Search Results (248)

Independent vector analysis (IVA) has emerged as a powerful tool for fusing and analyzing functional magnetic resonance imaging (fMRI) data. Applying IVA to multi-task fMRI data enhances analytical power by capturing the relationships across different tasks in order to discover their underlying multivariate relationship to one another. Incorporation of prior information into IVA enhances the separability and interpretability of estimated components. In this paper, we demonstrate successful fusion of multi-task fMRI feature data under two settings: constrained IVA and constrained transposed IVA (tIVA). We show that using these methods for fusing multi-task fMRI feature data offers novel ways to improve the quality and interpretability of the analysis. While constrained IVA extracts components linked to distinct brain networks, tIVA reverses the roles of spatial components and subject profiles, enabling flexible analysis of behavioral effects. We apply both methods to a multi-task fMRI dataset of 247 subjects. We demonstrate that for task-based fMRI, structural MRI (sMRI) references provide a better match for task data than resting-state fMRI (rs-fMRI) references, and using sMRI priors improves identification of group differences in task-related networks, such as the sensory-motor network during the Auditory Oddball (AOD) task. Additionally, constrained tIVA allows for targeted investigation of the effects of behavioral variables by applying them individually during the analysis. For instance, by using the letter number sequence subtest, a measure of working memory, as a behavioral constraint in tIVA, we observed significant group differences in the auditory and sensory-motor networks during the AOD task. Results show that the use of two constrained approaches, guided by well-aligned structural and behavioral references, enables a more comprehensive analysis of underlying brain function as modulated by task. Full article

Background: Approximately 20–30% of ultra-high risk (UHR) individuals transition to psychosis within 2–3 years. Neurobiological markers predicting conversion remain critical for precision prevention strategies. Objective: To systematically identify and evaluate structural and functional neuroimaging biomarkers at UHR baseline that predict subsequent conversion to psychosis. Methods: Following PRISMA 2020 guidelines, we searched five databases from January 2000 to February 2025. Two independent reviewers screened studies and assessed quality using the Newcastle–Ottawa Scale. Eligible studies examined baseline neuroimaging measures (structural MRI, functional MRI, diffusion tensor imaging, magnetic resonance spectroscopy) as predictors of psychosis conversion in UHR cohorts. Results: Twenty-five studies comprising 2436 UHR individuals (627 converters, 25.7%) were included (80.0% high quality). Reduced baseline gray matter volume in medial temporal structures (hippocampus: Cohen’s d = −0.45 to −0.68; parahippocampal gyrus: d = −0.52 to −0.71) and prefrontal cortex (d = −0.41 to −0.68) consistently predicted conversion. Progressive gray matter loss in superior temporal gyrus distinguished converters (d = −0.72). Reduced prefrontal–temporal functional connectivity predicted conversion (AUC = 0.73–0.82). Compromised white matter integrity in uncinate fasciculus (fractional anisotropy: d = −0.47 to −0.71) and superior longitudinal fasciculus predicted transition. Elevated striatal glutamate predicted conversion (d = 0.52–0.76). Thalamocortical dysconnectivity showed large effects (Hedges’ g = 0.66–0.88). Multimodal imaging models achieved 78–85% classification accuracy. Conclusions: Neuroimaging biomarkers, particularly medial temporal and prefrontal structural alterations, functional dysconnectivity, and white matter abnormalities, demonstrate moderate-to-large effect sizes in predicting UHR conversion. Multimodal approaches combining structural, functional, and neurochemical measures show promise for individualized risk prediction and early intervention targeting in precision prevention strategies. Full article

Brain magnetic resonance imaging (MRI) is highly susceptible to motion artifacts that degrade fine structural details and undermine quantitative analysis. Conventional U-Net-based deep learning approaches for motion artifact reduction typically operate only in the image domain and are often trained on data with simplified motion patterns, thereby limiting physical plausibility and generalization. We propose Sim-DDNet, a simulation-data-based dual-domain network that combines k-space-based motion simulation with a joint image-k-space reconstruction architecture. Motion-corrupted data were generated from T2-weighted Alzheimer’s Disease Neuroimaging Initiative brain MR scans using a k-space replacement scheme with three to five random rotational and translational events per volume, yielding 69,283 paired samples (49,852/6969/12,462 for training/validation/testing). Sim-DDNet integrates a real-valued U-Net-like image branch and a complex-valued k-space branch using cross attention, FiLM-based feature modulation, soft data consistency, and composite loss comprising L1, structural similarity index measure (SSIM), perceptual, and k-space-weighted terms. On the independent test set, Sim-DDNet achieved a peak signal-to-noise ratio of 31.05 dB, SSIM of 0.85, and gradient magnitude similarity deviation of 0.077, consistently outperforming U-Net and U-Net++ across all three metrics while producing less blurring, fewer residual ghost/streak artifacts, and reduced hallucination of non-existent structures. These results indicate that dual-domain, data-consistency-aware learning, which explicitly exploits k-space information, is a promising approach for physically plausible motion artifact correction in brain MRI. Full article

Deep learning-based analysis of brain magnetic resonance imaging (MRI) plays a crucial role in the early diagnosis of Alzheimer’s disease (AD). However, data scarcity and racial bias present significant challenges to the generalization of diagnostic models. Large-scale public datasets, which are predominantly composed of Caucasian individuals, often lead to performance degradation when applied to other ethnic groups owing to domain shifts. To address these issues, this study proposes a two-stage transfer learning framework. Initially, a 3D ResNet model was pretrained on a large-scale Alzheimer’s disease neuroimaging initiative (ADNI) dataset to learn structural brain features. Subsequently, the pretrained weights were transferred and fine-tuned on a small-scale Korean dataset utilizing only 30% of the data for training. The proposed model achieved superior performance in classifying mild cognitive impairment (MCI), which is crucial for early diagnosis, compared with a model trained from scratch using 70% of the Korean data. Furthermore, it effectively mitigated the significant performance degradation observed when directly applying the pretrained model, demonstrating its ability to resolve the domain-shift issue. This study explored the feasibility of transfer learning to address data scarcity and domain shift issues in AD classification, underscoring its potential for developing AI-based diagnostic systems tailored to specific ethnic populations. Full article

Background/Objectives: This study aimed to characterize objective sleep measures in subacute acquired brain injury (ABI) and examine if disturbed sleep is associated with poor recovery outcomes. Another objective was to compare the functional connectivity of the brain between ABI poor sleepers and ABI normal sleepers as measured by resting state functional magnetic resonance imaging (rs-fMRI). Methods: This was a pilot, prospective, observational study of ABI subjects compared with age and gender-matched healthy controls. A total of 27 ABI subjects (consisting of ischemic or haemorrhagic stroke, or traumatic injury) were recruited from the outpatient clinics of a tertiary hospital with a neurological centre, and 49 healthy controls were recruited by word-of-mouth referrals. Study procedure involved subjective and objective sleep measures, self-report psychological measures, cognitive tests, and structural and functional MRI of the brain. Results: The frequency of poor-quality sleep was 66.67% in the ABI group and not significantly different from 67.35% in the control group when compared by chi-squared test (p = 0.68). ABI subjects with poor sleep had worse performance on a test of sustained attention (Colour Trails Test 1) than healthy controls with poor sleep when compared by Student’s t-test (mean 55.95 s, SD ± 18.48 vs. mean 40.04 s, SD ± 14.31, p = 0.01). Anxious ABI subjects have poorer sleep efficiency and greater time spent awake after sleep onset (WASO). ABI-poor sleepers show significantly greater functional connectivity within a frontoparietal network and bilateral cerebellum. Conclusions: Sleep problems after ABI are associated with poorer cognitive and psychological outcomes. ABI-poor sleepers exhibit altered functional connectivity within regions that contribute to motor planning, attention, and self-referential processes, suggesting that disrupted sleep after ABI may impair the integration of sensorimotor and cognitive control systems, and therefore, impair recovery. Full article

Background/Objectives: Drug-resistant epilepsy (DRE) is a significant health problem leading to cognitive impairment and reduced quality of life. This study aimed to investigate the incidence and etiology of DRE in children in Estonia. Methods: A retrospective, population-based study of childhood DRE was conducted in Estonia from 1 January 2013, to 31 December 2017. All cases were identified through the only two pediatric neurology departments in the country, both located at tertiary care hospitals (Tartu University Hospital and Tallinn Children’s Hospital), ensuring complete nationwide coverage. Epidemiological, magnetic resonance imaging (MRI), and genetic data (chromosomal microarray, single-gene tests, gene panels, and exome/genome sequencing) were collected. Results: The incidence rate of childhood epilepsy was 84.1 per 100,000. DRE developed in 10% of children with new-onset epilepsy, corresponding to an incidence rate of 8.5 per 100,000. Etiologically relevant MRI abnormalities were identified in 43% of patients with DRE, most commonly congenital brain malformations (19%). Pathogenic single-gene sequence variants were detected in 25 of 110 patients (23%), copy number variants in four patients (4%), and chromosomal aberrations in one patient (1%). Novel candidate disease genes of uncertain pathogenicity were identified in four patients (4%). The most frequent etiology of DRE was structural (29%), followed by genetic (19%), with combined etiologies (13%) also contributing significantly. Conclusions: Our study is the first epidemiological study of DRE in children in Estonia and the Baltic region. The relatively low incidence observed may reflect the comprehensive national ascertainment and centralized management of pediatric epilepsy in tertiary care centers. Full article

This work presents the development of an Artificial Intelligence (AI)-based pipeline for patient-specific three-dimensional (3D) reconstruction from oncological magnetic resonance imaging (MRI), leveraging image-derived information to enhance the analysis process. These developments were carried out within the framework of Cella Medical Solutions, forming part of a broader initiative to improve and optimize the company’s medical-image processing pipeline. The system integrates automatic MRI sequence classification using a ResNet-based architecture and segmentation of anatomical structures with a modular nnU-Net v2 framework. The classification stage achieved over 90% accuracy and showed improved segmentation performance over prior state-of-the-art pipelines, particularly for contrast-sensitive anatomies such as the hepatic vasculature and pancreas, where dedicated vascular networks showed Dice score differences of approximately 20–22%, and for musculoskeletal structures, where the model outperformed specialized networks in several elements. In terms of computational efficiency, the complete processing of a full MRI case, including sequence classification and segmentation, required approximately four minutes on the target hardware. The integration of sequence-aware information allows for a more comprehensive understanding of MRI signals, leading to more accurate delineations than approaches without such differentiation. From a clinical perspective, the proposed method has the potential to be integrated into surgical planning workflows. The segmentation outputs were converted into a patient-specific 3D model, which was subsequently integrated into Cella’s surgical planner as a proof of concept. This process illustrates the transition from voxel-wise anatomical labels to a fully navigable 3D reconstruction, representing a step toward more robust and personalized AI-driven medical-image analysis workflows that leverage sequence-aware information for enhanced clinical utility. Full article

Background/Objectives: Alzheimer’s disease (AD) has a prolonged preclinical phase and marked heterogeneity. Brain age and the Brain Age Gap (BAG), derived from neuroimaging and machine learning (ML), offer a non-invasive, system-level indicator of brain integrity, with potential relevance for early detection, risk stratification, and intervention monitoring. This review summarizes the conceptual basis, imaging characteristics, biological relevance, and explores its potential clinical utility of BAG across the AD continuum. Methods: We conducted a narrative synthesis of evidence from morphometric structural magnetic resonance imaging (sMRI), connectivity-based functional magnetic resonance imaging (fMRI), positron emission tomography (PET), and diffusion tensor imaging (DTI), alongside recent advances in deep learning architectures and multimodal fusion techniques. We further examined associations between BAG and the Amyloid/Tau/Neurodegeneration (A/T/N) framework, neuroinflammation, cognitive reserve, and lifestyle interventions. Results: BAG may reflect neurodegeneration associated with AD, showing greater deviations in individuals with mild cognitive impairment (MCI) and early AD, and is correlated with tau pathology, neuroinflammation, and metabolic or functional network dysregulation. Multimodal and deep learning approaches enhance the sensitivity of BAG to disease-related deviations. Longitudinal BAG changes outperform static BAG in forecasting cognitive decline, and lifestyle or exercise interventions can attenuate BAG acceleration. Conclusions: BAG emerges as a promising, dynamic, integrative, and modifiable complementary biomarker with the potential for assessing neurobiological resilience, disease staging, and personalized intervention monitoring in AD. While further standardization and large-scale validation are essential to support clinical translation, BAG provides a novel systems-level perspective on brain health across the AD continuum. Full article

Although Artificial Intelligence (AI) has achieved notable performance, particularly in medicine, the structural opacity leading to the black-box phenomenon inhibits interpretability, thus necessitating a balance (Symmetry) between performance and transparency. Specifically, in the medical domain, effective diagnosis requires that high predictive performance be symmetrically counterbalanced by sufficient trust and explainability for clinical practice. Existing visualization techniques like Grad-CAM can highlight attention regions but provide limited insight into the reasoning process and often focus on irrelevant areas. To address this limitation, we propose a Fuzzy Attention Rule (FAR) model that extends fuzzy inference to MRI (Magnetic Resonance Imaging) image classification. The FAR model applies pixel-level fuzzy membership functions and logical operations (AND, OR, AND + OR, AND × OR) to generate rule-based attention maps, enabling explainable and convolution-free feature extraction. Experiments on Kaggle’s Brain MRI and Alzheimer’s MRI datasets show that FAR achieves comparable accuracy to Resnet50 while using far fewer parameters and significantly outperforming MLP. Quantitative and qualitative analyses confirm that FAR focuses more precisely on lesion regions than Grad-CAM. These results demonstrate that fuzzy logic can enhance both the explainability and reliability of medical AI systems without compromising performance. Full article

Accurate co-registration between on-scalp Optically Pumped Magnetometer (OPM)–Magnetoencephalography (MEG) sensors and anatomical Magnetic Resonance Imaging (MRI) remains a critical bottleneck restricting the spatial fidelity of source localization. Optical Scanning Image (OSI) methods can provide high spatial accuracy but depend on surface visibility and cannot directly determine the internal sensitive point of each OPM sensor. Coil-based magnetic dipole localization, in contrast, targets the sensor’s internal sensitive volume and is robust to occlusion, yet its accuracy is affected by coil fabrication imperfections and the validity of the dipole approximation. To integrate the complementary advantages of both approaches, we propose a hybrid co-registration framework that combines Rigid Coil Structures (RCS), magnetic dipole-based sensor localization, and optical orientation constraints. A complete multi-stage co-registration pipeline is established through a unified mathematical formulation, including MRI–OSI alignment, OSI–RCS transformation, and final RCS–sensor localization. Systematic simulations are conducted to evaluate the accuracy of the magnetic dipole approximation for both cylindrical helical coils and planar single-turn coils. The results quantify how wire diameter, coil radius, and turn number influence dipole model fidelity and offer practical guidelines for coil design. Experiments using 18 coils and 11 single-axis OPMs demonstrate positional accuracy of a few millimeters, and optical orientation priors suppress dipole-only orientation ambiguity in unstable channels. To improve the stability of sensor orientation estimation, optical scanning of surface markers is incorporated as a soft constraint, yielding substantial improvements for channels that exhibit unstable results under dipole-only optimization. Overall, the proposed hybrid framework demonstrates the feasibility of combining magnetic and optical information for robust OPM–MEG co-registration. Full article

The promise of intracortical neural interfaces—to restore lost sensory and motor function and probe the brain’s activity—has long been constrained by device instability over chronic implantation. Conventional silicon-based probes, composed of heterogeneous materials, often fail due to mechanical mismatch, inflammatory responses, and interface-driven degradation, where stress can induce cracking, swelling, and exposure of cytotoxic elements to neural tissue. Silicon carbide (SiC) offers a compelling solution, combining chemical inertness, structural strength, and biocompatibility in both amorphous and crystalline forms. In this review, we discuss advances in SiC neural interfaces, highlighting contributions from multiple laboratories and emphasizing our own work on monolithic devices, constructed entirely from a single, homogeneous SiC material system. These devices mitigate interface-driven failures and show preliminary indications of magnetic resonance imaging (MRI) compatibility, with minimal image artifacts observed compared to conventional silicon probes, though further in vivo studies are needed to confirm thermal safety at high-field conditions. Collectively, SiC establishes a versatile platform for next-generation, durable neural interfaces capable of reliable, long-term brain interaction for both scientific and clinical applications. Full article

Alzheimer’s disease (AD) is a neurodegenerative condition that gradually deteriorates memory and cognitive abilities, posing a significant global health challenge. While convolutional neural networks (CNNs) applied to structural magnetic resonance imaging (MRI) have achieved high diagnostic accuracy, their decision-making processes often lack transparency, which can limit clinical trust. This study presents a structured evaluation framework by applying multiple gradient-based and model-agnostic interpretability methods, such as Grad-CAM, Grad-CAM++, HiRes-CAM, Backpropagation, Guided Backpropagation, Kernel SHAP, LIME, and RISE, to pre-trained and custom CNN architectures for AD classification. We utilized the ADNI MRI dataset and assessed models based on accuracy, sensitivity, specificity, and visual alignment of highlighted brain regions with established biomarkers. By analyzing both predictive performance and explanation validity, this study aims to assist clinicians in making informed diagnoses, ultimately strengthening trust in AI-assisted tools. Full article

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder characterized by subtle structural changes in the brain, which can be observed through MRI scans. Although traditional diagnostic approaches rely on clinical and neuropsychological assessments, deep learning-based methods such as 3D convolutional neural networks (CNNs) have recently been introduced to improve diagnostic accuracy. However, their high computational complexity remains a challenge. To address this, we propose a lightweight magnetic resonance imaging (MRI) classification framework that integrates adaptive multi-scale feature extraction with structural pruning and parameter optimization. The pruned model achieving a compact architecture with approximately 490k parameters (0.49 million), 4.39 billion floating-point operations, and a model size of 1.9 MB, while maintaining high classification performance across three binary tasks. The proposed framework was evaluated on the Alzheimer’s Disease Neuroimaging Initiative dataset, a widely used benchmark for AD research. Notably, the model achieves a performance density(PD) of 189.87, where PD is a custom efficiency metric defined as the classification accuracy per million parameters (% pm), which is approximately 70× higher than the basemodel, reflecting its balance between accuracy and computational efficiency. Experimental results demonstrate that the proposed framework significantly reduces resource consumption without compromising diagnostic performance, providing a practical foundation for real-time and resource-constrained clinical applications in Alzheimer’s disease detection. Full article

Background: The clinical imperative to reduce patient ionizing radiation exposure during diagnosis and treatment planning necessitates robust, high-fidelity synthetic imaging solutions. Current cross-modal synthesis techniques, primarily based on GANs and deterministic CNNs, exhibit instability and critical errors in modeling high-contrast tissues, thereby hindering their reliability for safety-critical applications such as radiotherapy. Objectives: Our primary objective was to develop a stable, high accuracy framework for 3D Magnetic Resonance Imaging (MRI) to Computed Tomography (CT) synthesis capable of generating clinically equivalent synthetic CTs (sCTs) across multiple anatomical sites. Methods: We introduce a novel 3D Latent Diffusion Model (3DLDM) that operates in a compressed latent space, mitigating the computational burden of 3D diffusion while leveraging the stability of the denoising objective. Results: Across the Head & Neck, Thorax, and Abdomen, the 3DLDM achieved a Mean Absolute Error (MAE) of 56.44 Hounsfield Units (HU). This result demonstrates a significant 3.63% reduction in overall error compared to the strongest adversarial baseline, CycleGAN (MAE = 60.07 HU, p < 0.05), a 10.76% reduction compared to NNUNet (MAE = 67.20 HU, p < 0.01), and a 20.79% reduction compared to the transformer-based SwinUNeTr (MAE = 77.23 HU, p < 0.0001). The model also achieved the highest structural similarity (SSIM = 0.885 ± 0.031), significantly exceeding SwinUNeTr (p < 0.0001), NNUNet (p < 0.01), and Pix2Pix (p < 0.0001). Likewise, the 3D-LDM achieved the highest peak signal-to-noise ratio (PSNR = 29.73 ± 1.60 dB), with statistically significant gains over CycleGAN (p < 0.01), NNUNet (p < 0.001), and SwinUNeTr (p < 0.0001). Conclusions: This work validates a scalable, accurate approach for volumetric synthesis, positioning the 3DLDM to enable MR-only radiotherapy planning and accelerate radiation-free multi-modal imaging in the clinic. Full article

Background/Objectives: The stellate ganglion (SG), formed by the fusion of the inferior cervical and first thoracic sympathetic ganglia in approximately 80% of individuals, plays crucial roles in cardiac innervation, pain management, and autonomic regulation. This review examines the anatomical variations, histological structure, clinical applications, and therapeutic implications of the SG and stellate ganglion block (SGB), presenting original high-resolution magnetic resonance imaging (MRI) evidence of SG visualization, an underutilized approach in autonomic nervous system research. Methods: We conducted a comprehensive literature review of anatomical, physiological, and clinical studies on the SG, incorporating original anatomical dissections and high-resolution MRI. Contemporary research on SGB applications, complications, and mechanisms of action was analysed and correlated with imaging characteristics. Results: The SG demonstrates significant anatomical variability, including the presence of intermediate ganglia, accessory nerve pathways, and variable relationships with surrounding vascular structures. Our original MRI imaging consistently identified the SG at the thoracic inlet, anterior to the neck of the first rib, lateral to the longus colli muscle, and posterior to the vertebral artery, demonstrating that advanced imaging can reliably visualize this critical autonomic structure and its anatomical variants. Histologically, it contains typical sympathetic architecture, comprising postganglionic neurons, satellite glial cells, and specialized SIF cells that modulate ganglionic transmission. SGB shows therapeutic efficacy across diverse conditions, including cardiac arrhythmias, chronic pain syndromes, post-traumatic stress disorder, sleep disorders, and immune dysfunction. The procedure’s mechanisms involve both direct sympathetic blockade and complex neuroimmune pathways that affect central autonomic centers and lymphoid organs. Complications include vascular injury, pneumothorax, and nerve blocks affecting the recurrent laryngeal and phrenic nerves. Conclusions: The SG represents a critical autonomic structure with expanding clinical applications. This work advances the field by demonstrating that high-resolution MRI can consistently and non-invasively visualize the SG and its anatomical variations, knowledge previously mostly limited to cadaveric studies. Understanding these imaging-defined anatomical variations is essential for optimizing therapeutic interventions. Advanced imaging guidance integrated with comprehensive anatomical knowledge is crucial for maximizing efficacy while minimizing complications in stellate ganglion block procedures. Full article