Clinical prediction from structural brain MRI scans: a large-scale empirical study

Individualized multi-modal MRI biomarkers predict 1-year clinical outcome in first-episode drug-naïve schizophrenia patients

Background

Antipsychotic medications offer limited long-term benefit to about 30% of patients with schizophrenia. We aimed to explore the individual-specific imaging markers to predict 1-year treatment response of schizophrenia.

Methods

Structural morphology and functional topological features related to treatment response were identified using an individualized parcellation analysis in conjunction with machine learning (ML). We performed dimensionality reductions using the Pearson correlation coefficient and three feature selection analyses and classifications using 10 ML classifiers. The results were assessed through a 5-fold cross-validation (training and validation cohorts, n = 51) and validated using the external test cohort (n = 17).

Results

ML algorithms based on individual-specific brain network proved more effective than those based on group-level brain network in predicting outcomes. The most predictive features based on individual-specific parcellation involved the GMV of the default network and the degree of the control, limbic, and default networks. The AUCs for the training, validation, and test cohorts were 0.947, 0.939, and 0.883, respectively. Additionally, the prediction performance of the models constructed by the different feature selection methods and classifiers showed no significant differences.

Conclusion

Our study highlighted the potential of individual-specific network parcellation in treatment resistant schizophrenia prediction and underscored the crucial role of feature attributes in predictive model accuracy.

Contrastive Brain Network Learning via Hierarchical Signed Graph Pooling Model

Recently, brain networks have been widely adopted to study brain dynamics, brain development, and brain diseases. Graph representation learning techniques on brain functional networks can facilitate the discovery of novel biomarkers for clinical phenotypes and neurodegenerative diseases. However, current graph learning techniques have several issues on brain network mining. First, most current graph learning models are designed for unsigned graph, which hinders the analysis of many signed network data (e.g., brain functional networks). Meanwhile, the insufficiency of brain network data limits the model performance on clinical phenotypes' predictions. Moreover, few of the current graph learning models are interpretable, which may not be capable of providing biological insights for model outcomes. Here, we propose an interpretable hierarchical signed graph representation learning (HSGPL) model to extract graph-level representations from brain functional networks, which can be used for different prediction tasks. To further improve the model performance, we also propose a new strategy to augment functional brain network data for contrastive learning. We evaluate this framework on different classification and regression tasks using data from human connectome project (HCP) and open access series of imaging studies (OASIS). Our results from extensive experiments demonstrate the superiority of the proposed model compared with several state-of-the-art techniques. In addition, we use graph saliency maps, derived from these prediction tasks, to demonstrate detection and interpretation of phenotypic biomarkers.

Brain age prediction across the human lifespan using multimodal MRI data

Measuring differences between an individual's age and biological age with biological information from the brain have the potential to provide biomarkers of clinically relevant neurological syndromes that arise later in human life. To explore the effect of multimodal brain magnetic resonance imaging (MRI) features on the prediction of brain age, we investigated how multimodal brain imaging data improved age prediction from more imaging features of structural or functional MRI data by using partial least squares regression (PLSR) and longevity data sets (age 6-85 years). First, we found that the age-predicted values for each of these ten features ranged from high to low: cortical thickness (R = 0.866, MAE = 7.904), all seven MRI features (R = 0.8594, MAE = 8.24), four features in structural MRI (R = 0.8591, MAE = 8.24), fALFF (R = 0.853, MAE = 8.1918), gray matter volume (R = 0.8324, MAE = 8.931), three rs-fMRI feature (R = 0.7959, MAE = 9.744), mean curvature (R = 0.7784, MAE = 10.232), ReHo (R = 0.7833, MAE = 10.122), ALFF (R = 0.7517, MAE = 10.844), and surface area (R = 0.719, MAE = 11.33). In addition, the significance of the volume and size of brain MRI data in predicting age was also studied. Second, our results suggest that all multimodal imaging features, except cortical thickness, improve brain-based age prediction. Third, we found that the left hemisphere contributed more to the age prediction, that is, the left hemisphere showed a greater weight in the age prediction than the right hemisphere. Finally, we found a nonlinear relationship between the predicted age and the amount of MRI data. Combined with multimodal and lifespan brain data, our approach provides a new perspective for chronological age prediction and contributes to a better understanding of the relationship between brain disorders and aging.

Translating phenotypic prediction models from big to small anatomical MRI data using meta-matching

Individualized phenotypic prediction based on structural MRI is an important goal in neuroscience. Prediction performance increases with larger samples, but small-scale datasets with fewer than 200 participants are often unavoidable. We have previously proposed a "meta-matching" framework to translate models trained from large datasets to improve the prediction of new unseen phenotypes in small collection efforts. Meta-matching exploits correlations between phenotypes, yielding large improvement over classical machine learning when applied to prediction models using resting-state functional connectivity as input features. Here, we adapt the two best performing meta-matching variants ("meta-matching finetune" and "meta-matching stacking") from our previous study to work with T1-weighted MRI data by changing the base neural network architecture to a 3D convolution neural network. We compare the two meta-matching variants with elastic net and classical transfer learning using the UK Biobank (N = 36,461), Human Connectome Project Young Adults (HCP-YA) dataset (N = 1,017) and HCP-Aging dataset (N = 656). We find that meta-matching outperforms elastic net and classical transfer learning by a large margin, both when translating models within the same dataset, as well as translating models across datasets with different MRI scanners, acquisition protocols and demographics. For example, when translating a UK Biobank model to 100 HCP-YA participants, meta-matching finetune yielded a 136% improvement in variance explained over transfer learning, with an average absolute gain of 2.6% (minimum = -0.9%, maximum = 17.6%) across 35 phenotypes. Overall, our results highlight the versatility of the meta-matching framework.

Estimating the Total Variance Explained by Whole-Brain Imaging for Zero-inflated Outcomes

Zero-inflated outcomes are very common in behavioral data, particularly for responses to psychological questionnaires. Modeling these challenging distributions is further exacerbated by the absence of established statistical models capable of characterizing total signals attributed to whole-brain imaging features, making the accurate assessment of brain-behavior relationships particularly formidable. Given this critical need, we have developed a novel variational Bayes algorithm that characterizes the total signal captured by whole-brain imaging features for zero-inflated outcomes . Our zero-inflated variance (ZIV) estimator robustly estimates the fraction of variance explained (FVE) and the proportion of non-null effects from large-scale imaging data. In simulations, ZIV outperformed other linear prediction algorithms. Applying ZIV to data from one of the largest neuroimaging studies, the Adolescent Brain Cognitive Development SM (ABCD) Study, we found that whole-brain imaging features have a larger FVE for externalizing compared to internalizing behavior. We also demonstrate that the ZIV estimator, especially applied to focal sub-scales, can localize key neurocircuitry associated with human behavior.

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.

One Size Does Not Fit All: Methodological Considerations for Brain-Based Predictive Modeling in Psychiatry

Psychiatric illnesses are heterogeneous in nature. No illness manifests in the same way across individuals, and no two patients with a shared diagnosis exhibit identical symptom profiles. Over the last several decades, group-level analyses of in vivo neuroimaging data have led to fundamental advances in our understanding of the neurobiology of psychiatric illnesses. More recently, access to computational resources and large, publicly available datasets alongside the rise of predictive modeling and precision medicine approaches have facilitated the study of psychiatric illnesses at an individual level. Data-driven machine learning analyses can be applied to identify disease-relevant biological subtypes, predict individual symptom profiles, and recommend personalized therapeutic interventions. However, when developing these predictive models, methodological choices must be carefully considered to ensure accurate, robust, and interpretable results. Choices pertaining to algorithms, neuroimaging modalities and states, data transformation, phenotypes, parcellations, sample sizes, and populations we are specifically studying can influence model performance. Here, we review applications of neuroimaging-based machine learning models to study psychiatric illnesses and discuss the effects of different methodological choices on model performance. An understanding of these effects is crucial for the proper implementation of predictive models in psychiatry and will facilitate more accurate diagnoses, prognoses, and therapeutics.

Two Routes to Alzheimer's Disease Based on Differential Structural Changes in Key Brain Regions

BACKGROUND

Alzheimer's disease (AD) is a neurodegenerative disorder with homogenous disease patterns. Neuropathological changes precede symptoms by up to two decades making neuroimaging biomarkers a prime candidate for early diagnosis, prognosis, and patient stratification.

OBJECTIVE

The goal of the study was to discern intermediate AD stages and their precursors based on neuroanatomical features for stratifying patients on their progression through different stages.

METHODS

Data include grey matter features from 14 brain regions extracted from longitudinal structural MRI and cognitive data obtained from 1,017 healthy controls and AD patients of ADNI. AD progression was modeled with a Hidden Markov Model, whose hidden states signify disease stages derived from the neuroanatomical data. To tie the progression in brain atrophy to a behavioral marker, we analyzed the ADAS-cog sub-scores in the stages.

RESULTS

The optimal model consists of eight states with differentiable neuroanatomical features, forming two routes crossing once at a very early point and merging at the final state. The cortical route is characterized by early and sustained atrophy in cortical regions. The limbic route is characterized by early decrease in limbic regions. Cognitive differences between the two routes are most noticeable in the memory domain with subjects from the limbic route experiencing stronger memory impairments.

CONCLUSION

Our findings corroborate that more than one pattern of grey matter deterioration with several discernable stages can be identified in the progression of AD. These neuroanatomical subtypes are behaviorally meaningful and provide a door into early diagnosis of AD and prognosis of the disease's progression.

Fused deep learning paradigm for the prediction of o6-methylguanine-DNA methyltransferase genotype in glioblastoma patients: A neuro-oncological investigation

BACKGROUND

The O6-methylguanine-DNA methyltransferase (MGMT) is a deoxyribonucleic acid (DNA) repairing enzyme that has been established as an essential clinical brain tumor biomarker for Glioblastoma Multiforme (GBM). Knowing the status of MGMT methylation biomarkers using multi-parametric MRI (mp-MRI) helps neuro-oncologists to analyze GBM and its treatment plan.

METHOD

The hand-crafted radiomics feature extraction of GBM's subregions, such as edema(ED), tumor core (TC), and enhancing tumor (ET) in the machine learning (ML) framework, was investigated using support vector machine(SVM), K-Nearest Neighbours (KNN), random forest (RF), LightGBM, and extreme gradient boosting (XGB). For tissue-level analysis of the promotor genes in GBM, we used the deep residual neural network (ResNet-18) with 3D architecture, followed by EfficientNet-based investigation for variants as B0 and B1. Lastly, we analyzed the fused deep learning (FDL) framework that combines ML and DL frameworks.

RESULT

Structural mp-MRI consisting of T1, T2, FLAIR, and T1GD having a size of 400 and 185 patients, respectively, for discovery and replication cohorts. Using the CV protocol in the ResNet-3D framework, MGMT methylation status prediction in mp-MRI gave the AUC of 0.753 (p < 0.0001) and 0.72 (p < 0.0001) for the discovery and replication cohort, respectively. We presented that the FDL is ∼7% superior to solo DL and ∼15% to solo ML.

CONCLUSION

The proposed study aims to provide solutions for building an efficient predictive model of MGMT for GBM patients using deep radiomics features obtained from mp-MRI with the end-to-end ResNet-18 3D and FDL imaging signatures.

Exploiting task relationships for Alzheimer's disease cognitive score prediction via multi-task learning

Alzheimer's disease (AD) is highly prevalent and a significant cause of dementia and death in elderly individuals. Motivated by breakthroughs of multi-task learning (MTL), efforts have been made to extend MTL to improve the Alzheimer's disease cognitive score prediction by exploiting structure correlation. Though important and well-studied, three key aspects are yet to be fully handled in an unified framework: (i) appropriately modeling the inherent task relationship; (ii) fully exploiting the task relatedness by considering the underlying feature structure. (iii) automatically determining the weight of each task. To this end, we present the Bi-Graph guided self-Paced Multi-Task Feature Learning (BGP-MTFL) framework for exploring the relationship among multiple tasks to improve overall learning performance of cognitive score prediction. The framework consists of the two correlation regularization for features and tasks, ℓ_2,1 regularization and self-paced learning scheme. Moreover, we design an efficient optimization method to solve the non-smooth objective function of our approach based on the Alternating Direction Method of Multipliers (ADMM) combined with accelerated proximal gradient (APG). The proposed model is comprehensively evaluated on the Alzheimer's disease neuroimaging initiative (ADNI) datasets. Overall, the proposed algorithm achieves an nMSE (normalized Mean Squared Error) of 3.923 and an wR (weighted R-value) of 0.416 for predicting eighteen cognitive scores, respectively. The empirical study demonstrates that the proposed BGP-MTFL model outperforms the state-of-the-art AD prediction approaches and enables identifying more stable biomarkers.

Analysis of Cases with Cerebrospinal Fluid Characteristics Similar to Tuberculous Meningitis

Purpose

The diagnosis of tuberculous meningitis (TBM) is difficult and relies on the patient's clinical presentation and initial cerebrospinal fluid testing. Treatment outcomes for some patients with early consideration of TBM meningitis are often poor. Patients and Methods. In this study, we retrospectively analyzed 24 non-TBM patients whose early changes of cerebrospinal fluid were similar to those of TBM through the second-generation cerebrospinal fluid sequencing technology.

Results

All patients included in this study had an acute onset, including 5 patients with a history of upper respiratory tract infection, 9 patients with fever, 6 patients with headache, 5 patients with psychiatric symptoms, 6 patients with cognitive impairment, 9 patients with signs of meningeal irritation, and 6 patients with seizures. Sixteen patients presented with altered content and level of consciousness during their admission. The leukocyte counts (median, 124.0 × 10⁶/L) and total protein concentrations (median, 1300 mg/L) were higher than normal reference values in all patients, whereas glucose (median, 1.345 mmol/L) and chloride concentration values (average, 111.7 ± 5.2 mmol/L) were lower than normal reference values. The patients included 2 cases of Liszt's meningitis, 2 cases of Brucella infection in the CNS, 4 cases of Varicella zoster virus encephalitis, 2 cases of human herpes simplex virus type 1, 2 cases of lupus encephalopathy, 2 cases of anti-NMDAR receptor encephalitis, 2 cases of meningeal carcinomatosis, 5 cases of cryptococcal meningitis, 2 cases of CNS sarcoidosis, and a case of invasive Rhizopus oryzae infection. All patients were tested for NGS in cerebrospinal fluid. Eight patients were diagnosed with anti-NMDAR encephalitis, meningeal carcinomatosis, lupus encephalopathy, and CNS sarcoidosis. Nine patients experienced death; 15 patients had a good prognosis and left no significant sequelae.

Conclusion

The analysis of patients with TBM-like cerebrospinal fluid changes will help improve the diagnostic accuracy of the disease and reduce misdiagnosis and underdiagnosis.

Comparison of individualized behavioral predictions across anatomical, diffusion and functional connectivity MRI

A fundamental goal across the neurosciences is the characterization of relationships linking brain anatomy, functioning, and behavior. Although various MRI modalities have been developed to probe these relationships, direct comparisons of their ability to predict behavior have been lacking. Here, we compared the ability of anatomical T1, diffusion and functional MRI (fMRI) to predict behavior at an individual level. Cortical thickness, area and volume were extracted from anatomical T1 images. Diffusion Tensor Imaging (DTI) and approximate Neurite Orientation Dispersion and Density Imaging (NODDI) models were fitted to the diffusion images. The resulting metrics were projected to the Tract-Based Spatial Statistics (TBSS) skeleton. We also ran probabilistic tractography for the diffusion images, from which we extracted the stream count, average stream length, and the average of each DTI and NODDI metric across tracts connecting each pair of brain regions. Functional connectivity (FC) was extracted from both task and resting-state fMRI. Individualized prediction of a wide range of behavioral measures were performed using kernel ridge regression, linear ridge regression and elastic net regression. Consistency of the results were investigated with the Human Connectome Project (HCP) and Adolescent Brain Cognitive Development (ABCD) datasets. In both datasets, FC-based models gave the best prediction performance, regardless of regression model or behavioral measure. This was especially true for the cognitive component. Furthermore, all modalities were able to predict cognition better than other behavioral components. Combining all modalities improved prediction of cognition, but not other behavioral components. Finally, across all behaviors, combining resting and task FC yielded prediction performance similar to combining all modalities. Overall, our study suggests that in the case of healthy children and young adults, behaviorally-relevant information in T1 and diffusion features might reflect a subset of the variance captured by FC.

Multi-Task Weakly-Supervised Attention Network for Dementia Status Estimation With Structural MRI

Accurate prediction of clinical scores (of neuropsychological tests) based on noninvasive structural magnetic resonance imaging (MRI) helps understand the pathological stage of dementia (e.g., Alzheimer's disease (AD)) and forecast its progression. Existing machine/deep learning approaches typically preselect dementia-sensitive brain locations for MRI feature extraction and model construction, potentially leading to undesired heterogeneity between different stages and degraded prediction performance. Besides, these methods usually rely on prior anatomical knowledge (e.g., brain atlas) and time-consuming nonlinear registration for the preselection of brain locations, thereby ignoring individual-specific structural changes during dementia progression because all subjects share the same preselected brain regions. In this article, we propose a multi-task weakly-supervised attention network (MWAN) for the joint regression of multiple clinical scores from baseline MRI scans. Three sequential components are included in MWAN: 1) a backbone fully convolutional network for extracting MRI features; 2) a weakly supervised dementia attention block for automatically identifying subject-specific discriminative brain locations; and 3) an attention-aware multitask regression block for jointly predicting multiple clinical scores. The proposed MWAN is an end-to-end and fully trainable deep learning model in which dementia-aware holistic feature learning and multitask regression model construction are integrated into a unified framework. Our MWAN method was evaluated on two public AD data sets for estimating clinical scores of mini-mental state examination (MMSE), clinical dementia rating sum of boxes (CDRSB), and AD assessment scale cognitive subscale (ADAS-Cog). Quantitative experimental results demonstrate that our method produces superior regression performance compared with state-of-the-art methods. Importantly, qualitative results indicate that the dementia-sensitive brain locations automatically identified by our MWAN method well retain individual specificities and are biologically meaningful.

Brain Morphology Predictors of Alcohol, Tobacco, and Cannabis Use in Adolescence: A Systematic Review

In the last decade, extensive research has emerged on the predictive value of brain morphology for substance use initiation and related problems during adolescence. This systematic review provides an overview of longitudinal studies on pre-existing brain variations and later initiation of alcohol, tobacco, and cannabis use (N = 18). Adolescent structural neuroimaging studies that started before substance use initiation suggest that a smaller anterior cingulate cortex (ACC) volume, thicker or smaller superior frontal gyrus, and larger nucleus accumbens (NAcc) volume are associated with future alcohol use. Also, both smaller and larger orbitofrontal cortex (OFC) volumes were associated with future cannabis and combined alcohol/cannabis use. Smaller amygdala volumes were related to future daily tobacco smoking. These findings could point to specific vulnerabilities for adolescent substance use, as these brain areas are involved in cognitive control (ACC), reward (NAcc), motivation (OFC), and emotional memory (amygdala). However, the reported findings were inconsistent in directionality and laterality, and the largest study on alcohol use predictors reported null findings. Therefore, large population-based longitudinal studies should investigate the robustness and mechanisms of these associations. We suggested future research directions regarding sample selection, timing of baseline and follow-up measurements, and a harmonization approach of study methods.

A Hierarchical Graph Learning Model for Brain Network Regression Analysis

Brain networks have attracted increasing attention due to the potential to better characterize brain dynamics and abnormalities in neurological and psychiatric conditions. Recent years have witnessed enormous successes in deep learning. Many AI algorithms, especially graph learning methods, have been proposed to analyze brain networks. An important issue for existing graph learning methods is that those models are not typically easy to interpret. In this study, we proposed an interpretable graph learning model for brain network regression analysis. We applied this new framework on the subjects from Human Connectome Project (HCP) for predicting multiple Adult Self-Report (ASR) scores. We also use one of the ASR scores as the example to demonstrate how to identify sex differences in the regression process using our model. In comparison with other state-of-the-art methods, our results clearly demonstrate the superiority of our new model in effectiveness, fairness, and transparency.

MPC-STANet: Alzheimer's Disease Recognition Method Based on Multiple Phantom Convolution and Spatial Transformation Attention Mechanism

Alzheimer's disease (AD) is a progressive neurodegenerative disease with insidious and irreversible onset. The recognition of the disease stage of AD and the administration of effective interventional treatment are important to slow down and control the progression of the disease. However, due to the unbalanced distribution of the acquired data volume, the problem that the features change inconspicuously in different disease stages of AD, and the scattered and narrow areas of the feature areas (hippocampal region, medial temporal lobe, etc.), the effective recognition of AD remains a critical unmet need. Therefore, we first employ class-balancing operation using data expansion and Synthetic Minority Oversampling Technique (SMOTE) to avoid the AD MRI dataset being affected by classification imbalance in the training. Subsequently, a recognition network based on Multi-Phantom Convolution (MPC) and Space Conversion Attention Mechanism (MPC-STANet) with ResNet50 as the backbone network is proposed for the recognition of the disease stages of AD. In this study, we propose a Multi-Phantom Convolution in the way of convolution according to the channel direction and integrate it with the average pooling layer into two basic blocks of ResNet50: Conv Block and Identity Block to propose the Multi-Phantom Residual Block (MPRB) including Multi-Conv Block and Multi-Identity Block to better recognize the scattered and tiny disease features of Alzheimer's disease. Meanwhile, the weight coefficients are extracted from both vertical and horizontal directions using the Space Conversion Attention Mechanism (SCAM) to better recognize subtle structural changes in the AD MRI images. The experimental results show that our proposed method achieves an average recognition accuracy of 96.25%, F1 score of 95%, and mAP of 93%, and the number of parameters is only 1.69 M more than ResNet50.

Dementia-related user-based collaborative filtering for imputing missing data and generating a reliability scale on clinical test scores

Medical doctors may struggle to diagnose dementia, particularly when clinical test scores are missing or incorrect. In case of any doubts, both morphometrics and demographics are crucial when examining dementia in medicine. This study aims to impute and verify clinical test scores with brain MRI analysis and additional demographics, thereby proposing a decision support system that improves diagnosis and prognosis in an easy-to-understand manner. Therefore, we impute the missing clinical test score values by unsupervised dementia-related user-based collaborative filtering to minimize errors. By analyzing succession rates, we propose a reliability scale that can be utilized for the consistency of existing clinical test scores. The complete base of 816 ADNI1-screening samples was processed, and a hybrid set of 603 features was handled. Moreover, the detailed parameters in use, such as the best neighborhood and input features were evaluated for further comparative analysis. Overall, certain collaborative filtering configurations outperformed alternative state-of-the-art imputation techniques. The imputation system and reliability scale based on the proposed methodology are promising for supporting the clinical tests.

Diagnostic Performance of Generative Adversarial Network-Based Deep Learning Methods for Alzheimer’s Disease: A Systematic Review and Meta-Analysis

Alzheimer’s disease (AD) is the most common form of dementia. Currently, only symptomatic management is available, and early diagnosis and intervention are crucial for AD treatment. As a recent deep learning strategy, generative adversarial networks (GANs) are expected to benefit AD diagnosis, but their performance remains to be verified. This study provided a systematic review on the application of the GAN-based deep learning method in the diagnosis of AD and conducted a meta-analysis to evaluate its diagnostic performance. A search of the following electronic databases was performed by two researchers independently in August 2021: MEDLINE (PubMed), Cochrane Library, EMBASE, and Web of Science. The Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool was applied to assess the quality of the included studies. The accuracy of the model applied in the diagnosis of AD was determined by calculating odds ratios (ORs) with 95% confidence intervals (CIs). A bivariate random-effects model was used to calculate the pooled sensitivity and specificity with their 95% CIs. Fourteen studies were included, 11 of which were included in the meta-analysis. The overall quality of the included studies was high according to the QUADAS-2 assessment. For the AD vs. cognitively normal (CN) classification, the GAN-based deep learning method exhibited better performance than the non-GAN method, with significantly higher accuracy (OR 1.425, 95% CI: 1.150–1.766, P = 0.001), pooled sensitivity (0.88 vs. 0.83), pooled specificity (0.93 vs. 0.89), and area under the curve (AUC) of the summary receiver operating characteristic curve (SROC) (0.96 vs. 0.93). For the progressing MCI (pMCI) vs. stable MCI (sMCI) classification, the GAN method exhibited no significant increase in the accuracy (OR 1.149, 95% CI: 0.878–1.505, P = 0.310) or the pooled sensitivity (0.66 vs. 0.66). The pooled specificity and AUC of the SROC in the GAN group were slightly higher than those in the non-GAN group (0.81 vs. 0.78 and 0.81 vs. 0.80, respectively). The present results suggested that the GAN-based deep learning method performed well in the task of AD vs. CN classification. However, the diagnostic performance of GAN in the task of pMCI vs. sMCI classification needs to be improved.

Systematic Review Registration: [PROSPERO], Identifier: [CRD42021275294].

Early Detection of Alzheimer’s Disease using Bottleneck Transformers

Early detection of Alzheimer’s Disease (AD) and its prodromal state, Mild Cognitive Impairment (MCI), is crucial for providing suitable treatment and preventing the disease from progressing. It can also aid researchers and clinicians to identify early biomarkers and minister new treatments that have been a subject of extensive research. The application of deep learning techniques on structural Magnetic Resonance Imaging (MRI) has shown promising results in diagnosing the disease. In this research, we intend to introduce a novel approach of using an ensemble of the self-attention-based Bottleneck Transformers with a sharpness aware minimizer for early detection of Alzheimer’s Disease. The proposed approach has been tested on the widely accepted ADNI dataset and evaluated using accuracy, precision, recall, F1 score, and ROC-AUC score as the performance metrics.

Population heterogeneity in clinical cohorts affects the predictive accuracy of brain imaging

Brain imaging research enjoys increasing adoption of supervised machine learning for single-participant disease classification. Yet, the success of these algorithms likely depends on population diversity, including demographic differences and other factors that may be outside of primary scientific interest. Here, we capitalize on propensity scores as a composite confound index to quantify diversity due to major sources of population variation. We delineate the impact of population heterogeneity on the predictive accuracy and pattern stability in 2 separate clinical cohorts: the Autism Brain Imaging Data Exchange (ABIDE, n = 297) and the Healthy Brain Network (HBN, n = 551). Across various analysis scenarios, our results uncover the extent to which cross-validated prediction performances are interlocked with diversity. The instability of extracted brain patterns attributable to diversity is located preferentially in regions part of the default mode network. Collectively, our findings highlight the limitations of prevailing deconfounding practices in mitigating the full consequences of population diversity.

Ten years of image analysis and machine learning competitions in dementia

Machine learning methods exploiting multi-parametric biomarkers, especially based on neuroimaging, have huge potential to improve early diagnosis of dementia and to predict which individuals are at-risk of developing dementia. To benchmark algorithms in the field of machine learning and neuroimaging in dementia and assess their potential for use in clinical practice and clinical trials, seven grand challenges have been organized in the last decade: MIRIAD (2012), Alzheimer's Disease Big Data DREAM (2014), CADDementia (2014), Machine Learning Challenge (2014), MCI Neuroimaging (2017), TADPOLE (2017), and the Predictive Analytics Competition (2019). Based on two challenge evaluation frameworks, we analyzed how these grand challenges are complementing each other regarding research questions, datasets, validation approaches, results and impact. The seven grand challenges addressed questions related to screening, clinical status estimation, prediction and monitoring in (pre-clinical) dementia. There was little overlap in clinical questions, tasks and performance metrics. Whereas this aids providing insight on a broad range of questions, it also limits the validation of results across challenges. The validation process itself was mostly comparable between challenges, using similar methods for ensuring objective comparison, uncertainty estimation and statistical testing. In general, winning algorithms performed rigorous data pre-processing and combined a wide range of input features. Despite high state-of-the-art performances, most of the methods evaluated by the challenges are not clinically used. To increase impact, future challenges could pay more attention to statistical analysis of which factors (i.e., features, models) relate to higher performance, to clinical questions beyond Alzheimer's disease, and to using testing data beyond the Alzheimer's Disease Neuroimaging Initiative. Grand challenges would be an ideal venue for assessing the generalizability of algorithm performance to unseen data of other cohorts. Key for increasing impact in this way are larger testing data sizes, which could be reached by sharing algorithms rather than data to exploit data that cannot be shared. Given the potential and lessons learned in the past ten years, we are excited by the prospects of grand challenges in machine learning and neuroimaging for the next ten years and beyond.

Research on Construction and Risk Management of Operating Room Based on IoTs and Digitization

This paper introduces the background and experience of the development of a digital operating room and designs the main functions of the digital operating room based on the Internet of Things, the impact on medical data in hospitals, and how to build the digital operating room to cope with the huge amount of data in the "data era." The infrastructure of the digital operating room is described, as well as how to collect and transmit medical data, how to store large amounts of medical data, and how to analyze medical data and explore its hidden data value are also described. One hundred and four surgical patients from June 2020 to June 2021 were randomly selected for the study, and they were randomly and equally divided into 52 cases each in the control group and the observation group, with the control group implementing the management of conventional care methods and the observation group implementing information technology for care management, comparing the management effects of patients in both groups. The satisfaction of patients in the observation group was significantly higher than that of the control group (P < 0.05). The use of information technology to ensure the quality of care in the operating room not only can help patients recover early but also can help patients relieve the psychological pressure after surgery, thus improving the doctor-patient relationship, and has a significant application effect.

The Role of Structure MRI in Diagnosing Autism

This study proposes a Computer-Aided Diagnostic (CAD) system to diagnose subjects with autism spectrum disorder (ASD). The CAD system identifies morphological anomalies within the brain regions of ASD subjects. Cortical features are scored according to their contribution in diagnosing a subject to be ASD or typically developed (TD) based on a trained machine-learning (ML) model. This approach opens the hope for developing a new CAD system for early personalized diagnosis of ASD. We propose a framework to extract the cerebral cortex from structural MRI as well as identifying the altered areas in the cerebral cortex. This framework consists of the following five main steps: (i) extraction of cerebral cortex from structural MRI; (ii) cortical parcellation to a standard atlas; (iii) identifying ASD associated cortical markers; (iv) adjusting feature values according to sex and age; (v) building tailored neuro-atlases to identify ASD; and (vi) artificial neural networks (NN) are trained to classify ASD. The system is tested on the Autism Brain Imaging Data Exchange (ABIDE I) sites achieving an average balanced accuracy score of 97±2%. This paper demonstrates the ability to develop an objective CAD system using structure MRI and tailored neuro-atlases describing specific developmental patterns of the brain in autism.

Machine learning in neuroimaging: from research to clinical practice

Neuroimaging is critical in clinical care and research, enabling us to investigate the brain in health and disease. There is a complex link between the brain's morphological structure, physiological architecture, and the corresponding imaging characteristics. The shape, function, and relationships between various brain areas change during development and throughout life, disease, and recovery. Like few other areas, neuroimaging benefits from advanced analysis techniques to fully exploit imaging data for studying the brain and its function. Recently, machine learning has started to contribute (a) to anatomical measurements, detection, segmentation, and quantification of lesions and disease patterns, (b) to the rapid identification of acute conditions such as stroke, or (c) to the tracking of imaging changes over time. As our ability to image and analyze the brain advances, so does our understanding of its intricate relationships and their role in therapeutic decision-making. Here, we review the current state of the art in using machine learning techniques to exploit neuroimaging data for clinical care and research, providing an overview of clinical applications and their contribution to fundamental computational neuroscience.

Advancing diagnostic performance and clinical applicability of deep learning-driven generative adversarial networks for Alzheimer's disease

Alzheimer's disease (AD) is a neurodegenerative disease that severely affects the activities of daily living in aged individuals, which typically needs to be diagnosed at an early stage. Generative adversarial networks (GANs) provide a new deep learning method that show good performance in image processing, while it remains to be verified whether a GAN brings benefit in AD diagnosis. The purpose of this research is to systematically review psychoradiological studies on the application of a GAN in the diagnosis of AD from the aspects of classification of AD state and AD-related image processing compared with other methods. In addition, we evaluated the research methodology and provided suggestions from the perspective of clinical application. Compared with other methods, a GAN has higher accuracy in the classification of AD state and better performance in AD-related image processing (e.g. image denoising and segmentation). Most studies used data from public databases but lacked clinical validation, and the process of quantitative assessment and comparison in these studies lacked clinicians' participation, which may have an impact on the improvement of generation effect and generalization ability of the GAN model. The application value of GANs in the classification of AD state and AD-related image processing has been confirmed in reviewed studies. Improvement methods toward better GAN architecture were also discussed in this paper. In sum, the present study demonstrated advancing diagnostic performance and clinical applicability of GAN for AD, and suggested that the future researchers should consider recruiting clinicians to compare the algorithm with clinician manual methods and evaluate the clinical effect of the algorithm.

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.

AutoAtlas: Neural Network for 3D Unsupervised Partitioning and Representation Learning

We present a novel neural network architecture called AutoAtlas for fully unsupervised partitioning and representation learning of 3D brain Magnetic Resonance Imaging (MRI) volumes. AutoAtlas consists of two neural network components: one neural network to perform multi-label partitioning based on local texture in the volume, and a second neural network to compress the information contained within each partition. We train both of these components simultaneously by optimizing a loss function that is designed to promote accurate reconstruction of each partition, while encouraging spatially smooth and contiguous partitioning, and discouraging relatively small partitions. We show that the partitions adapt to the subject specific structural variations of brain tissue while consistently appearing at similar spatial locations across subjects. AutoAtlas also produces very low dimensional features that represent local texture of each partition. We demonstrate prediction of metadata associated with each subject using the derived feature representations and compare the results to prediction using features derived from FreeSurfer anatomical parcellation. Since our features are intrinsically linked to distinct partitions, we can then map values of interest, such as partition-specific feature importance scores onto the brain for visualization.

Automatic classification of autism spectrum disorder in children using cortical thickness and support vector machine

OBJECTIVE

Autism spectrum disorder (ASD) is a neurodevelopmental condition with a heterogeneous phenotype. The role of biomarkers in ASD diagnosis has been highlighted; cortical thickness has proved to be involved in the etiopathogenesis of ASD core symptoms. We apply support vector machine, a supervised machine learning method, in order to identify specific cortical thickness alterations in ASD subjects.

METHODS

A sample of 76 subjects (9.5 ± 3.4 years old) has been selected, 40 diagnosed with ASD and 36 typically developed subjects. All children underwent a magnetic resonance imaging (MRI) examination; T1-MPRAGE sequences were analyzed to extract features for the characterization and parcellation of regions of interests (ROI); average cortical thickness (CT) has been measured for each ROI. For the classification process, the extracted features were used as input for a classifier to identify ASD subjects through a "learning by example" procedure; the features with best performance was then selected by "greedy forward-feature selection." Finally, this model underwent a leave-one-out cross-validation approach.

RESULTS

From the training set of 68 ROIs, five ROIs reached accuracies of over 70%. After this phase, we used a recursive feature selection process in order to identify the eight features with the best accuracy (84.2%). CT resulted higher in ASD compared to controls in all the ROIs identified at the end of the process.

CONCLUSION

We found increased CT in various brain regions in ASD subjects, confirming their role in the pathogenesis of this condition. Considering the brain development curve during ages, these changes in CT may normalize during development. Further validation on a larger sample is required.

Brain imaging-based machine learning in autism spectrum disorder: methods and applications

Autism spectrum disorder (ASD) is a neurodevelopmental condition with early childhood onset and high heterogeneity. As the pathogenesis is still elusive, ASD diagnosis is comprised of a constellation of behavioral symptoms. Non-invasive brain imaging techniques, such as magnetic resonance imaging (MRI), provide a valuable objective measurement of the brain. Many efforts have been devoted to developing imaging-based diagnostic tools for ASD based on machine learning (ML) technologies. In this survey, we review recent advances that utilize machine learning approaches to classify individuals with and without ASD. First, we provide a brief overview of neuroimaging-based ASD classification studies, including the analysis of publications and general classification pipeline. Next, representative studies are highlighted and discussed in detail regarding different imaging modalities, methods and sample sizes. Finally, we highlight several common challenges and provide recommendations on future directions. In summary, identifying discriminative biomarkers for ASD diagnosis is challenging, and further establishing more comprehensive datasets and dissecting the individual and group heterogeneity will be critical to achieve better ADS diagnosis performance. Machine learning methods will continue to be developed and are poised to help advance the field in this regard.

Multi-modal neuroimaging feature fusion via 3D Convolutional Neural Network architecture for schizophrenia diagnosis

Early and precise diagnosis of schizophrenia disorder (SZ) has an essential role in the quality of a patient’s life and future treatments. Structural and functional neuroimaging provides robust biomarkers for understanding the anatomical and functional changes associated with SZ. Each of the neuroimaging techniques shows only a different perspective on the functional or structural of the brain, while multi-modal fusion can reveal latent connections in the brain. In this paper, we propose an approach for the fusion of structural and functional brain data with a deep learning-based model to take advantage of data fusion and increase the accuracy of schizophrenia disorder diagnosis. The proposed method consists of an architecture of 3D convolutional neural networks (CNNs) that applied to magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and diffusion tensor imaging (DTI) extracted features. We use 3D MRI patches, fMRI spatial independent component analysis (ICA) map, and DTI fractional anisotropy (FA) as model inputs. Our method is validated on the COBRE dataset, and an average accuracy of 99.35% is obtained. The proposed method demonstrates promising classification performance and can be applied to real data.

Reproducible Evaluation of Diffusion MRI Features for Automatic Classification of Patients with Alzheimer's Disease

Diffusion MRI is the modality of choice to study alterations of white matter. In past years, various works have used diffusion MRI for automatic classification of Alzheimer's disease. However, classification performance obtained with different approaches is difficult to compare because of variations in components such as input data, participant selection, image preprocessing, feature extraction, feature rescaling (FR), feature selection (FS) and cross-validation (CV) procedures. Moreover, these studies are also difficult to reproduce because these different components are not readily available. In a previous work (Samper-González et al. 2018), we propose an open-source framework for the reproducible evaluation of AD classification from T1-weighted (T1w) MRI and PET data. In the present paper, we first extend this framework to diffusion MRI data. Specifically, we add: conversion of diffusion MRI ADNI data into the BIDS standard and pipelines for diffusion MRI preprocessing and feature extraction. We then apply the framework to compare different components. First, FS has a positive impact on classification results: highest balanced accuracy (BA) improved from 0.76 to 0.82 for task CN vs AD. Secondly, voxel-wise features generally gives better performance than regional features. Fractional anisotropy (FA) and mean diffusivity (MD) provided comparable results for voxel-wise features. Moreover, we observe that the poor performance obtained in tasks involving MCI were potentially caused by the small data samples, rather than by the data imbalance. Furthermore, no extensive classification difference exists for different degree of smoothing and registration methods. Besides, we demonstrate that using non-nested validation of FS leads to unreliable and over-optimistic results: 5% up to 40% relative increase in BA. Lastly, with proper FR and FS, the performance of diffusion MRI features is comparable to that of T1w MRI. All the code of the framework and the experiments are publicly available: general-purpose tools have been integrated into the Clinica software package ( www.clinica.run ) and the paper-specific code is available at: https://github.com/aramis-lab/AD-ML .

Understanding Vulnerability and Adaptation in Early Brain Development using Network Neuroscience

Early adversity influences brain development and emerging behavioral phenotypes relevant for psychiatric disorders. Understanding the effects of adversity before and after conception on brain development has implications for contextualizing current public health crises and pervasive health inequities. The use of functional magnetic resonance imaging (fMRI) to study the brain at rest has shifted understanding of brain functioning and organization in the earliest periods of life. Here we review applications of this technique to examine effects of early life stress (ELS) on neurodevelopment in infancy, and highlight targets for future research. Building on the foundation of existing work in this area will require tackling significant challenges, including greater inclusion of often marginalized segments of society, and conducting larger, properly powered studies.

Understanding the impact of preprocessing pipelines on neuroimaging cortical surface analyses

BACKGROUND

The choice of preprocessing pipeline introduces variability in neuroimaging analyses that affects the reproducibility of scientific findings. Features derived from structural and functional MRI data are sensitive to the algorithmic or parametric differences of preprocessing tasks, such as image normalization, registration, and segmentation to name a few. Therefore it is critical to understand and potentially mitigate the cumulative biases of pipelines in order to distinguish biological effects from methodological variance.

METHODS

Here we use an open structural MRI dataset (ABIDE), supplemented with the Human Connectome Project, to highlight the impact of pipeline selection on cortical thickness measures. Specifically, we investigate the effect of (i) software tool (e.g., ANTS, CIVET, FreeSurfer), (ii) cortical parcellation (Desikan-Killiany-Tourville, Destrieux, Glasser), and (iii) quality control procedure (manual, automatic). We divide our statistical analyses by (i) method type, i.e., task-free (unsupervised) versus task-driven (supervised); and (ii) inference objective, i.e., neurobiological group differences versus individual prediction.

RESULTS

Results show that software, parcellation, and quality control significantly affect task-driven neurobiological inference. Additionally, software selection strongly affects neurobiological (i.e. group) and individual task-free analyses, and quality control alters the performance for the individual-centric prediction tasks.

CONCLUSIONS

This comparative performance evaluation partially explains the source of inconsistencies in neuroimaging findings. Furthermore, it underscores the need for more rigorous scientific workflows and accessible informatics resources to replicate and compare preprocessing pipelines to address the compounding problem of reproducibility in the age of large-scale, data-driven computational neuroscience.

A novel pipeline leveraging surface-based features of small subcortical structures to classify individuals with autism spectrum disorder

Autism spectrum disorder (ASD) is accompanied with widespread impairment in social-emotional functioning. Classification of ASD using sensitive morphological features derived from structural magnetic resonance imaging (MRI) of the brain may help us to better understand ASD-related mechanisms and improve related automatic diagnosis. Previous studies using T1 MRI scans in large heterogeneous ABIDE dataset with typical development (TD) controls reported poor classification accuracies (around 60%). This may because they only considered surface-based morphometry (SBM) as scalar estimates (such as cortical thickness and surface area) and ignored the neighboring intrinsic geometry information among features. In recent years, the shape-related SBM achieves great success in discovering the disease burden and progression of other brain diseases. However, when focusing on local geometry information, its high dimensionality requires careful treatment in its application to machine learning. To address the above challenges, we propose a novel pipeline for ASD classification, which mainly includes the generation of surface-based features, patch-based surface sparse coding and dictionary learning, Max-pooling and ensemble classifiers based on adaptive optimizers. The proposed pipeline may leverage the sensitivity of brain surface morphometry statistics and the efficiency of sparse coding and Max-pooling. By introducing only the surface features of bilateral hippocampus that derived from 364 male subjects with ASD and 381 age-matched TD males, this pipeline outperformed five recent MRI-based ASD classification studies with >80% accuracy in discriminating individuals with ASD from TD controls. Our results suggest shape-related SBM features may further boost the classification performance of MRI between ASD and TD.

Predicting reoperation after operative treatment of proximal humerus fractures

PURPOSE

The current understanding of the factors associated with a second surgery or loss of alignment after operative treatment of a proximal humerus fracture has relied on small sample studies with stepwise regression analysis. In this study, we used a powerful regression analysis over a large sample and with many variables to test the null hypothesis that there are no factors associated with a revision surgery or loss of alignment after operative treatment of proximal humerus fractures.

METHODS

A retrospective review of all surgically treated proximal humerus fractures from January 1, 2000, to December 31, 2015, was performed at a tertiary level hospital. We extracted longitudinal medical records for all patients, and the data were organized into two categories of predictors: fracture/operative characteristics and patient characteristics.

RESULTS

During the study period, 423 patients met the inclusion criteria. Three hundred and fourteen of the fractures underwent Open Reduction Internal Fixation (ORIF) and 109 underwent Hemiarthroplasty. Thirty-three patients underwent revision surgery (8%). Seventy-nine patients treated with ORIF had loss of alignment (25%). Across the entire cohort, the least absolute shrinkage selection operator (LASSO) analysis found that patients between 40 and 60 years of age had a higher odds of revision surgery (OR = 1.6). In patients treated with ORIF, the LASSO regression found an unreduced calcar to be the strongest predictor of loss of alignment (OR = 5.5), followed by osteoporosis (OR = 1.3), prior radiation treatment (OR = 1.3), unreduced greater tuberosity (OR = 1.2) and age over 80 years (OR = 1.2).

CONCLUSION

Reoperation after proximal humerus surgery is infrequent even though loss of alignment is common. In our cohort, not all patients who had a loss of alignment underwent revision surgery; consequently, obtaining the best possible reduction at the index surgery is paramount.

Autism classified by magnetic resonance imaging: A pilot study of a potential diagnostic tool

OBJECTIVES

Individual anatomical biomarkers have limited power for the classification of autism. The present study introduces a multivariate classification approach using structural magnetic resonance imaging data from individuals with and without autism.

METHODS

The classifier utilizes z-normalization, parameter weighting, and interindividual comparison on brain segmentation data, for estimation of an individual summed total index (TI). The TI indicates whether the gross morphological pattern of each individual's brain is in the direction of cases or controls.

RESULTS

Morphometric analysis found significant differences within subcortical gray matter structures and limbic areas. There was no significant difference in total brain volume. A case-control pilot-study of TIs in normally intelligent individuals with autism (24) and without (21) yielded a maximal accuracy of 78.9% following cross-validation. It showed a high accuracy compared with machine learning methods when tested on the same dataset. The TI correlated well with the autism quotient (R = 0.51) across groups.

CONCLUSION

These results are on par with studies on autism using machine learning. The main contributions are its transparency and simplicity. The possibility of including additional neuroimaging data further increases the potential of the classifier as a diagnostic aid for neuropsychiatric disorders, as well as a research tool for neuroscientific investigations.

Brain MRI findings in relation to clinical characteristics and outcome of tuberculous meningitis

Neuroradiological abnormalities in tuberculous meningitis (TBM) are common, but the exact relationship with clinical and inflammatory markers has not been well established. We performed magnetic resonance imaging (MRI) at baseline and after two months treatment to characterise neuroradiological patterns in a prospective cohort of adult TBM patients in Indonesia. We included 48 TBM patients (median age 30, 52% female, 8% HIV-infected), most of whom had grade II (90%), bacteriologically confirmed (71%) disease, without antituberculotic resistance. Most patients had more than one brain lesion (83%); baseline MRIs showed meningeal enhancement (89%), tuberculomas (77%), brain infarction (60%) and hydrocephalus (56%). We also performed an exploratory analysis associating MRI findings to clinical parameters, response to treatment, paradoxical reactions and survival. The presence of multiple brain lesion was associated with a lower Glasgow Coma Scale and more pronounced motor, lung, and CSF abnormalities (p-value <0.05). After two months, 33/37 patients (89%) showed worsening of MRI findings, mostly consisting of new or enlarged tuberculomas. Baseline and follow-up MRI findings and paradoxical responses showed no association with six-month mortality. Severe TBM is characterized by extensive MRI abnormalities at baseline, and frequent radiological worsening during treatment.

Gray matter changes in chronic heavy cannabis users: a voxel-level study using multivariate pattern analysis approach

Recent structural MRI studies on gray matter (GM) volumes using group-level mass-univariate statistical analysis suggest that chronic and heavy cannabis exposure may affect brain region-based morphology. In this prospective study, we use a multivariate pattern analysis approach to investigate the voxel-level change of GM densities in chronic heavy cannabis users. Principal component analysis and linear support vector machine are used in this study, resulting in an 88.1% separation between chronic heavy cannabis users (N = 20) and non-cannabis healthy controls (HCs, N = 22) through leave-one-out cross-validation. The model's discriminative pattern showed that GM density decreases in the part of middle frontal gyrus, inferior frontal gyrus, middle temporal gyrus, inferior temporal gyrus and left occipital lobe in heavy cannabis users with respect to HCs and increases in the part of lentiform nucleus, left cerebellum and right parietal lobe. These results suggest that GM densities alteration has taken place on chronic heavy cannabis users compared with HCs at voxel level.

Deep Neural Network Algorithm Feedback Model with Behavioral Intelligence and Forecast Accuracy

When attempting to apply a large-scale database that holds the behavioral intelligence training data of deep neural networks, the classification accuracy of the artificial intelligence algorithm needs to reflect the behavioral characteristics of the individual. When a change in behavior is recognized, that is, a feedback model based on a data connection model is applied, an analysis of time series data is performed by extracting feature vectors and interpolating data in a deep neural network to overcome the limitations of the existing statistical analysis. Using the results of the first feedback model as inputs to the deep neural network and, furthermore, as the input values of the second feedback model, and interpolating the behavioral intelligence data, that is, context awareness and lifelog data, including physical activities, involves applying the most appropriate conditions. The results of this study show that this method effectively improves the accuracy of the artificial intelligence results. In this paper, through an experiment, after extracting the feature vector of a deep neural network and restoring the missing value, the classification accuracy was verified to improve by about 20% on average. At the same time, by adding behavioral intelligence data to the time series data, a new data connection model, the Deep Neural Network Feedback Model, was proposed, and it was verified that the classification accuracy can be improved by about 8 to 9% on average. Based on the hypothesis, the F (X′) = X model was applied to thoroughly classify the training data set and test data set to present a symmetrical balance between the data connection model and the context-aware data. In addition, behavioral activity data were extrapolated in terms of context-aware and forecasting perspectives to prove the results of the experiment.

Detecting schizophrenia at the level of the individual: relative diagnostic value of whole-brain images, connectome-wide functional connectivity and graph-based metrics

BACKGROUND

Previous studies using resting-state functional neuroimaging have revealed alterations in whole-brain images, connectome-wide functional connectivity and graph-based metrics in groups of patients with schizophrenia relative to groups of healthy controls. However, it is unclear which of these measures best captures the neural correlates of this disorder at the level of the individual patient.

METHODS

Here we investigated the relative diagnostic value of these measures. A total of 295 patients with schizophrenia and 452 healthy controls were investigated using resting-state functional Magnetic Resonance Imaging at five research centres. Connectome-wide functional networks were constructed by thresholding correlation matrices of 90 brain regions, and their topological properties were analyzed using graph theory-based methods. Single-subject classification was performed using three machine learning (ML) approaches associated with varying degrees of complexity and abstraction, namely logistic regression, support vector machine and deep learning technology.

RESULTS

Connectome-wide functional connectivity allowed single-subject classification of patients and controls with higher accuracy (average: 81%) than both whole-brain images (average: 53%) and graph-based metrics (average: 69%). Classification based on connectome-wide functional connectivity was driven by a distributed bilateral network including the thalamus and temporal regions.

CONCLUSION

These results were replicated across the three employed ML approaches. Connectome-wide functional connectivity permits differentiation of patients with schizophrenia from healthy controls at single-subject level with greater accuracy; this pattern of results is consistent with the 'dysconnectivity hypothesis' of schizophrenia, which states that the neural basis of the disorder is best understood in terms of system-level functional connectivity alterations.

Toward Robust Anxiety Biomarkers: A Machine Learning Approach in a Large-Scale Sample

BACKGROUND

The field of psychiatry has long sought biomarkers that can objectively diagnose patients, predict treatment response, or identify individuals at risk of illness onset. However, reliable psychiatric biomarkers have yet to emerge. The recent application of machine learning techniques to develop neuroimaging-based biomarkers has yielded promising preliminary results. However, much of the work in this domain has not met best practice standards from the field of machine learning. This is especially true for studies of anxiety, creating uncertainty about the potential for anxiety biomarker development.

METHODS

We applied machine learning tools to predict trait anxiety from neuroimaging measurements in humans. Using publicly available data from the Brain Genomics Superstruct Project, we compared a suite of neuroimaging-based machine learning models predicting anxiety within a discovery sample (n = 531, 307 women) via k-fold cross-validation, and we tested the final model (a stacked model incorporating region-to-region functional connectivity, amygdala seed-to-voxel connectivity, and volumetric and cortical thickness data) in a held-out, unseen test sample (n = 348, 209 women).

RESULTS

Though the best model was able to predict anxiety within the discovery sample (cross-validated R2 of .06, permutation test p < .001), the generalization test within the holdout sample failed (R2 of -.04, permutation test p > .05).

CONCLUSIONS

In this study, we did not find evidence of a generalizable anxiety biomarker. However, we encourage other researchers to investigate this topic, utilizing large samples and proper methodology, to clarify the potential of neuroimaging-based anxiety biomarkers.

Methods and Challenges for Assessing Heterogeneity

The widely acknowledged homogeneity assumption limits progress in refining clinical diagnosis, understanding mechanisms, and developing new treatments for mental health disorders. This homogeneity assumption drives both a comorbidity and a heterogeneity problem, where two different approaches tackle the problems. One, a unifying approach, tackles the comorbidity problem by assuming that a single general psychopathology factor underlies multiple disorders. Another, a multifactorial approach, tackles the heterogeneity problem by assuming that disorders comprise multiple subtypes driven by multiple discrete factors. We show how each of these approaches can make useful contributions to mental health-related research and clinical practice. For example, the unifying approach can develop a rapid assessment tool that may be clinically valuable for triaging cases. The multifactorial approach can reveal subtypes that are differentially responsive to treatments and highlight distinct mechanisms leading to similar phenotypes. Because both approaches tackle different problems, both have different limitations. We describe the statistical frameworks that incorporate and adjudicate between both approaches (e.g., the bifactor model, normative modeling, and the functional random forest). Such frameworks can identify whether sets of disorders are more affected by heterogeneity or comorbidity. Therefore, future studies that incorporate such frameworks can provide further insight into the nature of psychopathology.

Inferior temporal tau is associated with accelerated prospective cortical thinning in clinically normal older adults

Neurofibrillary tau tangles are a hallmark pathology of Alzheimer's disease (AD) and are more closely associated with AD-related cortical atrophy and symptom severity than amyloid-beta (Aβ). However, studies regarding the effect of tau on longitudinal cortical thinning, particularly in healthy aging and preclinical AD, have been limited in number due to the relatively recent introduction of in vivo PET tracers for imaging tau pathology. Here, we investigate [18F]-flortaucipir (FTP, a marker of paired helical filament tau) PET as a predictor of atrophy in healthy aging and preclinical AD. We examine longitudinal structural MRI brain imaging data, retrospectively and prospectively relative to FTP imaging, using piecewise linear mixed-effect models with time centered at each participant's FTP-PET session. Participants include 111 individuals from the Harvard Aging Brain Study who underwent at least three MRI sessions over an average of 4.46 years and one FTP-PET at the approximate midpoint of the observation period. Our primary analyses focus on inferior temporal (IT) FTP standardized uptake value ratios and longitudinal FreeSurfer defined cortical regions of interest. Relationships were also explored using other regional FTP measures (entorhinal, composite, and local), within high and low Pittsburgh compound-B (PiB) PET groups, and with longitudinal subcortical volume. Strong associations between IT FTP and cortical thinning were found, most notably in temporal, midline, and prefrontal regions, with stronger effects generally observed in the prospective as compared to retrospective time frame. Significant differences between prospective and retrospective rates of thinning were found in the inferior and middle temporal gyri, cingulate areas, as well as pars orbitalis such that higher IT FTP was associated with greater prospective rates of thinning. Within the high PiB group, significant differences between prospective and retrospective rates of thinning were similarly observed. However, no consistent pattern of tau-related change in cortical thickness within the low PiB group was discerned. These results provide support for the hypothesis that tau pathology is a driver of future atrophy as well as provide additional evidence for tau-PET as an effective AD biomarker for interventional clinical trials.

Characterizing Alzheimer's Disease With Image and Genetic Biomarkers Using Supervised Topic Models

Neuroimaging and genetic biomarkers have been widely studied from discriminative perspectives towards Alzheimer's disease (AD) classification, since neuroanatomical patterns and genetic variants are jointly critical indicators for AD diagnosis. Generative methods, designed to model common occurring patterns, could potentially advance the understanding of this disease, but have not been fully explored for AD characterization. Moreover, the introduction of a supervised component into the generative process can constrain the model for more discriminative characterization. In this study, we propose an original method based on supervised topic modeling to characterize AD from a generative perspective, yet maintaining discriminative power at differentiating disease populations. Our topic modeling jointly exploits discretized image features and categorical genetic features. Diagnostic information - cognitively normal (CN), mild cognitive impairment (MCI) and AD - is introduced as a supervision variable. Experimental results on the ADNI cohort demonstrate that our model, while achieving competitive discriminative performance, can discover topics revealing both well-known and novel neuroanatomical patterns including temporal, parietal and frontal regions; as well as associations between genetic factors and neuroanatomical patterns.

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.

Individual differences v. the average patient: mapping the heterogeneity in ADHD using normative models

BACKGROUND

The present paper presents a fundamentally novel approach to model individual differences of persons with the same biologically heterogeneous mental disorder. Unlike prevalent case-control analyses, that assume a clear distinction between patient and control groups and thereby introducing the concept of an 'average patient', we describe each patient's biology individually, gaining insights into the different facets that characterize persistent attention-deficit/hyperactivity disorder (ADHD).

METHODS

Using a normative modeling approach, we mapped inter-individual differences in reference to normative structural brain changes across the lifespan to examine the degree to which case-control analyses disguise differences between individuals.

RESULTS

At the level of the individual, deviations from the normative model were frequent in persistent ADHD. However, the overlap of more than 2% between participants with ADHD was only observed in few brain loci. On average, participants with ADHD showed significantly reduced gray matter in the cerebellum and hippocampus compared to healthy individuals. While the case-control differences were in line with the literature on ADHD, individuals with ADHD only marginally reflected these group differences.

CONCLUSIONS

Case-control comparisons, disguise inter-individual differences in brain biology in individuals with persistent ADHD. The present results show that the 'average ADHD patient' has limited informative value, providing the first evidence for the necessity to explore different biological facets of ADHD at the level of the individual and practical means to achieve this end.