Biocybernetics and Biomedical Engineering最新文献

{"title":"Lumbar intervertebral disc biomechanics: Geometry and collagen fiber orientation configurations effects","authors":"Zhongwei Sun ,&nbsp;Jiabao Pan ,&nbsp;Weishi Liang ,&nbsp;Changwen Mi ,&nbsp;Peng Yin","doi":"10.1016/j.bbe.2025.07.003","DOIUrl":"10.1016/j.bbe.2025.07.003","url":null,"abstract":"<div><div>This study proposes a probabilistic biphasic-swelling parameterized finite element framework, with the aim of which is to systematically evaluate the impact of lumbar intervertebral disc (L-IVD) geometry and annulus fibrosus collagen fiber configuration on multi-axial biomechanical behavior. Thirty anatomical L-IVD geometric sets were sampled via Latin hypercube sampling of clinical anatomical variations. Three annulus fibrosus layer-wise fiber configurations were implemented: Constant <span><math><msup><mn>30</mn><mo>∘</mo></msup></math></span>, Circumferential variation (<span><math><mrow><msup><mn>25</mn><mo>∘</mo></msup><mo>−</mo><mo>−</mo><msup><mn>45</mn><mo>∘</mo></msup></mrow></math></span>), and Circumferential-radial variation (<span><math><mrow><msup><mn>23</mn><mo>∘</mo></msup><mo>−</mo><mo>−</mo><msup><mn>50</mn><mo>∘</mo></msup></mrow></math></span>). Consequently, the construction of three groups, comprising a total of ninety biphasic L-IVD finite element models, was undertaken. Five loading protocols were then simulated to reveal the critical dependencies of L-IVD biomechanical behavior. A statistical comparative analysis was performed to evaluate the influence of disc geometries and orientation strategies. The findings demonstrated that fiber orientation configuration exerts a substantial influence on swelling responses, compression stiffness, and flexion stiffness (<span><math><mrow><mi>p</mi><mo>&lt;</mo><mo>.</mo><mn>050</mn></mrow></math></span>). Disc height exhibited strong inverse correlations with intradiscal pressure (<span><math><mrow><mi>r</mi><mo>&lt;</mo><mo>−</mo><mn>0.80</mn></mrow></math></span>, <span><math><mrow><mi>p</mi><mo>&lt;</mo><mo>.</mo><mn>001</mn></mrow></math></span>) and compression stiffness (<span><math><mrow><mi>r</mi><mo>&lt;</mo><mo>−</mo><mn>0.85</mn></mrow></math></span>, <span><math><mrow><mi>p</mi><mo>&lt;</mo><mo>.</mo><mn>001</mn></mrow></math></span>). Anterior-posterior length emerged as the primary predictor of sagittal stiffness (flexion: <span><math><mrow><mi>r</mi><mo>&gt;</mo><mn>0.70</mn></mrow></math></span>; extension: <span><math><mrow><mi>r</mi><mo>&gt;</mo><mn>0.75</mn></mrow></math></span>) and torsional resistance (<span><math><mrow><mi>r</mi><mo>&gt;</mo><mn>0.50</mn></mrow></math></span>), linked to altered moment arm mechanics. The nucleus pulposus volume ratio moderately affected intradiscal pressure (<span><math><mrow><mi>r</mi><mo>&gt;</mo><mn>0.30</mn></mrow></math></span>, <span><math><mrow><mi>p</mi><mo>&lt;</mo><mo>.</mo><mn>05</mn></mrow></math></span>) but showed negligible impact on segmental stiffness. This parametric modelling framework facilitates systematic investigation of L-IVD biomechanics across anatomical variations. Additionally, these findings advocate for microstructure-informed computational models to optimize personalized implant designs and biomechanical assessments.</div></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":"45 3","pages":"Pages 496-506"},"PeriodicalIF":5.3,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144654464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Can cerebral autoregulation be monitored with non-linear correlation indices? A proof-of-concept study","authors":"Karol Sawicki ,&nbsp;Arkadiusz Syta ,&nbsp;Pawel Dzienis ,&nbsp;Lukasz Tymiński ,&nbsp;Bartlomiej Ambrożkiewicz ,&nbsp;Andrzej Koszewnik ,&nbsp;Magdalena Maria Sawicka ,&nbsp;Tomasz Łysoń ,&nbsp;Zofia Czosnyka ,&nbsp;Marek Czosnyka","doi":"10.1016/j.bbe.2025.07.005","DOIUrl":"10.1016/j.bbe.2025.07.005","url":null,"abstract":"<div><h3>Objective</h3><div>Cerebral autoregulation (CA) is the mechanism by which cerebral vessels self-regulate blood flow to maintain adequate brain perfusion. Although CA monitoring is recommended in neurocritical care as a means to improve therapy, there is currently no consensus on the most effective computational technique. The aim of this study was to evaluate the feasibility of measuring CA using recurrence quantification analysis (RQA)—a non-linear method for analysing complex systems—as an alternative to traditional, linear correlation-based indices.</div></div><div><h3>Methods</h3><div>A retrospective analysis was conducted on a database of head-injured patients treated in a neurocritical care unit who developed spontaneous intracranial pressure (ICP) elevations known as plateau waves. Signals from arterial blood pressure, ICP, and cerebral blood flow velocity were segmented into stable phases of elevated ICP (associated with CA deterioration) and the preceding baseline. Non-linear RQA correlations were calculated for both periods, and the results were statistically compared. For reference, well-established linear CA indices were assessed in the same manner.</div></div><div><h3>Results</h3><div>The non-linear correlations followed a similar pattern to the linear CA indices and successfully differentiated the plateau wave phase with a comparable, high level of statistical significance (p &lt; 0.0001), while demonstrating higher values and reduced data dispersion.</div></div><div><h3>Conclusion</h3><div>Non-linear RQA correlation is feasible<!--> <!-->for CA assessment.<!--> <!-->To the best of the authors’ knowledge, this is the first evaluation of RQA feasibility in CA research. In the pursuit of a reliable<!--> <!-->index suitable for widespread implementation in neurocritical care, a non-linear approach may offer a promising alternative to traditional linear correlation-based indices.</div></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":"45 3","pages":"Pages 485-495"},"PeriodicalIF":5.3,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144633201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Movement and force dynamics in bimanual cooperative tasks in chronic stroke and healthy individuals","authors":"J. Podobnik,&nbsp;M. Munih,&nbsp;M. Mihelj","doi":"10.1016/j.bbe.2025.07.002","DOIUrl":"10.1016/j.bbe.2025.07.002","url":null,"abstract":"<div><div>Stroke rehabilitation often involves the use of haptic robots to improve motor control and bimanual coordination. This study examines how damping affects movement and force dynamics in bimanual tasks performed by healthy participants and participants with chronic stroke using a haptic robotic system equipped with force sensors for each hand. Participants completed tasks at three damping levels: <span><math><mrow><mn>0</mn><mspace></mspace><mfrac><mrow><mi>N</mi></mrow><mrow><mi>m</mi><mo>/</mo><mi>s</mi></mrow></mfrac></mrow></math></span> (no damping), <span><math><mrow><mn>20</mn><mspace></mspace><mfrac><mrow><mi>N</mi></mrow><mrow><mi>m</mi><mo>/</mo><mi>s</mi></mrow></mfrac></mrow></math></span> (low damping), and <span><math><mrow><mn>40</mn><mspace></mspace><mfrac><mrow><mi>N</mi></mrow><mrow><mi>m</mi><mo>/</mo><mi>s</mi></mrow></mfrac></mrow></math></span> (moderate damping). Key parameters for trajectory of movement, velocity, manipulation force, and internal force were analyzed to assess movement stability and control. The results revealed that damping <span><math><mrow><mn>20</mn><mspace></mspace><mfrac><mrow><mi>N</mi></mrow><mrow><mi>m</mi><mo>/</mo><mi>s</mi></mrow></mfrac></mrow></math></span> effectively stabilized movements in persons with stroke, reducing velocity deviations and making their performance more comparable to healthy participants, without introducing excessive resistance. In contrast, damping <span><math><mrow><mn>40</mn><mspace></mspace><mfrac><mrow><mi>N</mi></mrow><mrow><mi>m</mi><mo>/</mo><mi>s</mi></mrow></mfrac></mrow></math></span> acted as resistance training. Participants with stroke exhibited consistently higher internal forces than healthy participants, reflecting compensatory strategies and inefficient motor control. These findings demonstrate that low damping (<span><math><mrow><mn>20</mn><mspace></mspace><mfrac><mrow><mi>N</mi></mrow><mrow><mi>m</mi><mo>/</mo><mi>s</mi></mrow></mfrac></mrow></math></span>) offers an optimal balance between movement stabilization and resistance, highlighting its potential as a rehabilitation strategy, while moderate damping (<span><math><mrow><mn>40</mn><mspace></mspace><mfrac><mrow><mi>N</mi></mrow><mrow><mi>m</mi><mo>/</mo><mi>s</mi></mrow></mfrac></mrow></math></span>) may be reserved for resistance training.</div></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":"45 3","pages":"Pages 476-484"},"PeriodicalIF":5.3,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144611678","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Toward the integration of mixed reality and brain-computer interfaces based on code-modulated visual evoked potentials","authors":"Selene Moreno-Calderón ,&nbsp;Víctor Martínez-Cagigal ,&nbsp;Ana Martín-Fernández ,&nbsp;Eduardo Santamaría-Vázquez ,&nbsp;Roberto Hornero","doi":"10.1016/j.bbe.2025.06.003","DOIUrl":"10.1016/j.bbe.2025.06.003","url":null,"abstract":"<div><div><em>Background and objective</em>: Brain-computer interface (BCI) systems can assist individuals with severe motor disabilities by enabling communication through their brain signals using spellers, which allow selecting commands from a set of options. For this technology, accuracy, speed and user comfort are essential. Code-modulated visual evoked potentials (c-VEPs) have demonstrated promising performance in BCI control. Integrating BCI systems with mixed reality (MR) could provide portability and autonomy. However, to the best of our knowledge, no existing studies have explored the feasibility of combining MR with c-VEP-based BCIs. This study aims to: (1) evaluate the performance of integrating MR with c-VEP-based BCIs and (2) study the visual fatigue induced by c-VEPs compared to traditional screen. <em>Methods</em>: Twenty participants used a 36-character speller to select words in both MR and traditional screen conditions. Metrics like accuracy and information transfer rate (ITR) were measured. Usability and eyestrain were evaluated through questionnaires. <em>Results</em>: The integration of MR with c-VEPs achieved an accuracy of 96.71 % and an ITR of 27.55 bits/min, compared to 95.98 % accuracy and 27.10 bits/min for the conventional screen condition. The questionnaires revealed minimal levels of visual fatigue in both conditions and high usability. No significant differences were observed between conditions in terms of performance or visual fatigue. <em>Conclusions</em>: The c-VEP-based speller with MR-BCI technology proved feasible, achieving performance levels similar to the conventional setup, with high accuracy in both conditions. The study also found comparable visual fatigue between MR and traditional screens, supporting the practicality of MR integration in BCI systems.</div></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":"45 3","pages":"Pages 528-538"},"PeriodicalIF":5.3,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144713606","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Relevance of harmonic content findings of hand motor (dys)functionalities in Parkinson’s disease revealed by means of a sensory glove","authors":"Luca Pietrosanti ,&nbsp;Martina Patera ,&nbsp;Antonio Suppa ,&nbsp;Giovanni Costantini ,&nbsp;Nicola Arangino ,&nbsp;Franco Giannini ,&nbsp;Giovanni Saggio","doi":"10.1016/j.bbe.2025.07.004","DOIUrl":"10.1016/j.bbe.2025.07.004","url":null,"abstract":"<div><div>Hand functions are vital for performing daily activities, ensuring independence, and maintaining quality of life. In Parkinson’s disease (PD), impaired hand function affects fine motor skills, dexterity, and coordination, leading to difficulties in self-care, communication, and work-related tasks. As such, correct hand function assessment in PD is among the crucial aspects in evaluating motor impairment, in guiding treatment and tracking disease progression. Here, we report objective results obtained in assessing hand (dys)functionalities using an on-the-shelves fingerless sensory glove, named MANUS Quantum Metaglove, capable of sensing the variations of an electromagnetic field (EMF) sourced on the dorsal part of the hand and revealed by EMF coils at the fingers tips. A total of 65 people (35 PD patients and 30 healthy subjects for reference) were asked to perform standard motor tasks, and both most affected and least affected hands were assessed for opening-closing, grasping and pronation-supination movements. Differing from the generally adopted spatiotemporal analysis, taking a cue from non-linear theory adopted in electronics, we focused on spectral characteristics of the measured signals, specifically examining harmonic content and related harmonic distortions. As a result, we report how the adopted sensory glove, ensemble with spectral analysis, can be able to consistently assess hand motor (in)abilities in PD subjects and healthy subjects. In fact according to our results, PD patients significatively performed with hand motion signals affected by harmonic distortions, which revealed that the greater the complexity of the motor task, the greater the spread of the signal across harmonic frequencies, whilst healthy subjects perform with signals mostly around the fundamental frequency, as a marker of movement smoothness.</div></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":"45 3","pages":"Pages 507-514"},"PeriodicalIF":5.3,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144694330","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dysphonia discovering using a Goertzel algorithm implementation for vocal signals analysis","authors":"Patrizia Vizza ,&nbsp;Giuseppe Tradigo ,&nbsp;Pietro Hiram Guzzi ,&nbsp;Pierangelo Veltri","doi":"10.1016/j.bbe.2025.07.001","DOIUrl":"10.1016/j.bbe.2025.07.001","url":null,"abstract":"<div><div><em>Background and objectives:</em> The identification, study and classification of anomalies in vocal signals are used to support physicians in the diagnosis and monitoring of vocal robe pathologies. Dysphonia is the most common disorder causing difficulties in voice production. Dysphonia refers to any impairment in voice quality, and significantly impacts on the quality of life. Early detection is imperative to prevent severe pathologies or to early detect chronic ones. Voice signal processing techniques, such as Fast Fourier Transform (FFT) and Praat, are noninvasive tools used to study phonatory apparatus diseases. Nevertheless there is room for improving efficacy in vocal signal patterns identification that could be related to vocal robe related pathologies.</div><div><em>Methods:</em> The focus is on the possibility of using Goertzel Algorithm (GA) characteristics to improve state of the art for pattern identification in vocal signals. A tool for early identification of dysphonia based on GA is presented. An optimized version of GA, able to detect voice frequency anomalies has been implemented.</div><div><em>Results:</em> The proposed tool has been tested with vocal signal datasets containing both normophonic and pathological subjects. The results are reported in terms of different implementation strategies and techniques. Experimental tests were performed comparing GA based and FFT based signal analysis tools in terms of: (i) efficiency and (ii) capacity of features identification. Performance parameters report: (i) an efficiency in terms of processing time improved by 37 % (i.e. 16.78 ms for FFT vs 12.26 ms for GA) and memory requirements reduced by 74 %; (ii) GA enabled the identification of healthy and pathological conditions better than FFT with a significance level below 0.05.</div><div><em>Conclusions:</em> Results of using GA-based method on vocal signal processing, compared with existing methods, demonstrate the reliability of the proposed method in early identification of dysphonia and in clinical monitoring of patients post treatment.</div></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":"45 3","pages":"Pages 469-475"},"PeriodicalIF":5.3,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144556997","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep spatio-temporal features optimised fusion with coordinate attention mechanism for EEG lower limb pre-movement intention decoding","authors":"Runlin Dong ,&nbsp;Xiaodong Zhang ,&nbsp;Zhengzheng Zhou ,&nbsp;Wenyu Zha ,&nbsp;Aibin Zhu","doi":"10.1016/j.bbe.2025.06.004","DOIUrl":"10.1016/j.bbe.2025.06.004","url":null,"abstract":"<div><h3>Background and Objective</h3><div>Decoding pre-movement intention is crucial in developing a brain-computer interface (BCI) for neuro-rehabilitation robotic systems. However, the weak amplitude and non-smooth characteristics of EEG signals lead to the inability of existing methods to achieve the accuracy for proper applications. This study proposed a novel pre-movement intention decoding network framework to improve accuracy by extracting and optimizing the deep spatio-temporal features of EEG signals.</div></div><div><h3>Methods</h3><div>A deep spatio-temporal neural network structure was constructed based on the brain intention generation mechanism and its movement expression. The collected multi-channel EEG data were reorganized into brain topographic distributions, after the initial extraction of the features and optimization using the coordinate attention mechanism, a 3-layer dense block with two bi-directional gated recirculation units was designed to effectively extract the deep spatial and temporal features, further decoding the pre-movement intention efficiently.</div></div><div><h3>Results</h3><div>The experimental results showed an average accuracy of 95.51 ± 1.79 % for healthy subjects and 90.48 ± 2.90 % for stroke survivors in decoding pre-movement intention. All evaluation indexes are excellent. Pseudo-online testing showed the average TPR was 95.45 ± 3.80 % and 90.71 ± 7.77 % for healthy subjects and stroke survivors, respectively, and the latency was −1965 ± 48 ms and −1974 ± 36 ms. The results of the ablation and comparative analysis showed that the proposed framework is justified and its decoding capability outperforms other state-of-the-art algorithms.</div></div><div><h3>Conclusion</h3><div>The method proposed in this study has high decoding accuracy and good online performance in pre-movement intention decoding based on EEG signals, which lays the foundation for further neuro-rehabilitation robotic systems.</div></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":"45 3","pages":"Pages 515-527"},"PeriodicalIF":5.3,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144702745","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MRS thermometry – Importance of scanner-specific calibrations for accurate brain temperature estimations","authors":"Marcin Sińczuk ,&nbsp;Jacek Rogala ,&nbsp;Piotr Bogorodzki","doi":"10.1016/j.bbe.2025.06.001","DOIUrl":"10.1016/j.bbe.2025.06.001","url":null,"abstract":"<div><div>This study explores the importance of scanner-specific calibration measurements for Magnetic Resonance Spectroscopy Thermometry (MRST) in human brain temperature estimations. Data acquisition was conducted on a 3-T GE scanner. Calibration constants for the water-chemical shift were obtained using a temperature-controlled phantom containing an aqueous solution of N-acetyl aspartate (NAA), Creatine (Cr), and Choline (Cho), and data from three different research groups using the same metabolites. Temperatures were estimated utilizing correlation of water chemical shift with NAA, Cr and Cho. For data acquisition, commercially available single-voxel point-resolved spectroscopy (PRESS) sequences were used for calibrations and in vivo temperature estimations. Each sequence included spectras without (WU) and with (WS) water suppression. In vivo study consisted of two PRESS sequences, one before and one after extensive 30-minute fMRI task acquisition. Significant differences were found between absolute brain temperatures measured using scanner-specific calibrations and those from other researchers, varying from −0.68 °C to + 0.37 °C for NAA, −0.92 °C to 0.37 °C for Cr, and −0.78 °C to 0.7 °C for Cho. Each method reported a similar temperature decrease of −0.26 ∓ 0.03 °C between before and after fMRI measurements. These findings suggest that while absolute temperatures from non-scanner specific calibrations may be inaccurate, comparative estimates are valid.</div></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":"45 3","pages":"Pages 451-456"},"PeriodicalIF":5.3,"publicationDate":"2025-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144489482","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improving the quality of respiratory signals extracted from the segmented mask area","authors":"Natalia Kowalczyk,&nbsp;Jacek Rumiński,&nbsp;Magdalena Mazur-Milecka","doi":"10.1016/j.bbe.2025.06.002","DOIUrl":"10.1016/j.bbe.2025.06.002","url":null,"abstract":"<div><div>The COVID-19 pandemic has underscored the importance of wearing facial masks and monitoring respiratory health to prevent the spread of the virus. In this study, we developed a model for segmenting facial masks in thermal images. We applied the model to segment face masks in different conditions, including a person walking toward the observing camera. The segmented regions were further processed using different erosion masks to analyze the influence of the selected sources on the quality of the estimated respiratory signals. The Signal-to-Noise Ratio (SNR) was used as a quality measure. Additionally, the extracted respiratory signals were compared with two reference signals: binary signals generated by participants who signaled the inhalation phase and pressure signals measured with a respiratory belt. Our findings show a high level of concordance between the respiratory signals derived from the segmented mask region and those from the respiratory belt, validating the effectiveness of thermal imaging for capturing respiratory patterns. Notably, the signal-to-noise ratio (SNR) was higher for the segmented mask than the detection methods used in previous works. Specifically, for the mask segmentation task, the mean SNR improved by 4.3 compared to facial mask detection. The segmentation model achieved a mean Average Precision (mAP) of 0.992 for segmentation tasks and 0.857 mAP at the 50–95 % threshold using the Yolov8 “nano” architecture. This study underscores the potential of thermal imaging for non-invasive respiratory monitoring and highlights the explainability and accuracy of selecting the facial mask region for signal extraction.</div></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":"45 3","pages":"Pages 457-468"},"PeriodicalIF":5.3,"publicationDate":"2025-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144489483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrative and interpretable framework to unveil the neurophysiological fingerprint of Alzheimer’s disease and mild cognitive impairment: A machine learning-SHAP approach","authors":"Víctor Gutiérrez-de Pablo ,&nbsp;María Herrero-Tudela ,&nbsp;Marina Sandonís-Fernández ,&nbsp;Jesús Poza ,&nbsp;Aarón Maturana-Candelas ,&nbsp;Víctor Rodríguez-González ,&nbsp;Miguel Ángel Tola-Arribas ,&nbsp;Mónica Cano ,&nbsp;Hideyuki Hoshi ,&nbsp;Yoshihito Shigihara ,&nbsp;Roberto Hornero ,&nbsp;Carlos Gómez","doi":"10.1016/j.bbe.2025.05.011","DOIUrl":"10.1016/j.bbe.2025.05.011","url":null,"abstract":"<div><div>Dementia and mild cognitive impairment (MCI) due to Alzheimer’s disease (AD) are neurological pathologies associated with disruptions in brain electromagnetic activity, typically studied using magnetoencephalography (MEG) and electroencephalography (EEG). To quantify diverse brain properties, different families of parameters can be computed from MEG and EEG (i.e., spectral, non-linear, morphological, functional connectivity, or network structure and organisation). However, studying these characteristics separately overlooks the complex nature of brain activity. Integrative frameworks can be useful to unveil the intricate neurophysiological fingerprint, as well as to characterise pathological conditions comprehensively. To that purpose, data fusion methodologies are crucial, despite their interpretational challenges. In this study, Machine Learning (ML) models were trained to discriminate between groups of severity, whereas the SHapley Additive eXplanations (SHAP) algorithm was afterwards utilised to assess the relevance of the input characteristics into the output classification. Three databases were analysed: MEG (55 healthy controls, HC, 42 MCI patients, and 86 AD patients), EEG1 (51 HC, 52 MCI, and 100 AD), and EEG2 (45 HC, 69 MCI, and 82 AD). The best results for the three-class classification problem were obtained by Gradient Boosting for the MEG database: 3-class Cohen’s kappa coefficient of 0.5452 and accuracy of 72.63 %. Afterwards, using SHAP on Gradient Boosting, it has been shown that spectral features were identified as highly relevant across all databases. Furthermore, morphology measures presented high relevance for the MEG database, whereas EEG1 and EEG2 databases showed functional connectivity and multiplex organisation measures, respectively, as relevant subgroups of parameters. Finally, commonly relevant features across databases were selected using SHAP to generate the neurophysiological fingerprints of AD and MCI. This study highlights the relevance of different MEG and EEG parameters in characterising neurological pathologies. The proposed framework, based on MEG and EEG, can be used to generate interpretable, robust, and accurate neurophysiological fingerprints of AD and MCI.</div></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":"45 3","pages":"Pages 438-450"},"PeriodicalIF":5.3,"publicationDate":"2025-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144279921","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}