BMC biomedical engineering最新文献

{"title":"A web modular AI interface for brain tumor MRI classification using deep learning models.","authors":"Jennifer Hamalaya, Hadi Fayad, Tarraf Torfeh, Sandy Rihana","doi":"10.1186/s42490-026-00123-w","DOIUrl":"https://doi.org/10.1186/s42490-026-00123-w","url":null,"abstract":"<p><p>In order to improve patient outcomes and treatment processes, early and precise diagnosis of brain tumors is crucial. Despite the strong performance shown by deep learning models in classifying brain tumors from MRI scans, integrating these models into user-friendly clinical workflows remains challenging. This study presents a web-based AI platform designed for brain tumor classification using MRI images. The platform enables users to upload MRI scans, apply standardized preprocessing, select between different deep learning models, and receive real-time predictions. A custom convolutional neural network (CNN), pretrained VGG19, and pretrained Xception were evaluated using a publicly available T1-weighted contrast-enhanced brain MRI dataset of approximately 7,000 images across four classes: glioma, meningioma, pituitary tumor, and no tumor. The dataset lacks patient demographic and clinical metadata, limiting assessment of clinical generalizability. The models achieved test accuracies of 96.03%, 98%, and 96%, respectively, with VGG19 demonstrating the best performance. The study is limited by the use of a single public, slice-based dataset and the absence of external clinical validation; future work will focus on multi-sequence MRI and independent clinical cohorts.</p>","PeriodicalId":72425,"journal":{"name":"BMC biomedical engineering","volume":"8 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149247654","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated phase recognition in the cardiac catheterization laboratory with deep learning.","authors":"Teddy S Vijfvinkel, Emanuele Frassini, Yannick Weijenberg, Bardia Nikookar, Rick M Butler, Jan Constandse, Maarten van der Elst, Benno H W Hendriks, John J van den Dobbelsteen","doi":"10.1186/s42490-026-00122-x","DOIUrl":"10.1186/s42490-026-00122-x","url":null,"abstract":"<p><strong>Background: </strong>An efficient workflow in the cardiac catheterization laboratory is important to guarantee quality of care and keep healthcare affordable. Automated surgical process monitoring of diagnostic coronary angiograms (CAGs) has the potential to increase workflow efficiency, reduce non-clinical workload, and optimize scheduling. The aim of this study is to automatically classify workflow phases of CAGs using deep learning models trained on a real-world dataset.</p><p><strong>Methods: </strong>With an observational study we collected a dataset, composed of an integration of video recorded CAGs, clinical data, and system logging data. Every procedural phase was annotated by a medical doctor based on clinically relevant key points in time. A Scaled-YOLOv4 object detection algorithm was employed to extract features from the video images. We implemented Long short-term memory (LSTM) and LSTM-Fully convolutional network (LSTM-FCN) on the integrated time series data to classify the workflow phases. The accuracy in the classification was weighted on the duration of the phase.</p><p><strong>Results: </strong>A dataset including video, clinical and logging data of 222 CAG procedures was obtained. A weighted accuracy for phase classification of 91.3% was reached for the LSTM model, compared to 90.8% for the LSTM-FCN model. No significant difference was found after statistical comparison between both models. However, the LSTM network was 2.2 times faster in training while requiring around 40% less parameters.</p><p><strong>Conclusions: </strong>This study demonstrates the potential of deploying deep learning models on a real-world integrated dataset to automatically detect CAG phases with more than 90% accuracy. No statistically significant difference was found between the performance of the two models, although the LSTM model required less training time compared to the LSTM-FCN. Thus, we suggest the employment of these models for phase recognition challenges based on composite datasets. Given the promising accuracy of these deep learning techniques, automated phase recognition could become a cornerstone of dynamic schedule optimization and increase future hospital efficiency.</p>","PeriodicalId":72425,"journal":{"name":"BMC biomedical engineering","volume":"8 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13688766/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149240558","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of a hybrid manikin for extra-uterine life support technology innovation.","authors":"J S van Haren, B G van Willigen, C M van Riet, W J Loor, J R van den Broek, J Sterk, C Amendola, K Verschueren, M W H Thielen, M B van der Hout-van der Jagt, F L M Delbressine","doi":"10.1186/s42490-026-00120-z","DOIUrl":"10.1186/s42490-026-00120-z","url":null,"abstract":"<p><strong>Background: </strong>Preclinical studies have shown successful maintenance of fetuses on extra-uterine life support technology. This technology has the potential to offer a liquid-based alternative for the care of extremely premature infants.</p><p><strong>Methods: </strong>To bridge the gap between preclinical research and clinical translation, and to provide a low-risk environment, we developed a hybrid fetal manikin to complement animal studies and facilitate technology development and clinician training. Through these fetal manikins, characteristics of extremely premature infants can be mimicked through integrated actuators that respond to physiological parameters, which are monitored through integrated sensors.</p><p><strong>Results: </strong>Utilizing clinical data, we designed the manikin to realistically replicate anatomical structures, physiological properties, and symptom display. A wireless connection to a fetal digital twin enables sensor data transmission and downstream cascade calculations for symptom display on the manikin. Evaluation included qualitative and quantitative realism assessments, either comparing with patient data or clinician assessments.</p><p><strong>Conclusions: </strong>Our study demonstrates the applicability and potential of using simulation technologies for high-risk, human-centered MedTech development. It allows expanding stakeholder involvement during development, and it may better equip a medical team through simulation training and enhance the technology development.</p>","PeriodicalId":72425,"journal":{"name":"BMC biomedical engineering","volume":"8 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13621680/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149076496","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ADHD classification using spherical phase space partitioning and symbolic time series analysis of multi-channel EEG signals.","authors":"Neda Songhori, Nafise Niknam, Elham Eslamiyan, Moslem Solhirad","doi":"10.1186/s42490-026-00119-6","DOIUrl":"10.1186/s42490-026-00119-6","url":null,"abstract":"<p><p>Attention Deficit Hyperactivity Disorder (ADHD) is one of the most common neurodevelopmental disorders in children, making early detection and intervention critically important. In this study, we propose a novel EEG based classification framework for ADHD that integrates advanced nonlinear signal analysis with deep learning methodologies. EEG recordings were collected from 61 children diagnosed with ADHD and 60 age-matched healthy controls during a visual attention task, utilizing 19 electrodes placed according to the international 10-20 system. The preprocessing pipeline involved artifact rejection, independent component analysis (ICA), and band-pass filtering. A key innovation of our method is the integration of spherical phase space partitioning with entropy-optimized symbolic time series analysis (SPSP-STSA), allowing for reliable and noise-resilient feature extraction across multiple EEG channels. The extracted symbolic sequences were then used for classification via cosine similarity and a bidirectional Long Short-Term Memory (LSTM) network, which effectively models temporal patterns to improve diagnostic accuracy. The proposed method achieved a classification accuracy of up to 98% using window-based analysis of 20-second EEG segments. Our findings highlight the potential of SPSP-STSA and deep learning for advancing EEG-based ADHD diagnosis, offering improved robustness and interpretability compared to conventional approaches.</p>","PeriodicalId":72425,"journal":{"name":"BMC biomedical engineering","volume":"8 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13602667/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149042269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrating statistical parametric mapping, functional principal component analysis, explainable machine learning, and equivalence testing for multimodal gait signal analysis.","authors":"Kofi Nyantakyi Appiah, Edward Wilson Ansah, Frank Sarfo Dofour","doi":"10.1186/s42490-026-00118-7","DOIUrl":"10.1186/s42490-026-00118-7","url":null,"abstract":"<p><strong>Background: </strong>Gait speed is a key clinical indicator in neurological and orthopaedic conditions, yet waveform-level adaptations in ground reaction forces (GRF) and multi-muscle electromyography (EMG) remain poorly characterised. Existing approaches often analyse discrete outcomes or individual modalities, leaving limited integration of continuous waveform inference, dimensionality reduction, explainable machine learning, and equivalence testing within a unified multimodal framework.</p><p><strong>Objective: </strong>To compare three-axis GRF and six-muscle EMG between slow (0.5 m/s) and fast (1.0 m/s) treadmill walking using statistical parametric mapping (SPM), functional principal component analysis (fPCA), explainable machine learning, and equivalence testing.</p><p><strong>Methods: </strong>Fifty-eight healthy adults were analysed (55 with complete EMG). Paired SPM with cluster-based permutation assessed waveform differences. fPCA-derived features entered a Random Forest with leave-one-subject-out cross-validation and SHAP interpretability. Two one-sided tests (TOST) assessed equivalence of the vertical GRF.</p><p><strong>Results: </strong>No significant cluster-level SPM differences were found for any GRF component. In contrast, significant EMG clusters were detected in tibialis anterior (ten clusters), gastrocnemius medial and lateral, vastus lateralis, rectus femoris, and semitendinosus. The Random Forest achieved 87.2% accuracy (95% CI: 79.3-92.3%), improving 14.7% points over simple amplitude features, with tibialis anterior PC1 the most important predictor. TOST did not confirm equivalence within ± 0.2 N/kg, though no GRF clusters appeared.</p><p><strong>Conclusions: </strong>Moderate speed increases elicited distributed multi-muscle activation changes, whereas GRF waveform differences did not reach cluster-level significance within the present analytical framework. The integrated SPM-fPCA-SHAP-TOST pipeline provides an interpretable signal-processing framework for multimodal gait analysis and could serve as a foundation for future investigations in rehabilitation engineering, digital biomarkers, and wearable sensing, pending validation in clinical populations.</p>","PeriodicalId":72425,"journal":{"name":"BMC biomedical engineering","volume":"8 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13452104/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148698415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of a 3D-printed synthetic tracheal scaffold for partial tracheal wall reconstruction: an experimental animal study.","authors":"Ali Tadayon, Maryam Bahrani, Taha Negahdari, Mahsa Askari Jahromi, Shayan Yousufzai, Sepehr Moradi, Mobin Haghdel","doi":"10.1186/s42490-026-00117-8","DOIUrl":"10.1186/s42490-026-00117-8","url":null,"abstract":"<p><strong>Background: </strong>Tracheal reconstruction remains a significant clinical challenge due to the difficulty of maintaining airway patency and promoting epithelial regeneration following tracheal injury or resection. Recent advances in tissue engineering have explored 3D-printed scaffolds as potential solutions; however, limitations remain regarding scaffold biocompatibility, mechanical stability, and integration with host tissue. This study evaluated the feasibility of a non-biodegradable polyurethane-polyvinyl chloride (PU-PVC) composite scaffold for partial tracheal wall reconstruction in a rabbit model.</p><p><strong>Methods: </strong>Nine New Zealand white rabbits underwent anterior tracheal wall reconstruction using a customized half-pipe PU-PVC scaffold. Scaffold mechanical properties were characterized before implantation. Animals were monitored for 30 days, after which bronchoscopic evaluation was performed to assess luminal patency. Histological analysis was conducted to evaluate epithelialization and inflammatory response. Explanted scaffolds were also assessed for structural integrity and mechanical stability.</p><p><strong>Results: </strong>The 30-day survival rate was 88.9% (8/9; 95% CI 51.8%-99.7%), with one death occurring on postoperative day 14. Bronchoscopic examination demonstrated complete luminal patency in all surviving animals, with no evidence of stenosis, obstruction, or mucus plugging. Histological findings demonstrated variable epithelialization, with 50% (4/8) of rabbits showing favorable epithelial coverage accompanied by mild inflammation, while the remaining animals exhibited partial or minimal epithelialization associated with greater inflammatory responses. Post-explant evaluation demonstrated preservation of scaffold structure and mechanical properties, with only minor changes in tensile strength and porosity after implantation.</p><p><strong>Conclusion: </strong>In this preliminary single-cohort feasibility study, the PU-PVC composite scaffold-maintained airway patency throughout the 30-day observation period and demonstrated acceptable short-term mechanical stability following partial tracheal wall reconstruction in a rabbit model. Although epithelialization outcomes were variable and no comparator group was included, the findings support further preclinical investigation of this scaffold platform; however, long-term safety, durability, and biological integration remain to be established. Future studies incorporating appropriate control groups, longer follow-up periods, quantitative assessments of airway patency, and bioactive modifications such as cell seeding or growth factors are warranted to enhance tissue regeneration and better define the scaffold's translational potential.</p>","PeriodicalId":72425,"journal":{"name":"BMC biomedical engineering","volume":"8 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13386752/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148537806","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An edge-AI enabled wearable platform for real-time epileptic seizure detection with geolocated alerting.","authors":"Tsion Fekadu, Kidist Dagnachew, Abdi Bekele","doi":"10.1186/s42490-026-00116-9","DOIUrl":"10.1186/s42490-026-00116-9","url":null,"abstract":"<p><p>Epilepsy remains a major global health concern, particularly in regions where continuous medical monitoring is difficult to implement. This study introduces a wearable system powered by edge-based artificial intelligence, designed to detect epileptic seizures in real time. The device integrates multiple sensors-accelerometers for motion tracking, photoplethysmography (PPG) for cardiovascular monitoring, and GPS for location detection-to enhance reliability through sensor fusion. Multiple machine learning models, including support vector machines (SVM), neural networks (NN), and random forest classifiers, were deployed and assessed directly on the device. Among these, the optimized random forest algorithm achieved the highest accuracy and fastest response time. The fusion of sensor data significantly improved specificity and maintained a very low false alarm rate. When a seizure is detected, the system instantly sends SMS alerts with precise location details to assigned caregivers, enabling prompt medical intervention. Simulation results demonstrate that this cost-effective and self-contained platform offers strong potential for improving patient safety and facilitating rapid response in low-resource settings where conventional monitoring tools are unavailable.</p>","PeriodicalId":72425,"journal":{"name":"BMC biomedical engineering","volume":"8 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13332600/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148383329","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multimodal data synchronization: a high-level software methodology for heterogeneous devices.","authors":"Damiano Fruet, Stefano Cimignolo, Giandomenico Nollo","doi":"10.1186/s42490-026-00114-x","DOIUrl":"10.1186/s42490-026-00114-x","url":null,"abstract":"<p><strong>Background: </strong>Multimodal data acquisition from heterogeneous devices is frequently compromised by synchronization errors arising from clock skew and offset. Current solutions often necessitate complex external hardware or shared reference signals, which complicates deployment and limits system scalability.</p><p><strong>Methods: </strong>This research introduces a high-level software methodology that utilizes a dedicated data acquisition protocol to record device-specific timestamps alongside a master PC timestamp. An offline linear regression model is then employed to convert internal timestamps to a common reference, compensating for clock discrepancies. The method was validated using electrocardiographic and Inertial Measurement Unit devices compared against a gold-standard reference. The ECG R-peaks fiducial points from the synchronized devices and the gold standard were compared.</p><p><strong>Results: </strong>Validation showed an average R-peak synchronization delay of 20.1 ms over a one-hour acquisition (a 0.03% difference). The method successfully eliminates the need for external synchronization hardware, allowing scaling to be limited only by PC connectivity.</p><p><strong>Conclusion: </strong>While dependent on device Software Development Kits, this methodology provides a robust, scalable foundation for precise multimodal synchronization. This proof-of-concept demonstrates that high-level software control can achieve high accuracy for dynamic clock adjustment.</p>","PeriodicalId":72425,"journal":{"name":"BMC biomedical engineering","volume":"8 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13277054/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148280135","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effect of seat cushion resilience and hardness on lower-limb loading during sit-to-stand.","authors":"Yusuke Onoda, Ami Ogawa","doi":"10.1186/s42490-026-00115-w","DOIUrl":"10.1186/s42490-026-00115-w","url":null,"abstract":"<p><strong>Background: </strong>Seat cushion materials affect the mechanical demands of sit-to-stand (STS) movements; however, the effects of specific material properties, such as resilience and hardness, remain unclear. Understanding how these factors influence lower-limb joint moments and movement strategies during STS may contribute to the development of seat designs that assist individuals with reduced lower-limb strength. Therefore, this study aimed to clarify the fundamental mechanical effects of seat cushion resilience and hardness on STS.</p><p><strong>Methods: </strong>Fifteen healthy young adults performed STS from five polyurethane foam cushions that differed in resilience (14-55%) and 40% compression hardness (66-336 N). The material ranges were determined with reference to technical documents and a published patent specification to ensure they were within the range commonly used in everyday seating products. Kinematic and kinetic data were collected using a motion capture system and two force plates. Net joint moments were calculated via inverse dynamics, and differences among seat conditions were analyzed using repeated-measures ANOVA or the Friedman test, with Bonferroni-adjusted pairwise comparisons (α = 0.05).</p><p><strong>Results: </strong>Seat resilience significantly affected the peak hip and knee extensor moments (p < 0.01, η² = 0.35-0.48). High-resilience cushions delayed seat-off timing and maintained greater seat reaction force at the timings of peak hip and knee extensor moments. In contrast, seat hardness mainly influenced horizontal center-of-mass (COM) velocity and hip joint moment (p < 0.01, η² = 0.31-0.37), with softer seats producing larger values.</p><p><strong>Conclusion: </strong>High-resilience cushions delayed seat-off and maintained buttock support for a longer duration, thereby reducing the peak hip and knee extensor moments. In contrast, softer seats promoted a strategy involving greater horizontal momentum generation by the upper body, which consequently required an increased hip extensor moment to decelerate this momentum. Cushions with a resilience of ≥ 53% and 40% compression hardness of ≥ 180 N effectively reduced lower-limb joint loading. The results of this study provide fundamental insights that may contribute to future research on chair design and cushion selection in clinical and caregiving environments.</p><p><strong>Clinical trial: </strong>Not applicable.</p>","PeriodicalId":72425,"journal":{"name":"BMC biomedical engineering","volume":"8 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13277150/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148273982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bench testing a contact sensing tracheal tube for monitoring the cuff-trachea interface.","authors":"Tamaralayefa B Agbiki, Sandor Erdody, Ricardo Correia, Sergiy Korposh, David W Hewson, Andrew M Norris, Barrie R Hayes-Gill, Stephen P Morgan","doi":"10.1186/s42490-026-00113-y","DOIUrl":"10.1186/s42490-026-00113-y","url":null,"abstract":"<p><p>Cuffed tracheal tubes enable a secure airway during mechanical ventilation; however, improper cuff inflation can lead to complications such as inspiratory gas leaks, pulmonary ingress of orogastric secretions, or tracheal injury. This study explores a sensor-based approach to optimise cuff inflation using fibre Bragg grating (FBG) optical sensors embedded within the cuff to detect contact with the tracheal wall. Testing was conducted on multiple trachea models, including cylindrical and bio-inspired models, as well as ex vivo porcine trachea samples, to assess cuff-trachea contact. Seal performance was evaluated at both standard inflation pressures and contact-guided inflation pressures. The contact-sensing tracheal tube successfully detected cuff-trachea contact in all models and ex vivo samples tested. Seal tests showed that larger diameter tracheal models exhibited lower leakage rates at contact-guided inflation pressures compared with standard inflation, indicating improved sealing. In contrast, smaller diameter models showed higher leakage rates at contact-guided pressures due to cuff folding, which formed leakage pathways. These results demonstrate that contact sensing improved cuff performance in larger tracheal models by enhancing sealing effectiveness. The contact-sensing tracheal tube differentiated tracheal model sizes, indicating potential for personalised cuff inflation to accommodate variations in tracheal size and shape. Future work will focus on further sensor miniaturisation and integration within lower-volume cuffs to enable effective contact sensing across a wider range of tracheal geometries and support translation to in vivo use.</p>","PeriodicalId":72425,"journal":{"name":"BMC biomedical engineering","volume":"8 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13224478/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148139944","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}