Medical Engineering & Physics最新文献

{"title":"DDUM: Deformable Dilated U-structure Module for coronary stenosis detection","authors":"Chenru Wang ,&nbsp;Zirui Chen ,&nbsp;Muyao Li ,&nbsp;Haoran Yin ,&nbsp;Saijie Zhou ,&nbsp;Jingliang Zhang ,&nbsp;Xueying Zeng ,&nbsp;Qing Zhang","doi":"10.1016/j.medengphy.2025.104337","DOIUrl":"10.1016/j.medengphy.2025.104337","url":null,"abstract":"<div><div>Deep learning methods are increasingly popular in assisting physicians with diagnosing coronary artery disease and reducing errors caused by subjective judgment. However, accessing and labeling medical imaging data, especially coronary angiography data, is challenging. Consequently, models trained on such datasets often exhibit low accuracy, high false-positive rates, and limited generalization capabilities. We propose a Deformable Dilatable U-structure Module that can specialize a common network for coronary stenosis detection and enhance its generalization ability. Experiments demonstrate that our proposed module significantly improves the performance of various models. When applying DDUM to a model with ResNet50 as the backbone and faster R-CNN as the detector, the mean average precision increases from 33.76 to 42.39, a 25.56% improvement. Additionally, we show that DDUM enhances the network's generalization ability through transfer learning experiments. This module can improve the network's accuracy for stenosis detection and enhance the generalization ability of the original model. Fine-tuning reduces training costs and ensures that the model can be easily adapted and deployed across different devices.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"139 ","pages":"Article 104337"},"PeriodicalIF":1.7,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143814968","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A multiparameter comparative approach to the three-dimensional numerical analysis of the hemodynamics of total cavopulmonary connection","authors":"Paulo Cesar Duarte Junior ,&nbsp;Rudolf Huebner ,&nbsp;Hemerson Donizete Pinheiro","doi":"10.1016/j.medengphy.2025.104331","DOIUrl":"10.1016/j.medengphy.2025.104331","url":null,"abstract":"<div><h3>Purpose</h3><div>Univentricular congenital heart diseases represent a significant challenge in cardiology, requiring a complex staged treatment protocol involving total cavopulmonary connection via the Fontan procedure. The application of advanced numerical methods has proved fundamental to understanding post-surgical behavior, allowing the multidisciplinary team to design more efficient and physiologically realistic anatomies. However, the definition of boundary conditions to represent fluid behavior in anatomical changes following total cavopulmonary connection is still an emerging field, frequently relying on estimates and simplifications. This study aimed to identify an effective set of variables for simplifying the analysis of hemodynamic behavior in total cavopulmonary connection and reducing the requirement for extensive computational resources.</div></div><div><h3>Methods</h3><div>A multiparameter comparative analysis of simulations was performed by using several variables under rest conditions for specific Fontan configurations, accounting for factors such as turbulent versus laminar flow, Newtonian versus non-Newtonian fluid, and rigid versus flexible vascular walls.</div></div><div><h3>Results</h3><div>Two sets of variables were found to provide the best results: (i) Newtonian fluid behavior, turbulent flow, steady regime, and rigid walls were found suitable when the distribution of blood flow to the pulmonary arteries is the desired result and (ii) Newtonian fluid behavior, turbulent flow, transient regime, and rigid walls were found suitable when the distribution of blood flow to pulmonary arteries, shear stress, and energy loss are equally important.</div></div><div><h3>Conclusion</h3><div>The identified sets of variables provide a solid foundation for future analyses, ensuring reliable results and an efficient use of computational resources.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"139 ","pages":"Article 104331"},"PeriodicalIF":1.7,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143769017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated ADHD detection using dual-modal sensory data and machine learning","authors":"Yanqing Ji ,&nbsp;Janet Zhang-Lea ,&nbsp;John Tran","doi":"10.1016/j.medengphy.2025.104328","DOIUrl":"10.1016/j.medengphy.2025.104328","url":null,"abstract":"<div><div>This study explores using dual-modal sensory data and machine learning to objectively identify Attention-Deficit/Hyperactivity Disorder (ADHD), a neurodevelopmental disorder traditionally diagnosed through subjective clinical evaluations. Six machine learning algorithms, including Logistic Regression (LR), Random Forest (RF), XGBoost (XGB), LightGBM (LGBM), Neural Network (NN), and Support Vector Machine (SVM), were evaluated using both activity and heart rate variability (HRV) data collected from 103 participants. The results show that both activity and HRV data performed similarly when analyzed individually. However, when the two datasets were combined, the highest F1-score increased by 12 % compared to the activity data and 23 % compared to the HRV data. This combination leverages the complementary strengths of both data, representing a key contribution of our work. With the combined data, the SVM model performed best, achieving an F1-Score of 0.87 and a Matthews Correlation Coefficient of 0.77. This study highlights the significant potential of interdisciplinary collaboration and the use of diverse data sources to advance ADHD detection through cutting-edge machine learning techniques.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"139 ","pages":"Article 104328"},"PeriodicalIF":1.7,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143725879","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Degradation of the mechanical properties of poly-lactide-caprolactone-collagen composite for pulmonary artery banding after implantation into a rat's peritoneum","authors":"Lukáš Horný ,&nbsp;Lucie Vištejnová ,&nbsp;Tomáš Suchý ,&nbsp;Eva Kuželová Košťáková ,&nbsp;Hynek Chlup ,&nbsp;Jakub Kronek ,&nbsp;Zbyněk Sobotka ,&nbsp;Zdeněk Petřivý ,&nbsp;Margit Žaloudková ,&nbsp;Kristýna Havlíčková ,&nbsp;Jiří Moláček","doi":"10.1016/j.medengphy.2025.104319","DOIUrl":"10.1016/j.medengphy.2025.104319","url":null,"abstract":"<div><div>Pulmonary artery banding is a surgical procedure performed when there is a shunt between the left and right ventricle. Its aim is to constrict the lumen of the pulmonary artery by using a band to reduce blood flow to the lungs. In this study, we report the results of investigating the mechanical properties of a composite composed of poly(L-lactide-co-ε-caprolactone) layers and a collagen matrix (PLCL-COLL). PLCL layers were obtained by electrospinning, impregnated with collagen solution, and finally cross-linked to increase the stiffness of the material. Bands of PLCL-COLL were implanted into a rat peritoneum and explanted after 1, 3, and 6 months <em>in vivo</em>. The mechanical properties of the material before and after implantation were determined using uniaxial tensile tests. The same was done with samples of strips prepared from GORE-TEX material. By comparing the results of tensile tests before implantation and after explantation, it was found that PLCL-COLL degrades in the rat's body and that it exhibits a mechanical response showing of elastic modulus values that correspond well to arterial biomechanics (elastic modulus measured in the initial linear region of the deformation was found to be: 4.14 MPa ± 1.11 MPa, 2.34 MPa ± 1.02 MPa, 1.11 MPa ± 0.77 MPa, and 0.88 MPa ± 0.60 MPa before implantation, and 1, 3, and 6 months after implantation respectively). Similar to the elastic modulus, the strength of the PLCL-COLL composite decreased during <em>in vivo</em> exposure (1.32 ± 0.32 MPa, 0.60 ± 0.26 MPa, 0.44 ± 0.11 MPa, and 0.46 ± 0.28 MPa before implantation, and 1, 3, and 6 months after implantation respectively). In our experiments, PLCL-COLL material was always more compliant than GORE-TEX (elastic modulus 34.7 MPa ± 2.06 MPa before implantation, and 9.35 MPa ± 6.80 MPa after implantation). The results suggest that PLCL-COLL could be a suitable candidate for the development of artery banding tapes, and also for further use in cardiovascular surgery.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"138 ","pages":"Article 104319"},"PeriodicalIF":1.7,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143679402","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Measurement of heart rate from long-distance videos via projection of rotated orthogonal bases in POS","authors":"Bing Rao ,&nbsp;Ruige Fang ,&nbsp;Changchen Zhao ,&nbsp;Jie Bai","doi":"10.1016/j.medengphy.2025.104326","DOIUrl":"10.1016/j.medengphy.2025.104326","url":null,"abstract":"<div><div>Remote photoplethysmography (rPPG) has long been an active research topic. Existing rPPG approaches achieve high accuracy of heart rate extraction, as long as the user is relatively close to the camera (typically, less than 1 meter distance). This article investigates the performance of existing rPPG approaches under the long-distance recording conditions and proposes a novel Projection of Rotated Orthogonal Bases in POS (ProPOS) algorithm for heart rate extraction. A set of orthogonal projection bases is generated around the original plain of POS algorithm. The raw measurement traces are projected on these bases and the final output signal is obtained by a designed SNR selection criterion. The long-distance rPPG (LD-rPPG) dataset is established for long-distance rPPG research by varying the recording distance from 3 m-30 m. Extensive experiments are performed in comparison with existing approaches. Experiments show that videos recorded by HikVision DS-V108 and Logitech C920 cameras contain a certain amount of physiological signal whereas the videos recorded by HikVision DS-U102D and Mercury cameras contain little physiological signal. Using zoom lenses is beneficial to improve the rPPG measurement accuracy under long-distance conditions.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"138 ","pages":"Article 104326"},"PeriodicalIF":1.7,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143642666","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Surgical technique and implant design affect abduction kinematics and functional outcomes after reverse shoulder arthroplasty","authors":"Gillian Kane ,&nbsp;Clarissa LeVasseur ,&nbsp;Ajinkya Rai ,&nbsp;Maria Munsch ,&nbsp;Alexandra S. Gabrielli ,&nbsp;Christopher J. Como ,&nbsp;Jonathan D. Hughes ,&nbsp;William Anderst ,&nbsp;Albert Lin","doi":"10.1016/j.medengphy.2025.104323","DOIUrl":"10.1016/j.medengphy.2025.104323","url":null,"abstract":"<div><div>The purpose of this study was to identify surgical techniques and implant geometries that influence <em>in-vivo</em> kinematics, functional outcomes, and clinical outcomes after reverse shoulder arthroplasty (RSA). Synchronized biplane radiographs imaged the operated shoulder during scapular plane abduction in 35 patients who received RSA within the past 2.5 ± 1.2 yrs. Shoulder kinematics and arthrokinematics (contact paths) were determined by matching subject-specific CT-based bone-plus-implant models to the radiographs using a validated tracking technique. Torque and total work done during abduction were measured using an isokinetic dynamometer. Implant characteristics and surgical techniques that were associated with kinematics/arthrokinematics, strength, or patient-reported outcomes were identified using multiple linear regression. Neck shaft angle, glenosphere size, and retroversion were associated with <em>in-</em>vivo kinematics and functional outcomes during abduction after RSA. These findings improve our understanding of how implant design and surgical technique impact kinematics and functional outcomes after RSA. The results highlight the necessity of <em>in vivo</em> data to validate cadaver-based research and computer simulations of joint function after RSA, emphasizing that those models do not account for the dynamic healing process and neuromuscular adaptations that occur after surgery.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"138 ","pages":"Article 104323"},"PeriodicalIF":1.7,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143654556","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Blinded prediction of custom-made pelvic implant failure using patient-specific finite element modeling","authors":"Nicholas J. Dunbar ,&nbsp;Yuhui Zhu ,&nbsp;Ata Babazadeh-Naseri ,&nbsp;John E. Akin ,&nbsp;Benedetta Spazzoli ,&nbsp;Claudio Belvedere ,&nbsp;Davide M. Donati ,&nbsp;Alberto Leardini ,&nbsp;Benjamin J. Fregly","doi":"10.1016/j.medengphy.2025.104321","DOIUrl":"10.1016/j.medengphy.2025.104321","url":null,"abstract":"<div><div>Additively manufactured, custom-made implants used for reconstruction are a promising treatment following tumor resection. However, failure rates due to mechanical factors remain high when used in the pelvis for even state-of-the-art prosthesis designs. In a collaborative effort between a clinical and an engineering research team, this study evaluated whether patient-specific biomechanical modeling could predict, in a blinded fashion, the mode and location of a clinically-observed mechanical failure. Multiple failure criteria were considered including the risk of bone fracture due to overloading or stress shielding and prosthesis fracture due to overloading or fatigue. The blinded predictions indicated that the risk of fatigue failure in the pubic screws were eight times higher than the most critical ilium screw and two times higher than the most critical cancellous screw. Simulation of stress-shielding during walking matched evidence of osteolysis in the ilium and pubis. Incorporating patient-specific modeling into the custom implant design process may lead to improved durability.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"138 ","pages":"Article 104321"},"PeriodicalIF":1.7,"publicationDate":"2025-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143629568","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A wireless intraoperative joint force sensing system for total hip arthroplasty","authors":"Masaru Higa ,&nbsp;Hiromasa Tanino ,&nbsp;Hirai Yusuke ,&nbsp;Inoue Seita ,&nbsp;Mitsutake Ryo ,&nbsp;Ito Hiroshi","doi":"10.1016/j.medengphy.2025.104325","DOIUrl":"10.1016/j.medengphy.2025.104325","url":null,"abstract":"<div><div>A wireless sensor-instrumented femoral head was developed that enables the intraoperative measurement of three force components in a total hip arthroplasty (THA). The design of the head was 32 mm in diameter with a 12/14 taper at the bottom, being compatible with commonly available THA. Inside the femoral head, there are three Hall effect sensors paired with permanent magnets, along with a microprocessor, a Bluetooth wireless module, a noncontact reed switch, and three lithium button batteries, all components were hermetically encapsulated. These components work together to measure and transmit the hip forces applied to the head during surgery. Through bench-top calibration, the system demonstrated a mean measurement error of approximately 8 % for forces up to 800 N. Additionally the practical applications of the prosthesis were tested on three hips from two cadavers undergoing THA. The hip forces were successively measured as the hip was passively moved, revealing insights into the potential for anterior or posterior dislocations with dislocation-prone positions. Understanding these intraoperative hip forces could aid surgeons in making the optimal decisions regarding implant placement and component selection, to minimize the risk of postoperative complications such as dislocation. Overall, this sensor-instrumented prosthesis will be useful for quantifying intraoperative hip forces.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"138 ","pages":"Article 104325"},"PeriodicalIF":1.7,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143620756","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advance signal processing and machine learning approach for analysis and classification of knee osteoarthritis vibroarthrographic signals","authors":"Vikas Kumar ,&nbsp;Pooja Kumari Jha ,&nbsp;Manoj Kumar Parida ,&nbsp;Jagannatha Sahoo","doi":"10.1016/j.medengphy.2025.104322","DOIUrl":"10.1016/j.medengphy.2025.104322","url":null,"abstract":"<div><div>Osteoarthritis is a common cause of disability among elderly significantly affecting their quality of life due to pain and functional limitations. This study proposes a novel, non-invasive, and cost-effective diagnostic technique using vibroarthrography (VAG) for early detection and grading of knee osteoarthritis (KOA) overcoming the limitations of traditional methods like X-rays, CT scans, and MRIs. Signal acquisition involved capturing of VAG signals from KOA patients using Thinklabs One digital stethoscope and a specialized knee brace within a frequency range of 20 Hz to 2000 Hz with a ± 3 dB tolerance at 44,000 samples per second. Various signal processing techniques, like time domain, statistical, PSD, wavelet, and Hilbert-Huang transform analysis, were used to study the resultant signal. Subsequently, a novel combination of self-organizing maps (SOMs) and K-means clustering was proposed to categorize VAG signals into distinct OA grade clusters. The resulting analysis identified distinct patterns in the time domain correlating with joint alteration severity. A SD/Mean ratio differentiated OA grades. Hilbert-Huang Transform established intrinsic mode functions relating frequency bands to OA stages, while wavelet and spectrogram analysis demonstrated increased signal complexity and variability with disease progression. The effectiveness of proposed clustering model was indicated by high mean Silhouette Coefficient (∼0.80) and low Davies-Bouldin Index (∼0.33) indicating distinct and accurate segmentation of OA stages. These findings clearly highlighted the potential of SOMs and K-means clustering in analysing VAG signals for classifying into different KOA grades. These results demonstrate the substantial potential of advanced signal processing, SOMs, and K-means clustering in uncovering complex patterns in VAG data, linking increasing knee sound signal complexity with OA progression. This highlights the potential of our approach in medical diagnostics, especially for chronic conditions like KOA, where early detection and ongoing monitoring are crucial.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"138 ","pages":"Article 104322"},"PeriodicalIF":1.7,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143620759","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A simple algorithm for primary emotion recognition from dual channel EEG signals","authors":"Avishek Paul ,&nbsp;Saurabh Pal ,&nbsp;Madhuchhanda Mitra","doi":"10.1016/j.medengphy.2025.104316","DOIUrl":"10.1016/j.medengphy.2025.104316","url":null,"abstract":"<div><div>With the development of neuroscience and computer science, there is a push to employ automated methods to assist individuals in identifying their emotions. Emotion detection is normally carried out by using electroencephalogram (EEG) signals. However, the medical equipment is costly, uncomfortable, and inconvenient because of the numerous electrodes and hair-covered scalp. This challenge demands for a solution to this problem where the requirement of so many electrodes will be replaced by one or two electrodes followed by a simpler signal processing steps. As a solution to this, the current study proposes an algorithm which uses only a pair of EEG electrodes for identifying primary emotions and classifies them based on threshold based rule along with standard classification techniques. The algorithm utilizes two simple features based on signal energy variations in the sub band levels and a feature fusion technique is adopted to further reduce the computational burden. This will lead to reduction in processing power to a greater extent and practical viability will be enhanced. The experimental results prove that the feature fusion strategy does raise recognition accuracy from 97.7 % to 98.4 %. It is shown that the suggested method for emotional recognition is workable and efficient which can be implemented on portable hardware platforms with minimum memory and computational power requirement.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"138 ","pages":"Article 104316"},"PeriodicalIF":1.7,"publicationDate":"2025-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143562597","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}