLUSIONS

The results of this study suggest that neuroimaging approaches have promise in the classification of psychosis. Interestingly, at present most modalities perform similarly in the classification of psychosis, with slight advantages for rs-FC relative to structural modalities in some specific cases. Notably, results differed substantially across studies, with suggestions of biased effect sizes, particularly highlighting the need for more studies using external prediction and large sample sizes. Adopting more rigorous and systematized standards will add significant value toward understanding and treating this critical population.

Dual Deep CNN for Tumor Brain Classification

Brain tumor (BT) is a serious issue and potentially deadly disease that receives much attention. However, early detection and identification of tumor type and location are crucial for effective treatment and saving lives. Manual diagnoses are time-consuming and depend on radiologist experts; the increasing number of new cases of brain tumors makes it difficult to process massive and large amounts of data rapidly, as time is a critical factor in patients' lives. Hence, artificial intelligence (AI) is vital for understanding disease and its various types. Several studies proposed different techniques for BT detection and classification. These studies are on machine learning (ML) and deep learning (DL). The ML-based method requires handcrafted or automatic feature extraction algorithms; however, DL becomes superior in self-learning and robust in classification and recognition tasks. This research focuses on classifying three types of tumors using MRI imaging: meningioma, glioma, and pituitary tumors. The proposed DCTN model depends on dual convolutional neural networks with VGG-16 architecture concatenated with custom CNN (convolutional neural networks) architecture. After conducting approximately 22 experiments with different architectures and models, our model reached 100% accuracy during training and 99% during testing. The proposed methodology obtained the highest possible improvement over existing research studies. The solution provides a revolution for healthcare providers that can be used as a different disease classification in the future and save human lives.

Brain-age prediction: A systematic comparison of machine learning workflows

The difference between age predicted using anatomical brain scans and chronological age, i.e., the brain-age delta, provides a proxy for atypical aging. Various data representations and machine learning (ML) algorithms have been used for brain-age estimation. However, how these choices compare on performance criteria important for real-world applications, such as; (1) within-dataset accuracy, (2) cross-dataset generalization, (3) test-retest reliability, and (4) longitudinal consistency, remains uncharacterized. We evaluated 128 workflows consisting of 16 feature representations derived from gray matter (GM) images and eight ML algorithms with diverse inductive biases. Using four large neuroimaging databases covering the adult lifespan (total N = 2953, 18-88 years), we followed a systematic model selection procedure by sequentially applying stringent criteria. The 128 workflows showed a within-dataset mean absolute error (MAE) between 4.73-8.38 years, from which 32 broadly sampled workflows showed a cross-dataset MAE between 5.23-8.98 years. The test-retest reliability and longitudinal consistency of the top 10 workflows were comparable. The choice of feature representation and the ML algorithm both affected the performance. Specifically, voxel-wise feature spaces (smoothed and resampled), with and without principal components analysis, with non-linear and kernel-based ML algorithms performed well. Strikingly, the correlation of brain-age delta with behavioral measures disagreed between within-dataset and cross-dataset predictions. Application of the best-performing workflow on the ADNI sample showed a significantly higher brain-age delta in Alzheimer's and mild cognitive impairment patients compared to healthy controls. However, in the presence of age bias, the delta estimates in the patients varied depending on the sample used for bias correction. Taken together, brain-age shows promise, but further evaluation and improvements are needed for its real-world application.

Prediction of individual trigeminal pain sensitivity from gray matter structure within the sensorimotor network

OBJECTIVE

To determine whether multivariate pattern regression analysis based on gray matter (GM) images constrained to the sensorimotor network could accurately predict trigeminal heat pain sensitivity in healthy individuals.

BACKGROUND

Prediction of individual pain sensitivity is of clinical relevance as high pain sensitivity is associated with increased risks of postoperative pain, pain chronification, and a poor treatment response. However, as pain is a subjective experience accurate identification of such individuals can be difficult. GM structure of sensorimotor regions have been shown to vary with pain sensitivity. It is unclear whether GM structure within these regions can be used to predict pain sensitivity.

METHODS

In this cross-sectional study, structural magnetic resonance images and pain thresholds in response to contact heat stimulation of the left supraorbital area were obtained from 79 healthy participants. Voxel-based morphometry was used to extract segmented and normalized GM images. These were then constrained to a mask encompassing the functionally defined resting-state sensorimotor network. The masked images and pain thresholds entered a multivariate relevance vector regression analysis for quantitative prediction of the individual pain thresholds. The correspondence between predicted and actual pain thresholds was indexed by the Pearson correlation coefficient (r) and the mean squared error (MSE). The generalizability of the model was assessed by 10-fold and 5-fold cross-validation. Non-parametric permutation tests were used to estimate significance levels.

RESULTS

Trigeminal heat pain sensitivity could be predicted from GM structure within the sensorimotor network with significant accuracy (10-fold: r = 0.53, p < 0.001, MSE = 10.32, p = 0.001; 5-fold: r = 0.46, p = 0.001, MSE = 10.54, p < 0.001). The resulting multivariate weight maps revealed that accurate prediction relied on multiple widespread regions within the sensorimotor network.

CONCLUSION

A multivariate pattern of GM structure within the sensorimotor network could be used to make accurate predictions about trigeminal heat pain sensitivity at the individual level in healthy participants. Widespread regions within the sensorimotor network contributed to the predictive model.

Survey of Supervised Learning for Medical Image Processing

Medical image interpretation is an essential task for the correct diagnosis of many diseases. Pathologists, radiologists, physicians, and researchers rely heavily on medical images to perform diagnoses and develop new treatments. However, manual medical image analysis is tedious and time consuming, making it necessary to identify accurate automated methods. Deep learning—especially supervised deep learning—shows impressive performance in the classification, detection, and segmentation of medical images and has proven comparable in ability to humans. This survey aims to help researchers and practitioners of medical image analysis understand the key concepts and algorithms of supervised learning techniques. Specifically, this survey explains the performance metrics of supervised learning methods; summarizes the available medical datasets; studies the state-of-the-art supervised learning architectures for medical imaging processing, including convolutional neural networks (CNNs) and their corresponding algorithms, region-based CNNs and their variants, fully convolutional networks (FCN) and U-Net architecture; and discusses the trends and challenges in the application of supervised learning methods to medical image analysis. Supervised learning requires large labeled datasets to learn and achieve good performance, and data augmentation, transfer learning, and dropout techniques have widely been employed in medical image processing to overcome the lack of such datasets.

Deep Transfer Learning for Cerebral Cortex Using Area-Preserving Geometry Mapping

Limited sample size hinders the application of deep learning in brain image analysis, and transfer learning is a possible solution. However, most pretrained models are 2D based and cannot be applied directly to 3D brain images. In this study, we propose a novel framework to apply 2D pretrained models to 3D brain images by projecting surface-based cortical morphometry into planar images using computational geometry mapping. Firstly, 3D cortical meshes are reconstructed from magnetic resonance imaging (MRI) using FreeSurfer and projected into 2D planar meshes with topological preservation based on area-preserving geometry mapping. Then, 2D deep models pretrained on ImageNet are adopted and fine-tuned for cortical image classification on morphometric shape metrics. We apply the framework to sex classification on the Human Connectome Project dataset and autism spectrum disorder (ASD) classification on the Autism Brain Imaging Data Exchange dataset. Moreover, a 2-stage transfer learning strategy is suggested to boost the ASD classification performance by using the sex classification as an intermediate task. Our framework brings significant improvement in sex classification and ASD classification with transfer learning. In summary, the proposed framework builds a bridge between 3D cortical data and 2D models, making 2D pretrained models available for brain image analysis in cognitive and psychiatric neuroscience.

Machine learning for brain age prediction: Introduction to methods and clinical applications

The rise of machine learning has unlocked new ways of analysing structural neuroimaging data, including brain age prediction. In this state-of-the-art review, we provide an introduction to the methods and potential clinical applications of brain age prediction. Studies on brain age typically involve the creation of a regression machine learning model of age-related neuroanatomical changes in healthy people. This model is then applied to new subjects to predict their brain age. The difference between predicted brain age and chronological age in a given individual is known as ‘brain-age gap’. This value is thought to reflect neuroanatomical abnormalities and may be a marker of overall brain health. It may aid early detection of brain-based disorders and support differential diagnosis, prognosis, and treatment choices. These applications could lead to more timely and more targeted interventions in age-related disorders.

The progression of disorder-specific brain pattern expression in schizophrenia over 9 years

Age plays a crucial role in the performance of schizophrenia vs. controls (SZ-HC) neuroimaging-based machine learning (ML) models as the accuracy of identifying first-episode psychosis from controls is poor compared to chronic patients. Resolving whether this finding reflects longitudinal progression in a disorder-specific brain pattern or a systematic but non-disorder-specific deviation from a normal brain aging (BA) trajectory in schizophrenia would help the clinical translation of diagnostic ML models. We trained two ML models on structural MRI data: an SZ-HC model based on 70 schizophrenia patients and 74 controls and a BA model (based on 561 healthy individuals, age range = 66 years). We then investigated the two models’ predictions in the naturalistic longitudinal Northern Finland Birth Cohort 1966 (NFBC1966) following 29 schizophrenia and 61 controls for nine years. The SZ-HC model’s schizophrenia-specificity was further assessed by utilizing independent validation (62 schizophrenia, 95 controls) and depression samples (203 depression, 203 controls). We found better performance at the NFBC1966 follow-up (sensitivity = 75.9%, specificity = 83.6%) compared to the baseline (sensitivity = 58.6%, specificity = 86.9%). This finding resulted from progression in disorder-specific pattern expression in schizophrenia and was not explained by concomitant acceleration of brain aging. The disorder-specific pattern’s progression reflected longitudinal changes in cognition, outcomes, and local brain changes, while BA captured treatment-related and global brain alterations. The SZ-HC model was also generalizable to independent schizophrenia validation samples but classified depression as control subjects. Our research underlines the importance of taking account of longitudinal progression in a disorder-specific pattern in schizophrenia when developing ML classifiers for different age groups.

Sex Differences of Longitudinal Brain Changes in Cognitively Unimpaired Adults

BACKGROUND

There is increasing evidence that AD progression differs by sex.

OBJECTIVE

The aim of this work was to determine sex differences in the association of baseline levels of cerebrospinal fluid (CSF) biomarkers (Aβ42, p-tau, YKL-40, sTREM2) with longitudinal brain changes in cognitively unimpaired (CU) older adults.

METHODS

This pilot study included 36 CU subjects (age 66.5±5.5, 12 male) scanned twice, two years apart. Using a voxel-wise analysis, we determined the sex differences in the association maps between CSF biomarkers and atrophy rates.

RESULTS

We did not find differences related to Aβ42. We found a greater impact of the rest of CSF biomarkers in areas of the Papez circuit in women versus men. Men showed greater involvement in lateral parietal and paracentral areas.

DISCUSSION

Results suggest an early differential progression of brain atrophy between sexes. Further research will elucidate whether the mechanisms responsible for sex-specific atrophy patterns are biological and/or environmental.

Deep brain stimulation response in obsessive-compulsive disorder is associated with preoperative nucleus accumbens volume

•

Preoperative MRI was associated with 12-months DBS treatment outcome in OCD patients.

•

Larger nucleus accumbens volume was associated with larger clinical improvement.

•

Machine learning analysis was not successful in predicting clinical improvement.

Background

Deep brain stimulation (DBS) is a new treatment option for patients with therapy-resistant obsessive–compulsive disorder (OCD). Approximately 60% of patients benefit from DBS, which might be improved if a biomarker could identify patients who are likely to respond. Therefore, we evaluated the use of preoperative structural magnetic resonance imaging (MRI) in predicting treatment outcome for OCD patients on the group- and individual-level.

Methods

In this retrospective study, we analyzed preoperative MRI data of a large cohort of patients who received DBS for OCD (n = 57). We used voxel-based morphometry to investigate whether grey matter (GM) or white matter (WM) volume surrounding the DBS electrode (nucleus accumbens (NAc), anterior thalamic radiation), and whole-brain GM/WM volume were associated with OCD severity and response status at 12-month follow-up. In addition, we performed machine learning analyses to predict treatment outcome at an individual-level and evaluated its performance using cross-validation.

Results

Larger preoperative left NAc volume was associated with lower OCD severity at 12-month follow-up (p_FWE < 0.05). None of the individual-level regression/classification analyses exceeded chance-level performance.

Conclusions

These results provide evidence that patients with larger NAc volumes show a better response to DBS, indicating that DBS success is partly determined by individual differences in brain anatomy. However, the results also indicate that structural MRI data alone does not provide sufficient information to guide clinical decision making at an individual level yet.

Brain age prediction: A comparison between machine learning models using region- and voxel-based morphometric data

Brain morphology varies across the ageing trajectory and the prediction of a person's age using brain features can aid the detection of abnormalities in the ageing process. Existing studies on such “brain age prediction” vary widely in terms of their methods and type of data, so at present the most accurate and generalisable methodological approach is unclear. Therefore, we used the UK Biobank data set (N = 10,824, age range 47–73) to compare the performance of the machine learning models support vector regression, relevance vector regression and Gaussian process regression on whole‐brain region‐based or voxel‐based structural magnetic resonance imaging data with or without dimensionality reduction through principal component analysis. Performance was assessed in the validation set through cross‐validation as well as an independent test set. The models achieved mean absolute errors between 3.7 and 4.7 years, with those trained on voxel‐level data with principal component analysis performing best. Overall, we observed little difference in performance between models trained on the same data type, indicating that the type of input data had greater impact on performance than model choice. All code is provided online in the hope that this will aid future research.

Multimodal Image Analysis of Apparent Brain Age Identifies Physical Fitness as Predictor of Brain Maintenance

Maintaining a youthful brain structure and function throughout life may be the single most important determinant of successful cognitive aging. In this study, we addressed heterogeneity in brain aging by making image-based brain age predictions and relating the brain age prediction gap (BAPG) to cognitive change in aging. Structural, functional, and diffusion MRI scans from 351 participants were used to train and evaluate 5 single-modal and 4 multimodal prediction models, based on 7 regression methods. The models were compared on mean absolute error and whether they were related to physical fitness and cognitive ability, measured both currently and longitudinally, as well as study attrition and years of education. Multimodal prediction models performed at a similar level as single-modal models, and the choice of regression method did not significantly affect the results. Correlation with the BAPG was found for current physical fitness, current cognitive ability, and study attrition. Correlations were also found for retrospective physical fitness, measured 10 years prior to imaging, and slope for cognitive ability during a period of 15 years. The results suggest that maintaining a high physical fitness throughout life contributes to brain maintenance and preserved cognitive ability.

Defining data-driven subgroups of obsessive-compulsive disorder with different treatment responses based on resting-state functional connectivity

Characterization of obsessive-compulsive disorder (OCD), like other psychiatric disorders, suffers from heterogeneities in its symptoms and therapeutic responses, and identification of more homogeneous subgroups may help to resolve the heterogeneity. We aimed to identify the OCD subgroups based on resting-state functional connectivity (rsFC) and to explore their differences in treatment responses via a multivariate approach. From the resting-state functional MRI data of 107 medication-free OCD patients and 110 healthy controls (HCs), we selected rsFC features, which discriminated OCD patients from HCs via support vector machine (SVM) analyses. With the selected brain features, we subdivided OCD patients into subgroups using hierarchical clustering analyses. We identified 35 rsFC features that achieved a high sensitivity (82.74%) and specificity (76.29%) in SVM analyses. The OCD patients were subdivided into two subgroups, which did not show significant differences in their demographic and clinical backgrounds. However, one of the OCD subgroups demonstrated more impaired rsFC that was involved either within the default mode network (DMN) or between DMN brain regions and other network regions. This subgroup also showed both lower improvements in symptom severity in the 16-week follow-up visit and lower responder percentage than the other subgroup. Our results highlight that not only abnormalities within the DMN but also aberrant rsFC between the DMN and other networks may contribute to the treatment response and support the importance of these neurobiological alterations in OCD patients. We suggest that abnormalities in these connectivity may play predictive biomarkers of treatment response, and aid to build more optimal treatment strategies.

From a deep learning model back to the brain-Identifying regional predictors and their relation to aging

We present a Deep Learning framework for the prediction of chronological age from structural magnetic resonance imaging scans. Previous findings associate increased brain age with neurodegenerative diseases and higher mortality rates. However, the importance of brain age prediction goes beyond serving as biomarkers for neurological disorders. Specifically, utilizing convolutional neural network (CNN) analysis to identify brain regions contributing to the prediction can shed light on the complex multivariate process of brain aging. Previous work examined methods to attribute pixel/voxel-wise contributions to the prediction in a single image, resulting in "explanation maps" that were found noisy and unreliable. To address this problem, we developed an inference scheme for combining these maps across subjects, thus creating a population-based, rather than a subject-specific map. We applied this method to a CNN ensemble trained on predicting subjects' age from raw T1 brain images in a lifespan sample of 10,176 subjects. Evaluating the model on an untouched test set resulted in mean absolute error of 3.07 years and a correlation between chronological and predicted age of r = 0.98. Using the inference method, we revealed that cavities containing cerebrospinal fluid, previously found as general atrophy markers, had the highest contribution for age prediction. Comparing maps derived from different models within the ensemble allowed to assess differences and similarities in brain regions utilized by the model. We showed that this method substantially increased the replicability of explanation maps, converged with results from voxel-based morphometry age studies and highlighted brain regions whose volumetric variability correlated the most with the prediction error.

Brain MRI analysis using a deep learning based evolutionary approach

Convolutional neural network (CNN) models have recently demonstrated impressive performance in medical image analysis. However, there is no clear understanding of why they perform so well, or what they have learned. In this paper, a three-dimensional convolutional neural network (3D-CNN) is employed to classify brain MRI scans into two predefined groups. In addition, a genetic algorithm based brain masking (GABM) method is proposed as a visualization technique that provides new insights into the function of the 3D-CNN. The proposed GABM method consists of two main steps. In the first step, a set of brain MRI scans is used to train the 3D-CNN. In the second step, a genetic algorithm (GA) is applied to discover knowledgeable brain regions in the MRI scans. The knowledgeable regions are those areas of the brain which the 3D-CNN has mostly used to extract important and discriminative features from them. For applying GA on the brain MRI scans, a new chromosome encoding approach is proposed. The proposed framework has been evaluated using ADNI (including 140 subjects for Alzheimer's disease classification) and ABIDE (including 1000 subjects for Autism classification) brain MRI datasets. Experimental results show a 5-fold classification accuracy of 0.85 for the ADNI dataset and 0.70 for the ABIDE dataset. The proposed GABM method has extracted 6 to 65 knowledgeable brain regions in ADNI dataset (and 15 to 75 knowledgeable brain regions in ABIDE dataset). These regions are interpreted as the segments of the brain which are mostly used by the 3D-CNN to extract features for brain disease classification. Experimental results show that besides the model interpretability, the proposed GABM method has increased final performance of the classification model in some cases with respect to model parameters.

An algorithm for learning shape and appearance models without annotations

This paper presents a framework for automatically learning shape and appearance models for medical (and certain other) images. The algorithm was developed with the aim of eventually enabling distributed privacy-preserving analysis of brain image data, such that shared information (shape and appearance basis functions) may be passed across sites, whereas latent variables that encode individual images remain secure within each site. These latent variables are proposed as features for privacy-preserving data mining applications. The approach is demonstrated qualitatively on the KDEF dataset of 2D face images, showing that it can align images that traditionally require shape and appearance models trained using manually annotated data (manually defined landmarks etc.). It is applied to the MNIST dataset of handwritten digits to show its potential for machine learning applications, particularly when training data is limited. The model is able to handle "missing data", which allows it to be cross-validated according to how well it can predict left-out voxels. The suitability of the derived features for classifying individuals into patient groups was assessed by applying it to a dataset of over 1900 segmented T1-weighted MR images, which included images from the COBRE and ABIDE datasets.

Quantifying performance of machine learning methods for neuroimaging data

Machine learning is increasingly being applied to neuroimaging data. However, most machine learning algorithms have not been designed to accommodate neuroimaging data, which typically has many more data points than subjects, in addition to multicollinearity and low signal-to-noise. Consequently, the relative efficacy of different machine learning regression algorithms for different types of neuroimaging data are not known. Here, we sought to quantify the performance of a variety of machine learning algorithms for use with neuroimaging data with various sample sizes, feature set sizes, and predictor effect sizes. The contribution of additional machine learning techniques - embedded feature selection and bootstrap aggregation (bagging) - to model performance was also quantified. Five machine learning regression methods - Gaussian Process Regression, Multiple Kernel Learning, Kernel Ridge Regression, the Elastic Net and Random Forest, were examined with both real and simulated MRI data, and in comparison to standard multiple regression. The different machine learning regression algorithms produced varying results, which depended on sample size, feature set size, and predictor effect size. When the effect size was large, the Elastic Net, Kernel Ridge Regression and Gaussian Process Regression performed well at most sample sizes and feature set sizes. However, when the effect size was small, only the Elastic Net made accurate predictions, but this was limited to analyses with sample sizes greater than 400. Random Forest also produced a moderate performance for small effect sizes, but could do so across all sample sizes. Machine learning techniques also improved prediction accuracy for multiple regression. These data provide empirical evidence for the differential performance of various machines on neuroimaging data, which are dependent on number of sample size, features and effect size.

Discriminating between neurofibromatosis-1 and typically developing children by means of multimodal MRI and multivariate analyses

Neurofibromatosis Type 1 leads to brain anomalies involving both gray and white matter. The extent and granularity of these anomalies, together with their possible impact on brain activity, is still unknown. In this multicentric cross-sectional study we submitted a sample of 42 typically developing and 38 neurofibromatosis-1 children to a multimodal MRI assessment including T1, diffusion weighted and resting state functional sequences. We used a pipeline involving several features selection steps coupled with multivariate statistical analysis (supporting vector machine) to discriminate between the two groups while having interpretable models. We used MRI indexes measuring macro (gray matter volume) and microstructural (fractional anisotropy, mean diffusivity) characteristics of the brain, as well as indexes of brain activity (fractional amplitude of low frequency fluctuations) and connectivity (local and global correlation) at rest. We found that structural indexes could discriminate between the two groups, with the mean diffusivity leading to performance as high as the combination of all structural indexes combined (accuracy = 0.86), while functional indexes had worse performances. The MRI signature of NF1 brain pathology is a combination of gray and white matter abnormalities, as measured with gray matter volume, fractional anisotropy, and mean diffusivity.

Unbiased age-specific structural brain atlases for Chinese pediatric population

In magnetic resonance (MR) imaging studies of child brain development, structural brain atlases usually serve as important references for the pediatric population, in which individual images are spatially normalized into a common or standard stereotactic space. However, the popular existing pediatric brain atlases (e.g., National Institutes of Health pediatric atlases, NIH-PD) are mostly based on MR images obtained from Caucasian populations and thus are not ideal for the characterization of the brains of Chinese children due to neuroanatomical differences related to genetic and environmental factors. Here, we use an unbiased template construction algorithm to create a set of age-specific Chinese pediatric (CHN-PD) atlases based on high-quality T1-and T2-weighted MR images from 328 cognitively normal Chinese children aged 6-12 years. The CHN-PD brain atlases include asymmetric and symmetric templates, sex-specific templates and tissue probability templates, and contain multiple age-specific templates at one-year intervals. A direct comparison of the CHN-PD and NIH-PD atlases reveals dramatic anatomical differences mainly in the bilateral frontal and parietal regions. After applying the CHN-PD and NIH-PD atlases to two independent Chinese pediatric datasets (N = 114 and N = 71), we find that the CHN-PD atlases result in significantly higher accuracy than the NIH-PD atlases in both predicting "brain age" and guiding brain tissue segmentation. These results suggest that the CHN-PD brain atlases are necessary for studies of the typical and atypical development of the Chinese pediatric population. These CHN-PD atlases have been released on the Neuroimaging Informatics Tools and Resources Clearinghouse (NITRC) website (https://www.nitrc.org/projects/chn-pd).