{"title":"Corrections to “Gastric Section Correlation Network for Gastric Precancerous Lesion Diagnosis”","authors":"Jyun-Yao Jhang;Yu-Ching Tsai;Tzu-Chun Hsu;Chun-Rong Huang;Hsiu-Chi Cheng;Bor-Shyang Sheu","doi":"10.1109/OJEMB.2024.3452970","DOIUrl":"https://doi.org/10.1109/OJEMB.2024.3452970","url":null,"abstract":"Presents corrections to the paper, Gastric Section Correlation Network for Gastric Precancerous Lesion Diagnosis.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"68-68"},"PeriodicalIF":2.7,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10750350","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600203","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":"IEEE Open Journal of Engineering in Medicine and Biology Author Instructions","authors":"","doi":"10.1109/OJEMB.2024.3387893","DOIUrl":"https://doi.org/10.1109/OJEMB.2024.3387893","url":null,"abstract":"","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"5 ","pages":"C3-C3"},"PeriodicalIF":2.7,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10747777","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142595891","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":"Design and Validation of a Tripping-Eliciting Platform Based on Compliant Random Obstacles","authors":"Eugenio Anselmino;Lorenzo Pittoni;Tommaso Ciapetti;Michele Piazzini;Claudio Macchi;Alberto Mazzoni;Silvestro Micera;Arturo Forner-Cordero","doi":"10.1109/OJEMB.2024.3493619","DOIUrl":"https://doi.org/10.1109/OJEMB.2024.3493619","url":null,"abstract":"<italic>Goal:</i>\u0000 The experimental study of the stumble phenomena is essential to develop novel technological solutions to limit harmful effects in at-risk populations. A versatile platform to deliver realistic and unanticipated tripping perturbations, controllable in their strength and timing, would be beneficial for this field of study. \u0000<italic>Methods:</i>\u0000 We built a modular tripping-eliciting system based on multiple compliant trip blocks that deliver unanticipated tripping perturbations. The system was validated with a study with 9 healthy subjects. \u0000<italic>Results:</i>\u0000 The system delivered 33 out of 34 perturbations (a minimum of 3 per subject) during the desired gait phase, and 31 effectively induced a tripping event. The recovery strategies adopted after the perturbations were qualitatively consistent with the literature. The analysis of the inertial motion unit signals and the questionnaires suggests a limited adaptation to the perturbation throughout experiments. \u0000<italic>Conclusions:</i>\u0000 The platform succeeded in providing realistic trip perturbations, concurrently limiting subjects’ adaptation. The presence of multiple compliant obstacles, tunable regarding position and perturbation strength, represents a novelty in the field, allowing the study of stumbling phenomena caused by obstacles with different levels of sturdiness. The overall system is modular and can be easily adapted for different applications.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"168-175"},"PeriodicalIF":2.7,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10747760","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142761398","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":"IEEE Open Journal of Engineering in Medicine and Biology Editorial Board Information","authors":"","doi":"10.1109/OJEMB.2024.3387895","DOIUrl":"https://doi.org/10.1109/OJEMB.2024.3387895","url":null,"abstract":"","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"5 ","pages":"C4-C4"},"PeriodicalIF":2.7,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10747779","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142595834","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":"Guest Editorial: Introduction to the Special Series on Advances in Cardiovascular and Respiratory Systems Engineering","authors":"Riccardo Barbieri;Maximiliano Mollura","doi":"10.1109/OJEMB.2024.3486457","DOIUrl":"https://doi.org/10.1109/OJEMB.2024.3486457","url":null,"abstract":"","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"5 ","pages":"803-805"},"PeriodicalIF":2.7,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10746532","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142595006","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":"HCM-Echo-VAR-Ensemble: Deep Ensemble Fusion to Detect Hypertrophic Cardiomyopathy in Echocardiograms","authors":"Abdulsalam Almadani;Atifa Sarwar;Emmanuel Agu;Monica Ahluwalia;Jacques Kpodonu","doi":"10.1109/OJEMB.2024.3486541","DOIUrl":"https://doi.org/10.1109/OJEMB.2024.3486541","url":null,"abstract":"<italic>Goal:</i>\u0000 To detect Hypertrophic Cardiomyopathy (HCM) from multiple views of Echocardiogram (cardiac ultrasound) videos. \u0000<italic>Methods:</i>\u0000 we propose \u0000<italic>HCM-Echo-VAR-Ensemble</i>\u0000, a novel framework that performs binary classification (HCM vs. no HCM) of echocardiogram videos directly using an ensemble of state-of-the-art deep VAR architectures models (SlowFast and I3D), and fuses their predictions using majority averaging ensembling. \u0000<italic>Results:</i>\u0000 \u0000<italic>HCM-Echo-VAR-Ensemble</i>\u0000 achieved state-of-the-art accuracy of 95.28%, an F1-Score of 95.20%, a specificity of 96.20%, a sensitivity of 93.97%, a PPV of 96.46%, an NPV of 94.17%, and an AUC of 98.42%, outperforming a comprehensive set of baselines including other ensembling approaches. \u0000<italic>Conclusions:</i>\u0000 Our proposed HCM-Echo-VAR-Ensemble framework demonstrates significant potential for improving the sensitivity and accuracy of HCM detection in clinical settings, particularly by ensembling the complementary strengths of the SlowFast and I3D deep VAR models. This approach can enhance diagnostic consistency and accuracy, enabling reliable HCM diagnoses even in low-resource environments.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"193-201"},"PeriodicalIF":2.7,"publicationDate":"2024-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10735780","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142825920","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":"Advancements in Clinical Evaluation and Regulatory Frameworks for AI-Driven Software as a Medical Device (SaMD)","authors":"Shiau-Ru Yang;Jen-Tzung Chien;Chen-Yi Lee","doi":"10.1109/OJEMB.2024.3485534","DOIUrl":"https://doi.org/10.1109/OJEMB.2024.3485534","url":null,"abstract":"Owing to the rapid progress in artificial intelligence (AI) and the widespread use of generative learning, the problem of sparse data has been solved effectively in various research fields. The application of AI technologies has resulted in important transformations in healthcare, particularly in radiology. To ensure the high quality, safety, and effectiveness of AI and machine learning (ML) medical devices, the US Food and Drug Administration (FDA) has established regulatory guidelines to support the performance evaluation of medical devices. Furthermore, the FDA has proposed continuous surveillance requirements for AI/ML medical devices. This paper presents a summary of SaMD products that have passed the FDA 510 (k) AI/ML pathway, the challenges associated with the current AI/ML software-as-a-medical-device, and solutions for promoting the development of AI technologies in medicine. We hope to provide valuable information pertaining to medical-device design, development, and monitoring to ultimately achieve safer and more effective personalized medical services.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"147-151"},"PeriodicalIF":2.7,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10729844","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142713805","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":"Generation of Seismocardiography Heartbeats Using a Wasserstein Generative Adversarial Network With Feature Control","authors":"James Skoric;Yannick D'Mello;David V. Plant","doi":"10.1109/OJEMB.2024.3485535","DOIUrl":"https://doi.org/10.1109/OJEMB.2024.3485535","url":null,"abstract":"<italic>Goal:</i>\u0000 Seismocardiography (SCG) offers critical insights into cardiac performance, but its analysis often faces challenges due to the limited availability of data. This study aims to generate synthetic SCG heartbeats which can augment existing datasets to enable more research avenues. \u0000<italic>Methods</i>\u0000: We trained a Wasserstein generative adversarial network (GAN) with gradient penalty on authentic SCG heartbeats. It was conditioned with embedded subject-specific identifiers to create individualized heartbeats. We employed linear permutations in the latent and conditional spaces to control signal features, and a convolutional network to classify lung volume states from real and synthetic data separately. \u0000<italic>Results</i>\u0000: The model effectively replicated SCG signal morphology, while maintaining a level of variance which matches the variability of cardiac activity. Comparisons with real SCG waveforms yielded Pearson's r-squared correlation of 0.62 for average heartbeats. Linear manipulations were successful in controlling simple features although they were limited in more complex characteristics. Additionally, the model demonstrated strong performance in practical applications, with the synthetic data achieving an accuracy of 88% in lung volume classification as compared to 89% achieved with real data. Augmenting real data with additional synthetic data improved performance by 3%. \u0000<italic>Conclusions</i>\u0000: GANs for artificial SCG heartbeat generation produce realistic and diverse results that have the potential to overcome data limitations, thereby enhancing SCG-based research.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"119-126"},"PeriodicalIF":2.7,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10731564","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142636366","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}
Ramon Rohner;David E. Bauer;Martin Hartmann;Tobias Götschi;Mazda Farshad;Jonas Widmer
{"title":"Feasibility of an Inductive Pedicle Screw Loosening Detection Concept Using a Pulse Induction Metal Detector","authors":"Ramon Rohner;David E. Bauer;Martin Hartmann;Tobias Götschi;Mazda Farshad;Jonas Widmer","doi":"10.1109/OJEMB.2024.3482878","DOIUrl":"https://doi.org/10.1109/OJEMB.2024.3482878","url":null,"abstract":"<italic>Introduction:</i>\u0000 Pedicle screw loosening is a major problem in spine surgery. Computed tomography (CT) is the gold standard to diagnose screw loosening. Disadvantages of CT include low sensitivity and specificity for the detection of loosened screws as well as the need for radiation exposure. The aim of this study was to provide a proof of concept of a novel, non-invasive, inductive sensing device for transcutaneous detection of screw loosening using a pulse induction metal detector. \u0000<italic>Materials/Methods:</i>\u0000 Two fresh frozen human cadavers were initially instrumented in the lumbar spinal region (L1 to L5). After assessment of the sensing device behavior using a wooden beam and 3D printed place holders of predefined distances, the ability of implant detection and screw stability determination were assessed during two experiments. Pedicle screw loosening was induced using 3D printed drill/loosening guides during the instrumentation of the lumbar spine. Screw stability was determined by applying weight to the spinous processes of interest and measuring the relative movement of the pedicle screw using the inductive sensor coil. \u0000<italic>Results:</i>\u0000 The sensitivity of our detection coil for an implant movement measurement showed to be high at close distances (60mV voltage change per mm movement), with signal amplitude vanishing at sensing distances of 50mm or greater. Signal amplitude significantly (p < .05) differed with the number of instrumented levels. When differentiating between instrumentation with and without loosened screws, significant (p < .05) mean differences were found in half of all comparative cases. All these differences were smaller than the predefined signal voltage threshold of (60 mV/mm). \u0000<italic>Discussion/Conclusion:</i>\u0000 In this study, the feasibility of a new, inductive and non-invasive sensor concept was tested. While the basic principle of the approach is promising, our implementation was not successful in demonstrating sufficient sensitivity for the required detectability. It appears conceivable that the concept can be successfully implemented with more sensitive sensors and more complex evaluation methods.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"113-118"},"PeriodicalIF":2.7,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10720821","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142636530","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":"Optimal Transport Based Graph Kernels for Drug Property Prediction","authors":"Mohammed Aburidi;Roummel Marcia","doi":"10.1109/OJEMB.2024.3480708","DOIUrl":"https://doi.org/10.1109/OJEMB.2024.3480708","url":null,"abstract":"<italic>Objective:</i>\u0000 The development of pharmaceutical agents relies heavily on optimizing their pharmacodynamics, pharmacokinetics, and toxicological properties, collectively known as ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity). Accurate assessment of these properties during the early stages of drug development is challenging due to resource-intensive experimental evaluation and limited comprehensive data availability. To overcome these obstacles, there has been a growing reliance on computational and predictive tools, leveraging recent advancements in machine learning and graph-based methodologies. This study presents an innovative approach that harnesses the power of optimal transport (OT) theory to construct three graph kernels for predicting drug ADMET properties. This approach involves the use of graph matching to create a similarity matrix, which is subsequently integrated into a predictive model. \u0000<italic>Results:</i>\u0000 Through extensive evaluations on 19 distinct ADMET datasets, the potential of this methodology becomes evident. The OT-based graph kernels exhibits exceptional performance, outperforming state-of-the-art graph deep learning models in 9 out of 19 datasets, even surpassing the most impactful Graph Neural Network (GNN) that excels in 4 datasets. Furthermore, they are very competitive in 2 additional datasets. \u0000<italic>Conclusion:</i>\u0000 Our proposed novel class of OT-based graph kernels not only demonstrates a high degree of effectiveness and competitiveness but also, in contrast to graph neural networks, offers interpretability, adaptability and generalizability across multiple datasets.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"152-157"},"PeriodicalIF":2.7,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10716457","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142905935","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}