Biomedical Signal Processing and Control

The -Bonacci weighted sequence space {ell}(,) is introduced for [&ge;] 2, 1 [&le;] < {infty}, and > 0). It is proved to be a Banach space which is isometrically isomorphic to {ell}, with an unconditional Schauder basis. The space is also reflexive and uniformly convex. Its strict inclusion chain, continuous dual, and asymptotic truncation estimate of order - / are also established. Based on this framework, Scaled &#119898-BonacciNet is proposed as a lightweight CNN that rescales Fibonacci-Net channels using the dominant &#119898-Bonacci root and employs depth wise separable convolutions. Tribonacci-Net achieved 96.09% accuracy and a 0.9581 macro F1-score on the 15-class Brain MRI dataset using 0.85 million parameters and 0.366 GFLOPs. Pentanacci-Net attained 95.87% accuracy on the 44-class dataset while reducing parameters and FLOPs by 47.10% and 44.48%, respectively. On the CKD ultrasound dataset, Hexanacci-Net achieved 83.75% accuracy and a 0.7941 macro F1-score, with corresponding reductions of 50.37% and 45.10%. These findings support dominant-root scaling as a structured approach to lightweight CNN design.

Background: Attention-Deficit/Hyperactivity Disorder (ADHD) is a common neurodevelopmental disorder characterized by persistent symptoms of inattention, hyperactivity, and impulsivity that significantly affect cognitive, academic, and social functioning. Although electroencephalography (EEG) has emerged as a promising non-invasive tool for identifying objective neurophysiological biomarkers of ADHD because of its high temporal resolution and cost-effectiveness, many existing machine learning studies rely on single-domain EEG features, which may not adequately capture the complex functional organization of the brain. Methods: This study proposes a subject-level EEG classification framework that integrates three complementary feature domains: spectral characteristics, weighted Phase Lag Index (wPLI)-based functional connectivity, and topological descriptors derived from persistent homology. EEG recordings from 121 subjects were preprocessed and segmented into overlapping windows for feature extraction. Window-level features were aggregated to generate subject-level representations. Recursive Feature Elimination (RFE) was employed to select the 110 most informative features from an initial set of 1,043 descriptors. Five machine learning classifiers, including Support Vector Machine (SVM), Random Forest, XGBoost, CatBoost, and Multi-Layer Perceptron (MLP), were evaluated using stratified five-fold cross-validation. An ablation study was further conducted to assess the contribution of each feature domain. Model interpretability was investigated using SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME), two widely adopted Explainable Artificial Intelligence techniques for interpreting machine learning models. Results: Among the evaluated classifiers, the SVM achieved the highest classification performance, yielding an accuracy of 80.17%, an F1-score of 80.95%, a balanced accuracy of 80.14%, a receiver operating characteristic area under the curve (ROC-AUC) of 86.72%, and a precision recall area under the curve (PR-AUC) of 87.34%. The ablation study demonstrated that combining spectral, functional connectivity, and topological features consistently outperformed individual feature domains, highlighting the complementary nature of these representations. Explainable AI analyses further identified functional connectivity features as the primary contributors to classification performance while confirming the additional value of spectral and topological descriptors. Conclusions: The proposed framework demonstrates that integrating spectral analysis, functional connectivity, and topological data analysis provides an effective and interpretable approach for subject-level ADHD classification from EEG recordings. The combination of recursive feature selection, multi-domain feature fusion, ablation analysis, and Explainable Artificial Intelligence establishes a transparent and reproducible pipeline that may facilitate the development of reliable EEG-based clinical decision-support systems for ADHD.

Objective: To develop and validate a dual-probe Diffuse Correlation Spectroscopy (DCS) system for non-invasive and simultaneous, monitoring of cerebral blood flow (CBF) in the bilateral Middle Cerebral Artery (MCA) territories, and expanding the utility of conventional DCS limited to cortical-volume-based CBF measurements to vessel-specific cerebral perfusion monitoring. Methods: A dual-probe DCS system was designed for non-invasive monitoring of MCA-specific perfusion. Probe placement and protocol optimization study has been performed using anatomical landmarks, motor and speech activation tasks in healthy volunteers. System stability and repeatability were further evaluated in a pilot cohort of 30 healthy (age, 25{+/-}7 years) participants using optimized probe position and protocol. A bilateral MCA ischemic Lacunar Infract stroke case report also validated the feasibility of the system in clinical settings. Results: Measurements demonstrated superior sensitivity towards MCA-territory perfusion at targeted probe locations compared to off-MCA positions. In pilot cohort, significant increase of 30.34 {+/-} 21.56% and 36.48 {+/-} 21.22% in rCBF corresponding to hand squeeze and speech task respectively showed reproducible physiological responsiveness of the system (p<0.001). Measurement done on a patient with bilateral MCA ischemic Lacunar Infract stroke showed a significant change of 30% during speech for both the MCAs but no significant change is observed for hand squeeze tasks. Conclusion: The custom built dual-probe DCS system enables non-invasive, operator-independent, targeted and continuous monitoring of rCBF within bilateral MCA territories. Significance: This approach enables the potential use of DCS system for bilateral and vessel-specific monitoring of cerebral perfusion in the MCA territories.

Deep learning models for electroencephalography (EEG) pathology detection achieve competitive accuracy but offer limited interpretability. In this paper, we introduce concept bottleneck models (CBMs) for EEG pathology detection which use clinical EEG biomarkers computed analytically from the signal as a bottleneck to be used for prediction. Those concepts include band power, spectral ratios, alpha peak frequency and amplitude, hemispheric asymmetry and phase locking values. With the backbone based on shallow convolutional neural network (CNN), we compare a black box baseline with two variants of CBMs. The hybrid variant is a classifier receives a residual projection of the backbone features. The pure variant is a CBM where the classifier receives only the predicted concepts. Models are evaluated on abnormality detection and dementia classification followed by concept prediction quality and leakage analysis. Both CBMs approach the baseline on TUAB (82.7-82.9% vs 83.6%) and are 2-5 percentage points lower on CAUEEG (57.9-60.5% vs 62.7%). The pure CBM exhibits concept fidelity concern where the predicted concepts deviate from their ground truth values. Replacing them with their true values causes severe cost on accuracy by 26 and 22 points on TUAB and CAUEEG. The concept fidelity concern is mitigated by increasing the weight of the concept loss to match the ground truth concepts. the mitigation comes with small accuracy cost on TUAB but a relatively larger cost on CAUEEG. The code of the experiments and full logs are available at https://www.github.com/mhmdrdwn/cbm.

Background and purpose: Accurate identification of cardiac MRI volume orientations is essential for reliable image interpretation and for enabling downstream automated analysis pipelines. However, orientation labels and commonly assigned manually, making the process time-consuming and prone to variability. Recent advances in vision-language models offers new opportunities for automated label generation by jointly modeling visual and semantic information. Methods: In this study, we systematically compare a conventional end-to-end transformer-based captioning model with a CLIPCap architecture for automated cardiac MRI view labelling. Both models were evaluated on a dataset of 1184 de-identified cardiac MR images spanning across six clinically relevant orientations: short axis, two-, three-, four-chamber views, left and right ventricular outflow tract views. The caption transformer was trained from scratch, whereas CLIPCap leveraged pretrained CLIP image embeddings combined with lightweight mapping network and a frozen language model. Results: Experimental results demonstrate a substantial performance advantage from CLIPCap, which achieved an overall accuracy of 98% compared to 68% for the caption transformer. CLIPCap consistently delivered high precision and recall across all orientation classes, including those of high clinical importance, while the end to end transformer exhibited unstable performance and complete failure in certain views. Conclusion: These findings highlight the benefits of leveraging large scale multimodal pretrained model for medical image labeling tasks, particularly in data limited settings. The study suggests that CLIPCap provides a more robust and clinically reliable solution for automated cardiac MRI orientation labeling, supporting its integration into efficient and scalable clinical workflows.

Background: Depth of anesthesia is routinely monitored using electroencephalographic (EEG) indices such as the Bispectral Index (BIS), which reduce cortical activity to a single numerical real-time series. However, these scalar descriptors fail to capture inter-individual variability, drug-specific EEG signatures, and transitions between brain states. Methods: We analyzed transient EEG patterns during general anesthesia induced by propofol and sevoflurane in 89 patients. Iso-electric suppressions (IES), $\alpha$-suppressions, and spectral power in the $\alpha$ and $\delta$ bands were quantified across controlled concentration plateaus. We compared conventional BIS monitoring with a novel State-Chart representation mapping EEG activity into discrete depth states. Results: Increasing hypnotic concentration produced a consistent shift from $\alpha$-dominant to $\delta$-dominant activity and a reduction in maximal $\alpha$ frequency. IES occurred predominantly at high propofol concentrations and remained infrequent under sevoflurane. Compared with BIS, the State-Chart showed a marked reduction in temporal variability (0.5 $\pm$ 0.6 vs 4.0 $\pm$ 2.9; $p<10^{-90}$). Importantly, our State-Chart separates stable from transition regimes and discriminates identical concentration levels. Statistics computed over prior dosing (ascending vs descending), reveals refined clustering not captured by BIS. Conclusions: Anesthesia depth drugs concentrations vs EEG effects is more accurately described by structured EEG state transitions than by a single numerical index. The State-Chart provides a stable, physiologically interpretable representation of brain activity and reveals transition states preceding deep cortical suppression, supporting individualized and predictive monitoring of anesthesia.

This study presents a systematic investigation of the brain's own microwave emissions in the 0.85-5.0 GHz range, aiming to validate microwave encephalography (MWEG) as a novel tool for cognitive state assessment. Early experiments (2016-2019) using comparisons with background noise, a control phantom, and different antenna types confirmed the endogenous origin of the recorded signals. In a 2021 experiment (118 measurements on one subject, right and left occipital areas), we observed a significant functional hemispheric asymmetry: the number of "substantial spikes" was significantly higher in darkness for the right hemisphere (p<0.001) and higher in light for the left hemisphere (p<0.001). A 2025 group study (three subjects) confirmed the asymmetry (p<0.05 for right, p<0.01 for left). We describe the signal processing pipeline, including spike detection and statistical analysis. Two complementary mathematical models are presented: an energy-based model linking optical input to microwave emission via neural activity modes, and an information-based model interpreting spectral changes in terms of structural pattern overlap with memory engrams. An estimation of the physical dimensions of possible brain resonators (2-22 mm) is provided. The results are discussed in the context of hemispheric specialization and the information commutation theory. This work opens new perspectives for developing low cost, contactless brain monitoring systems.

Independent component analysis (ICA) is widely used to remove artefacts from EEG and TMS-EEG recordings, but the components that correspond to artefacts are usually identified by manual inspection, which is subjective and difficult to reproduce. Existing automated classifiers are either designed for ordinary EEG and do not target the artefacts specific to concurrent transcranial magnetic stimulation, or are built on EEGLAB, so none is available for FieldTrip-based pipelines. We present TEFAR, a lightweight, configurable framework for semi-automatic artefact-component classification that applies the same detectors to ordinary EEG and TMS-EEG. TEFAR is built on FieldTrip and requires no additional MATLAB toolboxes. Each artefact class (line noise, blinks, lateral eye movements, cranial muscle, cardiac activity, and the TMS decay and recharge artefacts) is identified from the spectral, spatial, or temporal signature that its components are known to express. Detection thresholds use robust statistics (the median and the median absolute deviation rather than the mean and standard deviation), so that a single dominant artefact component cannot raise the threshold that is meant to detect it. In 30 ground-truth simulations, TEFAR reached a specificity of 1.000 and a sensitivity of 0.96-0.97 for both profiles. An application of TEFAR to real EEG and TMS-EEG recordings is the next step and will be reported separately.

With the rapid advancement of clinical neuroscience and Brain-Computer Interfaces (BCIs), there is an increasing demand for convenient, user-friendly EEG recording methods suitable for diverse environments, including mobile and home-based settings. Traditional gel-based EEG systems, while reliable, are inconvenient and time-consuming, whereas dry electrode systems tend to suffer from elevated noise levels. In this study, we investigated a novel methodological manipulation aimed at enhancing dry electrode signal quality: wetting the hair directly with tap water to improve scalp electrode conductivity. To this end, we recruited 22 healthy participants and compared their resting-state (RS) EEG activity across three experimental conditions (dry, semi-dry, and gel) within a single-session design. Specifically, we analyzed electrode impedance, spectral power (SP), and functional connectivity (FC). Our results show that basic hair-wetting substantially improved mean electrode impedance by 75.7% relative to the dry condition, reduced the proportion of bad channels from approximately 40% to 15%, and increased spectral-power similarity with gel recordings by 7.7% during eyes-closed recordings, and improved FC similarity by approximately 56-70% across frequency bands. Although this method does not fully match the signal quality of traditional gel-based systems, it represents a promising compromise, enhancing EEG data quality under suboptimal conditions. This approach offers a practical and non-invasive means to improve EEG signal quality, ultimately expanding real-world applications of EEG.

Background: High-definition transcranial alternating current stimulation (HD-tACS) is favored by the neurostimulation community for its precision and ability to influence neuronal dynamics. Yet, the exact mechanism by which the underlying brain structures are being affected remains unclear. We believe that the investigation of the aperiodic nature of the electroencephalograph (EEG) could shed light on the modulatory effects of HD-tACS. Methods: We analyzed the EEG of 9 participants during a compensatory tracking task (CTT) in two sessions, each with different HD-tACS protocols. Every session consisted of an initial period of no stimulation, followed by 30 Hz HD-tACS in the left motor (M30) or frontal (F30) cortex. We then isolated the aperiodic component of the EEG and calculated its spectral slope {beta}. Results and Discussion: {beta} decreased during F30 mainly in the right frontal cortex, indicating a shift towards higher frequencies and an increase of the excitatory/inhibitory balance. Additionally, we found that despite the long monotonus task the accuracy of the participants did not decrease, which might be attributed to the ability of both M30 and F30 to sustain attention for prolonged time. Finally, the change of CTT accuracy during the stimulation correlated with the {beta} of specific channels before the stimulation. This indicates the potential of {beta} to be used as a screening biomarker in future studies. In conclusion, we showed the ability of HD-tACS to alter EEG aperiodic dynamics and paved the way for future exploration of such dynamics in the field.

BackgroundObstructive sleep apnea (OSA) is a highly prevalent sleep disorder. Major risk factors include obesity, older age, and male sex. Given the well-established association between OSA and cardiovascular disease, markers of cardiovascular health derived from electrocardiography (ECG) may help identify individuals with undiagnosed OSA. This study evaluated whether 12-lead ECG features improve machine learning-based prediction of OSA beyond established clinical factors. MethodsWe conducted a retrospective cohort study of individuals who underwent diagnostic sleep studies at the University of Kansas Health System Sleep Disorders Center (2004-2025) and had a 12-lead ECG acquired within one year. Standard ECG features (intervals, amplitudes, voltage-time integrals, morphology descriptors) were extracted from the representative beat. Latent representations were derived using two variational autoencoder (VAE) models pretrained on >1 million ECGs: a 30-dimensional representative-beat VAE and a 90-dimensional full 10-second ECG VAE. Three LightGBM models were trained: clinical factors only (age, sex, weight, height, body mass index [BMI], Epworth sleepiness scale [ESS]), ECG features only, and a combined model. Feature selection and hyperparameter tuning were performed separately for each model within a 5-fold cross-validation scheme. The outcome was moderate-to-severe OSA (AHI[&ge;]15 events/h), evaluated by AUROC (bootstrapped 95% CI) in a 10% holdout test set. ResultsThe dataset included 7,699 individuals (52.2% women, mean age 58.0 {+/-} 14.2 years, BMI 33.6{+/-}8.2 kg/m{superscript 2}, ESS 8.8{+/-}5.1; 36.4% with moderate-to-severe OSA) Training AUROC (95% CI) was 0.71 (0.66-0.76) for the combined model, versus 0.65 (0.59-0.70) for the clinical-only model and 0.66 (0.61-0.72) for the ECG-only model. Holdout test AUROC was 0.78 (combined), 0.69 (clinical-only), and 0.71 (ECG-only). Feature importance identified age, BMI, weight, ECG VAE latent variables, height, sex, and P-wave voltage-time integral as relevant contributor to the predictions. ConclusionsLatent ECG features extracted by VAE improve prediction of moderate-to-severe OSA when combined with clinical factors.

Patients with implantable cardioverter-defibrillators (ICDs) often are excluded from receiving CMR scans at 3.0T due to ICD-induced image artifacts. This work aims to transfer sequence protocols established for CMR imaging in the presence of ICDs at 1.5T to a first human application at 3.0T. All measurements were performed on a clinical 3T MRI scanner. Phantom measurements were used to establish and optimize wideband PSIR LGE imaging at 3.0T. Volunteer measurements with externally placed ICDs were used for optimization of CINE imaging and wideband PSIR imaging. Thirdly, patients with implanted ICD were examined with the optimized protocols. Human measurements showed that SA stacks obtained with spoiled GRE after contrast agent showed a markedly lower artifact burden than the conventional approach. For scar imaging, a wideband PSIR with a bandwidth of 3kHz and a frequency offset of +750Hz allowed a sufficient suppression of relevant artifacts in the majority of scans. No strong correlation between the image quality and the distance between the cardiac silhouette and the device was detected. The presented work shows the feasibility of clinical cardiac MRI at 3.0T including GRE-CINE and wideband PSIR-LGE for patients with ICDs.

Objective Based on the bioinformatics method of multi-database integration, this study systematically analyzes the expression characteristics, clinical pathological correlation, prognostic value, potential molecular mechanisms, and immune infiltration patterns of hepatocyte growth factor receptor (MET) in gastric cancer. Methods The UALCAN and GEPIA databases were employed to examine the differential expression of MET between gastric cancer and normal gastric mucosal tissues, as well as its associations with clinicopathological features. Kaplan-Meier Plotter was utilized to evaluate the impact of MET expression on overall survival (OS) and progression-free survival (PFS). Protein-protein interaction (PPI) network was constructed via LinkedOmics, followed by Gene Ontology (GO) functional annotation and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis of co-expressed genes. Four algorithms, TIMER, CIBERSORT, EPIC, and MCPcounter, were used to cross evaluate the correlation between MET expression and immune cell infiltration; Further validate the cell type specific expression of MET using the gastric cancer single-cell sequencing queues (GSE134520, GSE167297) built into the TISCH database. Results MET expression was significantly elevated in gastric cancer tissues compared with normal gastric mucosa (P < .05), and its expression level was significantly correlated with tumor grade and TNM stage. Patients with high MET expression exhibited significantly poorer OS and PFS than those with low MET expression (P < .05). The PPI network revealed that MET could interact with 20 key proteins, including EGFR, ERBB2, HGF, STAT3, and GRB2 etc. GO enrichment analysis suggests that differentially expressed genes are significantly enriched in functions such as the ERBB signaling pathway, cadherin binding, and DNA repair complexes; KEGG enrichment analysis showed that MET related genes were significantly enriched in pathways such as homologous recombination, nuclear cytoplasmic transport, mismatch repair, and oxidative phosphorylation. Immune infiltration analysis showed that the negative association between MET and B cells infiltration has cross algorithm robustness, while the association with neutrophils, CD8+ T cells, CD4+ T cells, and macrophages exhibits algorithmic heterogeneity or insignificance; There is no significant correlation between MET and common immune checkpoint molecules such as PD-1, PD-L1, CTLA4, etc. Single cell validation further confirmed that MET is mainly enriched in malignant epithelial cells and endothelial cells, and is almost not expressed in immune cells. Conclusions Multidimensional bioinformatic analyses demonstrate that elevated MET expression serves as an independent risk factor for unfavorable prognosis in gastric cancer. MET may mediate dual drug resistance in gastric cancer via crosstalk with multiple signaling molecules (including EGFR, ERBB2, HGF, STAT3 and GRB2) and dysregulation of the homologous recombination repair pathway. Results from multiple-algorithm immune infiltration analysis, single-cell dataset analysis and immune checkpoint correlation analysis indicate that MET exerts only modest direct regulatory effects on the gastric cancer immune microenvironment. This exploratory study offers systematic bioinformatic evidence supporting MET as a candidate prognostic biomarker and potential therapeutic target for gastric cancer. Further functional experiments and prospective cohort studies are required to validate its molecular mechanisms and clinical utility.

From a statistical point of view, clustering spike time-windows from multi-electrode arrays (MEAs) recordings is a challenging high-dimensional, unsupervised clustering task where stationarity, commonly assumed in standard time-series analysis, is often violated and for which a gold standard is currently unavailable. Here we aim at providing practical guidance on how to cluster this type of data by systematically comparing 108 clustering pipelines differing along three main dimensions: (i) the data feature space; (ii) the metrics used to quantify distance between data points; and (iii) the clustering algorithm. For our benchmark we used both labeled synthetic data, mimicking four physiologically-inspired classes of spike time-windows, and a set of real MEAs recordings from a two-dimensional in-vitro neural culture. The performance of the competing pipelines was evaluated in terms of balanced accuracy and computational time when analyzing the synthetic datasets, while the Silhouette score was used for the real dataset, where no ground-truth is available. Overall, our analysis shows that the best combination is formed by k-means with Euclidean distance applied after Principal Component Analysis (PCA) of the spike time-windows. Conversely, hierarchical clustering showed the highest computational burden, while Independent Component Analysis and kernel PCA provided less effective noise suppression.

Microstate analysis studies dynamic brain activity through a discrete representation of electroencephalographic (EEG) signals and their topography. While the body of literature describing findings in diverse experimental and clinical settings is growing rapidly, the effects of several core components of the microstate algorithm are still insufficiently understood. This study systematically investigates how two common temporal smoothing algorithms, parametric smoothing and GFP peak interpolation, influence a wide range of microstate sequence parameters, and how they shape the integrated picture of brain dynamics inferred from these metrics. We study eyes-closed resting-state EEG recordings from N=201 healthy subjects from a public EEG database. For the elementary temporal metrics, we find that widening smoothing windows markedly increase microstate duration, reduce occurrence rates, but leave coverage mostly unaffected. In terms of simple syntax properties, smoothing windows above 30 ms yield an inconsistent picture with a memoryless, first-order Markov structure at short time scales, but a positive Hurst phenomenon suggestive of long-range correlations at long time scales. Evidence of asymmetry and non-equilibrium dynamics are suppressed by smoothing. At intermediate time scales, microstate periodicity was only observed up to a window size of 28 ms. Smoothing had a strong impact on the complexity metrics entropy rate and excess entropy, decreasing the former and increasing the latter. For most metrics, the effects of GFP peak interpolation were comparable to those of smoothing windows in the range between 28 ms and 44 ms. In conclusion, elementary and higher-order microstate parameters must be interpreted in the context of preprocessing, as many parameters change continuously with smoothing intensity. This limits the comparability of microstate parameters obtained with different preprocessing settings. Strong smoothing with a window size above 30 ms or GFP peak interpolation yields a fundamentally different picture of resting state brain dynamics, i.e. that of a memoryless, aperiodic, time-reversible first-order Markov chain. Since insights from other neurophysiological modalities suggest that time series memory and time-irreversibility are markers of normal brain activity, our recommendation is to avoid intense smoothing to minimize alterations of the initial sequences.

Significance: Wearable optical sensors could make continuous cerebral hemodynamic monitoring practical in daily life. Because any surface head sensor also samples extracerebral tissue, demonstrating cerebral relevance requires a reference that separates deep from superficial hemodynamics. Aim: We evaluated whether the Temple Brain Flow Index (Temple-BF), derived from a temple-worn photoplethysmographic wearable, covaried more strongly with the deeper (brain-assigned) than the superficial (scalp-assigned) hemodynamics recovered from time-domain near-infrared spectroscopy (TD-NIRS) during controlled postural challenges. Approach: Sixty sessions from 44 healthy young adult men were analyzed across three physiological challenges: 30{degrees} head-down tilt, stand-to-squat, and stand-to-supine transitions. Optical density and mean time of flight from a three-module TD-NIRS system were inverted with a Monte Carlo-derived two-layer model to obtain scalp- and brain-layer hemoglobin time series. Temple-BF was compared with these model-derived signals using lag-adjusted and zero-lag correlations, paired brain-versus-scalp comparisons, heart rate and short-separation-HbO adjusted partial correlations. Results: Median lag-adjusted correlations between Temple-BF and brain-layer {Delta}HbO traces were 0.912, 0.843, and 0.839 for head-down tilt, stand-to-squat, and stand-to-supine transitions, respectively; corresponding scalp-layer medians were 0.494, 0.700, and 0.767. Paired brain-minus-scalp differences were significant for head-down tilt (median 0.333, p < 0.001) and stand-to-squat (0.110, p < 0.001) but not for stand-to-supine (0.036, p = 0.082) transitions. Zero-lag brain-layer medians were 0.826, 0.701, and 0.796, and the association persisted after adjustment for heart rate (partial r = 0.832, 0.850, 0.654) and for short-separation superficial HbO (0.649, 0.570, 0.438). Transition-window correlations had medians of 0.878, 0.861, and 0.876, with directionally concordant transition responses in 59 of 60 sessions. Conclusions: Temple-BF tracked model-derived brain-layer TD-NIRS {Delta}HbO across all three postural challenges, with larger median correlations against the brain-layer than the scalp compartment in all three protocols, and transition responses in the same direction for almost all sessions. These results support Temple-BF as a relative marker of cerebral hemodynamic change during postural perturbations. Establishing cerebral specificity at the temple, and excluding residual systemic and superficial contributions, will require flow-sensitive references and fuller systemic monitoring.

Semi-occluded vocal tract (SOVT) exercises are widely used in voice training and therapy, but their immediate electroglottographic (EGG) effects remain incompletely characterized. In this pilot methodological study, six female community singers completed a no-straw baseline recording and then 1-min straw-phonation exercises with four straws (Household metal, Metal VoiceStraw, plastic, and paper), each followed by a no-straw EGG recording. Thirty 1s recordings were analyzed with a standardized pipeline including contact quotient (CQ), waveform skewness, contact-phase rise/fall timing, temporal skewness (s_t), a normalized derivative asymmetry index (NDAI), average-cycle morphology, and EGG spectral descriptors. Relative to baseline, group-mean CQ was higher after all four straws (by 0.027-0.058), waveform skewness and NDAI were lower, and the EGG spectral centroid was lower (by 9.6-15.3%). Contact-phase timing asymmetry did not change consistently: s_t exceeded baseline after three straws and fell below it after one, and the rise/fall ratio decreased in three to five of six participants depending on the straw. Four participants ranked the Metal VoiceStraw first and two ranked paper first. Because every straw condition followed the baseline, warm-up and order effects cannot be separated from straw effects. These hypothesis-generating results identify CQ, waveform skewness, and EGG spectral centroid as candidate endpoints for a larger controlled study

Parkinson disease (PD) affects speech production, motivating classification from repeated voice measurements. Record-wise evaluation can place recordings from the same participant in both training and test sets. We propose VoxNeuro, a novel subject-level framework combining Grassmann representations of repeated recordings with Euclidean mean-dispersion summaries through a provably positive-semidefinite kernel for support vector classification. Features undergo training-fold Gaussian rank normalization, and a supervised partial least squares subspace ensemble is activated when the feature count exceeds the number of training recordings. Two public cohorts were evaluated, UCI-489 (80 subjects) and PD-252 (252 subjects), each with three sustained-vowel recordings per subject. At the reference five-fold subject-disjoint partition, balanced accuracy was 87.5% and 81.6%, respectively, exceeding all five standard comparators under identical folds and normalization. PD-252 sensitivity was 89.9% and specificity was 73.4%. Across 20 additional subject partitions, PD-252 balanced accuracy averaged 78.4%, with a mean paired advantage of 3.2 percentage points over the highest-scoring standard comparator. VoxNeuro exceeded each standard comparator in at least 19 partitions for both balanced accuracy and macro-F1. Ablations favored rank normalization and the unaugmented supervised-subspace configuration on PD-252. VoxNeuro thus offers an effective and reproducible framework for subject-level analysis of repeated speech measurements in PD screening research.

Accurate classification of lung adenocarcinoma growth patterns from hematoxylin and eosin (H\&E)-stained whole-slide images is essential for treatment planning and prognosis. We develop and evaluate an exponentially weighted ensemble deep learning approach that combines five architectures (EfficientNet-B3, DeiT3, Swin Transformer, Vision Transformer, ConvNeXt) with weights determined by a softmax transformation of per-model Quadratic Weighted Kappa (QWK) scores. Using 25,545 image patches at 40x magnification from the Dartmouth-Hitchcock dataset, we evaluated performance with stratified 5-fold cross-validation. Individual model performance ranged from Cohen's kappa kappa = 0.5563 (ConvNeXt) to kappa = 0.9561 (EfficientNet-B3). The ensemble achieved 96.52% accuracy and kappa = 0.9648, exceeding the best individual model by delta kappa = +0.0087 with statistical significance (McNemar's test, chi^2 = 50.84, p < 10^-12; bootstrap 95% CI on delta kappa [+0.0056, +0.0117]. Pairwise disagreement rates of 16.6--43.2% between architectures indicate that the models capture different aspects of tissue morphology, and the framework automatically down-weights unreliable components, as illustrated by ConvNeXt receiving only 5.7% ensemble weight despite a single-fold training failure. The approach offers a clinically grounded method for ensemble aggregation in digital pathology.

Flow is a subjective state where tasks feel effortless and rewarding. It has been linked to distinct neural signatures, yet dynamics of these signals remain poorly understood. Here, we investigated spectral dynamics of brain activity in flow. We recorded electroencephalogram (EEG) data at positions AF7, AF8, TP9, and TP10 using a lightweight wearable device worn by ten adult participants while they completed a go-signal task and two stop-signal tasks. Task difficulty was continuously adjusted to induce either a sense of flow or frustration. Time-resolved spectral power and interregional coherence were extracted with continuous wavelet and wavelet coherence transforms; subjective flow was assessed after each block with the short-form Flow-State Scale. Subjective ratings confirmed that the flow and frustration conditions diverged in perception of flow. In the flow block, errors on stop trials coincided with pre-stimulus reductions in right temporoparietal gamma power and frontal beta and gamma power, alongside diminished frontotemporal gamma coherence. Comparison of flow and frustration revealed higher temporal beta power during frustration, consistent with greater cognitive load. Flow may involve finely balanced beta and gamma dynamics, and brief collapses of these rhythms may predict task errors. Spectral dynamics are actionable features for closed-loop engagement monitoring applications.