Open access series of imaging studies: longitudinal MRI data in nondemented and demented older adults

Automated algorithm for medical data structuring, and segmentation using artificial intelligence within secured environment for dataset creation

Objective

Routinely collected electronic health records using artificial intelligence (AI)-based systems bring out enormous benefits for patients, healthcare centers, and its industries. Artificial intelligence models can be used to structure a wide variety of unstructured data.

Methods

We present a semi-automatic workflow for medical dataset management, including data structuring, research extraction, AI-ground truth creation, and updates. The algorithm creates directories based on keywords in new file names.

Results

Our work focuses on organizing computed tomography (CT), magnetic resonance (MR) images, patient clinical data, and segmented annotations. In addition, an AI model is used to generate different initial labels that can be edited manually to create ground truth labels. The manually verified ground truth labels are later included in the structured dataset using an automated algorithm for future research.

Conclusion

This is a workflow with an AI model trained on local hospital medical data with output based/adapted to the users and their preferences. The automated algorithms and AI model could be implemented inside a secondary secure environment in the hospital to produce inferences.

3-Way hybrid analysis using clinical and magnetic resonance imaging for early diagnosis of Alzheimer's disease

Alzheimer's is a progressive neurodegenerative disorder that leads to cognitive impairment and ultimately death. To select the most effective treatment options, it is crucial to diagnose and classify the disease early, as current treatments can only delay its progression. However, previous research on Alzheimer's disease (AD) has had limitations, such as inaccuracies and reliance on a small, unbalanced binary dataset. In this study, we aimed to evaluate the early stages of AD using three multiclass datasets: OASIS, EEG, and ADNI MRI. The research consisted of three phases: pre-processing, feature extraction, and classification using hybrid learning techniques. For the OASIS and ADNI MRI datasets, we computed the mean RGB value and used an averaging filter to enhance the images. We balanced and augmented the dataset to increase its size. In the case of the EEG dataset, we applied a band-pass filter for digital filtering to reduce noise and also balanced the dataset using random oversampling. To extract and classify features, we utilized a hybrid technique consisting of four algorithms: AlexNet-MLP, AlexNet-ETC, AlexNet-AdaBoost, and AlexNet-NB. The results showed that the AlexNet-ETC hybrid algorithm achieved the highest accuracy rate of 95.32% for the OASIS dataset. In the case of the EEG dataset, the AlexNet-MLP hybrid algorithm outperformed other approaches with the highest accuracy of 97.71%. For the ADNI MRI dataset, the AlexNet-MLP hybrid algorithm achieved an accuracy rate of 92.59%. Comparing these results with the current state of the art demonstrates the effectiveness of our findings.

Let UNet Play an Adversarial Game: Investigating the Effect of Adversarial Training in Enhancing Low-Resolution MRI

Adversarial training has attracted much attention in enhancing the visual realism of images, but its efficacy in clinical imaging has not yet been explored. This work investigated adversarial training in a clinical context, by training 206 networks on the OASIS-1 dataset for improving low-resolution and low signal-to-noise ratio (SNR) magnetic resonance images. Each network corresponded to a different combination of perceptual and adversarial loss weights and distinct learning rate values. For each perceptual loss weighting, we identified its corresponding adversarial loss weighting that minimized structural disparity. Each optimally weighted adversarial loss yielded an average SSIM reduction of 1.5%. We further introduced a set of new metrics to assess other clinically relevant image features: Gradient Error (GE) to measure structural disparities; Sharpness to compute edge clarity; and Edge-Contrast Error (ECE) to quantify any distortion of the pixel distribution around edges. Including adversarial loss increased structural enhancement in visual inspection, which correlated with statistically consistent GE reductions (p-value << 0.05). This also resulted in increased Sharpness; however, the level of statistical significance was dependent on the perceptual loss weighting. Additionally, adversarial loss yielded ECE reductions for smaller perceptual loss weightings, while showing non-significant increases (p-value >> 0.05) when these weightings were higher, demonstrating that the increased Sharpness does not adversely distort the pixel distribution around the edges in the image. These studies clearly suggest that adversarial training significantly improves the performance of an MRI enhancement pipeline, and highlights the need for systematic studies of hyperparameter optimization and investigation of alternative image quality metrics.

MRI-informed machine learning-driven brain age models for classifying mild cognitive impairment converters

BACKGROUND

Brain age model, including estimated brain age and brain-predicted age difference (brain-PAD), has shown great potentials for serving as imaging markers for monitoring normal ageing, as well as for identifying the individuals in the pre-diagnostic phase of neurodegenerative diseases.

PURPOSE

This study aimed to investigate the brain age models in normal ageing and mild cognitive impairments (MCI) converters and their values in classifying MCI conversion.

METHODS

Pre-trained brain age model was constructed using the structural magnetic resonance imaging (MRI) data from the Cambridge Centre for Ageing and Neuroscience (Cam-CAN) project (N = 609). The tested brain age model was built using the baseline, 1-year and 3-year follow-up MRI data from normal ageing (NA) adults (n = 32) and MCI converters (n = 22) drew from the Open Access Series of Imaging Studies (OASIS-2). The quantitative measures of morphometry included total intracranial volume (TIV), gray matter volume (GMV) and cortical thickness. Brain age models were calculated based on the individual's morphometric features using the support vector machine (SVM) algorithm.

RESULTS

With comparable chronological age, MCI converters showed significant increased TIV-based (Baseline: P = 0.021; 1-year follow-up: P = 0.037; 3-year follow-up: P = 0.001) and left GMV-based brain age than NA adults at all time points. Higher brain-PAD scores were associated with worse global cognition. Acceptable classification performance of TIV-based (AUC = 0.698) and left GMV-based brain age (AUC = 0.703) was found, which could differentiate the MCI converters from NA adults at the baseline.

CONCLUSIONS

This is the first demonstration that MRI-informed brain age models exhibit feature-specific patterns. The greater GMV-based brain age observed in MCI converters may provide new evidence for identifying the individuals at the early stage of neurodegeneration. Our findings added value to existing quantitative imaging markers and might help to improve disease monitoring and accelerate personalized treatments in clinical practice.

Multivariate pattern analysis of medical imaging-based Alzheimer's disease

Alzheimer's disease (AD) is a devastating brain disorder that steadily worsens over time. It is marked by a relentless decline in memory and cognitive abilities. As the disease progresses, it leads to a significant loss of mental function. Early detection of AD is essential to starting treatments that can mitigate the progression of this disease and enhance patients' quality of life. This study aims to observe AD's brain functional connectivity pattern to extract essential patterns through multivariate pattern analysis (MVPA) and analyze activity patterns across multiple brain voxels. The optimized feature extraction techniques are used to obtain the important features for performing the training on the models using several hybrid machine learning classifiers for performing binary classification and multi-class classification. The proposed approach using hybrid machine learning classification has been applied to two public datasets named the Open Access Series of Imaging Studies (OASIS) and the AD Neuroimaging Initiative (ADNI). The results are evaluated using performance metrics, and comparisons have been made to differentiate between different stages of AD using visualization tools.

Uncertainty Quantification in SAR Induced by Ultra-High-Field MRI RF Coil via High-Dimensional Model Representation

As magnetic field strength in Magnetic Resonance Imaging (MRI) technology increases, maintaining the specific absorption rate (SAR) within safe limits across human head tissues becomes challenging due to the formation of standing waves at a shortened wavelength. Compounding this challenge is the uncertainty in the dielectric properties of head tissues, which notably affects the SAR induced by the radiofrequency (RF) coils in an ultra-high-field (UHF) MRI system. To this end, this study introduces a computational framework to quantify the impacts of uncertainties in head tissues' dielectric properties on the induced SAR. The framework employs a surrogate model-assisted Monte Carlo (MC) technique, efficiently generating surrogate models of MRI observables (electric fields and SAR) and utilizing them to compute SAR statistics. Particularly, the framework leverages a high-dimensional model representation technique, which constructs the surrogate models of the MRI observables via univariate and bivariate component functions, approximated through generalized polynomial chaos expansions. The numerical results demonstrate the efficiency of the proposed technique, requiring significantly fewer deterministic simulations compared with traditional MC methods and other surrogate model-assisted MC techniques utilizing machine learning algorithms, all while maintaining high accuracy in SAR statistics. Specifically, the proposed framework constructs surrogate models of a local SAR with an average relative error of 0.28% using 289 simulations, outperforming the machine learning-based surrogate modeling techniques considered in this study. Furthermore, the SAR statistics obtained by the proposed framework reveal fluctuations of up to 30% in SAR values within specific head regions. These findings highlight the critical importance of considering dielectric property uncertainties to ensure MRI safety, particularly in 7 T MRI systems.

Atypical intrinsic neural timescale in the left angular gyrus in Alzheimer's disease

Alzheimer's disease is characterized by cognitive impairment and progressive brain atrophy. Recent human neuroimaging studies reported atypical anatomical and functional changes in some regions in the default mode network in patients with Alzheimer's disease, but which brain area of the default mode network is the key region whose atrophy disturbs the entire network activity and consequently contributes to the symptoms of the disease remains unidentified. Here, in this case-control study, we aimed to identify crucial neural regions that mediated the phenotype of Alzheimer's disease, and as such, we examined the intrinsic neural timescales-a functional metric to evaluate the capacity to integrate diverse neural information-and grey matter volume of the regions in the default mode network using resting-state functional MRI images and structural MRI data obtained from individuals with Alzheimer's disease and cognitively typical people. After confirming the atypically short neural timescale of the entire default mode network in Alzheimer's disease and its link with the symptoms of the disease, we found that the shortened neural timescale of the default mode network was associated with the aberrantly short neural timescale of the left angular gyrus. Moreover, we revealed that the shortened neural timescale of the angular gyrus was correlated with the atypically reduced grey matter volume of this parietal region. Furthermore, we identified an association between the neural structure, brain function and symptoms and proposed a model in which the reduced grey matter volume of the left angular gyrus shortened the intrinsic neural time of the region, which then destabilized the entire neural timescale of the default mode network and resultantly contributed to cognitive decline in Alzheimer's disease. These findings highlight the key role of the left angular gyrus in the anatomical and functional aetiology of Alzheimer's disease.

AI-based differential diagnosis of dementia etiologies on multimodal data

Differential diagnosis of dementia remains a challenge in neurology due to symptom overlap across etiologies, yet it is crucial for formulating early, personalized management strategies. Here, we present an artificial intelligence (AI) model that harnesses a broad array of data, including demographics, individual and family medical history, medication use, neuropsychological assessments, functional evaluations and multimodal neuroimaging, to identify the etiologies contributing to dementia in individuals. The study, drawing on 51,269 participants across 9 independent, geographically diverse datasets, facilitated the identification of 10 distinct dementia etiologies. It aligns diagnoses with similar management strategies, ensuring robust predictions even with incomplete data. Our model achieved a microaveraged area under the receiver operating characteristic curve (AUROC) of 0.94 in classifying individuals with normal cognition, mild cognitive impairment and dementia. Also, the microaveraged AUROC was 0.96 in differentiating the dementia etiologies. Our model demonstrated proficiency in addressing mixed dementia cases, with a mean AUROC of 0.78 for two co-occurring pathologies. In a randomly selected subset of 100 cases, the AUROC of neurologist assessments augmented by our AI model exceeded neurologist-only evaluations by 26.25%. Furthermore, our model predictions aligned with biomarker evidence and its associations with different proteinopathies were substantiated through postmortem findings. Our framework has the potential to be integrated as a screening tool for dementia in clinical settings and drug trials. Further prospective studies are needed to confirm its ability to improve patient care.

A review of deep learning-based information fusion techniques for multimodal medical image classification

Multimodal medical imaging plays a pivotal role in clinical diagnosis and research, as it combines information from various imaging modalities to provide a more comprehensive understanding of the underlying pathology. Recently, deep learning-based multimodal fusion techniques have emerged as powerful tools for improving medical image classification. This review offers a thorough analysis of the developments in deep learning-based multimodal fusion for medical classification tasks. We explore the complementary relationships among prevalent clinical modalities and outline three main fusion schemes for multimodal classification networks: input fusion, intermediate fusion (encompassing single-level fusion, hierarchical fusion, and attention-based fusion), and output fusion. By evaluating the performance of these fusion techniques, we provide insight into the suitability of different network architectures for various multimodal fusion scenarios and application domains. Furthermore, we delve into challenges related to network architecture selection, handling incomplete multimodal data management, and the potential limitations of multimodal fusion. Finally, we spotlight the promising future of Transformer-based multimodal fusion techniques and give recommendations for future research in this rapidly evolving field.

Identifying discriminative features of brain network for prediction of Alzheimer's disease using graph theory and machine learning

Alzheimer's disease (AD) is a challenging neurodegenerative condition, necessitating early diagnosis and intervention. This research leverages machine learning (ML) and graph theory metrics, derived from resting-state functional magnetic resonance imaging (rs-fMRI) data to predict AD. Using Southwest University Adult Lifespan Dataset (SALD, age 21-76 years) and the Open Access Series of Imaging Studies (OASIS, age 64-95 years) dataset, containing 112 participants, various ML models were developed for the purpose of AD prediction. The study identifies key features for a comprehensive understanding of brain network topology and functional connectivity in AD. Through a 5-fold cross-validation, all models demonstrate substantial predictive capabilities (accuracy in 82-92% range), with the support vector machine model standing out as the best having an accuracy of 92%. Present study suggests that top 13 regions, identified based on most important discriminating features, have lost significant connections with thalamus. The functional connection strengths were consistently declined for substantia nigra, pars reticulata, substantia nigra, pars compacta, and nucleus accumbens among AD subjects as compared to healthy adults and aging individuals. The present finding corroborate with the earlier studies, employing various neuroimagining techniques. This research signifies the translational potential of a comprehensive approach integrating ML, graph theory and rs-fMRI analysis in AD prediction, offering potential biomarker for more accurate diagnostics and early prediction of AD.

Heterogeneity of morphometric similarity networks in health and schizophrenia

Introduction

Morphometric similarity is a recently developed neuroimaging phenotype of inter-regional connectivity by quantifying the similarity of a region to other regions based on multiple MRI parameters. Altered average morphometric similarity has been reported in psychotic disorders at the group level, with considerable heterogeneity across individuals. We used normative modeling to address cross-sectional and longitudinal inter-individual heterogeneity of morphometric similarity in health and schizophrenia.

Methods

Morphometric similarity for 62 cortical regions was obtained from baseline and follow-up T1-weighted scans of healthy individuals and patients with chronic schizophrenia. Cortical regions were classified into seven predefined brain functional networks. Using Bayesian Linear Regression and taking into account age, sex, image quality and scanner, we trained and validated normative models in healthy controls from eleven datasets (n = 4310). Individual deviations from the norm (z-scores) in morphometric similarity were computed for each participant for each network and region at both timepoints. A z-score ≧ than 1.96 was considered supra-normal and a z-score ≦ -1.96 infra-normal. As a longitudinal metric, we calculated the change over time of the total number of infra- or supra-normal regions per participant.

Results

At baseline, patients with schizophrenia had decreased morphometric similarity of the default mode network and increased morphometric similarity of the somatomotor network when compared with healthy controls. The percentage of patients with infra- or supra-normal values for any region at baseline and follow-up was low (<6%) and did not differ from healthy controls. Mean intra-group changes over time in the total number of infra- or supra-normal regions were small in schizophrenia and healthy control groups (<1) and there were no significant between-group differences.

Conclusions

In a case-control setting, a decrease of morphometric similarity within the default mode network may be a robust finding implicated in schizophrenia. However, normative modeling suggests that significant reductions and changes over time of regional morphometric similarity are evident only in a minority of patients.

The power of many brains: Catalyzing neuropsychiatric discovery through open neuroimaging data and large-scale collaboration

Recent advances in open neuroimaging data are enhancing our comprehension of neuropsychiatric disorders. By pooling images from various cohorts, statistical power has increased, enabling the detection of subtle abnormalities and robust associations, and fostering new research methods. Global collaborations in imaging have furthered our knowledge of the neurobiological foundations of brain disorders and aided in imaging-based prediction for more targeted treatment. Large-scale magnetic resonance imaging initiatives are driving innovation in analytics and supporting generalizable psychiatric studies. We also emphasize the significant role of big data in understanding neural mechanisms and in the early identification and precise treatment of neuropsychiatric disorders. However, challenges such as data harmonization across different sites, privacy protection, and effective data sharing must be addressed. With proper governance and open science practices, we conclude with a projection of how large-scale imaging resources and collaborations could revolutionize diagnosis, treatment selection, and outcome prediction, contributing to optimal brain health.

STF-Net: sparsification transformer coding guided network for subcortical brain structure segmentation

Subcortical brain structure segmentation plays an important role in the diagnosis of neuroimaging and has become the basis of computer-aided diagnosis. Due to the blurred boundaries and complex shapes of subcortical brain structures, labeling these structures by hand becomes a time-consuming and subjective task, greatly limiting their potential for clinical applications. Thus, this paper proposes the sparsification transformer (STF) module for accurate brain structure segmentation. The self-attention mechanism is used to establish global dependencies to efficiently extract the global information of the feature map with low computational complexity. Also, the shallow network is used to compensate for low-level detail information through the localization of convolutional operations to promote the representation capability of the network. In addition, a hybrid residual dilated convolution (HRDC) module is introduced at the bottom layer of the network to extend the receptive field and extract multi-scale contextual information. Meanwhile, the octave convolution edge feature extraction (OCT) module is applied at the skip connections of the network to pay more attention to the edge features of brain structures. The proposed network is trained with a hybrid loss function. The experimental evaluation on two public datasets: IBSR and MALC, shows outstanding performance in terms of objective and subjective quality.

Extensive T1-weighted MRI preprocessing improves generalizability of deep brain age prediction models

Brain age is an estimate of chronological age obtained from T1-weighted magnetic resonance images (T1w MRI), representing a straightforward diagnostic biomarker of brain aging and associated diseases. While the current best accuracy of brain age predictions on T1w MRIs of healthy subjects ranges from two to three years, comparing results across studies is challenging due to differences in the datasets, T1w preprocessing pipelines, and evaluation protocols used. This paper investigates the impact of T1w image preprocessing on the performance of four deep learning brain age models from recent literature. Four preprocessing pipelines, which differed in terms of registration transform, grayscale correction, and software implementation, were evaluated. The results showed that the choice of software or preprocessing steps could significantly affect the prediction error, with a maximum increase of 0.75 years in mean absolute error (MAE) for the same model and dataset. While grayscale correction had no significant impact on MAE, using affine rather than rigid registration to brain atlas statistically significantly improved MAE. Models trained on 3D images with isotropic 1mm3 resolution exhibited less sensitivity to the T1w preprocessing variations compared to 2D models or those trained on downsampled 3D images. Our findings indicate that extensive T1w preprocessing improves MAE, especially when predicting on a new dataset. This runs counter to prevailing research literature, which suggests that models trained on minimally preprocessed T1w scans are better suited for age predictions on MRIs from unseen scanners. We demonstrate that, irrespective of the model or T1w preprocessing used during training, applying some form of offset correction is essential to enable the model's performance to generalize effectively on datasets from unseen sites, regardless of whether they have undergone the same or different T1w preprocessing as the training set.

Macro- and Micro-Structural Alterations in the Midbrain in Early Psychosis

Introduction

Early psychosis (EP) is a critical period in the course of psychotic disorders during which the brain is thought to undergo rapid and significant functional and structural changes 1 . Growing evidence suggests that the advent of psychotic disorders is early alterations in the brain's functional connectivity and structure, leading to aberrant neural network organization. The Human Connectome Project (HCP) is a global effort to map the human brain's connectivity in healthy and disease populations; within HCP, there is a specific dataset that focuses on the EP subjects (i.e., those within five years of the initial psychotic episode) (HCP-EP), which is the focus of our study. Given the critically important role of the midbrain function and structure in psychotic disorders (cite), and EP in particular (cite), we specifically focused on the midbrain macro- and micro-structural alterations and their association with clinical outcomes in HCP-EP.

Methods

We examined macro- and micro-structural brain alterations in the HCP-EP sample (n=179: EP, n=123, Controls, n=56) as well as their associations with behavioral measures (i.e., symptoms severity) using a stepwise approach, incorporating a multimodal MRI analysis procedure. First, Deformation Based Morphometry (DBM) was carried out on the whole brain 3 Tesla T1w images to examine gross brain anatomy (i.e., seed-based and voxel-based volumes). Second, we extracted Fractional Anisotropy (FA), Axial Diffusivity (AD), and Mean Diffusivity (MD) indices from the Diffusion Tensor Imaging (DTI) data; a midbrain mask was created based on FreeSurfer v.6.0 atlas. Third, we employed Tract-Based Spatial Statistics (TBSS) to determine microstructural alterations in white matter tracts within the midbrain and broader regions. Finally, we conducted correlation analyses to examine associations between the DBM-, DTI- and TBSS-based outcomes and the Positive and Negative Syndrome Scale (PANSS) scores.

Results

DBM analysis showed alterations in the hippocampus, midbrain, and caudate/putamen. A DTI voxel-based analysis shows midbrain reductions in FA and AD and increases in MD; meanwhile, the hippocampus shows an increase in FA and a decrease in AD and MD. Several key brain regions also show alterations in DTI indices (e.g., insula, caudate, prefrontal cortex). A seed-based analysis centered around a midbrain region of interest obtained from freesurfer segmentation confirms the voxel-based analysis of DTI indices. TBSS successfully captured structural differences within the midbrain and complementary alterations in other main white matter tracts, such as the corticospinal tract and cingulum, suggesting early altered brain connectivity in EP. Correlations between these quantities in the EP group and behavioral scores (i.e., PANSS and CAINS tests) were explored. It was found that midbrain volume noticeably correlates with the Cognitive score of PA and all DTI metrics. FA correlates with the several dimensions of the PANSS, while AD and MD do not show many associations with PANSS or CAINS.

Conclusions

Our findings contribute to understanding the midbrain-focused circuitry involvement in EP and complimentary alteration in EP. Our work provides a path for future investigations to inform specific brain-based biomarkers of EP and their relationships to clinical manifestations of the psychosis course.

Fusion of biomedical imaging studies for increased sample size and diversity: a case study of brain MRI

Data collection, curation, and cleaning constitute a crucial phase in Machine Learning (ML) projects. In biomedical ML, it is often desirable to leverage multiple datasets to increase sample size and diversity, but this poses unique challenges, which arise from heterogeneity in study design, data descriptors, file system organization, and metadata. In this study, we present an approach to the integration of multiple brain MRI datasets with a focus on homogenization of their organization and preprocessing for ML. We use our own fusion example (approximately 84,000 images from 54,000 subjects, 12 studies, and 88 individual scanners) to illustrate and discuss the issues faced by study fusion efforts, and we examine key decisions necessary during dataset homogenization, presenting in detail a database structure flexible enough to accommodate multiple observational MRI datasets. We believe our approach can provide a basis for future similarly-minded biomedical ML projects.

AI-based differential diagnosis of dementia etiologies on multimodal data

Differential diagnosis of dementia remains a challenge in neurology due to symptom overlap across etiologies, yet it is crucial for formulating early, personalized management strategies. Here, we present an AI model that harnesses a broad array of data, including demographics, individual and family medical history, medication use, neuropsychological assessments, functional evaluations, and multimodal neuroimaging, to identify the etiologies contributing to dementia in individuals. The study, drawing on 51,269 participants across 9 independent, geographically diverse datasets, facilitated the identification of 10 distinct dementia etiologies. It aligns diagnoses with similar management strategies, ensuring robust predictions even with incomplete data. Our model achieved a micro-averaged area under the receiver operating characteristic curve (AUROC) of 0.94 in classifying individuals with normal cognition, mild cognitive impairment and dementia. Also, the micro-averaged AUROC was 0.96 in differentiating the dementia etiologies. Our model demonstrated proficiency in addressing mixed dementia cases, with a mean AUROC of 0.78 for two co-occurring pathologies. In a randomly selected subset of 100 cases, the AUROC of neurologist assessments augmented by our AI model exceeded neurologist-only evaluations by 26.25%. Furthermore, our model predictions aligned with biomarker evidence and its associations with different proteinopathies were substantiated through postmortem findings. Our framework has the potential to be integrated as a screening tool for dementia in various clinical settings and drug trials, with promising implications for person-level management.

A Survey of Publicly Available MRI Datasets for Potential Use in Artificial Intelligence Research

Artificial intelligence (AI) has the potential to bring transformative improvements to the field of radiology; yet, there are barriers to widespread clinical adoption. One of the most important barriers has been access to large, well-annotated, widely representative medical image datasets, which can be used to accurately train AI programs. Creating such datasets requires time and expertise and runs into constraints around data security and interoperability, patient privacy, and appropriate data use. Recognizing these challenges, several institutions have started curating and providing publicly available, high-quality datasets that can be accessed by researchers to advance AI models. The purpose of this work was to review the publicly available MRI datasets that can be used for AI research in radiology. Despite being an emerging field, a simple internet search for open MRI datasets presents an overwhelming number of results. Therefore, we decided to create a survey of the major publicly accessible MRI datasets in different subfields of radiology (brain, body, and musculoskeletal), and list the most important features of value to the AI researcher. To complete this review, we searched for publicly available MRI datasets and assessed them based on several parameters (number of subjects, demographics, area of interest, technical features, and annotations). We reviewed 110 datasets across sub-fields with 1,686,245 subjects in 12 different areas of interest ranging from spine to cardiac. This review is meant to serve as a reference for researchers to help spur advancements in the field of AI for radiology. LEVEL OF EVIDENCE: Level 4 TECHNICAL EFFICACY: Stage 6.

Semantic Harmonization of Alzheimer's Disease Datasets Using AD-Mapper

Background

Despite numerous past endeavors for the semantic harmonization of Alzheimer's disease (AD) cohort studies, an automatic tool has yet to be developed.

Objective

As cohort studies form the basis of data-driven analysis, harmonizing them is crucial for cross-cohort analysis. We aimed to accelerate this task by constructing an automatic harmonization tool.

Methods

We created a common data model (CDM) through cross-mapping data from 20 cohorts, three CDMs, and ontology terms, which was then used to fine-tune a BioBERT model. Finally, we evaluated the model using three previously unseen cohorts and compared its performance to a string-matching baseline model.

Results

Here, we present our AD-Mapper interface for automatic harmonization of AD cohort studies, which outperformed a string-matching baseline on previously unseen cohort studies. We showcase our CDM comprising 1218 unique variables.

Conclusion

AD-Mapper leverages semantic similarities in naming conventions across cohorts to improve mapping performance.

Ordinal Classification with Distance Regularization for Robust Brain Age Prediction

Age is one of the major known risk factors for Alzheimer's Disease (AD). Detecting AD early is crucial for effective treatment and preventing irreversible brain damage. Brain age, a measure derived from brain imaging reflecting structural changes due to aging, may have the potential to identify AD onset, assess disease risk, and plan targeted interventions. Deep learning-based regression techniques to predict brain age from magnetic resonance imaging (MRI) scans have shown great accuracy recently. However, these methods are subject to an inherent regression to the mean effect, which causes a systematic bias resulting in an overestimation of brain age in young subjects and underestimation in old subjects. This weakens the reliability of predicted brain age as a valid biomarker for downstream clinical applications. Here, we reformulate the brain age prediction task from regression to classification to address the issue of systematic bias. Recognizing the importance of preserving ordinal information from ages to understand aging trajectory and monitor aging longitudinally, we propose a novel ORdinal Distance Encoded Regularization (ORDER) loss that incorporates the order of age labels, enhancing the model's ability to capture age-related patterns. Extensive experiments and ablation studies demonstrate that this framework reduces systematic bias, outperforms state-of-art methods by statistically significant margins, and can better capture subtle differences between clinical groups in an independent AD dataset. Our implementation is publicly available at https://github.com/jaygshah/Robust-Brain-Age-Prediction.

A Review on the Use of Modern Computational Methods in Alzheimer's Disease-Detection and Prediction

Discoveries in the field of medical sciences are blooming rapidly at the cost of voluminous efforts. Presently, multidisciplinary research activities have been especially contributing to catering cutting-edge solutions to critical problems in the domain of medical sciences. The modern age computing resources have proved to be a boon in this context. Effortless solutions have become a reality, and thus, the real beneficiary patients are able to enjoy improved lives. One of the most emerging problems in this context is Alzheimer's disease, an incurable neurological disorder. For this, early diagnosis is made possible with benchmark computing tools and schemes. These benchmark schemes are the results of novel research contributions being made intermittently in the timeline. In this review, an attempt is made to explore all such contributions in the past few decades. A systematic review is made by categorizing these contributions into three folds, namely, First, Second, and Third Generations. However, priority is given to the latest ones as a handful of literature reviews are already available for the classical ones. Key contributions are discussed vividly. The objectives set for this review are to bring forth the latest discoveries in computing methodologies, especially those dedicated to the diagnosis of Alzheimer's disease. A detailed timeline of the contributions is also made available. Performance plots for certain key contributions are also presented for better graphical understanding.

BASE: Brain Age Standardized Evaluation

Brain age, most commonly inferred from T1-weighted magnetic resonance images (T1w MRI), is a robust biomarker of brain health and related diseases. Superior accuracy in brain age prediction, often falling within a 2-3 year range, is achieved predominantly through deep neural networks. However, comparing study results is difficult due to differences in datasets, evaluation methodologies and metrics. Addressing this, we introduce Brain Age Standardized Evaluation (BASE), which includes (i) a standardized T1w MRI dataset including multi-site, new unseen site, test-retest and longitudinal data, and an associated (ii) evaluation protocol, including repeated model training and upon based comprehensive set of performance metrics measuring accuracy, robustness, reproducibility and consistency aspects of brain age predictions, and (iii) statistical evaluation framework based on linear mixed-effects models for rigorous performance assessment and cross-comparison. To showcase BASE, we comprehensively evaluate four deep learning based brain age models, appraising their performance in scenarios that utilize multi-site, test-retest, unseen site, and longitudinal T1w brain MRI datasets. Ensuring full reproducibility and application in future studies, we have made all associated data information and code publicly accessible at https://github.com/AralRalud/BASE.git.

Predicting cognitive decline: Which is more useful, baseline amyloid levels or longitudinal change?

The use of biomarkers for the early detection of Alzheimer's disease (AD) is crucial for developing potential therapeutic treatments. Positron Emission Tomography (PET) is a well-established tool used to detect β-amyloid (Aβ) plaques in the brain. Previous studies have shown that cross-sectional biomarkers can predict cognitive decline (Schindler et al.,2021). However, it is still unclear whether longitudinal Aβ-PET may have additional value for predicting time to cognitive impairment in AD. The current study aims to evaluate the ability of baseline- versus longitudinal rate of change in-11C-Pittsburgh compound B (PiB) Aβ-PET to predict cognitive decline. A cohort of 153 participants who previously underwent PiB-PET scans and comprehensive clinical assessments were used in this study. Our analyses revealed that baseline Aβ is significantly associated with the rate of change in cognitive composite scores, with cognition declining more rapidly when baseline PiB Aβ levels were higher. In contrast, no signification association was identified between the rate of change in PiB-PET Aβ and cognitive decline. Additionally, the ability of the rate of change in the PiB-PET measures to predict cognitive decline was significantly influenced by APOE ε4 carrier status. These results suggest that a single PiB-PET scan is sufficient to predict cognitive decline and that longitudinal measures of Aβ accumulation do not improve the prediction of cognitive decline once someone is amyloid positive.

Predicting cognitive dysfunction and regional hubs using Braak staging amyloid-beta biomarkers and machine learning

Mild cognitive impairment (MCI) is a transitional stage between normal aging and early Alzheimer's disease (AD). The presence of extracellular amyloid-beta (Aβ) in Braak regions suggests a connection with cognitive dysfunction in MCI/AD. Investigating the multivariate predictive relationships between regional Aβ biomarkers and cognitive function can aid in the early detection and prevention of AD. We introduced machine learning approaches to estimate cognitive dysfunction from regional Aβ biomarkers and identify the Aβ-related dominant brain regions involved with cognitive impairment. We employed Aβ biomarkers and cognitive measurements from the same individuals to train support vector regression (SVR) and artificial neural network (ANN) models and predict cognitive performance solely based on Aβ biomarkers on the test set. To identify Aβ-related dominant brain regions involved in cognitive prediction, we built the local interpretable model-agnostic explanations (LIME) model. We found elevated Aβ in MCI compared to controls and a stronger correlation between Aβ and cognition, particularly in Braak stages III-IV and V-VII (p < 0.05) biomarkers. Both SVR and ANN, especially ANN, showed strong predictive relationships between regional Aβ biomarkers and cognitive impairment (p < 0.05). LIME integrated with ANN showed that the parahippocampal gyrus, inferior temporal gyrus, and hippocampus were the most decisive Braak regions for predicting cognitive decline. Consistent with previous findings, this new approach suggests relationships between Aβ biomarkers and cognitive impairment. The proposed analytical framework can estimate cognitive impairment from Braak staging Aβ biomarkers and delineate the dominant brain regions collectively involved in AD pathophysiology.

Extensive T1-weighted MRI Preprocessing Improves Generalizability of Deep Brain Age Prediction Models

Brain age is an estimate of chronological age obtained from T1-weighted magnetic resonance images (T1w MRI) and represents a simple diagnostic biomarker of brain ageing and associated diseases. While the current best accuracy of brain age predictions on T1w MRIs of healthy subjects ranges from two to three years, comparing results from different studies is challenging due to differences in the datasets, T1w preprocessing pipelines, and performance metrics used. This paper investigates the impact of T1w image preprocessing on the performance of four deep learning brain age models presented in recent literature. Four preprocessing pipelines were evaluated, differing in terms of registration, grayscale correction, and software implementation. The results showed that the choice of software or preprocessing steps can significantly affect the prediction error, with a maximum increase of 0.7 years in mean absolute error (MAE) for the same model and dataset. While grayscale correction had no significant impact on MAE, the affine registration, compared to the rigid registration of T1w images to brain atlas was shown to statistically significantly improve MAE. Models trained on 3D images with isotropic 1 mm3 resolution exhibited less sensitivity to the T1w preprocessing variations compared to 2D models or those trained on downsampled 3D images. Some proved invariant to the preprocessing pipeline, however only after offset correction. Our findings generally indicate that extensive T1w preprocessing enhances the MAE, especially when applied to a new dataset. This runs counter to prevailing research literature which suggests that models trained on minimally preprocessed T1w scans are better poised for age predictions on MRIs from unseen scanners. Regardless of model or T1w preprocessing used, we show that to enable generalization of model's performance on a new dataset with either the same or different T1w preprocessing than the one applied in model training, some form of offset correction should be applied.

A New Approach for Multimodal Usage of Gene Expression and Its Image Representation for the Detection of Alzheimer's Disease

Alzheimer's disease (AD) is a complex neurodegenerative disorder and the multifaceted nature of it requires innovative approaches that integrate various data modalities to enhance its detection. However, due to the cost of collecting multimodal data, multimodal datasets suffer from an insufficient number of samples. To mitigate the impact of a limited sample size on classification, we introduce a novel deep learning method (One2MFusion) which combines gene expression data with their corresponding 2D representation as a new modality. The gene vectors were first mapped to a discriminative 2D image for training a convolutional neural network (CNN). In parallel, the gene sequences were used to train a feed forward neural network (FNN) and the outputs of the FNN and CNN were merged, and a joint deep network was trained for the binary classification of AD, normal control (NC), and mild cognitive impairment (MCI) samples. The fusion of the gene expression data and gene-originated 2D image increased the accuracy (area under the curve) from 0.86 (obtained using a 2D image) to 0.91 for AD vs. NC and from 0.76 (obtained using a 2D image) to 0.88 for MCI vs. NC. The results show that representing gene expression data in another discriminative form increases the classification accuracy when fused with base data.

CReg-KD: Model refinement via confidence regularized knowledge distillation for brain imaging

One of the core challenges of deep learning in medical image analysis is data insufficiency, especially for 3D brain imaging, which may lead to model over-fitting and poor generalization. Regularization strategies such as knowledge distillation are powerful tools to mitigate the issue by penalizing predictive distributions and introducing additional knowledge to reinforce the training process. In this paper, we revisit knowledge distillation as a regularization paradigm by penalizing attentive output distributions and intermediate representations. In particular, we propose a Confidence Regularized Knowledge Distillation (CReg-KD) framework, which adaptively transfers knowledge for distillation in light of knowledge confidence. Two strategies are advocated to regularize the global and local dependencies between teacher and student knowledge. In detail, a gated distillation mechanism is proposed to soften the transferred knowledge globally by utilizing the teacher loss as a confidence score. Moreover, the intermediate representations are attentively and locally refined with key semantic context to mimic meaningful features. To demonstrate the superiority of our proposed framework, we evaluated the framework on two brain imaging analysis tasks (i.e. Alzheimer's Disease classification and brain age estimation based on T1-weighted MRI) on the Alzheimer's Disease Neuroimaging Initiative dataset including 902 subjects and a cohort of 3655 subjects from 4 public datasets. Extensive experimental results show that CReg-KD achieves consistent improvements over the baseline teacher model and outperforms other state-of-the-art knowledge distillation approaches, manifesting that CReg-KD as a powerful medical image analysis tool in terms of both promising prediction performance and generalizability.

Deep Multi-Branch CNN Architecture for Early Alzheimer's Detection from Brain MRIs

Alzheimer's disease (AD) is a neurodegenerative disease that can cause dementia and result in a severe reduction in brain function, inhibiting simple tasks, especially if no preventative care is taken. Over 1 in 9 Americans suffer from AD-induced dementia, and unpaid care for people with AD-related dementia is valued at USD 271.6 billion. Hence, various approaches have been developed for early AD diagnosis to prevent its further progression. In this paper, we first review other approaches that could be used for the early detection of AD. We then give an overview of our dataset and propose a deep convolutional neural network (CNN) architecture consisting of 7,866,819 parameters. This model comprises three different convolutional branches, each having a different length. Each branch is comprised of different kernel sizes. This model can predict whether a patient is non-demented, mild-demented, or moderately demented with a 99.05% three-class accuracy. In summary, the deep CNN model demonstrated exceptional accuracy in the early diagnosis of AD, offering a significant advancement in the field and the potential to improve patient care.

Automated Learning for Deformable Medical Image Registration by Jointly Optimizing Network Architectures and Objective Functions

Deformable image registration plays a critical role in various tasks of medical image analysis. A successful registration algorithm, either derived from conventional energy optimization or deep networks, requires tremendous efforts from computer experts to well design registration energy or to carefully tune network architectures with respect to medical data available for a given registration task/scenario. This paper proposes an automated learning registration algorithm (AutoReg) that cooperatively optimizes both architectures and their corresponding training objectives, enabling non-computer experts to conveniently find off-the-shelf registration algorithms for various registration scenarios. Specifically, we establish a triple-level framework to embrace the searching for both network architectures and objectives with a cooperating optimization. Extensive experiments on multiple volumetric datasets and various registration scenarios demonstrate that AutoReg can automatically learn an optimal deep registration network for given volumes and achieve state-of-the-art performance. The automatically learned network also improves computational efficiency over the mainstream UNet architecture from 0.558 to 0.270 seconds for a volume pair on the same configuration.

Automatic landmark detection and registration of brain cortical surfaces via quasi-conformal geometry and convolutional neural networks

In medical imaging, surface registration is extensively used for performing systematic comparisons between anatomical structures, with a prime example being the highly convoluted brain cortical surfaces. To obtain a meaningful registration, a common approach is to identify prominent features on the surfaces and establish a low-distortion mapping between them with the feature correspondence encoded as landmark constraints. Prior registration works have primarily focused on using manually labeled landmarks and solving highly nonlinear optimization problems, which are time-consuming and hence hinder practical applications. In this work, we propose a novel framework for the automatic landmark detection and registration of brain cortical surfaces using quasi-conformal geometry and convolutional neural networks. We first develop a landmark detection network (LD-Net) that allows for the automatic extraction of landmark curves given two prescribed starting and ending points based on the surface geometry. We then utilize the detected landmarks and quasi-conformal theory for achieving the surface registration. Specifically, we develop a coefficient prediction network (CP-Net) for predicting the Beltrami coefficients associated with the desired landmark-based registration and a mapping network called the disk Beltrami solver network (DBS-Net) for generating quasi-conformal mappings from the predicted Beltrami coefficients, with the bijectivity guaranteed by quasi-conformal theory. Experimental results are presented to demonstrate the effectiveness of our proposed framework. Altogether, our work paves a new way for surface-based morphometry and medical shape analysis.

Self-Supervised Tumor Segmentation With Sim2Real Adaptation

This paper targets on self-supervised tumor segmentation. We make the following contributions: (i) we take inspiration from the observation that tumors are often characterised independently of their contexts, we propose a novel proxy task "layer-decomposition", that closely matches the goal of the downstream task, and design a scalable pipeline for generating synthetic tumor data for pre-training; (ii) we propose a two-stage Sim2Real training regime for unsupervised tumor segmentation, where we first pre-train a model with simulated tumors, and then adopt a self-training strategy for downstream data adaptation; (iii) when evaluating on different tumor segmentation benchmarks, e.g. BraTS2018 for brain tumor segmentation and LiTS2017 for liver tumor segmentation, our approach achieves state-of-the-art segmentation performance under the unsupervised setting. While transferring the model for tumor segmentation under a low-annotation regime, the proposed approach also outperforms all existing self-supervised approaches; (iv) we conduct extensive ablation studies to analyse the critical components in data simulation, and validate the necessity of different proxy tasks. We demonstrate that, with sufficient texture randomization in simulation, model trained on synthetic data can effortlessly generalise to datasets with real tumors.

NeuroBridge: a prototype platform for discovery of the long-tail neuroimaging data

Introduction

Open science initiatives have enabled sharing of large amounts of already collected data. However, significant gaps remain regarding how to find appropriate data, including underutilized data that exist in the long tail of science. We demonstrate the NeuroBridge prototype and its ability to search PubMed Central full-text papers for information relevant to neuroimaging data collected from schizophrenia and addiction studies.

Methods

The NeuroBridge architecture contained the following components: (1) Extensible ontology for modeling study metadata: subject population, imaging techniques, and relevant behavioral, cognitive, or clinical data. Details are described in the companion paper in this special issue; (2) A natural-language based document processor that leveraged pre-trained deep-learning models on a small-sample document corpus to establish efficient representations for each article as a collection of machine-recognized ontological terms; (3) Integrated search using ontology-driven similarity to query PubMed Central and NeuroQuery, which provides fMRI activation maps along with PubMed source articles.

Results

The NeuroBridge prototype contains a corpus of 356 papers from 2018 to 2021 describing schizophrenia and addiction neuroimaging studies, of which 186 were annotated with the NeuroBridge ontology. The search portal on the NeuroBridge website https://neurobridges.org/ provides an interactive Query Builder, where the user builds queries by selecting NeuroBridge ontology terms to preserve the ontology tree structure. For each return entry, links to the PubMed abstract as well as to the PMC full-text article, if available, are presented. For each of the returned articles, we provide a list of clinical assessments described in the Section "Methods" of the article. Articles returned from NeuroQuery based on the same search are also presented.

Conclusion

The NeuroBridge prototype combines ontology-based search with natural-language text-mining approaches to demonstrate that papers relevant to a user's research question can be identified. The NeuroBridge prototype takes a first step toward identifying potential neuroimaging data described in full-text papers. Toward the overall goal of discovering "enough data of the right kind," ongoing work includes validating the document processor with a larger corpus, extending the ontology to include detailed imaging data, and extracting information regarding data availability from the returned publications and incorporating XNAT-based neuroimaging databases to enhance data accessibility.

Challenges of implementing computer-aided diagnostic models for neuroimages in a clinical setting

Advances in artificial intelligence have cultivated a strong interest in developing and validating the clinical utilities of computer-aided diagnostic models. Machine learning for diagnostic neuroimaging has often been applied to detect psychological and neurological disorders, typically on small-scale datasets or data collected in a research setting. With the collection and collation of an ever-growing number of public datasets that researchers can freely access, much work has been done in adapting machine learning models to classify these neuroimages by diseases such as Alzheimer's, ADHD, autism, bipolar disorder, and so on. These studies often come with the promise of being implemented clinically, but despite intense interest in this topic in the laboratory, limited progress has been made in clinical implementation. In this review, we analyze challenges specific to the clinical implementation of diagnostic AI models for neuroimaging data, looking at the differences between laboratory and clinical settings, the inherent limitations of diagnostic AI, and the different incentives and skill sets between research institutions, technology companies, and hospitals. These complexities need to be recognized in the translation of diagnostic AI for neuroimaging from the laboratory to the clinic.

RbQE: An Efficient Method for Content-Based Medical Image Retrieval Based on Query Expansion

Systems for retrieving and managing content-based medical images are becoming more important, especially as medical imaging technology advances and the medical image database grows. In addition, these systems can also use medical images to better grasp and gain a deeper understanding of the causes and treatments of different diseases, not just for diagnostic purposes. For achieving all these purposes, there is a critical need for an efficient and accurate content-based medical image retrieval (CBMIR) method. This paper proposes an efficient method (RbQE) for the retrieval of computed tomography (CT) and magnetic resonance (MR) images. RbQE is based on expanding the features of querying and exploiting the pre-trained learning models AlexNet and VGG-19 to extract compact, deep, and high-level features from medical images. There are two searching procedures in RbQE: a rapid search and a final search. In the rapid search, the original query is expanded by retrieving the top-ranked images from each class and is used to reformulate the query by calculating the mean values for deep features of the top-ranked images, resulting in a new query for each class. In the final search, the new query that is most similar to the original query will be used for retrieval from the database. The performance of the proposed method has been compared to state-of-the-art methods on four publicly available standard databases, namely, TCIA-CT, EXACT09-CT, NEMA-CT, and OASIS-MRI. Experimental results show that the proposed method exceeds the compared methods by 0.84%, 4.86%, 1.24%, and 14.34% in average retrieval precision (ARP) for the TCIA-CT, EXACT09-CT, NEMA-CT, and OASIS-MRI databases, respectively.

Machine Learning for Brain MRI Data Harmonisation: A Systematic Review

BACKGROUND

Magnetic Resonance Imaging (MRI) data collected from multiple centres can be heterogeneous due to factors such as the scanner used and the site location. To reduce this heterogeneity, the data needs to be harmonised. In recent years, machine learning (ML) has been used to solve different types of problems related to MRI data, showing great promise.

OBJECTIVE

This study explores how well various ML algorithms perform in harmonising MRI data, both implicitly and explicitly, by summarising the findings in relevant peer-reviewed articles. Furthermore, it provides guidelines for the use of current methods and identifies potential future research directions.

METHOD

This review covers articles published through PubMed, Web of Science, and IEEE databases through June 2022. Data from studies were analysed based on the criteria of Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). Quality assessment questions were derived to assess the quality of the included publications.

RESULTS

a total of 41 articles published between 2015 and 2022 were identified and analysed. In the review, MRI data has been found to be harmonised either in an implicit (n = 21) or an explicit (n = 20) way. Three MRI modalities were identified: structural MRI (n = 28), diffusion MRI (n = 7) and functional MRI (n = 6).

CONCLUSION

Various ML techniques have been employed to harmonise different types of MRI data. There is currently a lack of consistent evaluation methods and metrics used across studies, and it is recommended that the issue be addressed in future studies. Harmonisation of MRI data using ML shows promises in improving performance for ML downstream tasks, while caution should be exercised when using ML-harmonised data for direct interpretation.

Abnormal white matter changes in Alzheimer's disease based on diffusion tensor imaging: A systematic review

Alzheimer's disease (AD) is a degenerative neurological disease in elderly individuals. Subjective cognitive decline (SCD), mild cognitive impairment (MCI) and further development to dementia (d-AD) are considered to be major stages of the progressive pathological development of AD. Diffusion tensor imaging (DTI), one of the most important modalities of MRI, can describe the microstructure of white matter through its tensor model. It is widely used in understanding the central nervous system mechanism and finding appropriate potential biomarkers for the early stages of AD. Based on the multilevel analysis methods of DTI (voxelwise, fiberwise and networkwise), we summarized that AD patients mainly showed extensive microstructural damage, structural disconnection and topological abnormalities in the corpus callosum, fornix, and medial temporal lobe, including the hippocampus and cingulum. The diffusion features and structural connectomics of specific regions can provide information for the early assisted recognition of AD. The classification accuracy of SCD and normal controls can reach 92.68% at present. And due to the further changes of brain structure and function, the classification accuracy of MCI, d-AD and normal controls can reach more than 97%. Finally, we summarized the limitations of current DTI-based AD research and propose possible future research directions.

An open-source tool for longitudinal whole-brain and white matter lesion segmentation

In this paper we describe and validate a longitudinal method for whole-brain segmentation of longitudinal MRI scans. It builds upon an existing whole-brain segmentation method that can handle multi-contrast data and robustly analyze images with white matter lesions. This method is here extended with subject-specific latent variables that encourage temporal consistency between its segmentation results, enabling it to better track subtle morphological changes in dozens of neuroanatomical structures and white matter lesions. We validate the proposed method on multiple datasets of control subjects and patients suffering from Alzheimer's disease and multiple sclerosis, and compare its results against those obtained with its original cross-sectional formulation and two benchmark longitudinal methods. The results indicate that the method attains a higher test-retest reliability, while being more sensitive to longitudinal disease effect differences between patient groups. An implementation is publicly available as part of the open-source neuroimaging package FreeSurfer.

Conventional machine learning and deep learning in Alzheimer's disease diagnosis using neuroimaging: A review

Alzheimer's disease (AD) is a neurodegenerative disorder that causes memory degradation and cognitive function impairment in elderly people. The irreversible and devastating cognitive decline brings large burdens on patients and society. So far, there is no effective treatment that can cure AD, but the process of early-stage AD can slow down. Early and accurate detection is critical for treatment. In recent years, deep-learning-based approaches have achieved great success in Alzheimer's disease diagnosis. The main objective of this paper is to review some popular conventional machine learning methods used for the classification and prediction of AD using Magnetic Resonance Imaging (MRI). The methods reviewed in this paper include support vector machine (SVM), random forest (RF), convolutional neural network (CNN), autoencoder, deep learning, and transformer. This paper also reviews pervasively used feature extractors and different types of input forms of convolutional neural network. At last, this review discusses challenges such as class imbalance and data leakage. It also discusses the trade-offs and suggestions about pre-processing techniques, deep learning, conventional machine learning methods, new techniques, and input type selection.

Optimal transport features for morphometric population analysis

Brain pathologies often manifest as partial or complete loss of tissue. The goal of many neuroimaging studies is to capture the location and amount of tissue changes with respect to a clinical variable of interest, such as disease progression. Morphometric analysis approaches capture local differences in the distribution of tissue or other quantities of interest in relation to a clinical variable. We propose to augment morphometric analysis with an additional feature extraction step based on unbalanced optimal transport. The optimal transport feature extraction step increases statistical power for pathologies that cause spatially dispersed tissue loss, minimizes sensitivity to shifts due to spatial misalignment or differences in brain topology, and separates changes due to volume differences from changes due to tissue location. We demonstrate the proposed optimal transport feature extraction step in the context of a volumetric morphometric analysis of the OASIS-1 study for Alzheimer's disease. The results demonstrate that the proposed approach can identify tissue changes and differences that are not otherwise measurable.

BoF-SVM-based data intelligence model for detecting dementia

Dementia is a brain condition that impairs the cognitive abilities of an individual. Mild cognitive impairment is a mediator phase of healthy and dementia controls. The motivation of this study is to predict dementia using magnetic resonance imaging data, which is significant for the diagnosis of normal control and dementia patients. The proposed model leverages effective methods like Discrete Wavelet Transform, Bag of Features, and Support Vector Machine. The four wavelets haar, Daubechies, symlets, and coiflets are used for image compression. The results of the proposed data intelligence model are promising in terms of accuracy which is 92.32% which is better than the recently proposed models. Also, the proposed data intelligence model is compared with the models which may use curvelet transform, and shearlet transform and with the methods which have gone without using DWT transforms. The comparisons have also been made with the models that have used other prevalent techniques like Principal Component Analysis, Fisher Discriminant Ratio, and Gray Level Co-occurrence Matrix. The outcomes support the usage of each technique in the suggested data intelligence paradigm.

Transfer Learning on Small Datasets for Improved Fall Detection

Falls in the elderly are associated with significant morbidity and mortality. While numerous fall detection devices incorporating AI and machine learning algorithms have been developed, no known smartwatch-based system has been used successfully in real-time to detect falls for elderly persons. We have developed and deployed a SmartFall system on a commodity-based smartwatch which has been trialled by nine elderly participants. The system, while being usable and welcomed by the participants in our trials, has two serious limitations. The first limitation is the inability to collect a large amount of personalized data for training. When the fall detection model, which is trained with insufficient data, is used in the real world, it generates a large amount of false positives. The second limitation is the model drift problem. This means an accurate model trained using data collected with a specific device performs sub-par when used in another device. Therefore, building one model for each type of device/watch is not a scalable approach for developing smartwatch-based fall detection system. To tackle those issues, we first collected three datasets including accelerometer data for fall detection problem from different devices: the Microsoft watch (MSBAND), the Huawei watch, and the meta-sensor device. After that, a transfer learning strategy was applied to first explore the use of transfer learning to overcome the small dataset training problem for fall detection. We also demonstrated the use of transfer learning to generalize the model across the heterogeneous devices. Our preliminary experiments demonstrate the effectiveness of transfer learning for improving fall detection, achieving an F1 score higher by over 10% on average, an AUC higher by over 0.15 on average, and a smaller false positive prediction rate than the non-transfer learning approach across various datasets collected using different devices with different hardware specifications.

Sex difference in the associations of socioeconomic status, cognitive function and brain volume with dementia in old adults: Findings from the OASIS study

Background

Sex differences in the association of cognitive function and imaging measures with dementia have not been fully investigated while sex-based investigation of dementia has been discussed. Understanding sex differences in the dementia-related socioeconomic, cognitive, and imaging measurements is important for uncovering sex-related pathways to dementia and facilitating early diagnosis, family planning, and cost control.

Methods

We selected data from the Open Access Series of Imaging Studies with longitudinal measurements of brain volumes on 150 individuals aged 60 to 96 years. Dementia status was determined using the Clinical Dementia Rating (CDR) scale, and Alzheimer's disease was diagnosed as a CDR of ≥ 0.5. Generalized estimating equation models were used to estimate the associations of socioeconomic, cognitive and imaging factors with dementia in men and women.

Results

Lower education affected dementia more in women than in men. Age, education, Mini-Mental State Examination (MMSE), and normalized whole-brain volume (nWBV) were associated with dementia in women whereas only MMSE and nWBV were associated with dementia in men. Lower socioeconomic status was associated with a reduced estimated total intracranial volume in men, but not in women. Ageing and lower MMSE scores were associated with reduced nWBV in both men and women.

Conclusions

The association between education and prevalence of dementia differs in men and women. Women may have more risk factors for dementia than men.

Decoding the radiomic features of dorsolateral prefrontal cortex in individuals with accelerated cortical changes: implications for personalized transcranial magnetic stimulation

Purpose

Image-guided transcranial magnetic stimulation (TMS) is an emerging research field in neuroscience and rehabilitation medicine. Cortical morphometry, as a radiomic phenotype of aging, plays a vital role in developing personalized TMS model, yet few studies are afoot to examine the aging effects on region-specific morphometry and use it in the estimation of TMS-induced electric fields. Our study was aimed to investigate the radiomic features of bilateral dorsolateral prefrontal cortex (DLPFC) and quantify the TMS-induced electric fields during aging.

Approach

Baseline, 1-year and 3-year structural magnetic resonance imaging (MRI) scans from normal aging (NA) adults ( n = 32 ) and mild cognitive impairment (MCI) converters ( n = 22 ) were drawn from the Open Access Series of Imaging Studies. The quantitative measures of radiomics included cortical thickness, folding, and scalp-to-cortex distance. Realistic head models were developed to simulate the impacts of radiomic features on TMS-induced E-fields using the finite-element method.

Results

A pronounced aging-related decrease was found in the gyrification of left DLPFC in MCI converters ( t = 2.21 , p = 0.035 ), which could predict the decline of global cognition at 3-year follow up. Along with the decreased gyrification in left DLPFC, the magnitude of TMS-induced E-fields was rapidly decreased in MCI converters ( t = 2.56 , p = 0.018 ).

Conclusions

MRI-informed radiomic features of the treatment targets have significant effects on the intensity and distribution of the stimulation-induced electric fields in prodromal dementia patients. Our findings highlight the importance of region-specific radiomics when conducting the transcranial brain stimulation in individuals with accelerated cortical changes, such as Alzheimer's disease.

Robust Testing of Paired Outcomes Incorporating Covariate Effects in Clustered Data with Informative Cluster Size

Paired outcomes are common in correlated clustered data where the main aim is to compare the distributions of the outcomes in a pair. In such clustered paired data, informative cluster sizes can occur when the number of pairs in a cluster (i.e., a cluster size) is correlated to the paired outcomes or the paired differences. There have been some attempts to develop robust rank-based tests for comparing paired outcomes in such complex clustered data. Most of these existing rank tests developed for paired outcomes in clustered data compare the marginal distributions in a pair and ignore any covariate effect on the outcomes. However, when potentially important covariate data is available in observational studies, ignoring these covariate effects on the outcomes can result in a flawed inference. In this article, using rank based weighted estimating equations, we propose a robust procedure for covariate effect adjusted comparison of paired outcomes in a clustered data that can also address the issue of informative cluster size. Through simulated scenarios and real-life neuroimaging data, we demonstrate the importance of considering covariate effects during paired testing and robust performances of our proposed method in covariate adjusted paired comparisons in complex clustered data settings.

CerebNet: A fast and reliable deep-learning pipeline for detailed cerebellum sub-segmentation

Quantifying the volume of the cerebellum and its lobes is of profound interest in various neurodegenerative and acquired diseases. Especially for the most common spinocerebellar ataxias (SCA), for which the first antisense oligonculeotide-base gene silencing trial has recently started, there is an urgent need for quantitative, sensitive imaging markers at pre-symptomatic stages for stratification and treatment assessment. This work introduces CerebNet, a fully automated, extensively validated, deep learning method for the lobular segmentation of the cerebellum, including the separation of gray and white matter. For training, validation, and testing, T1-weighted images from 30 participants were manually annotated into cerebellar lobules and vermal sub-segments, as well as cerebellar white matter. CerebNet combines FastSurferCNN, a UNet-based 2.5D segmentation network, with extensive data augmentation, e.g. realistic non-linear deformations to increase the anatomical variety, eliminating additional preprocessing steps, such as spatial normalization or bias field correction. CerebNet demonstrates a high accuracy (on average 0.87 Dice and 1.742mm Robust Hausdorff Distance across all structures) outperforming state-of-the-art approaches. Furthermore, it shows high test-retest reliability (average ICC >0.97 on OASIS and Kirby) as well as high sensitivity to disease effects, including the pre-ataxic stage of spinocerebellar ataxia type 3 (SCA3). CerebNet is compatible with FreeSurfer and FastSurfer and can analyze a 3D volume within seconds on a consumer GPU in an end-to-end fashion, thus providing an efficient and validated solution for assessing cerebellum sub-structure volumes. We make CerebNet available as source-code (https://github.com/Deep-MI/FastSurfer).

Learning to segment subcortical structures from noisy annotations with a novel uncertainty-reliability aware learning framework

Accurate segmentation of subcortical structures is an important task in quantitative brain image analysis. Convolutional neural networks (CNNs) have achieved remarkable results in medical image segmentation. However, due to the difficulty of acquiring high-quality annotations of brain subcortical structures, learning segmentation networks using noisy annotations is an inevitable topic. A common practice is to select images or pixels with reliable annotations for training, which usually may not make full use of the information from the training samples, thus affecting the performance of the learned segmentation model. To address the above problem, in this work, we propose a novel robust learning method and denote it as uncertainty-reliability awareness learning (URAL), which can make sufficient use of all training pixels. At each training iteration, the proposed method first selects training pixels with reliable annotations from the set of pixels with uncertain network prediction, by utilizing a small clean validation set following a meta-learning paradigm. Meanwhile, we propose the online prototypical soft label correction (PSLC) method to estimate the pseudo-labels of label-unreliable pixels. Then, the segmentation loss of label-reliable pixels and the semi-supervised segmentation loss of label-unreliable pixels are used to calibrate the total segmentation loss. Finally, we propose a category-wise contrastive regularization to learn compact feature representations of all uncertain training pixels. Comprehensive experiments are performed on two publicly available brain MRI datasets. The proposed method achieves the best Dice scores and MHD values on both datasets compared to several recent state-of-the-art methods under all label noise settings. Our code is available at https://github.com/neulxlx/URAL.

Mapping lesion, structural disconnection, and functional disconnection to symptoms in semantic aphasia

Patients with semantic aphasia have impaired control of semantic retrieval, often accompanied by executive dysfunction following left hemisphere stroke. Many but not all of these patients have damage to the left inferior frontal gyrus, important for semantic and cognitive control. Yet semantic and cognitive control networks are highly distributed, including posterior as well as anterior components. Accordingly, semantic aphasia might not only reflect local damage but also white matter structural and functional disconnection. Here, we characterise the lesions and predicted patterns of structural and functional disconnection in individuals with semantic aphasia and relate these effects to semantic and executive impairment. Impaired semantic cognition was associated with infarction in distributed left-hemisphere regions, including in the left anterior inferior frontal and posterior temporal cortex. Lesions were associated with executive dysfunction within a set of adjacent but distinct left frontoparietal clusters. Performance on executive tasks was also associated with interhemispheric structural disconnection across the corpus callosum. In contrast, poor semantic cognition was associated with small left-lateralized structurally disconnected clusters, including in the left posterior temporal cortex. Little insight was gained from functional disconnection symptom mapping. These results demonstrate that while left-lateralized semantic and executive control regions are often damaged together in stroke aphasia, these deficits are associated with distinct patterns of structural disconnection, consistent with the bilateral nature of executive control and the left-lateralized yet distributed semantic control network.

Learning Deformable Image Registration From Optimization: Perspective, Modules, Bilevel Training and Beyond

Conventional deformable registration methods aim at solving an optimization model carefully designed on image pairs and their computational costs are exceptionally high. In contrast, recent deep learning-based approaches can provide fast deformation estimation. These heuristic network architectures are fully data-driven and thus lack explicit geometric constraints which are indispensable to generate plausible deformations, e.g., topology-preserving. Moreover, these learning-based approaches typically pose hyper-parameter learning as a black-box problem and require considerable computational and human effort to perform many training runs. To tackle the aforementioned problems, we propose a new learning-based framework to optimize a diffeomorphic model via multi-scale propagation. Specifically, we introduce a generic optimization model to formulate diffeomorphic registration and develop a series of learnable architectures to obtain propagative updating in the coarse-to-fine feature space. Further, we propose a new bilevel self-tuned training strategy, allowing efficient search of task-specific hyper-parameters. This training strategy increases the flexibility to various types of data while reduces computational and human burdens. We conduct two groups of image registration experiments on 3D volume datasets including image-to-atlas registration on brain MRI data and image-to-image registration on liver CT data. Extensive results demonstrate the state-of-the-art performance of the proposed method with diffeomorphic guarantee and extreme efficiency. We also apply our framework to challenging multi-modal image registration, and investigate how our registration to support the down-streaming tasks for medical image analysis including multi-modal fusion and image segmentation.