Brain Informatics

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.

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.

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: 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.

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.

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.

Stroke remains a leading cause of mortality and long-term disability worldwide, yet rapid diagnosis is often limited by the shortage of trained radiologists, particularly in resource-constrained settings. Automated analysis of CT imaging offers a potential solution, but existing methods often struggle to achieve clinically generalisable performance while jointly addressing multiple diagnostic tasks. Here we present the Intelligent Integrated Stroke Diagnosis System IISDS, an end-to-end deep learning framework built upon StrokeGNN, a graph-based architecture that integrates 3D contextual feature extraction with U-Net-based 2D lesion segmentation to enable comprehensive stroke analysis from non-contrast CT scans. IISDS performs stroke subtype classification, lesion segmentation and lesion volume estimation within a unified pipeline. To develop and validate the system, we collected and curated BGD-ISD through a collaboration between AI researchers, neurologists, radiologists and clinicians, resulting in a large multi-centre dataset comprising 1,507 CT scans from 597 stroke cases acquired across six hospitals and medical centres in Bangladesh. Across BGD-ISD and multiple publicly available datasets, IISDS achieves state-of-the-art performance on all tasks, improving segmentation accuracy by [&ge;]0.011 Dice score, reducing lesion volume estimation error by [&ge;]0.3 average symmetric surface distance (ASSD), and increasing classification performance by [&ge;]0.018 area under the receiver operating characteristic curve (AUC) compared with existing approaches. These results demonstrate the potential of graph-based deep learning to enable clinically generalisable, automated and scalable stroke diagnosis from CT imaging, supporting rapid clinical decision-making, particularly in healthcare environments with limited access to expert radiological interpretation.

Background: Hippocampal sclerosis (HS) is a common cause of drug-resistant focal epilepsy (DRFE) and amenable to neurosurgical treatment. Detection relies on MRI but can be challenging. 7 Tesla (T) ultra-high field MRI and automated MRI post-processing tools have independently been shown to improve radiological diagnosis of HS. However, combining these approaches remains underexplored. This study evaluated whether AID-HS, a tool for HS detection developed using 3T MRI, generalises to 7T MRI data. Methods: We collated a dataset of paired 3T and 7T T1-weighted MRI from four epilepsy centres, including 23 patients with HS, 39 healthy controls, and 23 individuals with focal cortical dysplasia as disease controls. Histopathology served as the gold standard for defining HS where available (n=7), otherwise radiological findings (n=16). AID-HS was applied to images acquired at both field strengths, and sensitivity and specificity for detection and lateralisation of HS were compared. Additionally, agreement of hippocampal features across 3T and 7T was evaluated. Results: We found no evidence of a difference in performance of AID-HS between 3T and 7T. Sensitivity for detection of unilateral HS was 63% (12/19) at 3T and 68% (13/19) at 7T (McNemar's exact test p=1.0). Specificity in controls was 97% (60/62) at 3T and 100% (62/62) at 7T (p=0.5). Bilateral HS was correctly flagged in 3 of 4 cases using feature-based criteria, with high specificity in controls. Quantitative hippocampal features showed moderate to good agreement across field strengths (ICC 0.70 to 0.98), with small differences observed for volume and thickness estimates. Conclusion: AID-HS provides robust detection and lateralisation of HS across multiple 7T MRI centres, highlighting its potential to enhance lesion detection. Future work is needed to investigate whether models trained on 7T data can leverage the improved image quality for further gains in HS detection performance.

Deep segmentation networks can degrade sharply when an expected MRI sequence is unavailable at inference. We present NeuroMesh, a bottleneck controller that combines a gated recurrent unit (GRU) with a graphconvolutional edge-activation mask, designed to adapt a U-Net-style segmentation backbone to missing input. We evaluate NeuroMesh in a pilot study using a 30-patient subset of the BraTS 2020 benchmark (22 training, 4 validation, and 4 held-out test patients) under a prespecified frozentest protocol. On the frozen test set, NeuroMesh has higher tumor-core and enhancing-tumor Dice than a plain U-Net in most evaluated missing-modality conditions, but wholetumor Dice falls from 0.596 to 0.108 when FLAIR is missing, compared with 0.604 to 0.545 for the plain U-Net. Direct analysis of the predicted edge-activation mask shows negligible change across modality-availability conditions. A parameter-light static-gating control reproduces the FLAIR failure mode without recurrence, a failure-signal input, or graph-structured machinery. These results do not support the intended interpretation that the trained controller performs input-conditional topology rewiring at the scale of this pilot. Instead, they expose a discrepancy between architectural intent and realized behavior and identify a specific missing-modality failure mode that warrants further investigation. Given the small validation and test sets, the findings are descriptive and do not establish clinical or population-level generalization.

Background: Choroid plexus (CP) volume is an emerging magnetic resonance imaging (MRI) biomarker in various disorders of the central nervous system (CNS). However, clinical translation is hindered by methodological heterogeneity and inconsistent anatomical coverage. Double inversion recovery (DIR) - a sequence providing dual-tissue suppression - is a promising candidate to improve CP segmentation. Methods: The dataset included 93 scans across healthy subjects and individuals with multiple sclerosis (MS), divided into a training set (n = 63), an internal test set (n = 20), and an external test set (n = 10). First, relative CP signal intensity and tissue contrast ratios on DIR were compared against fluid-attenuated inversion recovery (FLAIR) and T1-weighted (T1w) sequences (pre- and post-contrast). Reproducibility of manual CP segmentations was assessed via intraclass correlation coefficients (ICCs). Subsequently, we developed a 3D nnU-Net model for CP segmentation based on manually labeled DIR masks. Model performance was evaluated against manual segmentation using spatial overlap and volumetric error metrics. Finally, we compared our DIR-based model against three publicly available T1w- or FLAIR-based tools by assessing slice-wise volume distributions and voxel-wise density maps. Results: DIR demonstrated the highest CP signal intensity and most consistent tissue contrast among evaluated MRI sequences (p < 0.001). Intra- and inter-rater agreement for manual CP segmentations was robust (ICC = 0.92 and 0.83, respectively). The trained nnU-Net achieved high internal accuracy (Dice = 0.82) independent of scanner, diagnosis, or absolute CP volume, and generalized well to the external test set (Dice = 0.75). Compared to public T1w- and FLAIR-based models, DIR-based approaches (nnU-Net and manual) yielded significantly larger CP volumes (p < 0.01). Axial volume distribution analysis attributed this difference to a distinct bimodal profile in DIR segmentations, more fully capturing the CP inside the temporal horn of the lateral ventricle (p < 0.001 against T1w- and FLAIR-based models). Conclusions: By leveraging the superior tissue contrast of DIR, our nnU-Net model achieves highly accurate CP segmentation that generalizes across scanners and captures the inferior extent of the C-shaped structure often missed by conventional models. This may improve standardization of CP volumetry and allow for more reliable studies in CNS disorders.

To disentangle complex fiber configurations that remain challenging for diffusion MRI tractography, insights might be gained from microscopy tractography. Indeed, by precisely following small white matter (WM) fascicles invisible at the resolution of diffusion MRI, microscopy tractography can help explain how fiber populations are organized at the finest scales. Serial optical coherence tomography (S-OCT) is an imaging modality relying on the intrinsic contrast of a sample. When applied to brain tissues, the S-OCT contrast is primarily driven by the myelin reflectivity. Due to its high resolution, on the order of microns, and its 3D nature, S-OCT offers promise for studying WM connections at the microscale. However, while other microscopy imaging modalities have been shown to enable tractography, whether the reflectivity contrast from S-OCT supports the reconstruction of long-range WM fascicles at the microscale remains unknown. Furthermore, there is a gap in the literature regarding how an ideal microscopy tractography algorithm should behave with respect to the choice of tractography algorithm, tracking maps definition and microscale orientation distribution functions (ODF) estimation. In this work, we describe a tailored approach to reconstruct WM fascicles at the microscale from S-OCT acquisitions. We improve microscale orientation distribution functions (ODF) estimation by implementing a sliding-window formulation allowing the estimation of ODF at S-OCT resolution, and use apodized Dirac delta functions for reducing unwanted interference. We validate our approach on a simulated microscopy-like FiberCup dataset, and show that using multiscale Frangi filters for estimating ODF outperforms structure tensor analysis. We also show that particle filtering tractography with anatomical constraints enables targetted, region-to-region tractography, and outperforms standard deterministic or probabilistic tracking approaches. We further demonstrate our method on a whole mouse brain S-OCT reconstruction at 10 m by reconstructing the thalamocortical white-matter projections. Overall, our results show that S-OCT tractography recovers fine white matter fascicles visible at the microscale, and that these connections are supported by viral tracing experiments from the Allen Mouse Brain Connectivity Atlas. Moreover, this work shows the first ODF estimation and fully-3D probabilistic particle filtering tractography of the mouse brain from S-OCT reconstructions at 10 m isotropic resolution.

Purpose: Patient identity management is fundamental to healthcare information systems, as identification inconsistencies can compromise patient safety, data integrity, and clinical workflow efficiency. Reliable linkage of medical images acquired across different imaging modalities remains challenging because of variations in image appearance, acquisition geometry, and imaging characteristics. In this study, we developed an automated patient identity verification framework for multimodal medical imaging using deep metric learning and Data-Augmented Domain Adaptation (DADA). Methods: The proposed framework learned modality-invariant patient representations from labeled source-domain data while leveraging unlabeled target-domain data to mitigate cross-modality distribution shifts. Chest radiographs and computed tomography (CT) scout images obtained under routine clinical conditions were retrospectively collected and used for evaluation. Verification performance was assessed using receiver operating characteristic (ROC) analysis, with the area under the ROC curve (AUC) used as the primary performance metric. Results: The proposed framework achieved consistently high verification performance across all evaluation conditions, with AUC values ranging from 0.9997 to 0.9998. Similarity-score distributions demonstrated distinct separation between same-patient and different-patient image pairs despite substantial differences between imaging modalities. Conclusion: These findings indicate that patient-specific anatomical representations can be preserved across heterogeneous imaging domains through metric learning and domain adaptation. The proposed framework may serve as a practical infrastructure component for patient identity management, multimodal data integration, quality assurance, and patient safety applications within healthcare information systems.

1.IntroductionUnderstanding mid-term test-retest reliability and within-subject variability is important for interpreting changes observed in longitudinal and intervention studies. The reliability of resting-state functional magnetic resonance imaging (rs-fMRI) is known to vary across measures and brain regions. However, how reliability differs across functional networks and connectivity-and amplitude-based measures, and whether multi-echo acquisition and processing modify these patterns, remain incompletely characterized. MethodsTwenty-two healthy volunteers underwent two rs-fMRI sessions 15.7 {+/-} 4.0 days apart on a Compact 3T scanner. Multi-echo, middle-echo, and independently acquired single-echo datasets were compared, with multi-echo independent component analysis additionally evaluated as a denoising approach. Functional connectivity (FC) and three amplitude-based measures were evaluated using the Schaefer 400 parcellation. Reliability was systematically assessed using intraclass correlation coefficient (ICC), within-subject standard deviation (wSD), and systematic bias at edge or regional, and network levels. ResultsAcquisition-dependent differences in reliability were generally modest. Multi-echo acquisition and processing increased functional connectivity strength and the magnitude of amplitude-based measures and improved inferior cortical coverage, but these enhancements did not consistently translate into substantially higher ICC or lower wSD. In contrast, reliability showed clear network-dependent differences. FC reliability varied markedly across network pairs and was not explained by connectivity strength alone; pairs involving the default mode and control networks generally showed more favorable profiles than several somatomotor and visual network pairs. Fractional amplitude of low-frequency fluctuations (fALFF) also showed network-dependent reliability, with the most favorable regional reproducibility observed in the default mode and control networks and lower reproducibility in the somatomotor and visual networks. ConclusionThese findings provide practical mid-term reliability benchmarks for rs-fMRI on a Compact 3T scanner and show that measurement stability varies more clearly across measures and functional networks than across acquisition approaches. Key pointsO_LIMid-term test-retest reliability varied more clearly across resting-state measures and functional networks than across acquisition and processing approaches. C_LIO_LIMulti-echo acquisition and processing enhanced functional connectivity strength, amplitude-based signal magnitude, and inferior cortical coverage but did not consistently improve reliability. C_LIO_LIFunctional connectivity strength and fractional amplitude of low-frequency fluctuations showed distinct network-specific reliability profiles, with more favorable reproducibility in default mode and control networks than in several somatomotor and visual networks. C_LI

Traditional fMRI studies rely on predefined task paradigms, where fixed stimulus designs limit the flexibility with which brain-stimulus relationships can be explored. Here, we introduce Reinforcement Learning via Brain Feedback (RLBF), a framework and open-source software package for adaptive stimulus optimization using real-time fMRI. RLBF reverses the conventional direction of inference by using neural responses to guide the exploration of stimulus spaces through reinforcement learning, enabling optimization of predefined brain targets such as regional activity or multivariate neural signatures. The accompanying Python-based software provides a modular framework integrating real-time fMRI data processing, reinforcement learning agents, adaptive stimulus generation, simulation-based testing, and experiment monitoring. Its flexible architecture allows researchers to customize preprocessing pipelines, reward functions, stimulus spaces, and RL strategies for diverse closed-loop neuroimaging applications. We validate the framework in a proof-of-concept study (N=10), demonstrating real-time optimization of a simple visual stimulus space by adapting checkerboard contrast and frequency to maximize primary visual cortex (V1) responses within a single 10-minute fMRI session. RLBF provides an extensible foundation for brain-guided stimulus optimization and enables new approaches for investigating neural specificity, individualized brain-stimulus relationships, and adaptive experimental design.

Despite the growing use of functional near-infrared spectroscopy (fNIRS) hyperscanning to record brain activity simultaneously from interacting individuals in naturalistic settings, most analyses quantify functional connectivity separately for each channel pair. The resulting collection of pairwise estimates is difficult to integrate into a network-level characterization of intra- and inter-brain organization. Here, we present an open, configuration-driven Python toolkit that transforms preprocessed fNIRS hyperscanning time series into functional connectivity graphs. The toolkit constructs a bipartite inter-brain network for each dyad and separate intra-brain networks for each participant, computes node- and graph-level measures, and exports adjacency matrices, edge lists, analysis-ready summary tables, reproducibility metadata, and standardized visualizations. Dataset-specific parameters, including directory structure, participant naming, channel selection, epoch extraction, and edge-retention criteria, are defined in a human-readable YAML configuration file, enabling the same workflow to accommodate differently organized datasets without changes to the source code. We illustrate the pipeline using a representative recording from a mother-infant fNIRS hyperscanning dataset and present the resulting network outputs. The toolkit provides a reproducible framework for moving from pairwise functional connectivity estimates to network-level analyses of dyadic and individual brain organization.

Background: Alzheimer's Disease and Related Dementias (ADRD) is a growing global public health challenge, and caregivers experience high rates of burden, unmet needs, and system failures. These challenges vary by caregiver role and relationship to the care recipient, reflecting the heterogeneous nature of caregiving. Yet prior work has largely studied burden, unmet needs, and system failures as separate domains rather than examining how they co-occur within individual caregivers. Methods: We applied an LLM-based classification framework (Claude 3.5 Sonnet) to 7,198 posts from three ALZConnected caregiver forums (general, spouse/partner, and adult child caregivers), coding each post for burden, unmet needs, and system failures across 9, 12, and 10 categories respectively. We compared expression rates by caregiver role (primary vs. secondary) and relationship to the care recipient (spousal vs. child) and used post-level co-occurrence networks to map how categories cluster within and across domains. Results: Burden was expressed in 89.0% of posts and unmet needs in 93.3%, while system failures appeared in 34.8%. Primary caregivers reported burden more often than secondary caregivers (91.6% vs. 84.7%), while secondary caregivers reported more unmet needs (94.6% vs. 92.5%) and more system failures (37.2% vs. 33.4%). Child caregivers reported higher rates than spousal caregivers across all three domains. Co-occurrence networks showed dense within-domain clustering (density 0.61-0.65) and 84 significant cross-domain connections, with the strongest links between behavioral/safety burden and safety-management needs (21.7% of posts) and between emotional burden and emotional-support needs (20.9%). Conclusion: Burden, unmet needs, and system failures are not independent problems but form interconnected challenge ecosystems that vary by caregiver role and relationship. This suggests caregiver support should be designed around these connected patterns rather than treated as separate, single-domain interventions.

Aging affects individuals at varying biological rates, prompting the development of the Brain Age Index (BAI) to quantify neurobiological health relative to chronological age and disease risk. While structural MRI has dominated brain age prediction, its high cost, immobility, and low temporal resolution restrict its clinical scalability and responsiveness to transient neurophysiological changes. Electroencephalography (EEG) offers a highly scalable, portable, and temporally precise alternative capable of capturing dynamic brain states. However, the transition of EEG-based models to clinical biomarkers is impeded by methodological limitations, including small or biased datasets, inconsistent preprocessing pipelines, and a distinct lack of interpretable machine learning approaches. To address these persistent challenges, this paper presents a comprehensive, open-source, end-to-end pipeline for large-scale EEG-based brain age modeling. Developed using the Temple University Hospital EEG Corpus (TUEG) the largest publicly available resting-state EEG dataset. The pipeline encompasses rigorous data engineering, reproducible preprocessing, and robust feature extraction. Following quality control and subject-level dataset partitioning to definitively prevent data leakage, exactly 41,181 recordings were successfully retained. Two independent feature sets were extracted: the Catch22 time-series characteristics and a comprehensive set of spectral, aperiodic, and non-linear dynamics from the CCS toolbox. The methodology evaluates seven regression models, optimized via Optuna for hyperparameter tuning, and integrates SHAP (SHapley Additive exPlanations) for transparent feature importance analysis. By making this infrastructure publicly available, this work lowers the barrier to entry for large-cohort studies, fostering reproducible development and clinical validation of dynamic brain age biomarkers.

Background: Precise localisation of intracranial electrode contacts is essential for the interpretation of stereoelectroencephalography recordings and planning epilepsy surgery. In current clinical practice, this is typically a manual process, which is time-consuming and prone to variability. Existing automated solutions are often fragmented across multiple tools requiring technical expertise, limiting their adoption in routine clinical workflows. This study presents an open-source extension for 3D Slicer that provides an integrated, user-friendly standalone solution for the direct automatic detection of electrode contacts within a widely used medical imaging platform. Results: The proposed method combines anchor bolt-based initialisation, probabilistic segmentation of electrode structures, and non-linear modelling to precisely track true electrode trajectories. The approach was evaluated on a dataset comprising 78 cases from 73 patients, including 1,078 electrodes with 14,480 contacts. The method achieved high localisation accuracy, with a median (interquartile range) deviation of 0.10 (0.06, 0.15) mm. Only 7/1078 (0.65%) electrodes required manual correction; these specific cases were handled using tools provided within the proposed extension. Conclusions: The presented extension enables fast, accurate, and reproducible electrode contact localisation within a single integrated environment. By combining automation with intuitive user interaction, it significantly reduces processing time while maintaining clinical reliability. The tool's free availability as an extension in 3D Slicer lowers the barrier to adoption and supports the standardisation of workflows across clinical and research centres.

In-vivo examination of neurites to understand microstructural properties of white matter tissue utilizing neurite orientation dispersion and density imaging (NODDI) has shown sensitivity to healthy aging as well as disease biomarkers and status. Neurite density index (NDI), which is a proxy for the amount of neurites, in white matter tissue typically decreases with age. However, orientation dispersion index (ODI), which is a proxy for neurite dispersion or fanning, has been mixed with studies finding both increases and decreases with age. Furthermore, white matter tracts are not uniform and hold its own unique spatial pattern or gradient in microstructural properties. In addition to the spatial pattern of the microstructural property, age-related effects have also shown spatial patterns with stronger age effects in the medial, anterior, and dorsal portions of white matter tissue. However, spatial gradients along cardinal axes within an individual's tract have yet to be examined with age in an adult lifespan sample. The current aim of the study was to examine whether average and spatial gradients of neurite microstructural properties within tracts related to the cortico-striato-pallido-thalamic (CSPT) loop were age-sensitive. An adult lifespan sample aged 20-90 years old was recruited from the Dallas-Fort Worth metroplex (N = 104, 62% females) as part of the Dallas Area Longitudinal Lifespan Area Study (DALLAS). Participants completed an MRI session that included a structural T1-weighted image as well as multi-shell diffusion weighted imaging (MS-DWI). MS-DWI were preprocessed and tracts of interest related to the CSPT loop were obtained using probabilistic tractography. For most tracts, a significant inverted-U association with age was found for both average NDI and ODI. Most tracts revealed a reliable spatial gradient of NDI and ODI in the medial-to-lateral, posterior-to-anterior, and ventral-to-dorsal direction. Tracts related to CSPT loop were age-sensitive such that the spatial gradient was becoming more homogenous with age. This loss of spatial gradients with age is analogous to network-level dedifferentiation observed in BOLD functional connectivity. These findings highlight that age effects in a fundamental circuit for both basic and higher-order function is significantly age sensitive and while organized into spatial gradients, these gradients are also vulnerable to aging.

Purpose Open-source vision-language models (VLMs) can be locally deployed without external internet access, potentially enhancing data security. This study compared the diagnostic performance of general-purpose and medical-purpose open-source VLMs and evaluated their ability to characterize brain metastases on contrast-enhanced (CE) MRI. Materials and Methods Sixty lesion-positive axial CE T1-weighted images and sixty matched lesion-negative images from 60 patients were analyzed using three general-purpose VLMs-InternVL3-8B, Qwen2.5-VL-7B-Instruct, and MiniCPM-V-4.5-and three medical-purpose VLMs-MedGemma-4B-it, LLaVA-Med v1.5, and HuatuoGPT-Vision-7B. Lesion detection performance was assessed using sensitivity, specificity, and balanced accuracy. On lesion-positive images, accuracy was evaluated for lesion count, laterality, anatomic location, enhancement pattern, necrosis, vasogenic edema, and mass effect. Model differences were assessed using Cochran's Q tests followed by pairwise McNemar tests with Benjamini-Hochberg correction. Results The median age of the study patients was 67 years (IQR, 61.0-70.5 years), and 35 patients were male (58.3%). MiniCPM-V-4.5 showed the most balanced diagnostic performance, with a sensitivity of 78.3% (95% CI, 66.4-86.9%) and a specificity of 85.0% (95% CI, 73.9-91.9%), and significantly higher balanced accuracy than all other models. Significant overall differences were observed for lesion count, laterality, location, enhancement pattern, necrosis, and mass effect, but not for vasogenic edema (FDR-adjusted P = 0.056). HuatuoGPT-Vision-7B and MedGemma-4B-it showed relatively consistent accuracy across multiple image assessment tasks, although their performance remained modest. Conclusion Our study demonstrated substantial heterogeneity in the performance of open-source VLMs in brain metastasis evaluation, and medical-purpose VLMs did not outperform general-purpose VLMs.