Brain Informatics

The detection of small and subtle lesions in high-resolution 3D volumes is a highly relevant, yet far from solved task in biomedical imaging. We here address a specific task in detecting certain types of epileptogenic lesions through our novel semi-supervised spatially context aware transformer (SpyCAT) approach to anomaly detection. SpyCAT is modeling-based in the sense that it builds on specific assumptions that constitute what is normal and what constitues relevant deviations from normality. We explicitly use these assumptions to justify the inductive bias of our anomaly detection approach. The resulting SpyCAT system is patch-based and uses a transformer architecture to process discrete tokens obtained from a vector quantizing variational autoencoder, which produces counterfactual patches through full 3D convolutions of each patch. We evaluate our approach on the grounds of point-annotations of two subtypes of epileptogenic lesions, using validation measures that build on the Metrics Reloaded framework, showing that SpyCAT can reliably identify and localize the lesion types under consideration, and outperforms state-of-the-art reference methods.

Subcortical brain alterations are a key feature of dementia disease progression. Machine learning (ML) has been applied widely to MRI-based brain features in dementia, where performance depends on the model choice, training data size, and input feature characteristics. Most studies compare ML models using a single training sample size. Here, we evaluate the sample-size efficiency of ML models based on subcortical gross volume and vertex-wise shape features for dementia stage classification using 2,511 samples in the Alzheimer's Disease Neuroimaging Initiative (ADNI). Learning curves were generated for dementia vs. cognitively normal controls (CN), dementia vs. mild cognitive impairment (MCI), and MCI vs. CN across increasing training sample sizes. Classification performance improved when increasing sample size for all models, with late- fusion models consistently achieving the highest performance, and Logit-TVL1 outperforming the other shape-based models. Learning curve analysis showed that classification performance was driven by the training sample size and the magnitude of anatomical group differences, and can be used to optimize future model selection tasks in dementia and other brain disorders.

INTRODUCTION: The digital clock drawing test (dCDT) is a cognitive screening tool capturing high-resolution pen-movement data. Existing approaches for classifying cognitive impairment from dCDTs rely on selected features or image-based methods. We propose representing dCDTs as structural networks to classify cognitive impairment and characterize spatial organization in clock drawings. METHODS: Weighted networks were constructed from 3,362 Framingham Heart Study participants, with and without cognitive impairment. Network representations were generated separately for command and copy conditions, with nodes representing pre-defined clock components (digits, hands, clock face) and edges capturing pairwise spatial relationships between components. Random forest models and graph convolutional networks were trained to predict cognitive impairment from the networks. Models were benchmarked against demographics-only and established summary feature baselines. RESULTS: Network-based models achieved AUC values comparable to the established summary feature baseline across command-only and copy-only conditions. Differences in spatial organization between the cognitively intact and impaired groups were greatest in the upper-right clock region, involving digits 1 and 2, the clock hands, and the surrounding clock face. Differences between the command and copy networks were larger among cognitively impaired participants. DISCUSSION: The proposed network representations provide an objective, scalable, and flexible framework for representing clock drawings for use in classification models. dCDT networks matched the predictive performance of established summary feature-based approaches and identified clock regions where spatial organization differed by cognitive status. After external validation, this approach has the potential to be incorporated within a clinical workflow to support automated and interpretable cognitive screening.

The Alzheimer's Disease Neuroimaging Initiative (ADNI) is widely used to train machine learning models for Alzheimer's disease, yet whether it provides consistent ground truth for predictive modeling has not been systematically tested. In this paper, we showed that ADNI contains three interacting sources of bias with direct implications for machine learning: (a) diagnostic label inconsistency, (b) technical measurement drift, and (c) longitudinal survivor bias. A substantial proportion of cases, particularly within intermediate stages, fall outside ADNI's own diagnostic thresholds. MRI field strength and evolving processing pipelines introduce significant technical variability in hippocampal volume, while cohort survivor bias arising from differential retention of participants across phases further distorts longitudinal estimates of disease progression. These findings indicated that ADNI does not provide the stable, internally consistent labels often required in machine learning applications. We proposed a practical framework for diagnostic validation, feature harmonization, and cohort accounting, offering guidance for building more robust and biologically meaningful predictive models from large-scale neuroimaging cohorts.

Accurate stroke lesion segmentation is essential for large-scale neuroimaging studies, yet manual delineation remains labor-intensive, and existing automated methods often struggle to generalize across imaging protocols and stages of recovery. We developed MAESTRO, a deep learning framework for automated lesion segmentation across the stroke recovery continuum using T1-weighted (T1) MRI alone. We hypothesized that combining a transformer-based architecture with an image augmentation strategy would improve segmentation accuracy and robustness under heterogeneous imaging conditions. T1 MRI scans and expert-traced lesion masks from 955 stroke participants across 33 international cohorts were used to train and evaluate MAESTRO within the open-source nnU-Net framework. Performance was evaluated on a held-out test set using spatial and volumetric agreement metrics. An exploratory human-in-the-loop (HITL) evaluation compared correction of MAESTRO-generated segmentations with manual tracing from scratch. MAESTRO achieved the strongest performance across several evaluated model configurations, providing the most accurate lesion localization and lesion volume estimates (median Dice = 0.686; Pearson r = 0.861; ICC = 0.792). Segmentation performance was sensitive to lesion size and stroke chronicity but remained robust across diverse imaging conditions. Additionally, using a HITL workflow to correct MAESTRO segmentations reduced annotation time by 47.4% compared to manual tracing while improving accuracy relative to both automated and manual workflows. MAESTRO is publicly available to enable robust, automated stroke lesion segmentation from T1 MRI. When combined with human review and correction, MAESTRO offers a practical approach for generating standardized, high-quality lesion annotations, helping reduce a major practical barrier to large-scale stroke imaging studies.

Stroke remains one of the leading causes of disability and mortality worldwide, where timely and accurate diagnosis is critical for guiding treatment and improving patient outcomes. However, a global shortage of trained clinicians and radiologists continues to limit rapid and reliable interpretation of neuroimaging, particularly in resource-constrained settings. Artificial intelligence (AI) has emerged as a promising solution to this challenge by enabling efficient analysis of medical images. Here we present an Integrated Stroke Diagnosis System for MRI (ISDS-MRI), a unified framework that leverages graph neural networks and sequence-specific feature modeling for comprehensive ischemic stroke analysis. This framework is designed to detect ischemic stroke, segment lesions, and estimate lesion volume from multi-sequence MRI data, while accommodating incomplete combinations of MRI sequences. To ensure generalizability, we evaluate our approach across multiple publicly available MRI datasets and introduce a newly curated dataset, BGD-MRIS, comprising 532 MRI scans from three hospitals in Bangladesh. This newly curated dataset provides a multi-center MRI cohort from a resource-constrained setting, offering an additional test bed for evaluating stroke AI across heterogeneous clinical imaging protocols. Experimental results demonstrate that ISDS-MRI achieves a Dice score of 0.725 for lesion segmentation, a AUC of 0.962, and a lesion volume estimation relative error of 8.4%, outperforming comparison methods by 3.2% in Dice score and 2.6% in detection performance, while reducing volume estimation relative error by 1.9%. These results highlight the robustness and clinical potential of ISDS-MRI for scalable and comprehensive stroke diagnosis from MRI.

Cerebral microbleeds (CMBs) are established imaging biomarkers of cerebral small vessel disease and are a defining feature of cerebral amyloid angiopathy (CAA), yet their automated detection in susceptibility-weighted imaging (SWI) remains challenging due to high false-positive rates from vessel cross-sections, iron and calcium deposits, and other hypointense mimics. We present a fully automated, three-stage cascade pipeline that combines subject-adaptive unsupervised candidate generation with two successive lightweight 3D ResNet classifiers, trained with only human-in-the-loop quality-assurance (QA) labels (yes/no per candidate) rather than dense voxel-wise segmentation masks. The candidate generation stage is performed by fitting a Gaussian Mixture Model (GMM) to each subjects SWI intensity histogram to define an adaptive low-intensity threshold, followed by anatomical masking to exclude physiologically irrelevant regions (image edges, ventricles/CSF/choroid plexus, and cerebellum), and filters candidates by size and sphericity. The model was trained and evaluated across a nested 3x5-fold cross-validation on N = 30 subjects from a publicly available labeled microbleed dataset and a CAA cohort (11,424 CMB candidate lesions) with data augmentation during training. Stage A classifies all geometric candidates as CMB or non-CMB and Stage B refines the predicted positives to suppress false positives (cascade AUC = 0.9587, sensitivity = 0.712, specificity = 0.975, PPV = 0.676, F1 = 0.693). The cascade reduces Stage A false positives by 76.8% (888/1,157 false positives eliminated) while retaining competitive sensitivity. Inference was performed on 141 SWI scans, detecting a mean 40.3 CMBs per scan and being preferred for use in 85% of high CMB cases, as evaluated by a blinded neurologist. The inference pipeline outputs binary CMB segmentation NIfTI images and radiologist-ready QA visualizations.

Analytical variability in neuroimaging pipelines contributes to concerns about reproducibility in the field. In structural MRI, different segmentation tools produce discrepant morphometric estimates that may influence downstream analyses, such as predictive modeling. We tested whether integrating several segmentation pipelines improves brain age prediction, and characterized the spatial and demographic structure of pipeline differences across several datasets. T1-weighted scans from five open-access datasets were processed with four widely-used structural segmentation pipelines. Brain age models were trained using single-pipeline features and compared with multi-pipeline aggregation strategies. Inter-pipeline variability was assessed across shared subcortical structures and examined in relation to age and sex. Integrating features across distinct segmentation frameworks improved predictive performance relative to individual pipelines, whereas aggregation within closely related software versions provided limited benefit. Variability was spatially structured and volumetric measures were often systematically associated with age and sex. These results suggest that segmentation differences reflect structured, demographically sensitive variation rather than random noise, and that multi-pipeline feature integration can enhance robustness in neuroimaging-based prediction.

Explainability methods applied to deep learning models for Alzheimer's disease neuroimaging produce attribution maps that vary substantially across methods and architectures, yet no validated quantitative framework exists for determining which method most faithfully localises attribution signal within established AD biomarker anatomy at the individual subject level. Existing validation approaches rely on group-level comparisons or qualitative visual inspection, leaving individual-level biomarker alignment uncharacterised. We introduce the Biomarker Fidelity Score (BFS), a quantitative tool measuring spatial overlap between individual-level 3D explainability attention maps and atlas-registered AD-relevant neuroimaging ROIs across thirteen anatomically defined structures including hippocampus, entorhinal cortex, amygdala, and parahippocampal gyrus. Five explainability methods (GradCAM++, Integrated Gradients, DeepSHAP, LRP, ScoreCAM) were benchmarked across three volumetric architectures (3D ResNet-18, DenseNet-121, Swin-UNETR) on 327 balanced ADNI-3 subjects. Integrated Gradients achieved the highest BFS across all architectures while GradCAM++ consistently showed the lowest biomarker alignment (all p<0.001, Friedman test). The complete BFS pipeline replicated these rankings without retraining on 207 independent OASIS-3 subjects, with maximum absolute difference of 0.0005 across all fifteen method-architecture combinations and Spearman rank correlation of 0.964 between cohort rankings. By offering an externally validated, individual-level, biomarker-grounded quantitative standard, BFS equips clinicians and AI developers with practical guidance for selecting trustworthy explainability methods in AD neuroimaging.

The choroid plexus (ChP) is a highly vascularized structure located in the brain ventricles that plays important roles in multiple central nervous system functions. ChP enlargement has been implicated in many neuropsychiatric conditions such as multiple sclerosis, depression, schizophrenia, and Alzheimer's disease. However, limitation in the accuracy of the current segmentation tools highlight the need for more reliable methods to quantify ChP volume in healthy and clinical human populations. The shape and size of the ChP vary drastically from person to person, and currently there are no large ChP datasets which allow comprehensive training of segmentation models. Here we introduce DataPlex, a collection of 700 structural MRI brain images where the lateral ventricle ChP has been manually labeled and checked by expert human raters. DataPlex is balanced and representative across a wide range of scanning parameters, demographics, and clinical profiles, and subject-level information will be available for each labeled image. DataPlex will be open source to support the creation of reliable segmentation tools for the human lateral ventricle ChP.

Objective: Accurate volumetric analysis of the brain and cerebrospinal fluid (CSF) is essential for monitoring hydrocephalus, a significant pediatric neurological condition. While computed tomography (CT) provides high-quality volumetric assessment, its associated ionizing radiation poses risks, especially for children. Low-field magnetic resonance imaging (LF-MRI) offers a safer and more accessible alternative, particularly in resource-constrained settings. However, its lower resolution and increased susceptibility to structural distortions make accurate segmentation challenging. This study aims to demonstrate that reliable volumetric measurements can be obtained from LF-MRI that are comparable to CT, enabling safer and more frequent monitoring of infants with hydrocephalus. Approach: We propose EnSegNet-Cross, a cross-modality, enhancement-aware segmentation network for brain volume analysis using LF-MRI. The framework leverages high-fidelity CT data during training but requires only LF-MRI during inference. At the core of the framework is a novel cross-modal topological penalty designed to minimize discrepancies between predicted LF-MRI and CT structures. A central contribution is the integration of a three-dimensional topological loss based on persistent homology, which penalizes topological discrepancies in CSF regions, specifically CSF holes formed by enclosed brain parenchyma, between CT and LF-MRI segmentations. Incorporating these structural priors facilitates generalization across heterogeneous clinical cases while eliminating the need for CT data during inference, resulting in more anatomically coherent and topologically faithful segmentations. Main Results: On a curated cohort of infants with hydrocephalus who had paired LF-MRI and CT scans, including cases with infectious and non-infectious causes, EnSegNet-Cross consistently outperformed state-of-the-art machine learning alternatives. It achieved the highest Dice score of 0.8532 plus/minus 0.03 and Volume Score of 0.9318 plus/minus 0.03. The method also demonstrated robust performance in challenging cases with confounding factors, achieving a Dice score of 0.8340 plus/minus 0.03 and a Volume Score of 0.9111 plus/minus 0.05. By leveraging CT-derived topological priors, EnSegNet-Cross successfully handled anatomically complex scenarios in which conventional models failed. Significance: EnSegNet-Cross provides a reliable and interpretable solution for brain and CSF segmentation, particularly in complex cases of hydrocephalus. This study demonstrates that high-fidelity volumetric estimates can be achieved using only LF-MRI, facilitating frequent, radiation-free monitoring. By bridging the fidelity gap between low-quality LF-MRI and high-resolution CT through clinically grounded enhancement and topological supervision, EnSegNet-Cross offers a robust clinical tool for brain volumetric analysis in infants with hydrocephalus using LF-MRI.

Background. Deep-learning models predict mild cognitive impairment (MCI)-to-Alzheimer's disease (AD) conversion from structural MRI with high accuracy. However, they are typically validated within a single cohort and judged on discrimination alone. Whether their risk scores are biologically grounded, and whether they generalise to independent data, remains unclear. Methods. We applied the ADNI-trained Temporal Adaptive Fusion Network (TAF-Net), without retraining, to 101 MCI participants from OASIS-3 (25 converters, 76 stable) and tested whether its conversion-risk scores were grounded in independent structural, functional, and cognitive markers of AD. Regional atrophy rates were derived from longitudinal FreeSurfer, cognition from longitudinal MMSE and CDR-Sum-of-Boxes, and baseline resting-state functional connectivity from fMRIPrep, in structural and functional subsamples of 41 and 40 participants. Associations used rank-based statistics with false-discovery-rate correction. Results. Higher TAF-Net risk tracked faster atrophy in medial-temporal AD-signature regions but not in AD-spared cortex, an anatomically specific coupling that survived adjustment for global atrophy. In external validation, risk discriminated converters (AUC = 0.72), comparable to native atrophy and strongly concordant with it; atrophy statistically accounted for the model's prognostic signal. Discrimination transferred but calibration did not: the two lowest tertiles of risk were assigned near-zero probability yet converted at 15%. Risk also tracked the multi-year rate of cognitive decline and, at baseline, was associated with reduced within-network functional-connectivity integrity, concentrated in salience and default-mode hubs; longitudinal functional analyses were underpowered. Conclusions. A conversion model trained on one cohort produced risk scores that, in an independent cohort, were grounded in the structural, functional, and cognitive hallmarks of Alzheimer's disease, supporting biological validity and external generalisation. The score, however, largely re-expresses the neurodegenerative substrate captured by structural atrophy. Rank ordering transferred across cohorts but absolute risk did not, so the score requires recalibration before its values can be interpreted as individual probabilities.

Neuroimaging research focusing on subcortical brain regions showed that they play a role in a wide range of cognitive functions and associated their structural alterations to various psychiatric disorders. Methods to analyse such structures were developed to observe changes, not simply in terms of volumes, but in terms of surfaces, which are able to detect subtle and local changes in shape and geometrical configuration. Such advanced analyses have however been largely restricted to command line environments with relatively limited access to Python users or researchers with low technical expertise. We present SubCortexMesh as a user-friendly toolbox which covers automated surface estimation from popular subcortical volume segmentations (FreeSurfer and the Functional Magnetic Resonance Imaging of the Brain Software Library (FSL)), computes shape-related vertex-wise metrics (thickness, surface area and curvature) for whole cohorts and includes statistical analyses. This is all done inside Python, automatically computing all subjects of a given preprocessed directory, with the explicit intent to minimise steps and manual coding required from the users. SubCortexMesh includes statistical tools which allow conventional random field theory-based cluster analyses on native subject metrics, standardised within common surface templates, thus containing a whole workflow necessary to run an up-to-date shape-wise subcortical analyses in one package.

Background: Quantitative MRI (qMRI) provides voxel-wise measurements of tissue properties related to myelin, iron and water content, making it a powerful tool for studying brain aging and microstructural alterations in vivo. However, conventional spatial smoothing can introduce partial-volume effects and blur tissue boundaries, potentially affecting both statistical sensitivity and anatomical specificity. Several tissue-specific smoothing strategies have been proposed to address these limitations, yet their relative impact on voxel-wise statistical analyses remains insufficiently characterized. The present study aims (i) to systematically compare three tissue-specific smoothing strategies: a linear tissue-weighted compensated approach (TWS), a generalized version of nonlinear tissue-masked compensated smoothing approach (gTSPOON), and an intensity-weighted edge-preserving approach based on the Smallest Univalue Segment Assimilating Nucleus smoothing (SUSANs), and (ii) to investigate how smoothing approaches interact with statistical inference frameworks by comparing parametric and non-parametric voxel-wise analyse. Methods: Analyses were performed on a publicly available lifespan qMRI dataset comprising 138 healthy participants (19-75 years) and quantitative maps of MTsat, PD, R1, and R2*. The generalized TSPOON (gTSPOON) method was implemented using tissue-specific masks derived from probabilistic tissue segmentation. All three smoothing approaches (TWS, gTSPOON and SUSANs) were parameterized to achieve comparable nominal spatial smoothing. Age-related effects were investigated separately in GM and WM using voxel-wise general linear models following a previously published framework. Statistical inference was assessed using multiple complementary approaches, including parametric Random Field Theory (RFT), under both stationarity and non-stationarity assumptions, as well as non-parametric permutation-based inference. In addition to conventional thresholded statistical parametric maps, voxel-wise log-likelihood (LL) maps were computed to quantify general linear model (GLM) goodness-of-fit independently of statistical thresholding. Bland-Altman analyses and spatial agreement metrics were subsequently used to compare smoothing strategies. Results: TWS and gTSPOON produced highly similar spatial distributions of age-related effects across all qMRI parameters and tissue classes. However, TWS consistently yielded a larger number of significant voxels and clusters, reflecting slightly higher sensitivity, from slightly wider effective smoothness and reduced RESEL counts. By contrast, SUSANs generated substantially fewer significant voxels and clusters, associated with approximately half the effective smoothness and a markedly larger number of RESELs. Despite these differences in statistical sensitivity, voxel-wise LL analyses revealed distinct anatomical preferences for each smoothing strategy. TWS provided the best model fit predominantly within GM, whereas gTSPOON showed superior performance in homogeneous WM regions. Conversely, SUSANs achieved the highest LL values at GM-WM interfaces, particularly within sulcal and gyral transitions, indicating improved preservation of sharp anatomical gradients. These spatial patterns were consistently observed across MTsat, PD, R1 and R2* maps. Comparisons across stationary and non-stationary RFT assumptions revealed only minor differences, while non-parametric inference produced highly concordant results, indicating that the primary source of variability originated from the smoothing procedure itself rather than the inference framework. Conclusions: Tissue-specific smoothing strategies substantially influence both statistical sensitivity and voxel-wise model fitting in qMRI analyses. While TWS and gTSPOON provide highly consistent results, the edge-preserving SUSANs approach preferentially enhances model fit at tissue boundaries. Importantly, voxel-wise log-likelihood mapping revealed that no smoothing strategy is uniformly optimal throughout the brain; instead, each method exhibits anatomically preferential regions where model fit is maximized. These findings suggest that smoothing should be viewed as a region-dependent optimization problem and highlight voxel-wise LL mapping as a principled framework for selecting or developing adaptive smoothing strategies tailored to specific neuroanatomical structures and biological processes, including age-related brain changes.

Neuroimaging studies that pool data across clinical sites often suffer from site effects --- variability in imaging measures that arises from technical heterogeneity across sites as opposed to true biological signal. While numerous harmonization methods have been proposed to remove site effects from imaging features, less attention has been placed on how to incorporate harmonization models into common machine-learning pipelines. We demonstrate that current approaches for integration either suffer from data leakage, fail to fully remove site effects from the target data, or attenuate true biological associations during the harmonization process. To address these issues, we propose Multiple Imputation for Removing Technical Heterogeneity (MIRTH), which uses imputed outcomes to harmonize the test data. We benchmark MIRTH's performance using both simulated and real-world volumetric data from the Alzheimer's Disease Neuroimaging Initiative and the Baltimore Longitudinal Study of Aging, demonstrating that MIRTH can achieve high predictive accuracy while avoiding inflated performance when the outcome is imbalanced across clinical sites.

Deep-learning-based segmentation algorithms have gained considerable accuracy for processing biological images. In particular, the introduction of large foundation models, novel architectures, and semantically varied datasets now allows for deployment of state-of-the-art models for clean image cohorts with limited re-training or, in the best of cases, in an out-of-the-box fashion. Biological imaging, however, is liable to corruptions that can hinder their deployment. While some methods document their robustness to the most common corruptions, a systematic robustness analysis of the state of the art to the expansive gamut of corruptions in biological imaging remains to be done. We perform this benchmarking by simulating 36 corruption types with varying degradation severity on images sampled from 30 different datasets. Our benchmark accounts both for the variety in biological images and the nature of corruptions. Among other things, our study reveals that performance on clean images does not correlate with overall robustness to image corruptions. In fact, we find that a decade-old method, StarDist, is more robust than many of its more recent foundation-model-based counterparts. We also show in a dedicated representation analysis that the performance of segmentation models collapses in the early layers of the encoding phase.

Background: Ultra-low field (ULF) magnetic resonance imaging (MRI) offers accessible point-of-care neuroimaging, yet its capability to support multivariate network analyses remains understudied. Methods: We systematically evaluated the feasibility and reliability of Morphometric Similarity Networks (MSN) and Morphometric Inverse Divergence (MIND) networks derived from paired high-field (HF, 3T/1.5T) and ULF (64mT) scans in a primary cohort(N=23) and an independent replication cohort (N=19). We tested the impact of super-resolution processing, cortical parcellation granularity (Desikan-Killiany vs. Destrieux), and mesh resolution (fsnative vs. fsaverage5) on edge-level cross-scanner agreement (Lin's concordance correlation coefficient, CCC) and subject-level identifiability. Results: MIND networks demonstrated higher edge-level HF-ULF agreement (mean CCC = 0.95) and ULF reproducibility (mean CCC = 0.98) compared to MSNs (mean CCC = 0.86-0.87 and 0.91-0.94, respectively). In contrast, MSNs yielded higher subject-level differential identifiability across field strengths due to a broader distinction between within- and between-subject similarity. Reconstructing MIND networks on native high-resolution meshes (fsnative) maximised cross-scanner agreement, whereas coarser meshes and finer cortical parcellations enhanced individual network identifiability. Conclusions: Structural similarity networks can be reliably constructed from ULF MRI data. Optimal analytic choices depend on study objectives: MIND on native meshes maximises cross-scanner stability, whereas MSNs excel at preserving individual uniqueness, paving the way for globally scalable connectomic research.

There is increasing demand for quantitative measurements in neuroimaging research, including absolute quantification of regional myelin density. Fast whole-brain macromolecular proton fraction (MPF) imaging enables acquisition and reconstruction of quantitative maps of MPF, a biomarker of myelin, and has been used in many research applications. To date, no standard protocols have been published for parcellating MPF maps. FreeSurfer is a widely used software package for automated brain parcellation. It is designed for use with high-resolution T1-weighted anatomical images, typically acquired with an MPRAGE sequence. MPF maps inherently provide high contrast between white and gray matter and can potentially be used as input images for parcellation, enabling simultaneous quantitative tissue characterization and volumetric assessment. However, it is unclear how the use of MPF maps as input images with FreeSurfer software affect reliability and repeatability of regional MPF and volume estimates. We evaluated three FreeSurfer parcellation workflows for this purpose. The workflows differed in the amount of neuroimaging data required and computational intensity. MPF and MPRAGE data were acquired in two separate sessions for 11 adults. Reliability was evaluated using mean relative differences in estimates, Bland-Altman analysis, and intra-class correlation coefficients (ICCs). Repeatability was assessed using within-subject coefficients of variation (CVws). All three workflows produced similarly high within-subject repeatability across scans. However, reliability in regional MPF estimates was lower in gray matter than in white matter for workflows that used MPF maps as input. Workflows that use MPF maps as FreeSurfer input may be adequate for estimating mean MPF in GM and WM of cortical parcels and in subcortical regions. However, the MPRAGE-based workflow is recommended when reliable individual-level estimates or volume estimates are required.

Alzheimer's Disease (AD) remains a leading cause of cognitive decline with no known cure, motivating the development of therapies that slow neurodegeneration. Rapamycin, an FDA-approved inhibitor of the mammalian target of rapamycin (mTOR) pathway, has demonstrated promising anti-aging and neuroprotective effects. However, characterizing its treatment effects and identifying the biological factors that contribute to treatment response remain challenging because of complex interactions across multiple biological systems and the limited availability of patient data. In this work, we propose a three-stage multimodal deep learning framework called TreatmentFormer for predicting rapamycin treatment status from heterogeneous biomedical data including both brain imaging data and tabular data (e.g., microbiome profiles, blood-based biomarkers, cerebral blood flow measurements, and clinical variables (e.g., gender, age, and body mass index)). First, a Random Forest-based feature selection module reduces noise in high-dimensional tabular data while preserving representation across modalities. Second, modality-specific encoders map imaging and tabular inputs into a shared latent space via self-supervised contrastive learning, enabling alignment across modalities. Finally, a transformer-based architecture integrates these representations to capture cross-modal interactions and perform treatment classification. Evaluated on a cohort of 23 participants with baseline and post-treatment timepoints, TreatmentFormer achieves an average prediction accuracy of 71.25\% across 10 independent test runs. Despite the challenges of small sample size and heterogeneous data, the model demonstrates stable and consistent performance. Post hoc SHAP-based feature analysis further identifies key biomarkers associated with treatment response, particularly within blood-based and inflammatory modalities. These findings demonstrate that combining feature selection with multimodal representation learning provides a promising and robust approach for modeling treatment effects in small-sample biomedical studies. Importantly, this framework may have significant implications for clinical research and medical applications by identifying the biological features and quantitative measurements that drive individual responses to rapamycin. Such insights could facilitate the development of predictive biomarkers, improve patient stratification, and ultimately inform future approaches to AD diagnosis and therapeutic development.

Automatic segmentation of medical images could accelerate clinical and research workflows, yet existing tools are rarely compared independently on shared benchmarks, making it difficult to assess genuine progress. This is particularly consequential for limb muscle segmentation in magnetic resonance imaging (MRI), which underpins volumetric analysis, radiomics, and fat fraction quantification used as biomarkers in neuromuscular disease -- applications where segmentation errors can directly affect interpretation. Despite the availability of multiple open-source segmentation tools spanning diverse architectures, no independent head-to-head comparison has appeared in the literature. We address this gap by evaluating eight tools, six of which run independently, and the other two of which are meant to be auxiliary algorithms once muscles have been somehow initially labeled. We evaluated these tools on three-dimensional MRI volumes across three base datasets and then later against derived datasets, assessing both quantitative metrics and qualitative usability. Our results reveal substantial performance variation across methods and datasets, with many methods showing reduced accuracy on pathological cases. Domain-specific models trained on large datasets consistently outperformed foundation models and newer general-purpose architectures. Our results reveal practical trade-offs between accuracy, generalizability, and ease of use that are critical for clinical adoption, while raising concerns for deployment on underrepresented populations and pathologies.