Search Results (2,420)

Background/Objectives: Brain tumor analysis using magnetic resonance imaging (MRI) remains a challenging task due to tumor heterogeneity, complex anatomical structures, and reliance on expert interpretation. Although deep learning approaches have shown promising results in medical image analysis, many existing studies focus on either tumor classification or segmentation independently, limiting their applicability in comprehensive automated brain tumor analysis workflows. This study proposes an integrated dual-task deep learning framework for automated brain tumor classification and segmentation using MRI scans. The framework aims to provide complementary diagnostic support by combining tumor-type prediction and tumor boundary delineation within an integrated workflow. Methods: The proposed framework utilizes EfficientNet-based convolutional neural networks for multi-class brain tumor classification and U-Net++ architectures with EfficientNet encoders for tumor segmentation. Experiments were conducted using the BRISC2025 dataset, consisting primarily of 6000 T1-weighted 2D MRI slices collected from axial, coronal, and sagittal planes. Standard preprocessing, augmentation, transfer learning, and selective fine-tuning strategies were applied. Multiple architectures were systematically evaluated using evaluation metrics. Results: EfficientNet-B1 achieved a classification accuracy of 99.70% with near-perfect precision, recall, and F1-scores across glioma, meningioma, pituitary tumor, and no-tumor classes. For segmentation, U-Net++ with an EfficientNet-B1 encoder achieved a Dice score of 0.9055, an IoU score of 0.8442, and an HD95 value of 12.21 pixels on the held-out test set. The proposed framework demonstrated robust performance in detecting small and low-contrast tumor regions while maintaining strong generalization performance across diverse MRI samples. Conclusions: The proposed integrated framework demonstrated strong performance in both brain tumor classification and segmentation tasks, effectively detecting small and low-contrast tumor regions while maintaining good generalization across diverse MRI samples. These findings suggest that the framework may serve as a reliable decision-support tool for automated brain tumor analysis in clinical practice. Full article

Neuroticism, a Big Five trait characterized by emotional instability and susceptibility to negative affect, is a robust transdiagnostic predictor for the onset, severity, and persistence of anxiety disorders, major depressive disorder (MDD), and other affective conditions. Recent advances in functional magnetic resonance imaging (fMRI) techniques—including resting-state fMRI, multimodal neuroimaging, and their integration with machine learning—have enabled multi-perspective investigations into the neural substrates of neuroticism. Current research in this field primarily follows three complementary approaches: cross-sectional studies identifying key brain regions for emotional processing and cognitive control (e.g., amygdala (AMG), prefrontal cortex); longitudinal studies capturing neural mechanisms evolution across adolescence, middle age, and old age to elucidate relationships between neuroticism and brain plasticity; and intervention studies exploring plastic pathways for reshaping the neural representations of neuroticism, challenging the classic “trait stability” paradigm. This review synthesizes recent progress in the cognitive neuroscience of neuroticism across these three approaches, proposes a unified emotion-cognition neural model centered on the AMG-prefrontal-default mode network circuit, and outlines a hypothesized lifespan trajectory of Limbic Sensitivity → Regulatory Strain → Prefrontal Decline. While accumulated evidence broadly supports the cross-sectional and interventional pillars of this framework, the lifespan trajectory remains a theoretically informed working model requiring further longitudinal validation. The field still faces critical limitations, including small effect sizes, methodological heterogeneity, and unresolved questions regarding causality and circuit specificity. This review aims to provide a conceptual integration of existing findings, identify key uncertainties, and propose evidence-based future directions. We further link the proposed neural model to clinical phenotypic characteristics of high neuroticism and discuss its implications for targeted neural interventions, thereby advancing our understanding of the biological basis of neuroticism and providing a theoretical framework for prevention and intervention in neuroticism-related affective disorders. Full article

49,XXXXY syndrome (Fraccaro syndrome) is a rare sex chromosome pentasomy, historically considered a severe variant within the Klinefelter spectrum. It is characterized by intellectual disability, craniofacial dysmorphism, skeletal anomalies, hypogonadism, and congenital cardiac defects. Although neuroimaging abnormalities have increasingly been recognized in 49,XXXXY syndrome, neonatal diagnosis prompted primarily by ventriculomegaly remains rare. We report a neonate with prenatally detected ventriculomegaly in whom postnatal evaluation revealed cleft palate, congenital cardiac defects, bilateral cryptorchidism, and auditory dysfunction. Cranial ultrasonography and brain magnetic resonance imaging demonstrated bilateral ventriculomegaly with colpocephaly and a cavum vergae variant. Cytogenetic analysis confirmed the presence of a 49,XXXXY karyotype. This case highlights ventriculomegaly as a potential early diagnostic clue in 49,XXXXY syndrome and underscores the importance of chromosomal analysis in neonates presenting with structural brain abnormalities associated with multisystem anomalies. Early recognition is important for timely multidisciplinary surveillance and long-term endocrine follow-up. Full article

Introduction: Progressive supranuclear palsy (PSP) is an atypical Parkinsonian disorder characterized by a range of clinical phenotypes, reflecting its multiple subtypes. As a result, accurate diagnosis during life remains challenging, underscoring the need for reliable biomarkers. The present narrative review aims to evaluate whether dopamine transporter single-photon emission computed tomography (DaT-SPECT) can serve as a biomarker in the assessment of PSP. Methods: The database search identified 31 original research articles relevant to our study objective. Of these, 17 studies included PSP patients and utilized DaT-SPECT as the sole molecular imaging modality; 9 studies combined DaT-SPECT with at least one additional molecular imaging technique; and 5 studies integrated DaT-SPECT with a laboratory-based biomarker of neurodegenerative disease. Results: DaT-SPECT appears to demonstrate low specificity and variable sensitivity for PSP across studies. Discussion: Combining DaT-SPECT with other diagnostic biomarkers, especially brain magnetic resonance imaging and other nuclear imaging modalities, may improve diagnostic accuracy, especially given its relatively low specificity for PSP. Nevertheless, these initially promising findings need to be validated in large, multicenter studies that include and clearly define multiple, autopsy-confirmed PSP subtypes. Full article

Background: While disease-modifying therapies reduce inflammatory activity in multiple sclerosis (MS), long-term disability progression remains insufficiently controlled. Increasing evidence points to modifiable environmental and lifestyle factors—such as smoking, sun exposure, comorbidities, and obesity—as contributors to neurodegeneration and progression independent of relapse activity. Objective: To evaluate the associations between smoking, comorbid conditions, sun exposure, and obesity on clinical and radiological progression in patients with relapsing–remitting MS (RRMS) over a 48-month observational period. Methods: We performed a retrospective secondary analysis of a previously described longitudinal cohort of 132 patients with RRMS who were monitored over four years with serial assessments of EDSS, magnetic resonance imaging (MRI) inflammatory activity as gadolinium-enhancing lesions (GELs), new or enlarged T2-weighted lesions, serum 25(OH)D levels, and linear brain atrophy metrics. Sun exposure, smoking status, obesity, and comorbidity burden were recorded at each time point. Results: Low sun exposure was associated with higher EDSS trajectories and lower serum 25(OH)D levels (p < 0.01). Smoking was associated with a higher probability of GELs (p < 0.05), while comorbidities were associated with relapse occurrence and GELs. Obesity was associated with vitamin D insufficiency but not clearly with clinical relapse activity, GELs, or EDSS trajectories. MRI-based indices confirmed increasing brain atrophy during follow-up, particularly in patients with multiple risk factors. Conclusions: Our findings suggest that selected modifiable lifestyle and clinical factors are associated with distinct clinical and radiological outcomes in RRMS. Integrating sun-safe outdoor activity, smoking cessation, comorbidity management, and weight control into MS care may support comprehensive risk management alongside pharmacological therapy. Full article

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder characterized by cognitive decline and memory impairment, most commonly observed in older adults. Accurate classification of AD-related conditions from magnetic resonance imaging (MRI) plays an important role in supporting research and analytical studies in medical imaging. In this study, we investigate the performance of deep learning models for multi-class classification of AD-related diagnostic categories using MRI data. Convolutional Neural Network (CNN), Residual Network (ResNet-50), and Densely Connected Convolutional Network (DenseNet121) architectures were evaluated on a five-class dataset derived from the TR-MoH (Ministry of Health of the Republic of Türkiye), consisting of Alzheimer’s disease–related diagnostic codes. A consistent preprocessing pipeline, including slice extraction, resizing, normalization, and data augmentation, was applied prior to model training. In addition, experiments on a publicly available Kaggle dataset were conducted to assess model behavior across datasets with different characteristics. Grad-CAM visualizations were additionally employed to improve model interpretability by highlighting the brain regions that contributed most to the classification decisions. The results show that individual models achieved accuracy values ranging from 89.31% to 91.07% on the TR-MoH dataset and from 98.86% to 99.93% on the Kaggle dataset. A weighted ensemble approach combining multiple architectures yielded the most effective results, reaching 93.05% and 99.94% on the respective datasets. These results indicate that deep learning models can effectively learn discriminative patterns from heterogeneous MRI data and perform multi-class classification tasks with notable class differentiation capability. However, the results should be interpreted within the scope of the defined classification problem and dataset characteristics. Overall, the study highlights the potential of ensemble-based deep learning approaches for supporting MRI-based categorization of AD-related conditions in a research context. Full article

Background: Cognitive difficulties are common after SARS-CoV-2 infection, yet their neurobiological underpinnings remain uncertain. Cognitive symptoms in post-COVID-19 condition (PCC) are often characterised by attentional and executive dysfunction, although the relationship between subjective symptoms and objective neurobiological changes remains uncertain. Methods: Adults previously hospitalised with COVID-19 who reported persistent cognitive symptoms underwent neuropsychological testing and 3 T MRI. The protocol included high-resolution volumetric imaging, diffusion-based tractography, and magnetic resonance spectroscopy (MRS) of frontal white matter. Data were compared with age- and sex-matched controls from a pre-COVID-19 cohort and against pooled normative MRS datasets. Analyses adjusted for intracranial volume, sex, and time since infection, with false-discovery-rate correction. This study was exploratory and hypothesis-generating in design. Results: Thirty participants were recruited; twenty-nine completed MRI acquisition. Participants (mean age 58 years; 62% female; approximately two years post-infection) demonstrated selective impairments in attention, working memory, and verbal fluency. No widespread volumetric or white-matter differences were identified, although reduced posterior hypothalamic volume and altered occipito-parietal connectivity were observed. MRS demonstrated reduced N-acetylaspartate and elevated choline, myo-inositol, and glutamate-glutamine ratios relative to normative reference ranges. No significant associations were observed between imaging measures and cognitive or symptoms outcomes after correction. Conclusions: PCC is characterised by circumscribed cognitive changes and subtle neural differences, but these objective changes do not closely align with subjective symptom severity. This mismatch shares phenotypic features with functional cognitive disorder and suggests that post-COVID-19 “brain fog” is not driven by structural or neurochemical changes alone. Instead, it potentially reflects a combination of mild neurobiological effects and functional cognitive processes. Together, these findings highlight the importance of considering both brain-based and functional contributors to persistent cognitive complaints after SARS-CoV-2 infection. Full article

Background/Objectives: Accurate automatic segmentation of multimodal magnetic resonance imaging (MRI) is essential for neurosurgical planning and image-guided procedures. However, existing three-dimensional segmentation models often struggle with low lesion-to-tissue contrast, ambiguous tumor boundaries, small enhancing tumor regions, and performance degradation caused by missing imaging modalities. This study aimed to develop a robust segmentation framework that improves cross-modal representation learning, boundary recovery, and segmentation performance under incomplete-input conditions. Methods: We propose PF-CMNet, a Progressive Frequency-Aware Cross-Modal Network with Missing-Modality Distillation for three-dimensional brain tumor segmentation. The network introduces a Cross-Modal Selective Frequency Attention module in the early encoder stage to model modality-specific frequency responses and spatially adaptive cross-modal correlations. A Progressive Cross-Scale Detail Fusion decoder is further employed to aggregate multilevel semantic features and refine high-resolution boundary details. To enhance robustness under missing-modality conditions, a teacher–student distillation strategy transfers full-modality predictions and shallow feature knowledge to a student network trained with random modality dropout. Results: On the MSD Task01_BrainTumour dataset, PF-CMNet achieved an average Dice score of 84.3%, with Dice scores of 79.6%, 82.8%, and 90.4% for enhancing tumor, tumor core, and whole tumor, respectively. On the BraTS2021 dataset, the model achieved an average Dice score of 88.2% and the lowest average 95th percentile Hausdorff distance among the compared methods. In predefined complete-modality absence stress tests, where unavailable MRI sequences were zero-masked to model the absence of input modalities rather than partial image degradation, the distilled model maintained average Dice scores of 78.64%, 82.58%, 58.39%, 82.03%, and 79.29% when FLAIR, T1, T1ce, T2, and T1 + T2 were unavailable, respectively. Conclusions: PF-CMNet provides a unified framework for multimodal brain tumor segmentation, improving full-modality segmentation accuracy, boundary consistency, and robustness to incomplete MRI inputs while maintaining a favorable accuracy–efficiency trade-off. Full article

Objectives: Contrast-enhanced magnetic resonance imaging (CE-MRI) plays an important role in the diagnosis, treatment monitoring, and follow-up of brain tumors. However, the use of gadolinium-based contrast agents (GBCAs) is limited in patients with contraindications, such as severe renal impairment or situations requiring repeated examinations. This study aimed to develop a diffusion model-based Difference-Aware Guided Control Network (DAGCN) for synthesizing high-quality contrast-enhanced T1-weighted MRI (T1-CE) from non-contrast T1-weighted images in combination with an auxiliary sequence. Methods: Using the BraTS 2021 dataset, we proposed a two-stage generative framework that first localizes lesion-related enhancement cues and then guides image synthesis. In the first stage, a Difference-Aware Fusion and Prediction (DAFP) module was designed to extract complementary information from non-contrast T1-weighted images and an auxiliary sequence (T2-weighted or FLAIR) through dual-branch feature extraction and cross-modal channel attention fusion, followed by prediction of a lesion-related discrepancy map. In the second stage, the predicted discrepancy map was concatenated with the original T1-weighted images and introduced into a ControlNet-guided diffusion model to constrain the reverse denoising process and generate the target T1-CE image. Model performance was evaluated by visual comparison, quantitative metrics including peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), visual information fidelity (VIF), and normalized cross-correlation (NCC), as well as blinded radiologist scoring of image quality (IQ), clinical replaceability (IC), contrast enhancement (CE), and lesion conformity (CF). Results: DAGCN generated synthetic T1-CE images with preserved global anatomical structure and faithful local lesion enhancement without the need for contrast agent administration. Compared with baseline methods, DAGCN achieved the highest PSNR and NCC under both T1 + T2 and T1 + FLAIR settings, while showing competitive SSIM and VIF performance. Visual comparison and radiologist-based subjective evaluation further indicated improved lesion-focused enhancement fidelity and reduced false-positive enhancement. Among the two auxiliary sequence settings, the T1 + FLAIR configuration provided more specific lesion localization and cleaner background suppression than the T1 + T2 configuration, particularly by reducing interference from cerebrospinal fluid signals. Conclusions: The proposed DAGCN framework enables the synthesis of clinically informative contrast-enhanced-like MRI from non-contrast multi-sequence inputs and may provide a promising alternative for patients in whom gadolinium administration is contraindicated or should be avoided. In particular, the FLAIR-guided setting showed advantages in lesion specificity, background cleanliness, and overall diagnostic quality. Full article

Background: Diagnostic anchoring to a presumed infectious etiology may delay recognition of underlying genetic disorders in children with neurodevelopmental impairment. Case presentation: A case of a child with sensorineural hearing loss, visual impairment, and developmental delay is reported; cytomegalovirus (CMV) infection was identified at 6 months of age based on positive serology and detection of viral DNA in serum and urine. Given the timing of testing, congenital CMV infection (cCMV) could not be definitively confirmed. Antiviral therapy with valganciclovir was administered. Despite antiviral treatment, severe neurodevelopmental impairment and hearing loss persisted, associated with facial dysmorphism, bilateral cryptorchidism, pectus excavatum, and optic nerve hypoplasia, findings not fully attributable to CMV infection. Brain magnetic resonance imaging (MRI) showed nonspecific findings. Chromosomal microarray analysis (CMA) performed at 4.5 years of age identified a heterozygous 908 kb de novo microdeletion at 19p13.2p13.13 containing NFIX (MIM *164005) and other morbid genes. The de novo variant was confirmed by parental testing, and the unifying genetic diagnosis of NFIX-related Malan syndrome (MIM#614753) was established. Conclusions: This case emphasizes the importance of reconsidering the initial diagnosis when the clinical phenotype is not fully consistent with an infectious etiology. Early genomic testing, including CMA, may facilitate timely recognition of underlying genetic syndromes in children with complex neurodevelopmental presentations. Full article

Early and accurate brain tumor detection is vital for effective treatment. We propose a deep learning framework for MRI-based brain tumor classification, featuring a novel Custom CNN evaluated independently alongside six pre-trained models for comparative analysis (InceptionV3, EfficientNetV2L, ResNet152V2, Xception, VGG16, and MobileNetV2). Additionally, three separate ensemble models are constructed to analyze whether model combination improves performance. Experiments conducted on the Kaggle-Multiclass brain MRI dataset show that the proposed Custom CNN achieves the best performance, with an accuracy of 99.54%, and features a task-specific architecture (0.57M parameters) that achieves superior performance through domain-specific feature learning and computational efficiency, thus outperforming both individual pre-trained models and ensemble approaches. Among pre-trained models, EfficientNetV2L (99.47%) and InceptionV3 (99.39%) show competitive results, while the best ensemble model achieves 99.47% accuracy, indicating clinical deployment potential pending external validation. These results demonstrate that the proposed Custom CNN provides superior performance without requiring ensemble complexity, thus highlighting its effectiveness and efficiency for automated brain tumor classification. Full article

Background: Chemotherapy-induced peripheral neuropathy (CIPN) is a common, disabling toxicity with no validated biomarkers. MRI-based functional neuroimaging could offer insight into central pain processing and may reveal reproducible brain signatures of CIPN. Methods: Following PRISMA 2020 (PROSPERO: CRD420251132102), we systematically reviewed whole-brain MRI studies in adult cancer patients with CIPN. Eligible MRI techniques included task-based fMRI, resting-state fMRI, perfusion MRI, and structural MRI. Data were synthesized through voxelwise activation likelihood estimation (ALE), systems-level region-of-interest (ROI) mapping, and proportion meta-analysis of regional involvement. Results: Of 2488 screened records, five observational studies were included. The voxelwise ALE analysis did not identify clusters surviving correction, but dispersed foci appeared within the default mode network (DMN), prefrontal executive cortex, and primary sensorimotor regions, suggesting the engagement of these pain-processing networks. ROI synthesis confirmed consistent alterations in the DMN and executive prefrontal and sensorimotor cortices in CIPN patients compared with controls, while the brainstem/periaqueductal gray and cerebellum were rarely implicated. Proportion meta-analysis further quantified these differences: CIPN patients showed altered involvement in 30% (95% CI 0.16–0.48) of contrasts, with the highest frequencies in the DMN (50%), sensorimotor (33%), and executive prefrontal regions (33%). By contrast, control-higher contrasts were less frequent (10%, 95% CI 0.03–0.27), highlighting CIPN-related increases particularly in self-referential and somatosensory networks. Conclusions: Across analytic approaches, CIPN is characterized by reproducible alterations in the DMN and executive prefrontal and sensorimotor networks. These central pain signatures represent promising MRI-based biomarkers for identifying and monitoring CIPN in oncology. Full article

Background: Accurate brain tumor segmentation from Magnetic Resonance Imaging (MRI) depends on the fusion of multiple complementary modalities. However, clinical practice often faces incomplete modality sets due to acquisition failures, patient contraindications, or protocol variations. Current methods either treat each modality feature extractor in isolation or depend on computationally expensive teacher networks for cross-modal knowledge transfer. Objective: This paper presents Hierarchical Adaptive Group Self-Support Learning with Boundary-Aware Calibration (HAGSS), a framework that overcomes three key limitations of existing group self-support methods: static group formation that ignores temporal prediction quality, uniform treatment of boundary and interior voxels, and distribution mismatch across heterogeneous modality logits. Methods: We propose a hierarchical adaptive group formation mechanism that reassigns group leader roles at each epoch based on voxel-level prediction confidence scores instead of fixed sensitivity priors. We also introduce a boundary-aware calibration module that applies spatially varied distillation weights with greater emphasis on tumor boundary regions. In addition, we design a cross-scale consistency regularization term that enforces agreement between multi-resolution predictions to stabilize the self-support target. Results: Experiments on BraTS2020, BraTS2018, and BraTS2021 datasets show that HAGSS achieves consistent improvements over state-of-the-art baselines. The average Dice gains across the whole tumor, tumor core, and enhancing tumor regions reach 1.30% on BraTS2020 and 1.61% on BraTS2021 compared to existing methods. All improvements are statistically significant ($p<0.05$). Conclusions: HAGSS operates exclusively during training, adds no parameters or inference cost, and can be applied as a plug-in module to any multi-encoder incomplete multi-modal segmentation architecture. Code is publicly available at GitHub. Full article

Attention Deficit Hyperactivity Disorder (ADHD) is a heterogeneous neurodevelopmental disorder whose diagnosis is mainly based on behavioral assessment and is often delayed due to clinical complexity and limited availability of specialists. Resting-state functional magnetic resonance imaging (rs-fMRI) provides a valuable source of information for supporting automated and objective diagnosis. However, existing studies often do not fully capture the complex interactions of functional connectivity between different brain regions. To address this limitation, this work proposes a graph-based deep learning framework for ADHD classification from rs-fMRI that combines functional connectivity modeling with graph representation learning. The approach used Phase-Locking Value (PLV)-based connectivity estimation and Graph Sample and Aggregate (GraphSAGE) to jointly capture regional brain activity and inter-regional interactions in a scalable and efficient manner. GraphSAGE improves robustness to noise and inter-subject variability by aggregating information from stable local graph neighborhoods. This integration allows the model to learn discriminative connectivity-aware representations while remaining robust to signal variability and adaptable to multi-site data. The proposed framework was evaluated on the publicly available ADHD-200 dataset across multiple acquisition sites as well as on a combined multi-site dataset. The results indicate consistent performance across individual sites and on the combined dataset. The model achieved an Accuracy of 0.89, an AUC of 0.96, and a Specificity of 0.96 on the combined dataset, outperforming several existing methods in this setting. By integrating PLV-based connectivity with GraphSAGE learning, the approach provides an effective and scalable solution for automated ADHD classification from rs-fMRI data, contributing to data-driven approaches for the analysis of neurodevelopmental disorders. Full article

Objective: Rapid-sequence magnetic resonance imaging (rMRI) has emerged as a radiation-free alternative to computed tomography (CT) in pediatric neuroimaging. This study aimed to evaluate the diagnostic utility, clinical consequences, and subgroup-specific differences in pediatric patients undergoing rMRI for emergency neurosurgical indications. Methods: We conducted a retrospective, single-center study of 158 rMRIs in 73 pediatric patients who underwent rMRI between January 2017 and December 2023 due to suspected complications of hydrocephalus and brain tumors. A short MRI protocol (195 s) including FLAIR BLADE and T2 HATSE sequences was employed. Patients were categorized into tumor non-related and tumor-related hydrocephalus groups. Results: A total of 158 rMRIs in 73 pediatric patients were included. The mean age was 7.09 ± 4.63 years, with 69.6% male patients. Ventricular size monitoring was the most common rMRI indication (96.2%). Clinical consequences followed in 52.5% of cases, including surgical interventions (21.5%) and shunt valve adjustments (37.3%). Sedation was required in only 5.1% of patients. Only 1.9% required follow-up CT. Statistically significant intergroup differences were found in drainage type (p < 0.001), diagnosis (p < 0.001), and need for follow-up MRI (17.4% in the tumor-related hydrocephalus group vs. 4.5% in the tumor non-related hydrocephalus group; p = 0.014). Conclusions: rMRI is a safe, efficient, and effective alternative to CT for emergency neuroimaging in pediatric patients with hydrocephalus, tumors, or shunts. It facilitates timely clinical decision-making while avoiding radiation exposure. Our findings support broader implementation of rMRI protocols, particularly for patients requiring ongoing tumor surveillance. Full article