Brain Informatics

Background and ObjectiveNormative modeling is a key tool for understanding brain alterations in neurodegenerative diseases, such as cerebellar-type multiple system atrophy. However, existing methods lack interpretability and fail to capture clinically meaningful pathological changes. This study presents DINMC, a Deep Interpretable Normative Model Construction framework, which combines autoencoder-based learning with statistical hypothesis testing to better capture and interpret disease-specific neu-roanatomical changes. MethodsThe DINMC framework constructs normative models using neuroimaging data from multi-site large healthy cohorts. It utilizes a U-shaped convolutional autoencoder to train these models, which are then applied to reconstruct brain features from both patients and healthy controls within the same study cohort. Pathological confidence values are derived by fusing original and deviation feature spaces, offering a measure of disease-related pathology reflected in each dimension of the features. The framework was validated through statistical analysis and prognostic classification and regression tasks. ResultsThe pathological confidence provides valuable insights into the neuroanatomical regions most affected by the disease, as well as the correlation between changes in these regions and clinical assessment scales. Our optimal model outperform traditional methods in prognostic prediction tasks, with an AUC of 0.972 for classification tasks and an R2 of 0.432 for regression tasks. ConclusionDINMC provides a novel and interpretable framework for neuroimaging analysis. By combining deep learning and statistical hypothesis testing, this framework offers a unique solution to improving both the interpretability and performance of normative models in neuroimaging. The approach is scalable to other neuroimaging datasets, offering a versatile tool for broader biomedical applications.

Objectives To evaluate whether class-conditional conformal prediction (CP) can provide reliable uncertainty quantification (UQ) under severe class imbalance and distribution shift, using multiple sclerosis (MS) diagnosis from magnetic resonance imaging (MRI) as a clinical exemplar. Methods We evaluated marginal and class-conditional CP using 720 T2-weighted MRI scans (142 MS, 578 controls). A convolutional neural network trained on 3 T data was evaluated under distribution shift (1.5 T acquisitions and synthetic image degradations). Through 100 Monte Carlo experiments, we assessed coverage guarantees, class-specific performance, and relationships between calibration set size, coverage variance, and uncertainty. Results Marginal CP severely under-covered the minority MS class (16.9% mean coverage at 1.5 T vs. 95.2% for controls) despite valid population-level guarantees. Class-conditional CP dramatically improved MS coverage to 77.5% at 1.5 T and 85.8% at 3 T, significantly reducing severe undercoverage (<80%) frequency while maintaining >89% control coverage. Minority class coverage variance increased due to limited calibration samples, matching theoretical Beta-binomial predictions. CP maintained validity under distribution shift; prediction set sizes scaled monotonically with shift severity, yielding clinically interpretable UQ. Conclusions Class-conditional CP successfully mitigates systematic undercoverage of minority disease classes while maintaining validity under distribution shift. The approach offers a practical, model-agnostic solution for uncertainty quantification applicable across clinical AI systems, though increased coverage variance for less represented conditions reflects fundamental statistical constraints. By characterizing these variance trade-offs, this framework enables more reliable deployment of diagnostic AI in heterogeneous clinical environments across diverse medical domains where minority disease class detection is critical.

Multimodal machine learning leverages complementary information from diverse data sources and has shown strong promise in medical imaging, where multimodal data is critical for clinical decision making. In glioma grading, integrating MRI modalities with clinical data can improve diagnostic accuracy, yet systematic comparisons of fusion strategies remain limited. This study evaluates early, intermediate, and late fusion approaches, addressing the question: How does the inclusion of clinical data alongside MRI modalities influence grading performance? To assess modality contributions, we design adaptable fusion layers and employ interpretability techniques, including attention-based analysis. Our results show that incorporating clinical data consistently outperforms unimodal and MRI-only baselines, with intermediate fusion yielding the most reliable gains. Beyond accuracy, the framework reveals how MRI and clinical features jointly shape predictions, underscoring the importance of both fusion design and interpretability for clinical adoption.

Emerging as a significant global health challenge, Alzheimer's Disease (AD) is a progressive neurodegenerative disorder that causes memory loss and cognitive decline. Despite the ever-increasing waiting time for a specialist diagnosis, the need for a cost-effective and fast diagnostic technique is evident. This study explores the development of an explainable deep learning model to diagnose AD using only routine and low-cost clinical data, including demographic information, patient history, and results of neuropsychological tests (limited to those that can be automatically acquired). The analysis was carried out using a dataset provided by the National Alzheimer's Coordinating Center, comprising 167,364 observations and 1,024 features. The findings demonstrate diagnostic performance comparable, and slightly superior, to that of clinicians when evaluated under similar informative constraints. This study introduces two classification models to discriminate whether the presumptive etiological cause of cognitive impairment is Alzheimer's disease. The deep neural network achieved an accuracy of 90\% with an area under the receiver operating characteristic curve (ROC-AUC) of 0.96, whereas the Light Gradient Boosting Machine reached the same accuracy with a ROC-AUC of 0.97.

Alzheimers disease (AD) is an irreversible neurodegenerative disorder that gradually impairs memory, cognition, and behavior, making early diagnosis essential for slowing disease progression and improving patients quality of life. Functional Magnetic Resonance Imaging (fMRI) provides a noninvasive tool to study brain activity, yet many existing diagnostic models rely on black-box architectures that lack interpretability. In this study, we introduce a computational framework that models each anatomical brain region as a Shannon information source, thereby quantifying both the intrinsic information content of regions and the interactions among them. We used kernel density estimation to compute the probability density functions (PDFs) of voxel-level BOLD time series. From these PDFs, we derived regional entropy and pairwise Kullback-Leibler (KL) divergence measures. These measures were used to construct feature spaces representing information dynamics across the brain. We applied the framework to the ADNI resting-state fMRI dataset, which includes cognitively normal (CN), early mild cognitive impairment (EMCI), late mild cognitive impairment (LMCI), and AD subjects. Our findings indicate that entropy values increase with disease progression, while KL-based connectivity networks reveal a progressive loss of inter-regional interactions, especially in frontal, temporal, and parietal lobes. For classification, we trained multilayer perceptrons using voxel BOLD signals, entropy vectors, and KL divergence vectors. Models trained on KL features achieved the highest performance, outperforming both entropy-based and voxel-based approaches. These results demonstrate that the Shannon information source model offers an interpretable and statistically grounded approach for characterizing brain dynamics, while achieving superior diagnostic accuracy. Beyond AD, the proposed framework provides a generalizable tool for studying brain network alterations in neurological and psychiatric disorders.

BackgroundFederated learning (FL) enables collaborative model training across institutions without sharing patient-level data. However, standard FL algorithms such as FedAvg degrade under non-independently and non-identically distributed (non-IID) data, a prevalent condition when patient demographics, scanner hardware, and disease prevalence differ across hospital sites. ObjectiveWe propose iPS-MFFL (Individualized Per-Site Meta-Federated Feature Learning), a federated framework with a hierarchical local-model architecture that addresses non-IID heterogeneity through (1) a shared feature extractor, (2) multiple weak-learner classification heads that can be trained with heterogeneous training objectives to promote complementary decision boundaries, (3) independent per-learner server aggregation so that each weak learners parameters are averaged only with its counterparts at other clients, and (4) a lightweight meta-model -- itself federated -- that adaptively stacks the weak-learner outputs. The specific choices of backbone, weak-learner training objectives, and meta-model are implementation details; in this work we use an ImageNet-pretrained ResNet18 and three heterogeneous losses as a concrete instantiation. MethodsWe evaluate on the Brain Tumor MRI Classification dataset (7,200 images; 4 classes: glioma, meningioma, pituitary tumor, no tumor) partitioned across K = 5 simulated hospital sites using Dirichlet non-IID sampling ( = 0.3). Four baselines are compared: Local-only training, FedAvg, FedProx, and Freeze-FT. All experiments are repeated over three random seeds (13, 42, 2025) and evaluated using paired t-tests, Cohens d effect sizes, and post-hoc power analysis. ResultsiPS-MFFL achieved the highest mean final-round test accuracy point estimate of 85.42 {+/-} 8.70% (mean {+/-} SD across three seeds), compared to FedAvg (78.48 {+/-} 12.66%), FedProx (78.33 {+/-} 14.64%), Freeze-FT (73.98 {+/-} 21.09%), and Local (58.10 {+/-} 11.77%). iPS-MFFL showed the smallest cross-seed SD, suggesting greater robustness to partition heterogeneity. However, one-way ANOVA did not reach statistical significance (F = 1.52, p = 0.270), reflecting the limited number of experimental seeds. Cohens d effect sizes relative to iPS-MFFL ranged from 0.59 (vs. FedProx) to 2.64 (vs. Local); post-hoc pairwise comparisons are reported as exploratory given the non-significant omnibus test. Post-hoc power analysis indicated that statistical power for FL baseline comparisons was only 0.10-0.12 for the observed effect sizes (d {approx} 0.6) at n = 3 seeds. ConclusionsiPS-MFFL provides a practical approach to heterogeneous federated brain tumor classification by combining transfer learning, contrastive weak-learner diversity, and meta-learning. The framework demonstrated the highest mean accuracy and lowest variance across diverse data partitions. Validation with larger seed pools ([&ge;] 10 seeds for 80% power), ablation studies, and external multi-center cohorts is needed to establish generality.

Background and ObjectiveGlioblastoma outcome prediction remains difficult because clinically relevant signals are distributed across heterogeneous imaging and genomic modalities, cohorts are small, and conventional neural predictors do not quantify their own uncertainty. This study evaluates a hybrid neural-Bayesian belief network framework for uncertainty-aware multimodal glioblastoma prediction and examines how modality selection, model family, and structure-aware regularization affect predictive performance and confidence quality. MethodsThe framework was evaluated on the TCGA-GBM radiogenomic cohort using four input modalities (T1Gd, FLAIR, mRNA, and CNA), five model families, five structural-weight settings, and 15 view subsets. A secondary benchmark on the UCI Human Activity Recognition dataset was included to assess whether observed limitations were specific to the glioblastoma setting. ResultsCNA features consistently reduced performance in most multimodal settings, and selective fusion excluding CNA outperformed both the full four-view baseline and imaging-only alternatives. Model families showed clear differences in uncertainty behaviour: non-Bayesian families achieved the strongest predictive accuracy, whereas the Bayesian family achieved the lowest calibration error over a narrower confidence range. Bayesian belief network regularization produced consistent directional improvements without supporting reliable structure-discovery claims, as learned graph structures were not reproducible across folds. On the secondary bench-mark, the same framework achieved much higher predictive performance, indicating that the glioblastoma performance ceiling primarily reflects data limitations rather than an architectural constraint. ConclusionsIn small-sample radiogenomic prediction, modality choice is at least as important as model choice, and uncertainty quality differs substantially across uncertainty-aware model families. The proposed framework provides a practical basis for comparing accuracy, calibration, modality selection, and structure-aware regularization in multimodal biomedical prediction.

Machine-learning models are increasingly used to predict cognitive and clinical outcomes from neuroimaging data, yet challenges in fairness and generalizability remain. Large-scale datasets are often racially and ethnically imbalanced, leading to systematic performance disparities, with models typically achieving higher accuracy for majority populations represented in the training data. In this study, we evaluated whether supervised domain adaptation methods--including balanced weighting, two-stage TrAdaBoost, feature augmentation with SrcOnly prediction, and linear interpolation--can mitigate these biases. Using the ABCD dataset, we assessed whether models trained on 80 MRI measures from White American participants could generalize more effectively to African American participants. All domain adaptation methods reduced prediction error for African American participants, particularly for MRI modalities with large baseline disparities (e.g., structural MRI), while offering limited improvements where initial gaps were smaller (e.g., functional connectivity). Among the approaches, balanced weighting performed best and remained stable and beneficial even when only 10 African American participants were used to adapt the original model trained exclusively on White American participants. These findings suggest that simple, low-cost strategies can effectively reduce cross-ethnic performance gaps and improve equity in predictive neuroimaging, offering a practical path forward for future neuroimaging predictive biomarkers. Significant StatementLarge-scale neuroimaging datasets increasingly enable machine-learning models to predict cognitive and clinical outcomes; however, these datasets are often ethnically/racially imbalanced. As a result, predictive models tend to generalize poorly to underrepresented populations. We demonstrate that, across 80 MRI phenotypes, a class of machine-learning approaches collectively known as supervised domain adaptation can substantially reduce cross-ethnicity disparities in neuroimaging-based cognitive prediction, even when only limited data from underrepresented groups are available. Among the methods evaluated, balanced weighting achieved the best performance while maintaining low computational cost. Together, these findings provide a practical and scalable framework for improving fairness and generalizability in neuroimaging-based machine learning under realistic conditions of ethnic/racial imbalance.

Understanding vascular contributions to disease is a major unmet need. White matter lesions (WML) are an accepted imaging marker of cerebral small vessel disease, giving insights into its related pathologies. A unified approach for WML analyses in large multi-site data is lacking despite the need for pooling of data to overcome the limitations of often small heterogenous MRI studies which make subtyping and identifying patterns within disease groups difficult. Our ENIGMA-PD-WML pipeline is an open-source containerized pipeline containing all the code and packages required for pre-processing, processing and post-processing of T1-weighted and FLAIR data, outputting accurate and reproducible binary WML maps using a UNet approach. The pipeline provides a standardized image analysis approach for WML and outputs data in both native and MNI space to allow for sharing and pooling of data from multiple sites for large-data analysis. In addition to a reliable standardized approach for WML segmentation, key priorities when developing the pipeline included: usability, i.e., requiring minimal manual input and technical expertise to use, and suitability to run on various MRI scanners and acquisition parameters as is common in multi-site data. This paper describes the pipeline in detail, with rationale for each step, providing transparency and facilitating its usage to overcome reproducibility issues in large-scale WML analyses.

Understanding the sequential order and timing of different biomarkers in the progression of Alzheimer's disease (AD) is paramount for understanding the pathophysiology of the disease, leading to better staging and improved prediction of clinical progression, providing crucial knowledge for the design and timing of effective clinical therapeutic trials. This study developed and evaluated a multi-modal phase plane (MMPP) method to construct long-term multivariate disease trajectory curves from short term longitudinal data for neuro-degenerative diseases like AD. The MMPP method is an extension to a previously presented four-step method for constructing single variable disease trajectories. A novel anchoring step which uses study participants' multivariate data to infer the staging of the separate single variable progression trajectories allows multivariate disease trajectory curves to be generated. Further, the anchoring step provides disease staging at the individual level. A bootstrapping protocol was employed, providing confidence limits on the predictions. We demonstrate that the MMPP method is able to accurately reconstruct multivariate disease trajectory curves and individuals' disease stage from simulated noisy short term longitudinal data. Specifically, the method successfully estimated the delay times between distinct progressing variables and reliably predicted individual baseline disease times (r2 = 0.981) for participants exhibiting significant early biomarker deviations.

Alzheimer's disease (AD) is clinically marked by difficulty retaining newly learned information, yet routine memory scores often conflate poor initial encoding with failure to stabilise information after encoding. This ambiguity limits the mechanistic interpretability of cognitive assessment during the transition from mild cognitive impairment to AD. Here we propose a Hippocampal Cortical Consolidation Bottleneck (HCCB) model to computationally separate these two components of new memory failure. The model represents newly presented information as a rapidly formed hippocampal trace and a slowly stabilised cortical trace, predicting a residual bottleneck when delayed recall falls below the level expected from immediate recall. We operationalised this prediction as Consolidation Bottleneck Index*(CBI*), a cognitively normal reference normalised residual index, and evaluated it using Alzheimer's Disease Neuroimaging Initiative (ADNI) cognitive and MRI data, with independent dynamical support from OpenNeuro EEG. Simulations showed recent memory vulnerability when hippocampal vulnerability exceeded cortical vulnerability. In ADNI, CBI* increased from cognitively normal participants to mild cognitive impairment nonconverters, reached Alzheimer like levels in mild cognitive impairment converters, and was associated with hippocampal atrophy. CBI* added minimal discrimination beyond established clinical and structural predictors, supporting its role as a mechanistic phenotype rather than a replacement prognostic model. OpenNeuro EEG further showed increased neurodynamic rigidity in AD. Our findings provide a computational framework for quantifying failed stabilisation of newly encoded information in AD progression.

Traumatic brain injury produces widespread axonal damage can be assessed histologically using amyloid precursor protein (APP) immunohistochemistry, which labels injured axonal profiles at cellular resolution [1, 2]. However, quantification of APP pathology remains a major bottleneck: annotation is manual, time-consuming, spatially localized, and variable across raters, limiting scalability and reproducibility. This limitation is particularly important in studies that use histology as a reference for neuroimaging or other tissue-level measurements, where cellular APP pathology must be quantified in a spatial form that can be aligned with imaging abnormalities. Here, we introduce PIGMENT, an annotation-efficient deep-learning framework for automated segmentation and quantification of APP-positive pathology in porcine white matter histology. PIGMENT uses a compact SegFormer-B0 architecture trained on 525 expert-annotated 512 x 512-pixel tiles from four APP-stained sections across three pigs. Because APP-positive profiles are sparse, fragmented, stain-variable, and morphologically diverse, PIGMENT combines limited expert labels with APP-specific augmentation designed to model variation in APP-positive intensity, size, continuity, fragmentation, and local tissue context. We evaluated PIGMENT using an instance-level detection rate that measures whether discrete APP-positive components are localized. Across held-out APP-stained data, PIGMENT achieved a mean instance-level detection rate of 0.86. Across the configurations tested, the highest mean detection rate was achieved by a training set that included sections from different animals, suggesting that annotation diversity may be an important factor under limited-label conditions. By extending limited high-confidence expert annotations into whole-section APP burden maps, PIGMENT provides a scalable framework for characterizing the extent and spatial distribution of traumatic axonal injury. These maps may support future studies that align histological injury burden with imaging-derived measures.

One of the prominent methods in neuroimaging data processing is SSM-PCA, which is based on principal component analysis and allows for the identification of diagnostically significant patterns in the form of statistical maps. We developed software, PIE Toolbox, employs SSM-PCA and classification based on the obtained diagnostic patterns revealed from functional and structural tomographic brain imaging. The program supports the entire analysis pipeline including preprocessing of brain images, diagnostic patterns extraction, building classification models, and prediction based on them. The resulting diagnostic patterns are weighted principal components obtained through SSM-PCA, or their linear combinations. PIE Toolbox allows selection of relevant structural and functional brain patterns, computation of their expression values in regions of interest, classification using support vector machines, and evaluation of model performance via cross-validation. This approach enables the use of patterns as features of intergroup differences for individual diagnosis. The software has been validated on both simulated and ADNI datasets.

The corpus callosum is a major white matter bundle responsible for connecting both hemispheres. In mammals, due to a variety of causes, the development of the corpus callosum can be impaired - this brain malformation is known as corpus callosum dysgenesis (CCD). The clinical presentation of CCD varies, with patients exhibiting three morphological phenotypes: agenesis, partial dysgenesis, and hypoplasia. Although the first two presentations are easily detectable on MRI scans, the latter is more challenging, as the structure is fully formed but has a reduced area. In this study, we develop (1) a pipeline to generate synthetic MRI scans with apparent anatomical variation and (2) train a U-Net-based tool to automatically segment the corpus callosum of marmosets in both healthy and disease contexts. Methodologically, a custom script was devised to apply rotation and translation to T1-weighted MRI scans at the volume level. Because the slicing grid remains unchanged, these rigid transformations translate into apparent anatomical variations at the slice level. We compared corpus callosum measurements obtained from automatically segmented masks with those from manually delineated masks. The average Dice score was above 0.90, and the Hausdorff distance was below 0.4 mm. We also stratified our cohort according to phenotype (healthy controls and hypoplastic animals). The magnitude of the effect and the significance level observed between the voxel counts of healthy and hypoplastic animals using manually delineated masks were comparable to those obtained via automatic segmentations. These results show that our pipeline can generate a sufficiently varied training pool to build an accurate U-Net segmentation model with high diagnostic capability.

Understanding brain-behavior relationships requires models capturing the distributed, interactive, and multiscale nature of neural systems. Traditional univariate approaches and single-biomarker models are inherently limited in this context, as they fail to represent dependencies across regions and the hierarchical organization of brain networks. In this study, we propose a graph-based multivariable framework for brain imaging analysis that integrates key organizational principles of brain function-including segregation, integration, modularity, and temporal dynamics-within a unified graph neural network architecture. The framework represents brain data as hierarchical graphs, where node features encode regional activation and temporal variability, and graph structure captures interactions within and between functional modules. The proposed approach is evaluated using functional near-infrared spectroscopy (fNIRS) data as a case study, where subject-specific brain graphs are constructed from task-based recordings acquired shortly after cochlear implant activation to predict speech understanding outcomes one year later. Under leave-one-subject-out validation, the model demonstrates strong predictive performance (R = 0.73, p < 0.001), outperforming previously reported single-biomarker approaches. Perturbation-based analyses further show that predictions are driven by distributed patterns of activity and interaction across regions and modalities, rather than isolated features. These results illustrate the capability of the proposed framework to capture complex brain organization and highlight its potential as a generalizable platform for multivariable analysis and prediction in neuroimaging applications beyond the specific clinical use case considered here.

We present the TopBrain 2025 Challenge, the first benchmark for fine-grained multiclass segmentation of the whole brain vasculature in both computed tomography angiography (CTA) and magnetic resonance angiography (MRA). Building on the TopCoW challenge, TopBrain scales vessel annotation from the Circle of Willis to the entire brain, introducing a dataset of 90 annotated volumes across 48 landmark vessel classes spanning arterial and venous systems, of which 50 training volumes are publicly released. Vessel definitions were consolidated from established neuroanatomical references into a unified annotation scheme, and vessel caliber measurements along the centerline are reported for the first time across the whole brain vascular anatomy. To address the unique challenges of multiclass brain vessel segmentation, we propose an evaluation framework that accounts for detection in segmentation performance, assesses anatomical plausibility, and introduces novel contamination metrics that characterize inter-class prediction errors. Fifteen teams from over 220 registered participants submitted algorithms to the benchmark. The top-performing teams built on nnUNet with principled system design choices, achieving around 80% Dice scores, near-zero invalid neighbor counts, over 60% F1 scores for side-road vessels, and below 18% foreground contamination ratio. Larger vessels are easier to segment, while smaller and more complex vessels remain the true bottleneck. The annotated datasets and podium-finish algorithms are made publicly available on Zenodo.

MICAFlow is a fully automated MRI preprocessing pipeline designed to translate advanced neuroimaging workflows from research into routine clinical practice. The pipeline emphasizes speed, robustness, and ease of use, focusing on structural and diffusion MRI. Key innovations include a Label-Augmented Modality-Agnostic Registration (LAMAReg) technique driven by deep learning segmentations for reliable cross-modal alignment, integration of state-of-the-art distortion corrections, and adherence to reproducible standards (Snakemake workflow, BIDSApp specifications). We describe the design of MICAFlow and evaluate its performance across heterogeneous datasets. First, accessibility: MICAFlow processes a multimodal MRI exam in minutes with clinically accessible hardware and without requiring GPU access, making it feasible for same-day clinical use. Second, registration accuracy: LAMAReg achieves cutting-edge multi-modal registration accuracy, yielding accurate alignment of diffusion MRI, FLAIR, and intra-subject T1-weighted images while remaining generally robust to common artifacts. Third, data reliability: Using identifiability, we show MICAFlow maintains consistent performance across diverse datasets, including subjects with pathology, and is closely comparable to contemporary pipelines. In sum, MICAFlows combination of machine learning and efficient workflows produces research-grade data quality with clinical-grade speed. This work demonstrates that advanced MRI preprocessing can be done fast and robustly, helping close the gap between research neuroimaging and broad clinical application of quantitative MRI techniques. The source code for MICAFlow is available here: https://github.com/MICA-MNI/micaflow, and for LAMAReg here: https://github.com/MICA-MNI/LAMAReg.

Brain tumor detection using Magnetic Resonance Imaging (MRI) remains a challenging task due to tumor heterogeneity and imaging variability. This paper presents a novel hybrid Deep Convolutional Neural Network-Whale Optimization Algorithm (DCNN-WOA) framework for automated brain tumor detection and classification. The proposed method consists of four main stages: MRI data preprocessing and augmentation, deep feature extraction using multi-layer Convolutional Neural Networks (CNN), feature selection and hyperparameter optimization via the Whale Optimization Algorithm (WOA), and final classification with comprehensive performance evaluation. By jointly optimizing deep features and training parameters, the framework effectively reduces feature redundancy, accelerates convergence, and enhances model generalization. Experimental results on a publicly available MRI dataset demonstrate that the DCNN-WOA model outperforms conventional CNN and state-of-the-art Deep Learning (DL) architectures, achieving an accuracy of 97.8%, sensitivity of 96.4%, specificity of 98.1%, and F1-score of 97.2%. The practical impact of this approach makes it a promising solution for real-time clinical decision-support systems in neuroimaging.

AO_SCPLOWBSTRACTC_SCPLOWShortcut learning poses a significant challenge in clinical artificial intelligence, as models may rely on spurious signals rather than clinically relevant features, leading to biased predictions and poor generalization. Existing detection methods are fragmented and lack systematic evaluation across datasets and model architectures. To address this issue, we propose ShortKit-ML, an open-source Python framework for unified shortcut analysis in embedding spaces. The framework integrates over 20 detection methods and six mitigation strategies within a modular pipeline, encompassing embedding analysis, fairness metrics, training dynamics, causal methods, explainability, and representation analysis. We evaluate the framework on chest X-ray datasets (CheXpert and MIMIC-CXR), synthetic benchmarks, and an out-of-domain dataset (CelebA). Experimental results demonstrate that multi-method auditing provides more stable and interpretable evidence than individual methods, while detector disagreement reveals meaningful representational differences. The proposed framework offers automated reporting, interactive visualization, and is available as a pip-installable package. The source code and documentation are publicly available at https://github.com/criticaldata/ShortKit-ML and https://criticaldata.github.io/ShortKit-ML/.

The aim of this study was to evaluate the contributions of age, sex, and MRI vendor to variance in Diffusion Tensor Imaging (DTI) metrics, with a focus on understanding the impact of these factors in large-scale healthy brain datasets. A dataset of 2,700 DTI scans from healthy controls across multiple sites and MRI vendors was analyzed. The DTI scalar metrics fractional anisotropy (FA) and mean diffusivity (MD) were processed and the influence of age, sex, vendor, and brain atlas selection were determined. A statistical analysis was conducted and revealed significant (p<0.05) age-related differences in DTI metrics, with older participants showing reduced FA and increased MD, in line with known microstructural changes. Sex differences were observed, with females exhibiting slightly higher FA and lower MD in certain brain regions. Vendor variability was also noted, with all three MRI vendors showing significant differences in FA with Siemens machines typically exhibiting higher FA values and GE machines lower FA values (i.e. FASiemens > FAPhilips > FAGE). Atlas selection also highlighted some specific ROI behaviour (e.g. tapetum of the corpus callosum) as one of the most significant regions of interest (ROIs) in the JHU-Tracts atlas that demonstrated a large amount of deterioration with age, particularly in females. These findings emphasize the need to account for biological factors such as age and sex, as well as technical factors like ROI selection and MRI vendor, when interpreting DTI data. The results demonstrate the potential of large-scale, multi-vendor datasets to uncover meaningful biological trends, while also addressing the challenges of scanner-specific variability. Although previous work has shown sex and age differences, this is the first large scale DTI analysis that has included age, sex, and MRI vendor as sources of variance in one model.