Search Results (1,310)

Background: The Magnetic Resonance Imaging (MRI)-based tumor segmentation remains a challenging problem in medical imaging due to tumor heterogeneity, unpredictable morphological features, and the high complexity of calculations needed to implement it in clinical practice, putting it out of the scope of real-time applications. Although neural networks have significantly improved segmentation performance, they still struggle to capture morphological tumor features while maintaining computational efficiency. This work introduces Hybrid Adaptive Attention U-Net (HAAU-Net) framework, combining context-aware morphologically stable features and spatial channel attention to achieve high-quality tumor segmentation with less computational cost. Methods: The proposed HAAU-Net framework integrates multi-scale Adaptive Attention Blocks (AAB), Context-Aware Morphological Feature Module (CAMFM) and Spatial-Channel Hybrid Attention Mechanism (SCHAM). CAMFM is used to maintain the stability of morphological features by hierarchical aggregation and dynamic normalization of features. SCHAM enhances feature representation by modelling channels and spatial regions where the strongest feature are determined to use in segmentation. On the BRaTS 2022/2023 data, the proposed HAAU-Net is evaluated using four modalities including T1, T1GD, T2 and T2-FLAIR sequences. Results: The proposed model able to obtain 96.8% segmentation accuracy with a Dice coefficient of 0.89 on the entire tumor region, outperforming the alternative U-Net (0.83) and conventional CNN methods of segmentation (0.81). The proposed HAAU-Net architecture cuts the computational complexity of the standard deep learning models by 43% and still achieve real-time inference (28 FPS on a regular GPU). The hybrid model used to predict survival has a C-Index of 0.91 which is higher than the traditional SVM-based methods (0.72). Conclusions: Spatial-channel attention, combined with morphologically stable features, can be combined to allow clinically significant interpretability in attention maps. The proposed framework significantly improves segmentation performance while maintaining computational effeciency. This broad system has a serious potential of AI-enabled clinical decision support system and early prognostic diagnosis in neuro-oncology with practical deployment capability. Full article

Background/Objectives: Risk stratification in asymptomatic carotid stenosis has traditionally relied on the degree of luminal narrowing; however, plaque vulnerability may better predict cerebrovascular events. Ipsilateral silent brain lesions (SBLs) are considered surrogate markers of stroke risk. This study aimed to identify carotid plaque features on duplex ultrasound (DUS) and computed tomography angiography (CTA), as well as circulating biomarkers, associated with ipsilateral SBL in patients with clinically asymptomatic ≥70% internal carotid artery stenosis. Methods: This prospective observational study with cross-sectional imaging analysis included 316 clinically asymptomatic patients with ≥70% carotid stenosis treated between January 2022 and October 2024. All patients underwent cranial non-contrast CT for SBL detection, DUS plaque characterization (according to the Gray–Weale classification and plaque surface morphology), and CTA analysis, including plaque surface, composition, length, and attenuation values categorized according to Schroeder’s criteria (<50 HU lipid-rich; 51–120 HU fibrous; >120 HU calcified). Demographic, clinical, and laboratory parameters, including inflammatory biomarkers, were recorded. Multivariate logistic regression was performed to identify independent predictors of SBL. Results: SBL were detected in 72 patients (22.8%). On DUS, SBL were significantly associated with Gray–Weale class II plaques, heterogeneous composition, and irregular or ulcerated surfaces (all p < 0.001). On CTA, lipid-rich plaques (<50 HU), ulcerated surfaces, heterogeneous morphology, and lower median plaque density were significantly more frequent in the SBL group (all p < 0.001). In multivariate analysis, independent predictors of SBL were male sex (OR 2.2; 95% CI 1.2–5.7; p = 0.029), Gray–Weale class II plaques (p = 0.002), lipid-rich plaque morphology (OR 21.39; 95% CI 6.86–66.76; p < 0.001), and ulcerated plaque surface on CTA (OR 20.62; 95% CI 7.37–57.68; p < 0.001). Conclusions: Specific ultrasound and CT plaque characteristics were associated with ipsilateral silent brain lesions in patients with asymptomatic ≥70% carotid stenosis. A multiparametric imaging approach may improve risk stratification beyond stenosis severity alone. Full article

Background: Glioblastoma (GBM) remains the most aggressive primary brain tumor, and intraoperative frozen section analysis is the current standard for rapid histopathological assessment. However, this approach is time-consuming and resource-intensive. Stimulated Raman scattering (SRS) imaging has emerged as a label-free technique enabling near real-time microscopic evaluation of fresh tissue. This study compares the visualization of selected histopathological features in a newly developed intraoperative SRS system with conventional hematoxylin–eosin (HE) staining in confirmed GBM. Methods: Tumor samples from 30 patients with neuropathologically confirmed GBM were analyzed. For each case, both HE-stained frozen sections and SRS-generated virtual HE-like images were prepared from separate portions of the specimen. Twelve neuropathologists with varying levels of experience assessed 60 images according to seven predefined GBM criteria, resulting in 720 image evaluations. Feature detection was analyzed using cluster-adjusted generalized estimating equation models, and interobserver agreement was assessed using Fleiss’ κ. Results: Descriptively, hypercellularity and hypervascularization were identified at similar frequencies in both modalities, whereas pleomorphism, endothelial proliferation, mitotic activity, and necrosis were more often recognized in HE images. In cluster-adjusted analyses, SRS showed significantly lower detection rates for hypercellularity, pleomorphism, endothelial proliferation, and mitotic activity, while no significant difference was observed for hypervascularization, necrosis, or pseudopalisading after false discovery rate correction. Interobserver agreement was feature-dependent and generally higher for HE than SRS, particularly for hypercellularity. Conclusions: In this feature-level analysis of neuropathologically confirmed GBM, SRS imaging provided rapid, label-free morphological information and showed comparable visualization of selected histopathological features, particularly hypervascularization. While conventional HE-stained frozen sections remained superior for certain WHO-defining features, SRS represents a promising intraoperative adjunct that may complement established neuropathological workflows. Further studies including non-tumor tissue and a broader range of glioma grades are needed to determine the full diagnostic accuracy and clinical applicability of this technique. Full article

Background/Objectives: Speech-evoked brain potentials provide a window into the neural encoding of speech, experience-dependent plasticity, and deficits in central auditory processing from communication disorders. Stronger and faster frequency-following responses (FFRs) and cortical event-related potentials (ERPs) have been interpreted as reflecting more robust and efficient auditory–sensory processing across brainstem and cortical levels. Importantly, these neural signatures relate to real-world listening skills like speech-in-noise (SIN) perception. How functional FFR/ERPs relate to the underlying anatomical structures that generate these responses in brainstem and cortex is unknown. Methods: Using a multimodal imaging approach, we recorded FFRs and ERPs to clean and noise-degraded speech sounds to assess the strength of listeners’ neural encoding of speech at brainstem (FFR) and cortical (ERP) levels. MRI volumetrics of midbrain and transverse temporal gyrus (Heschl’s gyrus) quantified morphological variation in subcortical and cortical anatomy that underly these EEG potentials. We used the QuickSIN to assess behavioral SIN abilities. Results: We found larger and thicker right (but not left) Heschl’s gyrus was related to listeners’ SIN perception as well as the size of their cortical ERPs. Structural and functional measures interacted at a subcortical level. For listeners with smaller midbrain volumes, larger speech FFRs were associated with better QuickSIN scores, whereas in individuals with larger midbrain volumes, larger FFRs were related to poorer QuickSIN scores. Conclusions: Our findings reveal common functional signatures of speech sound processing (FFRs, ERPs) are related to the anatomy of their underlying generator sources and suggest that both auditory brain structure and function can account for perceptual SIN capacity. Full article

Background/Objectives: The gut–brain axis is increasingly recognized as a critical modulator of cognitive function. This study investigated the neurotoxic effects of combined exposure to bacterial lipopolysaccharide (LPS) and the antiretroviral drug zidovudine (ZDV) in a mouse model, and evaluated the protective potential of two probiotic interventions: Bacillus subtilis and a mixture of lactobacilli. Methods: Cognitive function was assessed using the Morris water maze (MWM). Gut microbiota composition was analyzed by 16S rRNA sequencing, and intestinal morphology was examined histologically. Gene expression of neuroinflammatory markers and mitophagy-related genes in brain tissue was quantified by RT-PCR. Plasma levels of cell-free mitochondrial DNA (cf-mtDNA) were measured as a marker of mitochondrial damage. Results: Combined LPS + ZDV exposure induced systemic inflammation, impaired spatial memory, damaged the intestinal mucosa, and caused dysbiosis characterized by an increase in pro-inflammatory Muribaculaceae. In the brain, LPS + ZDV significantly upregulated Tnfa expression, confirming neuroinflammation. Bacillus subtilis administration prevented cognitive deficits, maintained Tnfa at control levels, and significantly reduced Il1b and Il6 expression compared to the LPS + ZDV group. This was accompanied by activation of the PINK1/PTEN-dependent mitophagy pathway, prevention of cf-mtDNA release, and restoration of gut microbial diversity. In contrast, the Lactobacilli mixture not only failed to improve outcomes but was associated with exacerbated intestinal damage, more pronounced cognitive dysfunction, and no reduction in neuroinflammatory markers. Conclusions: Combined exposure to LPS and ZDV induces gut–brain axis dysfunction characterized by neuroinflammation, cognitive impairment, intestinal damage, and dysbiosis. Bacillus subtilis effectively preserves cognitive function through activation of PINK1/PTEN-dependent mitophagy and suppression of neuroinflammation, highlighting its potential as a therapeutic candidate for cognitive impairments associated with gut–brain axis dysfunction. The contrasting effects of the lactobacilli mixture underscore the critical importance of strain-specificity in probiotic interventions. Full article

Accurate and robust brain tumor segmentation remains a critical challenge in medical image analysis due to high inter-patient variability, complex tumor morphology, and modality-specific noise in MRI scans. This study proposes PSO-GA-U-Net, a novel hybrid deep learning framework that integrates Particle Swarm Optimization (PSO) and Genetic Algorithms (GAs) to optimize the U-Net architecture, enhancing segmentation performance and generalization. PSO dynamically tunes the learning rate to accommodate modality-specific variations, while the GA adaptively regulates dropout to improve feature diversity and reduce overfitting. The model was evaluated on three benchmark datasets—FBTS, BraTS 2021, and BraTS 2018—using five-fold cross-validation. PSO-GA-U-Net achieves Dice Similarity Coefficients (DSC) of 0.9587, 0.9406, and 0.9480 and Jaccard Index (JI) scores of 0.9209, 0.8881, and 0.9024, respectively, consistently outperforming state-of-the-art models in both overlap accuracy and boundary delineation. Statistical tests confirm that these improvements are significant across folds ($p<0.05$). Visual heatmaps further illustrate the model’s ability to preserve structural integrity across tumor types and modalities. These results indicate that metaheuristic-guided deep learning offers a promising and clinically applicable solution for automatic tumor segmentation in radiological workflows. Full article

Improving absolute accuracy in industrial manipulators remains difficult because rigid-body kinematic calibration cannot fully represent configuration-dependent non-geometric effects. Drawing inspiration from biological brain–body co-adaptation, this study presents an Evolutionary Neuro-Physical Hybrid (Evo-NPH) framework in which rigid geometric parameters and neural compensator weights are treated as a single co-evolving decision vector. In the offline phase, a Dual-Strategy Adaptive Differential Evolution (DS-ADE) optimizer performs global joint identification using complementary exploration–exploitation behaviors and success-history inheritance, analogous to morphology-control co-evolution in biological systems. In the online phase, a Neuro-Physical Hybrid Jacobian (NPHJ) solver augments the analytical Jacobian with gradients from a Graph Kolmogorov–Arnold Network (GKAN), enabling sensorimotor-like real-time compensation on the learned physical manifold. Experiments on an ABB IRB 120 manipulator with 600 configurations (500 training, 100 testing) report a testing distance-residual RMSE of 0.62 mm, STD of 0.59 mm, and MAX of 0.83 mm. Relative to the uncalibrated baseline, RMSE is reduced by 86.75%; compared with the strongest published baseline, RMSE improves by 23.46%. Ablation results show that joint DS-ADE optimization outperforms a sequential pipeline by 32.6%, and the graph-structured KAN outperforms a parameter-matched MLP by 26.2%. Wilcoxon signed-rank tests ($p<0.001$) confirm statistical significance. Full article

The ontological categorization of the cellular elements of the brain was proposed over a century ago by Santiago Ramón y Cajal (neurons, astroglia) and Pío del Río-Hortega (oligodendroglia, microglia). It combines histochemical observations of morphology with allied inferences about the specialized functions and origins (ectoderm or mesoderm) of each cellular element. This ontology shapes modern neuroscience, with the main non-neuronal cells—astroglia, oligodendroglia and microglia—viewed as having distinct primary roles relating respectively to the metabolic support, myelination and immunoprotection of neurons, the information signaling cells. Yet contemporary techniques, ranging from electrophysiology to single-cell transcriptomics and ultrahigh resolution spectroscopy, are revealing intersecting molecular profiles and functional capacities of these cell groups, for example metabolic support, neuroimmune and signaling functions in oligodendroglia. Here we identify discrepancies in current glial paradigms, from empirical, evolutionary and pragmatic perspectives. We suggest a subset of small, iron-rich glial cells, usually with few processes, often viewed as oligodendroglia with myelin-related primary functions, instead have iron-related primary functions that are central to all aspects of brain activity. We call these ‘ferriglia’. We discuss implications for pathogenesis across the spectrum of neuropsychiatric and neurological disorders, including neurodegenerative conditions such as Alzheimer’s disease and other less common cognitive, movement and neurobehavioral disorders, stroke and cerebrovascular disease, glioblastoma and other brain cancers and neuroimmune conditions. We also briefly address the question of where ferriglia may reside within existing glial compartments and lineages, implications for the ontological classification of other glial cells, and research challenges that must be overcome going forward. Full article

From an epidemiological perspective, polymorphous low-grade neuroepithelial tumor (PLNTY) represents a small proportion of brain tumors encountered in epilepsy surgery series. Their rarity and relatively recent recognition likely contribute to underdiagnosis and poor prognosis. In terms of histopathological features, they are similar to oligodendrogliomas. Molecular analyses can be used to show the fusion between fibroblast growth factor receptor (FGFR3) and transforming acidic coiled coil (TACC) proteins, which most commonly results in progression towards glioblastoma (GBM). We report a case of a 62-year-old man who underwent left frontal craniotomy to remove a frontal mass. Histologically, the glial lesion consisted of elements associated with oligodendroglia-like features. Immunohistochemistry was positive for glial fibrillary acidic protein (GFAP), oligodendrocyte transcription factor 2 (OLIG2), and α-thalassemia X-linked mental retardation syndrome (ATRX) nuclear expression, but negative for isocitrate dehydrogenase 1 (IDH1) and BRAF-V600E. Next-generation sequencing showed the FGFR-TACC3 fusion, and taken together, these findings supported the final diagnosis of PLNTY. During follow-up, the patient underwent a second neurosurgery, where histological evaluation indicated a GMB. This article presents clinical and radiological data, morphology, immunohistochemistry, molecular features, and treatment to enhance the clinical and pathological understanding of PLNTY with FGFR3-TACC3 fusion for all professionals involved in medical decisions. Full article

The substitution of fish meal with soybean meal (SBM) in aquafeeds aligns with sustainable development but often leads to depressed feed intake and growth in fish. This study aimed to investigate the mitigating effect of earthworm powder (EP) on these negative impacts in rice field eels (Monopterus albus), focusing on appetite regulation, intestinal health, and gut microbiota. Three isonitrogenous (~41% crude protein) and isolipidic (~6.4% crude lipid) diets (control [CON], high-SBM [SBM], and SBM + 2.5% EP [EP]) were tested in a 56-day trial. Juveniles (initial weight 18.00 ± 0.01 g) were stocked at 40 fish per net (0.5 m × 0.5 m× 0.5 m) and fed to visual satiety once daily. The results indicated that EP improved growth performance through a dual mechanism. Firstly, it was associated with significantly increased feed intake, correlated with the upregulated expression of orexigenic genes (agrp, npy) in the brain, and associated with reduced levels of anorexigenic hormones (Cholecystokinin, Leptin). Secondly, it correlated with enhanced intestinal health, evidenced by improved morphology (villus height, goblet cells), improved digestive enzyme activity, enhanced antioxidant capacity (increased Catalase and Superoxide Dismutase activities), repaired intestinal barrier function (upregulated zo-1, cla-12), and alleviated intestinal inflammation (downregulated tnf-α, il-1β). Furthermore, EP supplementation was associated with a shift in gut microbiota, including the suppression of the potential pathogen g_Clostridium_T and promotion of the beneficial bacterium g_Lactococcus_A, alongside increased concentrations of major short-chain fatty acids (acetate, propionate, and butyrate). These correlative observations suggest that EP may help mitigate the growth-inhibiting effects of SBM in Monopterus albus, offering a potential functional strategy for high-SBM aquafeeds. Full article

Multiple sclerosis (MS) is a highly disabling chronic autoimmune disease of the central nervous system with neuroinflammatory and neurodegenerative alterations found in the white and grey matter of the brain. The pathogenesis of MS is complex and not fully understood. Mitochondrial dysfunctions are suspected to play an important role. The visual system is often affected in MS. Optic neuritis is a frequent symptom, but also the retina itself, including retinal synapses appear compromised in MS independent from demyelination of the optic nerve. A previous study demonstrated synapse-specific alterations of mitochondria in photoreceptor synapses in the Experimental Autoimmune Encephalomyelitis (EAE) mouse model of MS at day 9 after injection, an early time point in pre-clinical EAE. In the present study, we analysed even earlier stages of pre-clinical EAE for possible alterations of synaptic mitochondria. For this purpose, we performed qualitative and quantitative immunolabelling analyses of the mitochondrial cristae organising protein MIC60 at retinal synapses and functional analyses by measuring synaptic mitochondrial membrane potential (during rest and depolarisation-induced exocytosis) and visually guided behaviour (optometry analyses). At day 3 after injection, morphological and functional data were indistinguishable between MOG/CFA-injected EAE mice and CFA-injected control mice. But already on day 5 after injection, we observed a decreased expression of the mitochondrial MIC60 protein at synaptic mitochondria, a decreased synaptic mitochondrial membrane potential at rest, an enhanced drop of mitochondrial membrane potential during stimulated exocytosis and a decreased visual performance of the respective EAE mice. These data argue that synaptic pathology in the EAE retina begins as early as day 5 after injection. Our data propose that dysfunctions of mitochondria play an important role already at the very early stages of synaptic pathology in EAE. Full article

Background/Objectives: Dementia remains one of the major global health challenges of the modern era. Researchers worldwide continue to seek effective therapeutic strategies to combat this neurodegenerative condition. Silymarin is a natural compound with strong neuroprotective and antioxidant properties that holds great potential for dementia management; however, its poor aqueous solubility and limited ability to cross the blood–brain barrier (BBB) have restricted its clinical application. This study focused on the formulation and evaluation of a heparin–pullulan silymarin liposomal (HPSL) nano-gel to enhance the neuroprotective efficacy of silymarin, with potential for improved brain targeting effects. Methods: The HPSL nano-gel was synthesized using the thin-film hydration technique and optimized based on entrapment efficiency, particle size distribution, zeta potential, and in vitro release kinetics. The neuroprotective efficacy of the HPSL nano-gel was evaluated in mice using behavioral evaluations, biochemical quantification of oxidative stress markers, evaluation of cholinergic enzyme activity and detailed histopathological examination of brain tissues. Results: Morphological characterization using scanning electron microscopy (SEM) confirmed a uniform nano-scale structure. The optimized formulation (HPSL-3) exhibited a particle size of 406.07 ± 19.33 nm, zeta potential of −23.72 ± 7.64 mV and an entrapment efficiency of 73.53 ± 12.05%, indicating good colloidal stability and efficient drug loading. The in vitro release profile followed non-Fickian diffusion kinetics, suggesting sustained drug release behavior. Behavioral studies in scopolamine-induced amnesic mice (elevated plus maze, hole board, and light/dark paradigms) demonstrated significant (p ≤ 0.001) improvements in learning and memory retention. Biochemical analyses showed increased levels of ChAT, SOD, CAT, and GSH, along with decreased AChE and MDA levels, supporting the neuroprotective potential of the formulation. Histopathological evaluation revealed marked attenuation of neuronal degeneration, inflammation, and edema (HAI = 4) compared to the scopolamine-treated group (HAI = 11). Conclusions: Overall, the HPSL-2 formulation effectively enhanced silymarin delivery across the BBB, demonstrating potent antioxidant, neuroprotective, and cholinergic modulatory effects. These findings suggest that HPSL-2 represents a promising nano-carrier system for the management of dementia and other oxidative-stress-related neurological disorders. Full article

Background/Objectives: Brain tumors are among the most severe neurological disorders, and their variability in size, morphology, and anatomical location complicates early and accurate diagnosis. Although magnetic resonance imaging (MRI) is the most reliable non-invasive modality for tumor detection, manual interpretation remains time-consuming, subjective, and susceptible to human error. This study aims to develop an optimization-driven hybrid machine learning framework for accurate and computationally efficient automatic brain tumor classification. Methods: The dataset includes 834 MRI images (583-training, 123-validation, 128-independent test). Because YOLOv11 detects tumor and non-tumor regions separately, the sample size doubled during region-based analysis, and all subsequent stages were conducted at the regions of interest (ROI) level. On the independent test set, YOLOv11 achieved 98.87% mAP@50, 98.54% precision, and 98.21% recall. The proposed framework combines automated tumor localization with image standardization using Gaussian noise reduction and bilinear interpolation. From the processed MR images, 39 entropy-based features were extracted. To enhance diagnostic performance and eliminate redundant information, the superb fairy-wren optimization algorithm (SFOA) was applied for feature selection and compared with particle swarm optimization (PSO), Harris hawk optimization (HHO), and puma optimization (PO). Final classification was primarily performed using k-nearest neighbors (kNN), while support vector machines (SVM) were used for comparative evaluation. Results: SFOA reduced the feature dimensionality from 39 to 5 features while achieving 99.20% classification accuracy on the independent test set. In comparison, PSO selected 10 features, HHO selected 6 features and PO selected 10 features, all achieving 98.45% accuracy. The best performance obtained with SVM was 98.45% accuracy (HHO-SVM), which remained lower than the 99.20% achieved by the proposed SFOA-kNN model. Conclusions: The results indicate that combining entropy-based feature extraction with SFOA-driven feature selection and kNN classification significantly enhances diagnostic accuracy while reducing computational complexity, highlighting the strong potential of the proposed framework for integration into computer-aided diagnosis systems to support clinical decision-making. Full article

The choroid plexus (CP) has traditionally been regarded as a cerebrospinal fluid-producing structure; however, increasing evidence indicates that it functions as a dynamic regulatory interface involved in immune surveillance, metabolic homeostasis, and brain clearance. Neuroimaging studies consistently report CP enlargement across aging and diverse neurological and neuropsychiatric disorders, yet the underlying cellular mechanisms remain poorly integrated. In this review, we synthesize morphological, molecular, and imaging evidence to propose a sequential degenerative model of the CP epithelium. This model comprises: (1) regulated epithelial cell loss via apical extrusion, (2) compensatory hypertrophy of residual cells, (3) mitochondrial remodeling with oncocytic-like change, and (4) progressive blood–cerebrospinal fluid barrier dysfunction. At the molecular level, alterations in epithelial adhesion systems—particularly SPINT1-mediated protease regulation and E-cadherin–based adherens junction stability—may initiate epithelial instability. Hypertrophic epithelial cells exhibit increased mitochondrial burden, reflected by Tom20 expression, which may initially support metabolic adaptation but ultimately contribute to oxidative stress and functional decline. At the macroscopic level, the cumulative effects of cell loss, hypertrophy, and mitochondrial remodeling likely underlie CP enlargement detectable by magnetic resonance imaging. This framework positions CP enlargement as an imaging-visible manifestation of epithelial stress and provides a structural–molecular basis for interpreting CP alterations in brain aging and neurodegenerative disorders. Full article

Hyperspectral imaging (HSI) extends conventional histopathology by combining spatial morphology with rich spectral information that reflects tissue biochemical composition, offering new opportunities for quantitative tissue analysis. However, reliable spectral analysis requires accurate instance-level segmentation of cell nuclei to enable the construction of meaningful nuclear spectral databases. In this work, a comprehensive methodology for generating hyperspectral databases of cell nuclei from histopathological samples is presented, including hyperspectral acquisition, preprocessing, nucleus segmentation, and spectral signature extraction. Three nucleus segmentation methods are evaluated: a spectral-only approach based on pixel-wise hyperspectral signatures in the visible–VNIR range; a spatial-only approach using synthetic RGB images derived from hyperspectral cubes; and a combined spatial–spectral approach that jointly exploits spatial and spectral information. The methods are assessed on a proprietary dataset of 30 hyperspectral cubes of tumor and healthy histopathological brain tissue annotated by expert pathologists. The spectral-only method achieves a Dice similarity coefficient (DSC) of 61.89% and produces severe over-segmentation, with cell count deviations exceeding substantially the ground truth in healthy tissue. The spatial-only method attains the highest pixel-wise accuracy (78.97% DSC) but underestimates nucleus counts by approximately 30% in tumor regions due to nucleus merging. The spatial–spectral method achieves a DSC of 73.13% and a mean cell count deviation of 4%, providing more reliable instance-level separation. These findings demonstrate that pixel-wise accuracy alone is insufficient for hyperspectral nuclear database generation. Full article