Frontiers in Neuroinformatics

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.

Background: Prostate-specific membrane antigen (PSMA) PET/CT is central to prostate cancer staging and theranostic workflows. To our knowledge, no direct within-patient comparison of [18F]FC303 ([18F]Florastamin) and [68Ga]Ga-PSMA-11 has been reported. We performed a preliminary paired method-comparison study under non-harmonized acquisition protocols. Patients and Methods: Twenty patients with histologically confirmed prostate cancer underwent [68Ga]Ga-PSMA-11 PET/CT (185 +/- 37 MBq, 60 +/- 10 min) followed by [18F]FC303 PET/CT (370 +/- 37 MBq, 105 +/- 15 min) on the same PET/CT system within each patient (median interval, 29.5 days). Index targets were anatomically matched to the biopsied or surgically sampled lesion or target region. The primary malignant set included 18 histologically malignant targets; two histology-negative or indeterminate targets were included only in sensitivity analysis. Fixed [68Ga]Ga-PSMA-11-first scan order and the 45-min uptake-time difference were central interpretive constraints. Results: Across five predefined reference organs, [18F]FC303 showed lower SUVmean than [68Ga]Ga-PSMA-11 (all Benjamini-Hochberg-adjusted p < 0.001; [68Ga]/[18F]FC303 geometric mean ratio [GMR], 1.29-3.89). In the primary malignant set, [18F]FC303 lesion SUVmax was lower than [68Ga]Ga-PSMA-11 (median, 11.3 vs 18.1; paired median difference, -5.50; 95% CI, -6.85 to -2.90; Wilcoxon p = 8.4 x 10-4), with strong rank correlation (Spearman {rho} = 0.90). Passing-Bablok regression yielded {beta} = 1.13 (95% CI, 1.04-1.45), and log-Bland-Altman GMR (FC303/[68Ga]) was 0.75, consistent with proportional non-interchangeability. Tumor-to-liver and tumor-to-mediastinum ratios did not differ significantly (GMR, 1.17 [95% CI, 0.94-1.45] and 0.96 [0.80-1.15], respectively); the study was not powered for equivalence. The n = 20 sensitivity analysis showed consistent directionality. Conclusions: Under non-harmonized acquisition conditions, [18F]FC303 showed lower physiologic reference-organ SUVmean and malignant target-region SUVmax than [68Ga]Ga-PSMA-11, whereas tumor-to-liver and tumor-to-mediastinum ratios were not significantly different. Absolute SUVs were not interchangeable; [68Ga]Ga-PSMA-11-derived SUV thresholds should not be directly transferred to [18F]FC303 without tracer-specific calibration.

The surge in medical imaging has spurred the development of vision-language models (VLMs) to alleviate radiologist workloads. However, clinical deployment is hindered by the lack of meaningful evaluation frameworks. Current metrics - ranging from semantic similarity to large language model (LLM) based judges - often fail to distinguish between clinically trivial and critical discrepancies, poorly reflecting real-world clinical judgment. To address this, we introduce DISCERN (Discordance and Significance-aware Entity-level Radiology Report Comparison). DISCERN is a significance-aware framework that weighs report errors based on their potential impact on patient care. Our results demonstrate that DISCERN powered by closed source LLMs aligns more closely with expert radiologist assessments than traditional metrics or current LLM evaluators, providing a more interpretable and clinically relevant benchmark. By modeling radiologist prioritization and entity-level feedback, DISCERN facilitates targeted model refinement and ensures the safer integration of generative AI into clinical workflows.

Background: Traditional diagnostic models lack explainability, while multimodal language models prone to hallucination remain unsafe for medical education. An interactive, risk-free artificial intelligence framework is required to serve as a reliable clinical mentor for radiology trainees. Methods: We propose a multi-agent architecture decoupling deterministic image analysis from generative consultation. Specialized computer vision models perform anatomical localization and pathological segmentation. These quantitative outputs are synthesized into a structured payload, which grounds a locally hosted large language model (LLaVA 7B) using strict prompt guardrails and prerequisite protocols. Results: The system effectively eliminates visual hallucinations by intercepting unanchored queries. The artificial intelligence tutor successfully contextualizes spatial anomalies and baseline metrics, generating accurate conversational explanations and formally structured radiology reports while strictly enforcing medical safety disclaimers. Discussion and Conclusion: By anchoring language generation exclusively to verified algorithmic realities, this framework transforms opaque diagnostic models into safe, interactive educational simulators. This establishes a highly reliable paradigm for integrating explainable artificial intelligence into medical training.

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.

Background and Objectives In ADHD, a heterogeneous neurodevelopmental condition, behavioral and motor manifestations may reflect multiple inefficient or perturbed inhibitory systems. To evaluate Transcranial Magnetic Stimulation (TMS) evoked cortical silent period (CSP) duration, an indicator of GABA(B) receptor-mediated inhibition in motor cortex, as a potential biomarker of Attention-Deficit/Hyperactivity Disorder (ADHD) in children. Method We retrospectively analyzed TMS data, obtained using both round and figure-of-8 coils, from three cross-sectional studies conducted in 8- to 12-year-old children with ADHD (n=79; 10.7 +/- 1.5 years old) and age-and-sex-matched typically developing controls (n=96; 10.5 +/- 1.4 years old). Results Median CSP was 32% shorter in ADHD (p=0.02). Regression analysis demonstrated a relationship between shorter CSP and both lower active motor thresholds (p < 0.0001) and more severe hyperactivity symptom rating (p = 0.026). Test-retest CSP measures in 83 children showed moderate reliability (intraclass correlation 0.77 [ADHD], 0.75 [controls]). Conclusion TMS-evoked CSP may be a useful biomarker in future investigations of ADHD subtypes, domains of impaired function, or treatment outcomes.

Background: Autosomal recessive spastic ataxia of Charlevoix-Saguenay (ARSACS) is a genetic disease characterized by spasticity and ataxia which reflects involvement of the corticospinal tracts (CST) and cerebellum. The primary involvement of the middle cerebellar peduncles (MCP) and transverse pontine fibers (TPF) at the crossing with the CST, and their role in the pathophysiology of the disease, is currently debated. Objectives: Advanced MRI techniques capable of isolating sub-voxel microstructural parameters can test the hypothesis that the MCP and TPF are abnormally large, compressing the CST at their crossing, and potentially impairing CST development. Methods: Tract macro- and micro-structural properties, including axon and tract caliber, axon density and geometry, and myelin content were estimated from diffusion-relaxometry and magnetization transfer imaging. These features were analyzed along segments of the CST, MCP, and TPF of 9 patients and 9 age-matched controls. Results: While the CST showed significant decreases in tract size, axon caliber, and myelination throughout its length compared to controls (p<0.01), the MCP and TPF were relatively unaffected. In our group, neither the MCP nor the pons were enlarged. The proximal MCP showed an increase in axon caliber. Conclusions: The increase in fractional anisotropy and axon density towards the center of the TPF could be driven by geometric confounds related to differences in the relative sizes of the CST and TPF compared to controls. This highlights the importance of investigating tract-specific microstructural profiles, particularly in regions of geometric complexity. The findings confirm the involvement of the CST, with a relatively limited involvement of the MCP and TPF.

Hypoxia-targeted BOLD MRI is a novel technique, which probes oxygenation physiology in response to a controlled transient hypoxia stimulus. In glioblastoma, the signal response is spatially and temporally heterogeneous. We developed a voxel-wise temporal decomposition framework for hypoxia-targeted BOLD MRI that separates the arrival of responses, transition phases, and steady state during controlled isocapnic hypoxia. Twenty healthy controls underwent 3-T BOLD MRI during a double hypoxic step challenge to establish a normative reference. Three patients with newly diagnosed glioblastoma were included as proof-of-concept cases. For each voxel, we estimated response arrival delay (Delaycorr), delay to plateau, delay to return and an O2-normalized steady-state response (HypoxiaSS). Healthy-control maps were used to construct a voxel-wise normative atlas and, for HypoxiaSS, a global-response-adjusted model for patient deviation mapping. In healthy controls, HypoxiaSS showed lower supratentorial between-subject variabilitythan both whole-stimulus comparators (coefficient of variation: 1.77 versus 2.36 for Hypoxiaavg) and higher voxel-level step-to-step agreement (ICC(2,1): median 0.951 versus 0.792 for Hypoxiaavg). Whole-stimulus averaging exhibited a systematic step-2 signal amplification present in 19 of 20 subjects, which was absent from HypoxiaSS. Asingle global response scalar explained a median 72.5% of voxel-wise between-subject variance in HypoxiaSS. In proof-of-concept patient analyses, G-adjusted HypoxiaSS deviation maps and timing maps identified spatially coherentabnormalities that were partly complementary and extended beyond conventional MRI-defined lesion margins.Temporal decomposition improves the stability and interpretability of hypoxia-targeted BOLD MRI and provides a practical framework for population-referenced physiological mapping and atlas-based deviation mapping in glioblastoma.

Blood biomarker models are increasingly used in Alzheimer's disease and related dementia translational research, but predictive performance can be inflated when the same dataset is used for both model development and evaluation. We assess the effect of data double dipping using simulations and NULISA proteomic data from the MYHAT-NI community-based cohort to predict brain amyloid-beta neuroimaging status. In both settings, training AUC increased as more biomarkers were added, while testing AUC peaked earlier and then declined. These findings show that data double dipping can inflate model performance and highlight the need for external validation or internal validation with data partitioning.

We trained a self-configuring nnU-Net model for CMB segmentation in a heterogeneous multicenter sample (n=264), including 1.5T and 3T field strengths, SWI and T2*-GRE sequences, and community and clinical cohorts. Model performance was evaluated using 5-fold cross-validation with a focus on object-level detection metrics. Real-world performance was evaluated on scans from an unseen dataset of people with cerebrovascular disease (n=20). The model achieved 0.82 cluster Dice, 0.88 precision, and 0.77 sensitivity on hold-out test data. Notably, the model demonstrated a low false-positive rate, averaging 0.58 false positives (FPs) per scan, an improvement on existing publicly available models. The model achieved high performance in dataset of those with Alzheimer's disease and mild cognitive impairment (0.89 cluster Dice, 0.94 sensitivity), supporting its utility in clinical settings where ARIA-H monitoring is critical. In external validation, the model maintained high robustness with 0.79 sensitivity and 0.95 FPs per scan. By leveraging a heterogenous training strategy and a self-adapting architecture, we demonstrate that deep learning can achieve high-precision CMB detection that is robust to domain shifts. The low FP rate suggests this publicly available pipeline is suitable for automated screening and lesion counting in heterogenous large-scale clinical trials, reducing the burden of manual quantification.

Purpose. The choroid plexus (ChP) is the primary source of cerebrospinal fluid and an emerging marker of cerebral health, with enlargement and hypoperfusion reported in aging and neurodegeneration. However, frequent ChP calcifications can confound volumetric and perfusion measures. Although computed tomography (CT) is the gold standard for detecting calcification, it is rarely available in research MRI. Quantitative susceptibility mapping (QSM) offers an alternative sensitive to diamagnetic mineralization but lacks validated susceptibility thresholds. Method. Participants underwent CT and MRI within four weeks, including 3D T1-weighted and a multi-echo gradient echo QSM MRI. ChP calcifications were identified on CT using standard diagnostic criteria. Using the Bayes decision boundary framework, we identified optimal susceptibility thresholds for detecting diamagnetic signals consistent with calcification and compared these thresholds with multiple density levels measured on gold standard CT images. Results. Across all participants (n=20; age=62.2+-12.0 yrs), the optimal susceptibility threshold separating background ChP signal from calcifications was -0.10 ppm at 60 HU (low-density) and -0.15 ppm at 100 HU (high-density). Susceptibility values within calcified tissue exhibited a linear relationship with CT-derived tissue density. A significant positive association was observed between ChP volume and calcification volume among participants with detectable calcification (beta=2.26, p=0.047). Conclusion. This work should provide a practical framework for quantifying ChP calcifications routinely from MRI. The observed relationship between ChP volume and calcification volume highlights the importance of accounting for calcified tissue, particularly when calcification burden is substantial, when investigating ChP abnormalities in aging and neurodegenerative disease.

Background: Three-dimensional visualization and quantitative analysis of cerebral arteries on 3DRA are central to endovascular treatment planning, device selection, and cerebrovascular research. Manual segmentation is time-consuming and operator-dependent, yet no open-source deep learning model has been prospectively validated for this task on 3DRA. Methods: A nnUNet v2 model was trained for binary cerebral artery segmentation on 400 consecutive 3DRA acquisitions from three angiographic systems, comparing four configurations across architectures and loss functions. The best-performing configurations were prospectively validated on 40 patients using a dual approach: quantitative metrics (DSC, clDice, HD95, ASD, Precision, Recall), and blinded expert qualitative evaluation by two interventional neuroradiologists assessing 12 arterial segments, a global quality score, and clinical usability across 40 test cases. Results: The ensemble model achieved median DSC 0.917, clDice 0.932, and HD95 1.494 mm. Global quality scores were significantly lower for nnUNet v2 than for expert segmentations (median 4 vs 5, p<0.001), but nnUNet v2 segmentations were rated clinically usable in 88-90% of cases versus 95-98% for expert segmentations, without significant difference on the binary usability criterion. A consistent proximal-to-distal quality gradient was identified, with comparable scores at proximal arteries and the largest differences at distal arterial segments. Conclusion: nnUNet v2 with topology-aware training provides clinically usable cerebral artery segmentations on 3DRA, prospectively validated through both quantitative metrics and structured expert qualitative assessment, and represents a reproducible open-source foundation for endovascular and research applications.

INTRODUCTION: Alzheimers disease (AD) is a multifactorial disorder, yet current research largely focuses on downstream biomarkers with limited attention to environmental contributors. Experimental studies suggest that per and polyfluoroalkyl substances (PFAS) may contribute to neuroimmune and neurodegenerative pathways relevant to AD. OBJECTIVE: To examine associations between PFAS exposure and neuroimmune and AD related plasma biomarkers in cognitively unimpaired rural adults. METHODS: In a cross sectional pilot study (n=48), serum concentrations of 33 PFAS were measured, including four legacy compounds (PFOS, PFHxS, PFOA, PFNA). Plasma neuroimmune related (ITGB2, SMOC1, TREM2, GFAP) and AD related biomarkers (Ab42/40, ptau217) were detected using proteomic analysis. RESULTS: PFOS showed moderate associations with ITGB2, SMOC1, and Ab42/40 in unadjusted analyses, which attenuated after adjustment for age. PFOA and PFNA demonstrated consistent inverse associations with TREM2 before and after adjustment. DISCUSSION: Findings suggest possible compound specific PFAS associations with immune and amyloid related biomarkers, supporting further investigation in longitudinal and PFAS mixture based studies.

Our study evaluated whether a deep learning auto segmentation model combined with machine learning triage can streamline radiotherapy clinical trial quality assurance (QA). We analyzed 107 stereotactic ablative radiotherapy (SABR) cases from a multi-institutional phase II clinical trial of neurovascular sparing prostate SABR, focusing on physician contours of the internal pudendal artery (IPA) as a novel organ-at-risk with substantial interobserver variability. Contours were scored by the trial principal investigator as Per-Protocol or Minor Deviation/Unacceptable. We applied a deep learning model for IPA auto-segmentation. Agreement between human and AI contours was then quantified using 14 overlap, distance, and surface metrics, and a supervised classifier was trained on these metrics to flag clinical trial protocol deviations. While AI segmentation achieved only modest geometric accuracy with mean Dice similarity coefficient of 0.446 and 95th percentile Hausdorff distance of 14.23, when incorporating all 14 metrics, a machine learning classifier yielded AUROC of 0.836, flagging all Minor Deviation/Unacceptable cases with 100% sensitivity on the 27 case hold-out set with 6 false positives and no false negatives. AI segmentation combined with metrics-based machine learning can triage protocol deviations within a multi-institution radiotherapy clinical trial, supporting prospective evaluation of AI-assisted trial QA.

ABSTRACT INTRODUCTION: Microscopic fractional anisotropy ({micro}FA), an emerging diffusion MRI metric, may be more sensitive than conventional metrics to gray matter microstructural changes in neurodegeneration. This pilot study compared {micro}FA, mean diffusivity (MD), and volume between genetic frontotemporal dementia (FTD) variant carriers and non-carriers in the insula, frontal pole, and medial orbitofrontal cortex (mOFC). METHODS: Carriers and familial non-carriers of FTD variants in C9orf72, GRN, or MAPT were scanned between October 2024-December 2025. Non-parametric aligned rank transform ANCOVAs were computed to analyze between-group differences in {micro}FA, MD, and volume while controlling for age. RESULTS: Carriers (n=12) exhibited lower insula {micro}FA than non-carriers (n=8): F(1,19)=5.89, 95% CI [-10.7,-0.75], p=0.027, 2p=0.26. No group-differences were observed in other metrics, including MD and volume. DISCUSSION: Reduced {micro}FA in the insula, a region vulnerable to early atrophy in FTD, may be more sensitive to early microstructural changes in genetic FTD than traditional diffusivity measures.

We investigated whether people with Parkinson's disease who are dual GBA1+LRRK2 carriers have a milder, LRRK2-like phenotype as previously reported. This was accomplished by comparing clinical features and alpha-synuclein seed amplification assay (SAA) positivity rates between dual GBA1+LRRK2-PD(n=13), GBA1-PD(n=169) and LRRK2-PD(n=175) carriers in a cross-sectional retrospective study of Parkinson's Progression Markers Initiative (PPMI) data. Our results show that GBA1+LRRK2-PD rate(83%) is closer to GBA1-PD rate(87%) rather than LRRK2-PD rate (62%mp-value>0.05). GBA1+LRRK2-PD have both non-motor and motor phenotypic similarity of GBA1-PD(p-value>0.05). This small PPMI cohort indicates that dual GBA1+LRRK2-PD carriers' SAA positivity and phenotype are aligned with GBA1-PD.

Objective:This study aims to compare the advantages and disadvantages of DLIR and adaptive statistical iterative reconstruction-V (ASIR-V) in thin-slice (2.5 mm) CT images of hepatic lesions characterized by high and low contrast. Additionally, the study seeks to determine the optimal DLIR strength for the evaluation of liver lesions. Methods:A retrospective analysis was performed on 90 patients who underwent abdominal contrast-enhanced CT scans. Group A comprised 48 patients with low-contrast lesions, while Group B included 42 patients with high-contrast lesions. The acquired images were reconstructed using post-processing DLIR at low (DLIR-L), medium (DLIR-M), and high (DLIR-H) strengths, all with a slice thickness of 2.5 mm (subgroups A1-A3, B1-B3). Furthermore, images were reconstructed with ASIR-V at 50% strength at slice thicknesses of 2.5 mm and 5 mm (subgroups A4/B4 and A5/B5, respectively). CT values and standard deviations (SD) of the liver and lesions were measured, and the corresponding signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were calculated. The edge rise slope (ERS) was determined using ImageJ software by measuring CT values along a line from the liver parenchyma to the lesion. Objective metrics were compared using one-way ANOVA, with independent samples t-tests applied for inter-group differences. Subjective scoring, which encompassed noise level, diagnostic confidence, and lesion margin delineation, was conducted by two radiologists, with differences analyzed using the Kappa test. Results: Objective evaluation revealed a progressive decrease in lesion SD and a progressive increase in SNR and CNR from subgroups A1/B1 to A3/B3. The SD of Group A2 decreased by 57.4% compared to A4, while the SNR and CNR of A2 icreased by 19.3% and 24.6% compared to A4. Although subgroup B2 had a lower SNR than B5, the difference was not statistically significant. SNR and CNR in B2 increased by 24.1% and 11.9%, respectively, compared to B4. ERS gradually decreased from A1/B1 to A3/B3. ERS values in A2 and B2 increased by 27.0% and 39.4%, respectively, relative to A5 and B5. Although A3 had a lower ERS than A1 and A2, all DLIR subgroups exhibited higher ERS than A5; similar trends were observed in Group B. Subjective evaluation indicated good inter-reader agreement (Kappa > 0.61, p < 0.05). As DLIR strength increased, noise scores rose progressively in both groups. However, noise in A2 and B2 was lower than in A4/A5 and B4/B5. Diagnostic confidence and lesion margin delineation scores were highest in A2 and B2, while all subjective scores were lowest in A5 and B5. Discussion: Most prior studies evaluated the liver, vessels, or confirmed that image quality can be guaranteed at low doses. However, there are few studies on specific individual lesions. Therefore, this study aims to investigate specific individual lesions. The details and detection rate were analyzed separately to confirm the clinical acceptability of 2.5-mm DLIR image in different contrast lesions. Conclusion: For both high- and low-contrast hepatic lesions, DLIR provides superior image quality compared to ASIR-V, with the 2.5mm DLIR-M setting being optimal. DLIR-M reduces image noise, improves spatial resolution, and produces images more suitable for diagnostic purposes.

Machine learning (ML) is being considered to help diagnose cardiovascular diseases (CVD). Still, challenges like inconsistent and limited datasets, limited infrastructure, and global inequalities lead to the need for a reliable and practicable ML solution. This paper presents an ML-driven framework for predicting CVD risk scores and classifying status. Several data preprocessing techniques, including multiple imputation by chained equations (MICE), outlier removal, are considered. In addition, hyperparameter tuning is performed with the GridSearchCV tuning technique. Moreover, a consensus-driven five-feature selection method is applied to identify optimal predictors. The dataset used in this study contains healthcare records related to future CVD risk scores, comprising 1,529 patient records with 22 features. The optimized stacked ensemble model is applied to the dataset and achieves a cross-validated coefficient of determination value of 98.13% for CVD risk score regression. Comparative evaluation with other ML models confirmed improved accuracy, efficiency, and interpretability. The explainable AI technique SHAP is applied to interpret predictions and highlight key risk factors. Moreover, a deployment-ready web platform with multi-role access has been developed that demonstrates clinical applicability. The proposed framework offers a reliable and interpretable tool for early detection of CVD and personalized risk assessment. In the future, this work can be extended to integrate longitudinal data, medical imaging, and deep learning to improve generalizability and strengthen real-world impact.

Quantitative eye movement analysis is important for neuro- logical diagnostics, yet existing video-oculography (VOG) systems typ- ically require calibration, device-specific settings, or accurate gaze la- bels. We present VOGeo-Gaze, a real-time, calibration-free, geometry- aware neural network that estimates gaze by reconstructing anatomi- cally meaningful eyeball parameters from image features. The method combines segmentation-driven projection geometry, a refraction-aware pupil correction module, and temporal anatomical stabilization, so gaze is derived from interpretable eye geometry rather than direct angular regression. Trained only on the public TEyeD dataset with weak gaze supervision, VOGeo-Gaze was evaluated on 116 clinical recordings from 17 patients and 19 healthy subjects using EyeSeeCam, a clinical gold- standard VOG system. It achieved median absolute angular errors of 0.33{whitebullet} horizontally and 0.35{whitebullet} vertically, with nearly 92% of recordings below 1{whitebullet} error while operating at >300 FPS. These results demonstrate sub-degree clinical gaze estimation without subject-specific calibration, camera intrinsics, or accurate gaze labels, providing a scalable and inter- pretable alternative to conventional VOG pipelines. Code is available at https://github.com/DSGZ-MotionLab/VOGeo-Gaze.

Pediatric patients with cardiac implantable electronic devices (CIEDs) face limited MRI access due to RF-induced heating, and computational modeling is increasingly used to characterize this risk. The validity of these simulations, however, depends on pairing body models with clinically realistic lead configurations, guidance that is currently lacking. We retrospectively analyzed 302 CIED surgeries in 281 pediatric patients to derive weight-based constraints for simulation design. Weight alone discriminated epicardial from endocardial lead implantation with AUC = 0.90, and adding age and height yielded no improvement, supporting weight as a sufficient single-parameter selection metric. The probabilistic crossover between approaches occurred at 44~kg, substantially higher than the 10 to 15~kg threshold commonly cited in the literature, with a broad transition zone of 21 to 66~kg in which both lead types were routinely used. Lead length was likewise weight-constrained: only 25~cm leads were observed in patients below 6~kg, and leads of 45~cm or longer were uncommon below 50~kg. These findings yield a three-tier framework, with epicardial-only configurations below 21~kg, dual configurations within 21 to 66~kg, and weight-thresholded lead lengths throughout, enabling MRI safety simulations to focus on clinically realizable anatomy and device combinations.