Brain-age prediction: Systematic evaluation of site effects, and sample age range and size.

Structural neuroimaging data have been used to compute an estimate of the biological age of the brain (brain-age) which has been associated with other biologically and behaviorally meaningful measures of brain development and aging. The ongoing research interest in brain-age has highlighted the need for robust and publicly available brain-age models pre-trained on data from large samples of healthy individuals. To address this need we have previously released a developmental brain-age model. Here we expand this work to develop, empirically validate, and disseminate a pre-trained brain-age model to cover most of the human lifespan. To achieve this, we selected the best-performing model after systematically examining the impact of seven site harmonization strategies, age range, and sample size on brain-age prediction in a discovery sample of brain morphometric measures from 35,683 healthy individuals (age range: 5-90 years; 53.59% female). The pre-trained models were tested for cross-dataset generalizability in an independent sample comprising 2101 healthy individuals (age range: 8-80 years; 55.35% female) and for longitudinal consistency in a further sample comprising 377 healthy individuals (age range: 9-25 years; 49.87% female). This empirical examination yielded the following findings: (1) the accuracy of age prediction from morphometry data was higher when no site harmonization was applied; (2) dividing the discovery sample into two age-bins (5-40 and 40-90 years) provided a better balance between model accuracy and explained age variance than other alternatives; (3) model accuracy for brain-age prediction plateaued at a sample size exceeding 1600 participants. These findings have been incorporated into CentileBrain (https://centilebrain.org/#/brainAGE2), an open-science, web-based platform for individualized neuroimaging metrics.

DeepComBat: A statistically motivated, hyperparameter-robust, deep learning approach to harmonization of neuroimaging data.

Neuroimaging data acquired using multiple scanners or protocols are increasingly available. However, such data exhibit technical artifacts across batches which introduce confounding and decrease reproducibility. This is especially true when multi-batch data are analyzed using complex downstream models which are more likely to pick up on and implicitly incorporate batch-related information. Previously proposed image harmonization methods have sought to remove these batch effects; however, batch effects remain detectable in the data after applying these methods. We present DeepComBat, a deep learning harmonization method based on a conditional variational autoencoder and the ComBat method. DeepComBat combines the strengths of statistical and deep learning methods in order to account for the multivariate relationships between features while simultaneously relaxing strong assumptions made by previous deep learning harmonization methods. As a result, DeepComBat can perform multivariate harmonization while preserving data structure and avoiding the introduction of synthetic artifacts. We apply this method to cortical thickness measurements from a cognitive-aging cohort and show DeepComBat qualitatively and quantitatively outperforms existing methods in removing batch effects while preserving biological heterogeneity. Additionally, DeepComBat provides a new perspective for statistically motivated deep learning harmonization methods.

Latent diffusion model-based MRI superresolution enhances mild cognitive impairment prognostication and Alzheimer's disease classification.

INTRODUCTION: Timely diagnosis and prognostication of Alzheimer's disease (AD) and mild cognitive impairment (MCI) are pivotal for effective intervention. Artificial intelligence (AI) in neuroradiology may aid in such appropriate diagnosis and prognostication. This study aimed to evaluate the potential of novel diffusion model-based AI for enhancing AD and MCI diagnosis through superresolution (SR) of brain magnetic resonance (MR) images. METHODS: 1.5T brain MR scans of patients with AD or MCI and healthy controls (NC) from Alzheimer's Disease Neuroimaging Initiative 1 (ADNI1) were superresolved to 3T using a novel diffusion model-based generative AI (d3T*) and a convolutional neural network-based model (c3T*). Comparisons of image quality to actual 1.5T and 3T MRI were conducted based on signal-to-noise ratio (SNR), naturalness image quality evaluator (NIQE), and Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE). Voxel-based volumetric analysis was then conducted to study whether 3T* images offered more accurate volumetry than 1.5T images. Binary and multiclass classifications of AD, MCI, and NC were conducted to evaluate whether 3T* images offered superior AD classification performance compared to actual 1.5T MRI. Moreover, CNN-based classifiers were used to predict conversion of MCI to AD, to evaluate the prognostication performance of 3T* images. The classification performances were evaluated using accuracy, sensitivity, specificity, F1 score, Matthews correlation coefficient (MCC), and area under the receiver-operating curves (AUROC). RESULTS: Analysis of variance (ANOVA) detected significant differences in image quality among the 1.5T, c3T*, d3T*, and 3T groups across all metrics. Both c3T* and d3T* showed superior image quality compared to 1.5T MRI in NIQE and BRISQUE with statistical significance. While the hippocampal volumes measured in 3T* and 3T images were not significantly different, the hippocampal volume measured in 1.5T images showed significant difference. 3T*-based AD classifications showed superior performance across all performance metrics compared to 1.5T-based AD classification. Classification performance between d3T* and actual 3T was not significantly different. 3T* images offered superior accuracy in predicting the conversion of MCI to AD than 1.5T images did. CONCLUSIONS: The diffusion model-based MRI SR enhances the resolution of brain MR images, significantly improving diagnostic and prognostic accuracy for AD and MCI. Superresolved 3T* images closely matched actual 3T MRIs in quality and volumetric accuracy, and notably improved the prediction performance of conversion from MCI to AD.

Fast refacing of MR images with a generative neural network lowers re-identification risk and preserves volumetric consistency.

With the rise of open data, identifiability of individuals based on 3D renderings obtained from routine structural magnetic resonance imaging (MRI) scans of the head has become a growing privacy concern. To protect subject privacy, several algorithms have been developed to de-identify imaging data using blurring, defacing or refacing. Completely removing facial structures provides the best re-identification protection but can significantly impact post-processing steps, like brain morphometry. As an alternative, refacing methods that replace individual facial structures with generic templates have a lower effect on the geometry and intensity distribution of original scans, and are able to provide more consistent post-processing results by the price of higher re-identification risk and computational complexity. In the current study, we propose a novel method for anonymized face generation for defaced 3D T1-weighted scans based on a 3D conditional generative adversarial network. To evaluate the performance of the proposed de-identification tool, a comparative study was conducted between several existing defacing and refacing tools, with two different segmentation algorithms (FAST and Morphobox). The aim was to evaluate (i) impact on brain morphometry reproducibility, (ii) re-identification risk, (iii) balance between (i) and (ii), and (iv) the processing time. The proposed method takes 9 s for face generation and is suitable for recovering consistent post-processing results after defacing.

Amyloid-related imaging abnormalities (ARIA): diagnosis, management, and care in the setting of amyloid-modifying therapy.

Amyloid-related imaging abnormalities, were originally described by dementia care experts. The wider use of aducanumab and now lecanemab warrant broader understanding by the health care provider continuum. The optimal care approach for patients with Alzheimer's dementia, treated with amyloid-targeted therapy, includes proper clinical diagnosis, complication surveillance, specific imaging protocols, expert specialty consultation, integrated treatment strategies, and proper facility system planning. Improved awareness and understanding of amyloid-modifying therapy, both benefits and potential complications, among the health care provider continuum is paramount to the success of complex care programs. Specifically, recognition of treatment high risk, high benefit groups, and the interface of concurrent antiplatelet and anticoagulation. This integrated acute, specialty, and primary care approach should improve patient care quality and outcome.

The Current Diagnostic Performance of MRI-Based Radiomics for Glioma Grading: A Meta-Analysis.

BACKGROUND: Multiple radiomics models have been proposed for grading glioma using different algorithms, features, and sequences of magnetic resonance imaging. The research seeks to assess the present overall performance of radiomics for grading glioma. METHODS: A systematic literature review of the databases Ovid MEDLINE PubMed, and Ovid EMBASE for publications published on radiomics for glioma grading between 2012 and 2023 was performed. The systematic review was carried out following the criteria of Preferred Reporting Items for Systematic Reviews and Meta-Analysis. RESULTS: In the meta-analysis, a total of 7654 patients from 40 articles, were assessed. R-package mada was used for modeling the joint estimates of specificity (SPE) and sensitivity (SEN). Pooled event rates across studies were performed with a random-effects meta-analysis. The heterogeneity of SPE and SEN were based on the χ2 test. Overall values for SPE and SEN in the differentiation between high-grade gliomas (HGGs) and low-grade gliomas (LGGs) were 84% and 91%, respectively. With regards to the discrimination between World Health Organization (WHO) grade 4 and WHO grade 3, the overall SPE was 81% and the SEN was 89%. The modern non-linear classifiers showed a better trend, whereas textural features tend to be the best-performing (29%) and the most used. CONCLUSIONS: Our findings confirm that present radiomics' diagnostic performance for glioma grading is superior in terms of SEN and SPE for the HGGs vs. LGGs discrimination task when compared to the WHO grade 4 vs. 3 task.

Disease-driven domain generalization for neuroimaging-based assessment of Alzheimer's disease.

Development of deep learning models to evaluate structural brain changes caused by cognitive impairment in MRI scans holds significant translational value. The efficacy of these models often encounters challenges due to variabilities arising from different data generation protocols, imaging equipment, radiological artifacts, and shifts in demographic distributions. Domain generalization (DG) techniques show promise in addressing these challenges by enabling the model to learn from one or more source domains and apply this knowledge to new, unseen target domains. Here we present a framework that utilizes model interpretability to enhance the generalizability of classification models across various cohorts. We used MRI scans and clinical diagnoses from four independent cohorts: Alzheimer's Disease Neuroimaging Initiative (ADNI, n = 1821), the Framingham Heart Study (FHS, n = 304), the Australian Imaging Biomarkers & Lifestyle Study of Ageing (AIBL, n = 661), and the National Alzheimer's Coordinating Center (NACC, n = 4647). With this data, we trained a deep neural network to focus on areas of the brain identified as relevant to the disease for model training. Our approach involved training a classifier to differentiate between structural neurodegeneration in individuals with normal cognition (NC), mild cognitive impairment (MCI), and dementia due to Alzheimer's disease (AD). This was achieved by aligning class-wise attention with a unified visual saliency prior, which was computed offline for each class using all the training data. Our method not only competes with state-of-the-art approaches but also shows improved correlation with postmortem histology. This alignment with the gold standard evidence is a significant step towards validating the effectiveness of DG frameworks, paving the way for their broader application in the field.

Harmonizing three-dimensional MRI using pseudo-warping field guided GAN.

In pursuit of cultivating automated models for magnetic resonance imaging (MRI) to aid in diagnostics, an escalating demand for extensive, multisite, and heterogeneous brain imaging datasets has emerged. This potentially introduces biased outcomes when directly applied for subsequent analysis. Researchers have endeavored to address this issue by pursuing the harmonization of MRIs. However, most existing image-based harmonization methods for MRI are tailored for 2D slices, which may introduce inter-slice variations when they are combined into a 3D volume. In this study, we aim to resolve inconsistencies between slices by introducing a pseudo-warping field. This field is created randomly and utilized to transform a slice into an artificially warped subsequent slice. The objective of this pseudo-warping field is to ensure that generators can consistently harmonize adjacent slices to another domain, without being affected by the varying content present in different slices. Furthermore, we construct unsupervised spatial and recycle loss to enhance the spatial accuracy and slice-wise consistency across the 3D images. The results demonstrate that our model effectively mitigates inter-slice variations and successfully preserves the anatomical details of the images during the harmonization process. Compared to generative harmonization models that employ 3D operators, our model exhibits greater computational efficiency and flexibility.

SAN: Mitigating spatial covariance heterogeneity in cortical thickness data collected from multiple scanners or sites.

In neuroimaging studies, combining data collected from multiple study sites or scanners is becoming common to increase the reproducibility of scientific discoveries. At the same time, unwanted variations arise by using different scanners (inter-scanner biases), which need to be corrected before downstream analyses to facilitate replicable research and prevent spurious findings. While statistical harmonization methods such as ComBat have become popular in mitigating inter-scanner biases in neuroimaging, recent methodological advances have shown that harmonizing heterogeneous covariances results in higher data quality. In vertex-level cortical thickness data, heterogeneity in spatial autocorrelation is a critical factor that affects covariance heterogeneity. Our work proposes a new statistical harmonization method called spatial autocorrelation normalization (SAN) that preserves homogeneous covariance vertex-level cortical thickness data across different scanners. We use an explicit Gaussian process to characterize scanner-invariant and scanner-specific variations to reconstruct spatially homogeneous data across scanners. SAN is computationally feasible, and it easily allows the integration of existing harmonization methods. We demonstrate the utility of the proposed method using cortical thickness data from the Social Processes Initiative in the Neurobiology of the Schizophrenia(s) (SPINS) study. SAN is publicly available as an R package.

LST-AI: A deep learning ensemble for accurate MS lesion segmentation.

Automated segmentation of brain white matter lesions is crucial for both clinical assessment and scientific research in multiple sclerosis (MS). Over a decade ago, we introduced an engineered lesion segmentation tool, LST. While recent lesion segmentation approaches have leveraged artificial intelligence (AI), they often remain proprietary and difficult to adopt. As an open-source tool, we present LST-AI, an advanced deep learning-based extension of LST that consists of an ensemble of three 3D U-Nets. LST-AI explicitly addresses the imbalance between white matter (WM) lesions and non-lesioned WM. It employs a composite loss function incorporating binary cross-entropy and Tversky loss to improve segmentation of the highly heterogeneous MS lesions. We train the network ensemble on 491 MS pairs of T1-weighted and FLAIR images, collected in-house from a 3T MRI scanner, and expert neuroradiologists manually segmented the utilized lesion maps for training. LST-AI also includes a lesion location annotation tool, labeling lesions as periventricular, infratentorial, and juxtacortical according to the 2017 McDonald criteria, and, additionally, as subcortical. We conduct evaluations on 103 test cases consisting of publicly available data using the Anima segmentation validation tools and compare LST-AI with several publicly available lesion segmentation models. Our empirical analysis shows that LST-AI achieves superior performance compared to existing methods. Its Dice and F1 scores exceeded 0.62, outperforming LST, SAMSEG (Sequence Adaptive Multimodal SEGmentation), and the popular nnUNet framework, which all scored below 0.56. Notably, LST-AI demonstrated exceptional performance on the MSSEG-1 challenge dataset, an international WM lesion segmentation challenge, with a Dice score of 0.65 and an F1 score of 0.63-surpassing all other competing models at the time of the challenge. With increasing lesion volume, the lesion detection rate rapidly increased with a detection rate of >75% for lesions with a volume between 10 mm3 and 100 mm3. Given its higher segmentation performance, we recommend that research groups currently using LST transition to LST-AI. To facilitate broad adoption, we are releasing LST-AI as an open-source model, available as a command-line tool, dockerized container, or Python script, enabling diverse applications across multiple platforms.

Combining neuropsychological assessment and structural neuroimaging to identify early Alzheimer's disease in a memory clinic cohort.

INTRODUCTION: The current study examined the contributions of comprehensive neuropsychological assessment and volumetric assessment of selected mesial temporal subregions on structural magnetic resonance imaging (MRI) to identify patients with amnestic mild cognitive impairment (aMCI) and mild probable Alzheimer's disease (AD) dementia in a memory clinic cohort. METHODS: Comprehensive neuropsychological assessment and automated entorhinal, transentorhinal, and hippocampal volume measurements were conducted in 40 healthy controls, 38 patients with subjective memory symptoms, 16 patients with aMCI, 16 patients with mild probable AD dementia. Multinomial logistic regression was used to compare the neuropsychological and MRI measures. RESULTS: Combining the neuropsychological and MRI measures improved group membership prediction over the MRI measures alone but did not improve group membership prediction over the neuropsychological measures alone. CONCLUSION: Comprehensive neuropsychological assessment was an important tool to evaluate cognitive impairment. The mesial temporal volumetric MRI measures contributed no diagnostic value over and above the determinations made through neuropsychological assessment.

Searching Reproducible Brain Features using NeuroMark: Templates for Different Age Populations and Imaging Modalities.

A primary challenge to the data-driven analysis is the balance between poor generalizability of population-based research and characterizing more subject-, study- and population-specific variability. We previously introduced a fully automated spatially constrained independent component analysis (ICA) framework called NeuroMark and its functional MRI (fMRI) template. NeuroMark has been successfully applied in numerous studies, identifying brain markers reproducible across datasets and disorders. The first NeuroMark template was constructed based on young adult cohorts. We recently expanded on this initiative by creating a standardized normative multi-spatial-scale functional template using over 100,000 subjects, aiming to improve generalizability and comparability across studies involving diverse cohorts. While a unified template across the lifespan is desirable, a comprehensive investigation of the similarities and differences between components from different age populations might help systematically transform our understanding of the human brain by revealing the most well-replicated and variable network features throughout the lifespan. In this work, we introduced two significant expansions of NeuroMark templates first by generating replicable fMRI templates for infants, adolescents, and aging cohorts, and second by incorporating structural MRI (sMRI) and diffusion MRI (dMRI) modalities. Specifically, we built spatiotemporal fMRI templates based on 6,000 resting-state scans from four datasets. This is the first attempt to create robust ICA templates covering dynamic brain development across the lifespan. For the sMRI and dMRI data, we used two large publicly available datasets including more than 30,000 scans to build reliable templates. We employed a spatial similarity analysis to identify replicable templates and investigate the degree to which unique and similar patterns are reflective in different age populations. Our results suggest remarkably high similarity of the resulting adapted components, even across extreme age differences. With the new templates, the NeuroMark framework allows us to perform age-specific adaptations and to capture features adaptable to each modality, therefore facilitating biomarker identification across brain disorders. In sum, the present work demonstrates the generalizability of NeuroMark templates and suggests the potential of new templates to boost accuracy in mental health research and advance our understanding of lifespan and cross-modal alterations.

Evaluating Biases and Quality Issues in Intermodality Image Translation Studies for Neuroradiology: A Systematic Review.

BACKGROUND: Intermodality image-to-image translation is an artificial intelligence technique for generating one technique from another. PURPOSE: This review was designed to systematically identify and quantify biases and quality issues preventing validation and clinical application of artificial intelligence models for intermodality image-to-image translation of brain imaging. DATA SOURCES: PubMed, Scopus, and IEEE Xplore were searched through August 2, 2023, for artificial intelligence-based image translation models of radiologic brain images. STUDY SELECTION: This review collected 102 works published between April 2017 and August 2023. DATA ANALYSIS: Eligible studies were evaluated for quality using the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) and for bias using the Prediction model Risk Of Bias ASsessment Tool (PROBAST). Medically-focused article adherence was compared with that of engineering-focused articles overall with the Mann-Whitney U test and for each criterion using the Fisher exact test. DATA SYNTHESIS: Median adherence to the relevant CLAIM criteria was 69% and 38% for PROBAST questions. CLAIM adherence was lower for engineering-focused articles compared with medically-focused articles (65% versus 73%, P < .001). Engineering-focused studies had higher adherence for model description criteria, and medically-focused studies had higher adherence for data set and evaluation descriptions. LIMITATIONS: Our review is limited by the study design and model heterogeneity. CONCLUSIONS: Nearly all studies revealed critical issues preventing clinical application, with engineering-focused studies showing higher adherence for the technical model description but significantly lower overall adherence than medically-focused studies. The pursuit of clinical application requires collaboration from both fields to improve reporting.

Improving 3D edge detection for visual inspection of MRI coregistration and alignment.

BACKGROUND: Visualizing edges is critical for neuroimaging. For example, edge maps enable quality assurance for the automatic alignment of an image from one modality (or individual) to another. NEW METHOD: We suggest that using the second derivative (difference of Gaussian, or DoG) provides robust edge detection. This method is tuned by size (which is typically known in neuroimaging) rather than intensity (which is relative). RESULTS: We demonstrate that this method performs well across a broad range of imaging modalities. The edge contours produced consistently form closed surfaces, whereas alternative methods may generate disconnected lines, introducing potential ambiguity in contiguity. COMPARISON WITH EXISTING METHODS: Current methods for computing edges are based on either the first derivative of the image (FSL), or a variation of the Canny Edge detection method (AFNI). These methods suffer from two primary limitations. First, the crucial tuning parameter for each of these methods relates to the image intensity. Unfortunately, image intensity is relative for most neuroimaging modalities making the performance of these methods unreliable. Second, these existing approaches do not necessarily generate a closed edge/surface, which can reduce the ability to determine the correspondence between a represented edge and another image. CONCLUSION: The second derivative is well suited for neuroimaging edge detection. We include this method as part of both the AFNI and FSL software packages, standalone code and online.

Multimodal active subspace analysis for computing assessment oriented subspaces from neuroimaging data.

BACKGROUND: For successful biomarker discovery, it is essential to develop computational frameworks that summarize high-dimensional neuroimaging data in terms of involved sub-systems of the brain, while also revealing underlying heterogeneous functional and structural changes covarying with specific cognitive and biological traits. However, unsupervised decompositions do not inculcate clinical assessment information, while supervised approaches extract only individual feature importance, thereby impeding qualitative interpretation at the level of subspaces. NEW METHOD: We present a novel framework to extract robust multimodal brain subspaces associated with changes in a given cognitive or biological trait. Our approach involves active subspace learning on the gradients of a trained machine learning model followed by clustering to extract and summarize the most salient and consistent subspaces associated with the target variable. RESULTS: Through a rigorous cross-validation procedure on an Alzheimer's disease (AD) dataset, our framework successfully extracts multimodal subspaces specific to a given clinical assessment (e.g., memory and other cognitive skills), and also retains predictive performance in standard machine learning algorithms. We also show that the salient active subspace directions occur consistently across randomly sub-sampled repetitions of the analysis. COMPARISON WITH EXISTING METHOD(S): Compared to existing unsupervised decompositions based on principle component analysis, the subspace components in our framework retain higher predictive information. CONCLUSIONS: As an important step towards biomarker discovery, our framework not only uncovers AD-related brain regions in the associated brain subspaces, but also enables automated identification of multiple underlying structural and functional sub-systems of the brain that collectively characterize changes in memory and proficiency in cognitive skills related to brain disorders like AD.

Potential of neuroimaging as a biomarker in amyotrophic lateral sclerosis: from structure to metabolism.

Amyotrophic lateral sclerosis (ALS) is a progressive neurodegenerative disease characterized by motor neuron degeneration. The development of ALS involves metabolite alterations leading to tissue lesions in the nervous system. Recent advances in neuroimaging have significantly improved our understanding of the underlying pathophysiology of ALS, with findings supporting the corticoefferent axonal disease progression theory. Current studies on neuroimaging in ALS have demonstrated inconsistencies, which may be due to small sample sizes, insufficient statistical power, overinterpretation of findings, and the inherent heterogeneity of ALS. Deriving meaningful conclusions solely from individual imaging metrics in ALS studies remains challenging, and integrating multimodal imaging techniques shows promise for detecting valuable ALS biomarkers. In addition to giving an overview of the principles and techniques of different neuroimaging modalities, this review describes the potential of neuroimaging biomarkers in the diagnosis and prognostication of ALS. We provide an insight into the underlying pathology, highlighting the need for standardized protocols and multicenter collaborations to advance ALS research.

Impact of MRI on decision-making in ICU patients with disorders of consciousness.

BACKGROUND: Recovery of consciousness is the most important survival factor in patients with acute brain injury and disorders of consciousness (DoC). Since most deaths in the intensive care unit (ICU) occur after withdrawal of life-support, medical decision-making is crucial for acute DoC patients. Neuroimaging informs decision-making, yet the precise effects of MRI on decision-making in the ICU are poorly understood. We investigated the impact of brain MRI on prognostication, therapeutic decisions and physician confidence in ICU patients with DoC. METHODS: In this simulated decision-making study utilizing a prospective ICU cohort, a panel of neurocritical experts first reviewed clinical information (without MRI) from 75 acute DoC patients and made decisions about diagnosis, prognosis and treatment. Following review of the MRI, the panel then decided if the initial decisions needed revision. In parallel, a blinded neuroradiologist reassessed all neuroimaging. RESULTS: MRI led to changes in clinical management of 57 (76%) of patients (Number-Needed-to-Test for any change: 1.32), including revised diagnoses (20%), levels of care (21%), diagnostic confidence (43%) and prognostications (33%). Decisions were revised more often with stroke than with other brain injuries (p = 0.02). However, although MRI revealed additional pathology in 81%, this did not predict revised clinical decision-making (p-values ≥0.08). CONCLUSION: MRI results changed decision-making in 3 of 4 ICU patients, but radiological findings were not predictive of clinical decision-making. This highlights the need to better understand the effects of neuroimaging on management decisions. How MRI influences decision-making in the ICU is an important avenue for research to improve acute DoC management.

Accurate brain-age models for routine clinical MRI examinations.

Convolutional neural networks (CNN) can accurately predict chronological age in healthy individuals from structural MRI brain scans. Potentially, these models could be applied during routine clinical examinations to detect deviations from healthy ageing, including early-stage neurodegeneration. This could have important implications for patient care, drug development, and optimising MRI data collection. However, existing brain-age models are typically optimised for scans which are not part of routine examinations (e.g., volumetric T1-weighted scans), generalise poorly (e.g., to data from different scanner vendors and hospitals etc.), or rely on computationally expensive pre-processing steps which limit real-time clinical utility. Here, we sought to develop a brain-age framework suitable for use during routine clinical head MRI examinations. Using a deep learning-based neuroradiology report classifier, we generated a dataset of 23,302 'radiologically normal for age' head MRI examinations from two large UK hospitals for model training and testing (age range = 18-95 years), and demonstrate fast (< 5 s), accurate (mean absolute error [MAE] < 4 years) age prediction from clinical-grade, minimally processed axial T2-weighted and axial diffusion-weighted scans, with generalisability between hospitals and scanner vendors (Δ MAE < 1 year). The clinical relevance of these brain-age predictions was tested using 228 patients whose MRIs were reported independently by neuroradiologists as showing atrophy 'excessive for age'. These patients had systematically higher brain-predicted age than chronological age (mean predicted age difference = +5.89 years, 'radiologically normal for age' mean predicted age difference = +0.05 years, p < 0.0001). Our brain-age framework demonstrates feasibility for use as a screening tool during routine hospital examinations to automatically detect older-appearing brains in real-time, with relevance for clinical decision-making and optimising patient pathways.

Attention-guided deep learning for gestational age prediction using fetal brain MRI.

Magnetic resonance imaging offers unrivaled visualization of the fetal brain, forming the basis for establishing age-specific morphologic milestones. However, gauging age-appropriate neural development remains a difficult task due to the constantly changing appearance of the fetal brain, variable image quality, and frequent motion artifacts. Here we present an end-to-end, attention-guided deep learning model that predicts gestational age with R2 score of 0.945, mean absolute error of 6.7 days, and concordance correlation coefficient of 0.970. The convolutional neural network was trained on a heterogeneous dataset of 741 developmentally normal fetal brain images ranging from 19 to 39 weeks in gestational age. We also demonstrate model performance and generalizability using independent datasets from four academic institutions across the U.S. and Turkey with R2 scores of 0.81-0.90 after minimal fine-tuning. The proposed regression algorithm provides an automated machine-enabled tool with the potential to better characterize in utero neurodevelopment and guide real-time gestational age estimation after the first trimester.

Mitigating site effects in covariance for machine learning in neuroimaging data.

To acquire larger samples for answering complex questions in neuroscience, researchers have increasingly turned to multi-site neuroimaging studies. However, these studies are hindered by differences in images acquired across multiple sites. These effects have been shown to bias comparison between sites, mask biologically meaningful associations, and even introduce spurious associations. To address this, the field has focused on harmonizing data by removing site-related effects in the mean and variance of measurements. Contemporaneously with the increase in popularity of multi-center imaging, the use of machine learning (ML) in neuroimaging has also become commonplace. These approaches have been shown to provide improved sensitivity, specificity, and power due to their modeling the joint relationship across measurements in the brain. In this work, we demonstrate that methods for removing site effects in mean and variance may not be sufficient for ML. This stems from the fact that such methods fail to address how correlations between measurements can vary across sites. Data from the Alzheimer's Disease Neuroimaging Initiative is used to show that considerable differences in covariance exist across sites and that popular harmonization techniques do not address this issue. We then propose a novel harmonization method called Correcting Covariance Batch Effects (CovBat) that removes site effects in mean, variance, and covariance. We apply CovBat and show that within-site correlation matrices are successfully harmonized. Furthermore, we find that ML methods are unable to distinguish scanner manufacturer after our proposed harmonization is applied, and that the CovBat-harmonized data retain accurate prediction of disease group.