Pub Date : 2025-02-04DOI: 10.1109/OJEMB.2025.3538256
{"title":"2024 Index IEEE Open Journal of Engineering in Medicine and Biology Vol. 5","authors":"","doi":"10.1109/OJEMB.2025.3538256","DOIUrl":"https://doi.org/10.1109/OJEMB.2025.3538256","url":null,"abstract":"","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"5 ","pages":"885-909"},"PeriodicalIF":2.7,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10870393","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106067","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}
Objective: Human movement augmentation through supernumerary effectors is an emerging field of research. However, controlling these effectors remains challenging due to issues with agency, control, and synchronizing movements with natural limbs. A promising control strategy for supernumerary effectors involves utilizing electroencephalography (EEG) through motor imagery (MI) functions. In this work, we investigate whether MI activity associated with a supernumerary effector could be reliably differentiated from that of a natural one, thus addressing the concern of concurrency. Twenty subjects were recruited to participate in a two-fold experiment in which they observed movements of natural and supernumerary thumbs, then engaged in MI of the observed movements, conducted in a virtual reality setting. Results: A lightweight deep-learning model that accounts for the temporal, spatial and spectral nature of the EEG data is proposed and called BandFocusNet, achieving an average classification accuracy of 70.9% using the leave-one-subject-out cross validation method. The trustworthiness of the model is examined through explainability analysis, and influential regions-of-interests are cross-validated through event-related-spectral-perturbation (ERSPs) analysis. Explainability results showed the importance of the right and left frontal cortical regions, and ERSPs analysis showed an increase in the delta and theta powers in these regions during the MI of the natural thumb but not during the MI of the supernumerary thumb. Conclusion: Evidence in the literature indicates that such activation is observed during the MI of natural effectors, and its absence could be interpreted as a lack of embodiment of the supernumerary thumb.
{"title":"BandFocusNet: A Lightweight Model for Motor Imagery Classification of a Supernumerary Thumb in Virtual Reality","authors":"Haneen Alsuradi;Joseph Hong;Alireza Sarmadi;Robert Volcic;Hanan Salam;S. Farokh Atashzar;Farshad Khorrami;Mohamad Eid","doi":"10.1109/OJEMB.2025.3537760","DOIUrl":"https://doi.org/10.1109/OJEMB.2025.3537760","url":null,"abstract":"<italic>Objective:</i> Human movement augmentation through supernumerary effectors is an emerging field of research. However, controlling these effectors remains challenging due to issues with agency, control, and synchronizing movements with natural limbs. A promising control strategy for supernumerary effectors involves utilizing electroencephalography (EEG) through motor imagery (MI) functions. In this work, we investigate whether MI activity associated with a supernumerary effector could be reliably differentiated from that of a natural one, thus addressing the concern of concurrency. Twenty subjects were recruited to participate in a two-fold experiment in which they observed movements of natural and supernumerary thumbs, then engaged in MI of the observed movements, conducted in a virtual reality setting. <italic>Results:</i> A lightweight deep-learning model that accounts for the temporal, spatial and spectral nature of the EEG data is proposed and called BandFocusNet, achieving an average classification accuracy of 70.9% using the leave-one-subject-out cross validation method. The trustworthiness of the model is examined through explainability analysis, and influential regions-of-interests are cross-validated through event-related-spectral-perturbation (ERSPs) analysis. Explainability results showed the importance of the right and left frontal cortical regions, and ERSPs analysis showed an increase in the delta and theta powers in these regions during the MI of the natural thumb but not during the MI of the supernumerary thumb. <italic>Conclusion:</i> Evidence in the literature indicates that such activation is observed during the MI of natural effectors, and its absence could be interpreted as a lack of embodiment of the supernumerary thumb.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"305-311"},"PeriodicalIF":2.7,"publicationDate":"2025-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10869342","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143512945","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}
Pub Date : 2025-01-16DOI: 10.1109/OJEMB.2025.3530841
Benjamin P. Veasey;Amir A. Amini
Goal: This paper investigates using Low-Rank Adaptation (LoRA) to adapt large vision models (LVMs) pretrained with self-supervised learning (SSL) for lung nodule malignancy classification. Inspired by LoRA's success in the field of Natural Language Processing, we hypothesized that such an adaptation technique can significantly improve classification performance, parameter efficiency, and training speed for the novel application of lung image cancer diagnostic. Methods: Utilizing two comprehensive lung nodule datasets, NLSTx and LIDC, which together encompass a diverse array of biopsy- and radiologist-confirmed lung CT scans, our rigorous experimental setup demonstrates that LoRA-adapted models markedly surpass traditional fine-tuning methods. Results: The best LoRA-adapted model achieved a 3% increase in ROC AUC over the state-of-the-art model, utilized 89.9% fewer parameters, and reduced training times by 36.5%. Conclusions: Integrating LoRA with out-of-domain pretrained LVMs offers a promising avenue for enhancing performance of lung nodule malignancy classification. The annotations for the NLSTx dataset are also released with this paper on GitHub at https://github.com/benVZ/NLSTx.
{"title":"Low-Rank Adaptation of Pre-Trained Large Vision Models for Improved Lung Nodule Malignancy Classification","authors":"Benjamin P. Veasey;Amir A. Amini","doi":"10.1109/OJEMB.2025.3530841","DOIUrl":"https://doi.org/10.1109/OJEMB.2025.3530841","url":null,"abstract":"<italic>Goal:</i> This paper investigates using Low-Rank Adaptation (LoRA) to adapt large vision models (LVMs) pretrained with self-supervised learning (SSL) for lung nodule malignancy classification. Inspired by LoRA's success in the field of Natural Language Processing, we hypothesized that such an adaptation technique can significantly improve classification performance, parameter efficiency, and training speed for the novel application of lung image cancer diagnostic. <italic>Methods:</i> Utilizing two comprehensive lung nodule datasets, NLSTx and LIDC, which together encompass a diverse array of biopsy- and radiologist-confirmed lung CT scans, our rigorous experimental setup demonstrates that LoRA-adapted models markedly surpass traditional fine-tuning methods. <italic>Results:</i> The best LoRA-adapted model achieved a 3% increase in ROC AUC over the state-of-the-art model, utilized 89.9% fewer parameters, and reduced training times by 36.5%. <italic>Conclusions:</i> Integrating LoRA with out-of-domain pretrained LVMs offers a promising avenue for enhancing performance of lung nodule malignancy classification. The annotations for the NLSTx dataset are also released with this paper on GitHub at <uri>https://github.com/benVZ/NLSTx</uri>.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"296-304"},"PeriodicalIF":2.7,"publicationDate":"2025-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10843806","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143361179","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}
Pub Date : 2025-01-14DOI: 10.1109/OJEMB.2025.3526457
Vasileios Skaramagkas;Ioannis Kyprakis;Georgia S. Karanasiou;Dimitris I. Fotiadis;Manolis Tsiknakis
Quality of Life (QoL) assessment has evolved over time, encompassing diverse aspects of human existence beyond just health. This paper presents a comprehensive review of the integration of Deep Learning (DL) techniques in QoL assessment, focusing on the analysis of wearable data. QoL, as defined by the World Health Organisation, encompasses physical, mental, and social well-being, making it a multifaceted concept. Traditional QoL assessment methods, often reliant on subjective reports or informal questioning, face challenges in quantification and standardization. To address these challenges, DL, a branch of machine learning inspired by the human brain, has emerged as a promising tool. DL models can analyze vast and complex datasets, including patient-reported outcomes, medical images, and physiological signals, enabling a deeper understanding of factors influencing an individual's QoL. Notably, wearable sensory devices have gained prominence, offering real-time data on vital signs and enabling remote healthcare monitoring. This review critically examines DL's role in QoL assessment through the use of wearable data, with particular emphasis on the subdomains of physical and psychological well-being. By synthesizing current research and identifying knowledge gaps, this review provides valuable insights for researchers, clinicians, and policymakers aiming to enhance QoL assessment with DL. Ultimately, the paper contributes to the adoption of advanced technologies to improve the well-being and QoL of individuals from diverse backgrounds.
{"title":"A Review on Deep Learning for Quality of Life Assessment Through the Use of Wearable Data","authors":"Vasileios Skaramagkas;Ioannis Kyprakis;Georgia S. Karanasiou;Dimitris I. Fotiadis;Manolis Tsiknakis","doi":"10.1109/OJEMB.2025.3526457","DOIUrl":"https://doi.org/10.1109/OJEMB.2025.3526457","url":null,"abstract":"Quality of Life (QoL) assessment has evolved over time, encompassing diverse aspects of human existence beyond just health. This paper presents a comprehensive review of the integration of Deep Learning (DL) techniques in QoL assessment, focusing on the analysis of wearable data. QoL, as defined by the World Health Organisation, encompasses physical, mental, and social well-being, making it a multifaceted concept. Traditional QoL assessment methods, often reliant on subjective reports or informal questioning, face challenges in quantification and standardization. To address these challenges, DL, a branch of machine learning inspired by the human brain, has emerged as a promising tool. DL models can analyze vast and complex datasets, including patient-reported outcomes, medical images, and physiological signals, enabling a deeper understanding of factors influencing an individual's QoL. Notably, wearable sensory devices have gained prominence, offering real-time data on vital signs and enabling remote healthcare monitoring. This review critically examines DL's role in QoL assessment through the use of wearable data, with particular emphasis on the subdomains of physical and psychological well-being. By synthesizing current research and identifying knowledge gaps, this review provides valuable insights for researchers, clinicians, and policymakers aiming to enhance QoL assessment with DL. Ultimately, the paper contributes to the adoption of advanced technologies to improve the well-being and QoL of individuals from diverse backgrounds.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"261-268"},"PeriodicalIF":2.7,"publicationDate":"2025-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10841411","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143105936","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}
Goal: Effective preoperative planning for shoulder joint replacement requires accurate glenohumeral joint (GH) digital surfaces and reliable clinical staging. Methods: xCEL-UNet was designed as a dual-task deep network for humerus and scapula bone reconstruction in CT scans, and assessment of three GH joint clinical conditions, namely osteophyte size (OS), joint space reduction (JS), and humeroscapular alignment (HSA). Results: Trained on a dataset of 571 patients, the model optimized segmentation and classification through transfer learning. It achieved median root mean squared errors of 0.31 and 0.24 mm, and Hausdorff distances of 2.35 and 3.28 mm for the humerus and scapula, respectively. Classification accuracy was 91 for OS, 93 for JS, and 85% for HSA. GradCAM-based activation maps validated the network's interpretability. Conclusions: this framework delivers accurate 3D bone surface reconstructions and dependable clinical assessments of the GH joint, offering robust support for therapeutic decision-making in shoulder arthroplasty.
{"title":"Context-Aware Dual-Task Deep Network for Concurrent Bone Segmentation and Clinical Assessment to Enhance Shoulder Arthroplasty Preoperative planning","authors":"Luca Marsilio;Andrea Moglia;Alfonso Manzotti;Pietro Cerveri","doi":"10.1109/OJEMB.2025.3527877","DOIUrl":"https://doi.org/10.1109/OJEMB.2025.3527877","url":null,"abstract":"<italic>Goal:</i> Effective preoperative planning for shoulder joint replacement requires accurate glenohumeral joint (GH) digital surfaces and reliable clinical staging. <italic>Methods:</i> xCEL-UNet was designed as a dual-task deep network for humerus and scapula bone reconstruction in CT scans, and assessment of three GH joint clinical conditions, namely osteophyte size (OS), joint space reduction (JS), and humeroscapular alignment (HSA). <italic>Results:</i> Trained on a dataset of 571 patients, the model optimized segmentation and classification through transfer learning. It achieved median root mean squared errors of 0.31 and 0.24 mm, and Hausdorff distances of 2.35 and 3.28 mm for the humerus and scapula, respectively. Classification accuracy was 91 for OS, 93 for JS, and 85% for HSA. GradCAM-based activation maps validated the network's interpretability. <italic>Conclusions:</i> this framework delivers accurate 3D bone surface reconstructions and dependable clinical assessments of the GH joint, offering robust support for therapeutic decision-making in shoulder arthroplasty.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"269-278"},"PeriodicalIF":2.7,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10835174","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143106057","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}
Pub Date : 2024-12-30DOI: 10.1109/OJEMB.2024.3523442
Kavit R. Amin;Samuel R. Smith;Amit N. Pujari;Syed Ali Raza Zaidi;Robert Horne;Atif Shahzad;Christopher Walshaw;Christy Holland;Stephen Halpin;Rory J. O'Connor
Spasticity is disabling feature of long-term neurological conditions that has substantial impact on people’ quality of life. Assessing spasticity and determining the efficacy of current treatments is limited by the measurement tools available in clinical practice. We convened an expert panel of clinicians and engineers to identify a solution to this urgent clinical need. We established that a reliable ambulatory spasticity monitoring system that collates clinically meaningful data remotely would be useful in the management of this complex condition. This paper provides an overview of current practices in managing and monitoring spasticity. Then, the paper describes how a remote monitoring system can help in managing spasticity and identifies challenges in development of such a system. Finally the paper proposes a monitoring system solution that exploits recent advancements in low-energy wearable systems comprising of printable electronics, a personal area network (PAN) to low power wide area networks (LPWAN) alongside back-end cloud infrastructure. The proposed technology will make an important contribution to patient care by allowing, for the first time, longitudinal monitoring of spasticity between clinical follow-up, and thus has life altering and cost-saving implications. This work in spasticity monitoring and management serves as an exemplar for other areas of rehabilitation.
{"title":"Remote Monitoring for the Management of Spasticity: Challenges, Opportunities and Proposed Technological Solution","authors":"Kavit R. Amin;Samuel R. Smith;Amit N. Pujari;Syed Ali Raza Zaidi;Robert Horne;Atif Shahzad;Christopher Walshaw;Christy Holland;Stephen Halpin;Rory J. O'Connor","doi":"10.1109/OJEMB.2024.3523442","DOIUrl":"https://doi.org/10.1109/OJEMB.2024.3523442","url":null,"abstract":"Spasticity is disabling feature of long-term neurological conditions that has substantial impact on people’ quality of life. Assessing spasticity and determining the efficacy of current treatments is limited by the measurement tools available in clinical practice. We convened an expert panel of clinicians and engineers to identify a solution to this urgent clinical need. We established that a reliable ambulatory spasticity monitoring system that collates clinically meaningful data remotely would be useful in the management of this complex condition. This paper provides an overview of current practices in managing and monitoring spasticity. Then, the paper describes how a remote monitoring system can help in managing spasticity and identifies challenges in development of such a system. Finally the paper proposes a monitoring system solution that exploits recent advancements in low-energy wearable systems comprising of printable electronics, a personal area network (PAN) to low power wide area networks (LPWAN) alongside back-end cloud infrastructure. The proposed technology will make an important contribution to patient care by allowing, for the first time, longitudinal monitoring of spasticity between clinical follow-up, and thus has life altering and cost-saving implications. This work in spasticity monitoring and management serves as an exemplar for other areas of rehabilitation.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"279-286"},"PeriodicalIF":2.7,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10817570","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143105935","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}
Pub Date : 2024-12-17DOI: 10.1109/OJEMB.2024.3387891
{"title":"IEEE Engineering in Medicine and Biology Society Information","authors":"","doi":"10.1109/OJEMB.2024.3387891","DOIUrl":"https://doi.org/10.1109/OJEMB.2024.3387891","url":null,"abstract":"","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"5 ","pages":"C2-C2"},"PeriodicalIF":2.7,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10805082","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142843067","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}
Pub Date : 2024-12-12DOI: 10.1109/OJEMB.2024.3516320
Christoforos Meliadis;Emily Feng;Ezekiel Johnson;Wendy Zhu;Paramesh Gopi;Vivek Mohan;Peter H. Hwang;Jacob Johnson;Bryant Y. Lin
Goal: This study aims to introduce a novel method for estimating maxillary sinus volume using smartphone technology, providing an accessible alternative to traditional imaging techniques. Methods: We recruited 40 participants to conduct a comparative analysis between Computed Tomography (CT) and face scans obtained using an Apple iPhone. Utilizing Apple's ARKit for 3D facial mesh modeling, we estimated sinus dimensions based on established craniofacial landmarks and calculated the volume through a geometric approximation of the maxillary sinus. Results: We demonstrated a high degree of agreement between CT and face scans, with Mean Absolute Percentage Errors (MAPE) of 8.006 ± 8.839% (Width), 6.725 ± 4.595% (Height), 9.952 ± 6.733% (Depth), and 10.429 ± 7.409% (Volume). These results suggest the feasibility of this non-invasive approach for clinical use. Conclusions: This method aligns with the growing focus on telemedicine, presenting significant reductions in healthcare costs and radiation exposure from CT scans. It marks a substantial advancement in otolaryngology and maxillofacial surgery, showcasing the integration of smartphone technology in medical diagnostics and opening avenues for innovative, patient-friendly, and cost-effective healthcare solutions.
{"title":"Estimating Maxillary Sinus Volume Using Smartphone Camera","authors":"Christoforos Meliadis;Emily Feng;Ezekiel Johnson;Wendy Zhu;Paramesh Gopi;Vivek Mohan;Peter H. Hwang;Jacob Johnson;Bryant Y. Lin","doi":"10.1109/OJEMB.2024.3516320","DOIUrl":"https://doi.org/10.1109/OJEMB.2024.3516320","url":null,"abstract":"<italic>Goal:</i>\u0000 This study aims to introduce a novel method for estimating maxillary sinus volume using smartphone technology, providing an accessible alternative to traditional imaging techniques. \u0000<italic>Methods:</i>\u0000 We recruited 40 participants to conduct a comparative analysis between Computed Tomography (CT) and face scans obtained using an Apple iPhone. Utilizing Apple's ARKit for 3D facial mesh modeling, we estimated sinus dimensions based on established craniofacial landmarks and calculated the volume through a geometric approximation of the maxillary sinus. \u0000<italic>Results:</i>\u0000 We demonstrated a high degree of agreement between CT and face scans, with Mean Absolute Percentage Errors (MAPE) of 8.006 ± 8.839% (Width), 6.725 ± 4.595% (Height), 9.952 ± 6.733% (Depth), and 10.429 ± 7.409% (Volume). These results suggest the feasibility of this non-invasive approach for clinical use. \u0000<italic>Conclusions:</i>\u0000 This method aligns with the growing focus on telemedicine, presenting significant reductions in healthcare costs and radiation exposure from CT scans. It marks a substantial advancement in otolaryngology and maxillofacial surgery, showcasing the integration of smartphone technology in medical diagnostics and opening avenues for innovative, patient-friendly, and cost-effective healthcare solutions.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"256-260"},"PeriodicalIF":2.7,"publicationDate":"2024-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10795754","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938158","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}
Pub Date : 2024-12-11DOI: 10.1109/OJEMB.2024.3515473
G. Luzzani;I. Buraioli;G. Guglieri;D. Demarchi
Objective: The growth of autonomous systems interacting with humans leads to assessing operators' stress and mental workload (MWL), especially in safety-critical situations. Therefore, a system providing information about the psychophysiological workers' condition is fundamental and still missing. This paper aims to study the statistical relationship between the variation of Photoplethysmogram signal (PPG), Electrodermal Activity (EDA), and skin temperature with respect to stress and MWL levels, assessed through an ad-hoc developed subjective questionnaire. Results: 43 features were calculated from these signals during the execution of two cognitive tests and processed through a statistical analysis based on Kruskal-Wallis and Mann-Whitney U tests. This analysis proved that about 50% of them offered statistical evidence in differentiating relaxed and altered emotional conditions. Moreover, fifteen features were found to provide sufficient information to detect at the same time stress and MWL. Conclusions: These results demonstrate the feasibility of this approach and push to continue this research about the relationship between physiological signals and the variation of stress and MWL by enhancing the population and considering more biosignals.
{"title":"EDA, PPG and Skin Temperature as Predictive Signals for Mental Failure by a Statistical Analysis on Stress and Mental Workload","authors":"G. Luzzani;I. Buraioli;G. Guglieri;D. Demarchi","doi":"10.1109/OJEMB.2024.3515473","DOIUrl":"https://doi.org/10.1109/OJEMB.2024.3515473","url":null,"abstract":"<italic>Objective:</i>\u0000 The growth of autonomous systems interacting with humans leads to assessing operators' stress and mental workload (MWL), especially in safety-critical situations. Therefore, a system providing information about the psychophysiological workers' condition is fundamental and still missing. This paper aims to study the statistical relationship between the variation of Photoplethysmogram signal (PPG), Electrodermal Activity (EDA), and skin temperature with respect to stress and MWL levels, assessed through an ad-hoc developed subjective questionnaire. \u0000<italic>Results:</i>\u0000 43 features were calculated from these signals during the execution of two cognitive tests and processed through a statistical analysis based on Kruskal-Wallis and Mann-Whitney U tests. This analysis proved that about 50% of them offered statistical evidence in differentiating relaxed and altered emotional conditions. Moreover, fifteen features were found to provide sufficient information to detect at the same time stress and MWL. \u0000<italic>Conclusions:</i>\u0000 These results demonstrate the feasibility of this approach and push to continue this research about the relationship between physiological signals and the variation of stress and MWL by enhancing the population and considering more biosignals.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"248-255"},"PeriodicalIF":2.7,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10791858","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142905895","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}
Pub Date : 2024-12-09DOI: 10.1109/OJEMB.2024.3512932
Chih-En Kuo;Jun-Zhou Li;Jenn-Jhy Tseng;Feng-Chu Lo;Ming-Jer Chen;Chien-Hsing Lu
Goal: Chromosomes are intracellular aggregates that carry genetic information. An abnormal number or structure of chromosomes causes chromosomal disorders. Thus, chromosome screening is crucial for prenatal care; however, manual analysis of chromosomes is time consuming. With the increasing popularity of prenatal diagnosis, human labor resources are overstretched. Therefore, an automatic approach for chromosome detection and recognition is necessary. Methods: In the present study, we proposed a deep learning–based system for the automatic chromosome detection and recognition of metaphase cell images. We used a large database that included 5,000 metaphase cell images consisting of a total of 229,852 chromosomes. The proposed system was then developed and evaluated. The system, called ChromosomesNet, which combines the advantages of one-stage and two-stage models. The model uses original images as inputs without requiring preprocessing; it is thus applicable for clinical settings. To verify the clinical applicability of our system, we included 3,827 simple images and 1,173 difficult images, as identified by physicians, in our database. Results: We used COCOAPI's mAP50 evaluation method, which has average performance and a high accuracy of 99.60%. Moreover, the recall and F1 score of our proposed method were 99.9% and 99.49%, respectively. We also compared our method with five well-known object detection methods, including Faster-RCNN, YOLOv7, Retinanet, Swin transformer, and Centernet++. The results indicated that ChromosomesNet had the highest accuracy, recall, and F1 score. Unlike previous studies that have reported simple chromosome images as identification results, we obtained a 99.5% accuracy in the detection of difficult images. Conclusions: The volume of data we tested, even including difficult images, was much larger than those in the literature. The results indicated that our proposed method is sufficiently stable, robustness, and practical for clinical use. Future studies are warranted to confirm the clinical applicability of our proposed method by using data from other hospitals for cross-hospital validation.
{"title":"ChromosomeNet: Deep Learning-Based Automated Chromosome Detection in Metaphase Cell Images","authors":"Chih-En Kuo;Jun-Zhou Li;Jenn-Jhy Tseng;Feng-Chu Lo;Ming-Jer Chen;Chien-Hsing Lu","doi":"10.1109/OJEMB.2024.3512932","DOIUrl":"https://doi.org/10.1109/OJEMB.2024.3512932","url":null,"abstract":"<italic>Goal:</i>\u0000 Chromosomes are intracellular aggregates that carry genetic information. An abnormal number or structure of chromosomes causes chromosomal disorders. Thus, chromosome screening is crucial for prenatal care; however, manual analysis of chromosomes is time consuming. With the increasing popularity of prenatal diagnosis, human labor resources are overstretched. Therefore, an automatic approach for chromosome detection and recognition is necessary. \u0000<italic>Methods:</i>\u0000 In the present study, we proposed a deep learning–based system for the automatic chromosome detection and recognition of metaphase cell images. We used a large database that included 5,000 metaphase cell images consisting of a total of 229,852 chromosomes. The proposed system was then developed and evaluated. The system, called ChromosomesNet, which combines the advantages of one-stage and two-stage models. The model uses original images as inputs without requiring preprocessing; it is thus applicable for clinical settings. To verify the clinical applicability of our system, we included 3,827 simple images and 1,173 difficult images, as identified by physicians, in our database. \u0000<italic>Results:</i>\u0000 We used COCOAPI's mAP50 evaluation method, which has average performance and a high accuracy of 99.60%. Moreover, the recall and F1 score of our proposed method were 99.9% and 99.49%, respectively. We also compared our method with five well-known object detection methods, including Faster-RCNN, YOLOv7, Retinanet, Swin transformer, and Centernet++. The results indicated that ChromosomesNet had the highest accuracy, recall, and F1 score. Unlike previous studies that have reported simple chromosome images as identification results, we obtained a 99.5% accuracy in the detection of difficult images. \u0000<italic>Conclusions:</i>\u0000 The volume of data we tested, even including difficult images, was much larger than those in the literature. The results indicated that our proposed method is sufficiently stable, robustness, and practical for clinical use. Future studies are warranted to confirm the clinical applicability of our proposed method by using data from other hospitals for cross-hospital validation.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"227-236"},"PeriodicalIF":2.7,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10786357","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142858871","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：