Pub Date : 2024-10-08DOI: 10.1109/OJEMB.2024.3475911
Collin D. Bowersock;Zachary F. Lerner
Objective: This pilot study investigated the feasibility and efficacy of using autonomous ankle exoskeletons in community settings among individuals with cerebral palsy (CP). Five participants completed two structured community walking protocols: a week-long ankle exoskeleton acclimation and training intervention, and a dose-matched Sham intervention of unassisted walking. Results: Results demonstrated significant improvements in acclimatized walking performance with the ankle exoskeleton, including increased speed and stride length. Participants also reported increased enjoyment and perceived benefits of using the exoskeleton. While ankle exoskeleton training did not lead to significant improvements in unassisted walking, this study demonstrates the feasibility of using ankle exoskeletons in the real world by people with CP. Conclusions: This study highlights the potential of wearable exoskeletons to augment community walking performance in CP, laying a foundation for further exploration in real-world environments.
{"title":"Feasibility of Using Autonomous Ankle Exoskeletons to Augment Community Walking in Cerebral Palsy","authors":"Collin D. Bowersock;Zachary F. Lerner","doi":"10.1109/OJEMB.2024.3475911","DOIUrl":"https://doi.org/10.1109/OJEMB.2024.3475911","url":null,"abstract":"<italic>Objective:</i>\u0000 This pilot study investigated the feasibility and efficacy of using autonomous ankle exoskeletons in community settings among individuals with cerebral palsy (CP). Five participants completed two structured community walking protocols: a week-long ankle exoskeleton acclimation and training intervention, and a dose-matched Sham intervention of unassisted walking. \u0000<italic>Results:</i>\u0000 Results demonstrated significant improvements in acclimatized walking performance with the ankle exoskeleton, including increased speed and stride length. Participants also reported increased enjoyment and perceived benefits of using the exoskeleton. While ankle exoskeleton training did not lead to significant improvements in unassisted walking, this study demonstrates the feasibility of using ankle exoskeletons in the real world by people with CP. \u0000<italic>Conclusions:</i>\u0000 This study highlights the potential of wearable exoskeletons to augment community walking performance in CP, laying a foundation for further exploration in real-world environments.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"75-81"},"PeriodicalIF":2.7,"publicationDate":"2024-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10709375","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600237","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: Respiration-correlated cone-beam computed tomography (4D-CBCT) is an X-ray-based imaging modality that uses reconstruction algorithms to produce time-varying volumetric images of moving anatomy over a cycle of respiratory motion. The quality of the produced images is affected by the number of CBCT projections available for reconstruction. Interpolation techniques have been used to generate intermediary projections to be used, along with the original projections, for reconstruction. Transfer learning is a powerful approach that harnesses the ability to reuse pre-trained models in solving new problems. Methods: Several state-of-the-art pre-trained deep learning models, used for video frame interpolation, are utilized in this work to generate intermediary projections. Moreover, a novel regression predictive modeling approach is also proposed to achieve the same objective. Digital phantom and clinical datasets are used to evaluate the performance of the models. Results: The results show that the Real-Time Intermediate Flow Estimation (RIFE) algorithm outperforms the others in terms of the Structural Similarity Index Method (SSIM): 0.986 $pm$ 0.010, Peak Signal to Noise Ratio (PSNR): 44.13 $pm$ 2.76, and Mean Square Error (MSE): 18.86 $pm$ 206.90 across all datasets. Moreover, the interpolated projections were used along with the original ones to reconstruct a 4D-CBCT image that was compared to that reconstructed from the original projections only. Conclusions: The reconstructed image using the proposed approach was found to minimize the streaking artifacts, thereby enhancing the image quality. This work demonstrates the advantage of using general-purpose transfer learning algorithms in 4D-CBCT image enhancement.
{"title":"Machine Learning-Based X-Ray Projection Interpolation for Improved 4D-CBCT Reconstruction","authors":"Jayroop Ramesh;Donthi Sankalpa;Rohan Mitra;Salam Dhou","doi":"10.1109/OJEMB.2024.3459622","DOIUrl":"10.1109/OJEMB.2024.3459622","url":null,"abstract":"<italic>Goal:</i>\u0000 Respiration-correlated cone-beam computed tomography (4D-CBCT) is an X-ray-based imaging modality that uses reconstruction algorithms to produce time-varying volumetric images of moving anatomy over a cycle of respiratory motion. The quality of the produced images is affected by the number of CBCT projections available for reconstruction. Interpolation techniques have been used to generate intermediary projections to be used, along with the original projections, for reconstruction. Transfer learning is a powerful approach that harnesses the ability to reuse pre-trained models in solving new problems. \u0000<italic>Methods:</i>\u0000 Several state-of-the-art pre-trained deep learning models, used for video frame interpolation, are utilized in this work to generate intermediary projections. Moreover, a novel regression predictive modeling approach is also proposed to achieve the same objective. Digital phantom and clinical datasets are used to evaluate the performance of the models. \u0000<italic>Results:</i>\u0000 The results show that the Real-Time Intermediate Flow Estimation (RIFE) algorithm outperforms the others in terms of the Structural Similarity Index Method (SSIM): 0.986 \u0000<inline-formula><tex-math>$pm$</tex-math></inline-formula>\u0000 0.010, Peak Signal to Noise Ratio (PSNR): 44.13 \u0000<inline-formula><tex-math>$pm$</tex-math></inline-formula>\u0000 2.76, and Mean Square Error (MSE): 18.86 \u0000<inline-formula><tex-math>$pm$</tex-math></inline-formula>\u0000 206.90 across all datasets. Moreover, the interpolated projections were used along with the original ones to reconstruct a 4D-CBCT image that was compared to that reconstructed from the original projections only. \u0000<italic>Conclusions:</i>\u0000 The reconstructed image using the proposed approach was found to minimize the streaking artifacts, thereby enhancing the image quality. This work demonstrates the advantage of using general-purpose transfer learning algorithms in 4D-CBCT image enhancement.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"61-67"},"PeriodicalIF":2.7,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10678916","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142225756","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}
Future space exploration missions will expose astronauts to various stressors, making the early detection of mental stress crucial for prolonged missions. Our study proposes using functional near infrared spectroscopy (fNIRS) combined with multiple machine learning models to assess the level of mental stress. Objective: The objective is to identify and quantify stress levels during 240 days confinement scenario. In this study, we utilize a diverse set of stress indicators including salivary alpha amylase (sAA) levels, reaction time (RT) to stimuli, accuracy of target detection, and power spectral density (PSD), in conjunction with functional connectivity networks (FCN). We estimate the PSD using Fast Fourier Transform (FFT) and the FCN using partial directed coherence. Results: Our findings reveal several intriguing insights. The sAA levels increased from the first 30 days in confinement to the culmination of the lengthy 240-day mission, suggesting a cumulative impact of stress. Conversely, RT and the accuracy of target detection exhibit significant fluctuations over the course of the mission. The power spectral density shows a significant increase with time-in-mission across all participants in most of the frontal area. The FCN shows a significant decrease in most of the right frontal areas. Five different machine learning classifiers are employed to differentiate between two levels of stress resulting in impressive classification accuracy rates: 96.44% with-nearest neighbor (KNN), 95.52% with linear discriminant analysis (LDA), 88.71% with Naïve Bayes (NB), 87.41 with decision trees (DT) and 96.48% with Support Vector Machine (SVM). In conclusion, this study demonstrates the effectiveness of combining functional near infrared spectroscopy (fNIRS) with multiple machine learning models to accurately assess and quantify mental stress levels during prolonged space missions, providing a promising approach for early stress detection in astronauts.
{"title":"Assessment of Brain Function After 240 Days Confinement Using Functional Near Infrared Spectroscopy","authors":"Fares Al-Shargie;Usman Tariq;Saleh Al-Ameri;Abdulla Al-Hammadi;Schastlivtseva Daria Vladimirovna;Hasan Al-Nashash","doi":"10.1109/OJEMB.2024.3457240","DOIUrl":"10.1109/OJEMB.2024.3457240","url":null,"abstract":"Future space exploration missions will expose astronauts to various stressors, making the early detection of mental stress crucial for prolonged missions. Our study proposes using functional near infrared spectroscopy (fNIRS) combined with multiple machine learning models to assess the level of mental stress. \u0000<italic>Objective:</i>\u0000 The objective is to identify and quantify stress levels during 240 days confinement scenario. In this study, we utilize a diverse set of stress indicators including salivary alpha amylase (sAA) levels, reaction time (RT) to stimuli, accuracy of target detection, and power spectral density (PSD), in conjunction with functional connectivity networks (FCN). We estimate the PSD using Fast Fourier Transform (FFT) and the FCN using partial directed coherence. \u0000<italic>Results:</i>\u0000 Our findings reveal several intriguing insights. The sAA levels increased from the first 30 days in confinement to the culmination of the lengthy 240-day mission, suggesting a cumulative impact of stress. Conversely, RT and the accuracy of target detection exhibit significant fluctuations over the course of the mission. The power spectral density shows a significant increase with time-in-mission across all participants in most of the frontal area. The FCN shows a significant decrease in most of the right frontal areas. Five different machine learning classifiers are employed to differentiate between two levels of stress resulting in impressive classification accuracy rates: 96.44% with-nearest neighbor (KNN), 95.52% with linear discriminant analysis (LDA), 88.71% with Naïve Bayes (NB), 87.41 with decision trees (DT) and 96.48% with Support Vector Machine (SVM). In conclusion, this study demonstrates the effectiveness of combining functional near infrared spectroscopy (fNIRS) with multiple machine learning models to accurately assess and quantify mental stress levels during prolonged space missions, providing a promising approach for early stress detection in astronauts.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"54-60"},"PeriodicalIF":2.7,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10670317","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142200295","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 : 2024-09-09DOI: 10.1109/OJEMB.2024.3455801
Mohammed Salman;Pradeep Kumar Das;Sanjay Kumar Mohanty
Infectious diseases are a major global public health concern. Precise modeling and prediction methods are essential to develop effective strategies for disease control. However, data imbalance and the presence of noise and intensity inhomogeneity make disease detection more challenging. Goal: In this article, a novel infectious disease pattern prediction system is proposed by integrating deterministic and stochastic model benefits with the benefits of the deep learning model. Results: The combined benefits yield improvement in the performance of solution prediction. Moreover, the objective is also to investigate the influence of time delay on infection rates and rates associated with vaccination. Conclusions: In this proposed framework, at first, the global stability at disease free equilibrium is effectively analysed using Routh-Haurwitz criteria and Lyapunov method, and the endemic equilibrium is analysed using non-linear Volterra integral equations in the infectious disease model. Unlike the existing model, emphasis is given to suggesting a model that is capable of investigating stability while considering the effect of vaccination and migration rate. Next, the influence of vaccination on the rate of infection is effectively predicted using an efficient deep learning model by employing the long-term dependencies in sequential data. Thus making the prediction more accurate.
{"title":"An Integrated Framework for Infectious Disease Control Using Mathematical Modeling and Deep Learning","authors":"Mohammed Salman;Pradeep Kumar Das;Sanjay Kumar Mohanty","doi":"10.1109/OJEMB.2024.3455801","DOIUrl":"10.1109/OJEMB.2024.3455801","url":null,"abstract":"Infectious diseases are a major global public health concern. Precise modeling and prediction methods are essential to develop effective strategies for disease control. However, data imbalance and the presence of noise and intensity inhomogeneity make disease detection more challenging. \u0000<italic>Goal:</i>\u0000 In this article, a novel infectious disease pattern prediction system is proposed by integrating deterministic and stochastic model benefits with the benefits of the deep learning model. \u0000<italic>Results:</i>\u0000 The combined benefits yield improvement in the performance of solution prediction. Moreover, the objective is also to investigate the influence of time delay on infection rates and rates associated with vaccination. \u0000<italic>Conclusions:</i>\u0000 In this proposed framework, at first, the global stability at disease free equilibrium is effectively analysed using Routh-Haurwitz criteria and Lyapunov method, and the endemic equilibrium is analysed using non-linear Volterra integral equations in the infectious disease model. Unlike the existing model, emphasis is given to suggesting a model that is capable of investigating stability while considering the effect of vaccination and migration rate. Next, the influence of vaccination on the rate of infection is effectively predicted using an efficient deep learning model by employing the long-term dependencies in sequential data. Thus making the prediction more accurate.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"41-53"},"PeriodicalIF":2.7,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10669273","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142200297","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 : 2024-09-06DOI: 10.1109/OJEMB.2024.3455011
Jose L. Agraz;Carlos Agraz;Andrew A. Chen;Charles Rice;Robert S. Pozos;Sven Aelterman;Amanda Tan;Angela N. Viaene;MacLean P. Nasrallah;Parth Sharma;Caleb M. Grenko;Tahsin Kurc;Joel Saltz;Michael D. Feldman;Hamed Akbari;Russell T. Shinohara;Spyridon Bakas;Parker Wilson
In the medical diagnostics domain, pathology and histology are pivotal for the precise identification of diseases. Digital histopathology, enhanced by automation, facilitates the efficient analysis of massive amount of biopsy images produced on a daily basis, streamlining the evaluation process. This study focuses in Stain Color Normalization (SCN) within a Whole-Slide Image (WSI) cohort, aiming to reduce batch biases. Building on published graphical method, this research demonstrates a mathematical population or data-driven method that optimizes the dependency on the number of reference WSIs and corresponding aggregate sums, thereby increasing SCN process efficiency. This method expedites the analysis of color convergence 50-fold by using stain vector Euclidean distance analysis, slashing the requirement for reference WSIs by more than half. The approach is validated through a tripartite methodology: 1) Stain vector euclidean distances analysis, 2) Distance computation timing, and 3) Qualitative and quantitative assessments of SCN across cancer tumors regions of interest. The results validate the performance of data-driven SCN method, thus potential to enhance the precision and reliability of computational pathology analyses. This advancement is poised to enhance diagnostic processes, therapeutic strategies, and patient prognosis.
在医疗诊断领域，病理学和组织学是精确鉴定疾病的关键。通过自动化增强的数字组织病理学有助于高效分析每天产生的大量活检图像，从而简化评估流程。本研究的重点是在全切片图像（WSI）群组中进行染色颜色归一化（SCN），旨在减少批次偏差。在已发表的图形方法基础上，本研究展示了一种数学群体或数据驱动方法，可优化对参考 WSI 数量和相应总和的依赖性，从而提高 SCN 流程的效率。该方法通过使用染色向量欧氏距离分析，将色彩收敛分析的速度提高了 50 倍，对参考 WSI 的要求降低了一半以上。该方法通过以下三方面的方法进行验证：1）染色矢量欧氏距离分析；2）距离计算计时；3）对癌症肿瘤相关区域的 SCN 进行定性和定量评估。结果验证了数据驱动 SCN 方法的性能，从而有望提高计算病理分析的精确度和可靠性。这一进步有望改善诊断过程、治疗策略和患者预后。
{"title":"Optimized Whole-Slide-Image H&E Stain Normalization: A Step Towards Big Data Integration in Digital Pathology","authors":"Jose L. Agraz;Carlos Agraz;Andrew A. Chen;Charles Rice;Robert S. Pozos;Sven Aelterman;Amanda Tan;Angela N. Viaene;MacLean P. Nasrallah;Parth Sharma;Caleb M. Grenko;Tahsin Kurc;Joel Saltz;Michael D. Feldman;Hamed Akbari;Russell T. Shinohara;Spyridon Bakas;Parker Wilson","doi":"10.1109/OJEMB.2024.3455011","DOIUrl":"10.1109/OJEMB.2024.3455011","url":null,"abstract":"In the medical diagnostics domain, pathology and histology are pivotal for the precise identification of diseases. Digital histopathology, enhanced by automation, facilitates the efficient analysis of massive amount of biopsy images produced on a daily basis, streamlining the evaluation process. This study focuses in Stain Color Normalization (SCN) within a Whole-Slide Image (WSI) cohort, aiming to reduce batch biases. Building on published graphical method, this research demonstrates a mathematical population or data-driven method that optimizes the dependency on the number of reference WSIs and corresponding aggregate sums, thereby increasing SCN process efficiency. This method expedites the analysis of color convergence 50-fold by using stain vector Euclidean distance analysis, slashing the requirement for reference WSIs by more than half. The approach is validated through a tripartite methodology: 1) Stain vector euclidean distances analysis, 2) Distance computation timing, and 3) Qualitative and quantitative assessments of SCN across cancer tumors regions of interest. The results validate the performance of data-driven SCN method, thus potential to enhance the precision and reliability of computational pathology analyses. This advancement is poised to enhance diagnostic processes, therapeutic strategies, and patient prognosis.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"35-40"},"PeriodicalIF":2.7,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10669194","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142200296","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 : 2024-09-05DOI: 10.1109/OJEMB.2024.3453049
Marissé Masís Solano;Remy Dumas;Mark R Lesk;Santiago Costantino
Objective: To assess the impact of microgravity exposure on ocular rigidity (OR), intraocular pressure (IOP), and ocular pulse amplitude (OPA) following long-term space missions. OR was evaluated using optical coherence tomography (OCT) and deep learning-based choroid segmentation. IOP and OPA were measured with the PASCAL Dynamic Contour Tonometer (DCT). Results: The study included 26 eyes from 13 crew members who spent 157 to 186 days on the International Space Station. Post-mission results showed a 25% decrease in OPA (p < 0.005), an 11% decrease in IOP from 16.0 mmHg to 14.2 mmHg (p = 0.04), and a 33% reduction in OR (p = 0.04). No significant differences were observed between novice and experienced astronauts. Conclusions: These findings reveal previously unknown effects of microgravity on the eye's mechanical properties, contributing to a deeper understanding of Spaceflight-Associated Neuro-ocular Syndrome (SANS). Long-term space missions significantly alter ocular biomechanics and have the potential to become biomarkers of disease progression.
{"title":"Ocular Biomechanical Responses to Long-Duration Spaceflight","authors":"Marissé Masís Solano;Remy Dumas;Mark R Lesk;Santiago Costantino","doi":"10.1109/OJEMB.2024.3453049","DOIUrl":"10.1109/OJEMB.2024.3453049","url":null,"abstract":"<italic>Objective:</i>\u0000 To assess the impact of microgravity exposure on ocular rigidity (OR), intraocular pressure (IOP), and ocular pulse amplitude (OPA) following long-term space missions. OR was evaluated using optical coherence tomography (OCT) and deep learning-based choroid segmentation. IOP and OPA were measured with the PASCAL Dynamic Contour Tonometer (DCT). \u0000<italic>Results:</i>\u0000 The study included 26 eyes from 13 crew members who spent 157 to 186 days on the International Space Station. Post-mission results showed a 25% decrease in OPA (p < 0.005), an 11% decrease in IOP from 16.0 mmHg to 14.2 mmHg (p = 0.04), and a 33% reduction in OR (p = 0.04). No significant differences were observed between novice and experienced astronauts. \u0000<italic>Conclusions:</i>\u0000 These findings reveal previously unknown effects of microgravity on the eye's mechanical properties, contributing to a deeper understanding of Spaceflight-Associated Neuro-ocular Syndrome (SANS). Long-term space missions significantly alter ocular biomechanics and have the potential to become biomarkers of disease progression.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"127-132"},"PeriodicalIF":2.7,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10666778","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142200298","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 : 2024-09-05DOI: 10.1109/OJEMB.2024.3454970
Simone Ranaldi;Leonardo Gizzi;Giacomo Severini;Cristiano De Marchis
The characterization, through the concept of muscle synergies, of clinical functional tests is a valid tool that has been widely adopted in the research field. While this theory has been exploited for a description of the motor control strategies underlying the biomechanical task, the biomechanical correlate of the synergistic activity is yet to be fully described. In this paper, the relationship between the activity of different synergies and the center of mass kinematic patterns has been investigated; in particular, a group of healthy subjects has been recruited to perform simple sit-to-stand tasks, and the electromyographic data has been recorded for the extraction of muscle synergies. An optimal model selection criterion has been adopted for dividing the participants by the number of synergies characterizing their own control schema. Synergistic activity has then been mapped onto the phase-space description of the center of mass kinematics, investigating whether a different number of synergies implies the exploration of different region of the phase-space itself. Results show how using an additional motor module allow for a wider trajectory in the phase-space, paving the way for the use of kinematic feedback to stimulate the activity of different synergies, with the aim of defining synergy-based rehabilitation or training protocols.
{"title":"Synergy-Dependent Center-of-Mass Control Strategies During Sit-to-Stand Movements","authors":"Simone Ranaldi;Leonardo Gizzi;Giacomo Severini;Cristiano De Marchis","doi":"10.1109/OJEMB.2024.3454970","DOIUrl":"10.1109/OJEMB.2024.3454970","url":null,"abstract":"The characterization, through the concept of muscle synergies, of clinical functional tests is a valid tool that has been widely adopted in the research field. While this theory has been exploited for a description of the motor control strategies underlying the biomechanical task, the biomechanical correlate of the synergistic activity is yet to be fully described. In this paper, the relationship between the activity of different synergies and the center of mass kinematic patterns has been investigated; in particular, a group of healthy subjects has been recruited to perform simple sit-to-stand tasks, and the electromyographic data has been recorded for the extraction of muscle synergies. An optimal model selection criterion has been adopted for dividing the participants by the number of synergies characterizing their own control schema. Synergistic activity has then been mapped onto the phase-space description of the center of mass kinematics, investigating whether a different number of synergies implies the exploration of different region of the phase-space itself. Results show how using an additional motor module allow for a wider trajectory in the phase-space, paving the way for the use of kinematic feedback to stimulate the activity of different synergies, with the aim of defining synergy-based rehabilitation or training protocols.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"28-34"},"PeriodicalIF":2.7,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10666157","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142200301","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 : 2024-09-05DOI: 10.1109/OJEMB.2024.3454958
Ting-Ruen Wei;Michele Hell;Aren Vierra;Ran Pang;Young Kang;Mahesh Patel;Yuling Yan
Goal: This study aims to enhance AI-assisted breast cancer diagnosis through dual-view sonography using a data-centric approach. Methods: We customize a DenseNet-based model on our exclusive dual-view breast ultrasound dataset to enhance the model's ability to differentiate between malignant and benign masses. Various assembly strategies are designed to integrate the dual views into the model input, contrasting with the use of single views alone, with a goal to maximize performance. Subsequently, we compare the model against the radiologist and quantify the improvement in key performance metrics. We further assess how the radiologist's diagnostic accuracy is enhanced with the assistance of the model. Results: Our experiments consistently found that optimal outcomes were achieved by using a channel-wise stacking approach incorporating both views, with one duplicated as the third channel. This configuration resulted in remarkable model performance with an area underthe receiver operating characteristic curve (AUC) of 0.9754, specificity of 0.96, and sensitivity of 0.9263, outperforming the radiologist by 50% in specificity. With the model's guidance, the radiologist's performance improved across key metrics: accuracy by 17%, precision by 26%, and specificity by 29%. Conclusions: Our customized model, withan optimal configuration for dual-view image input, surpassed both radiologists and existing model results in the literature. Integrating the model as a standalone tool or assistive aid for radiologists can greatly enhance specificity, reduce false positives, thereby minimizing unnecessary biopsies and alleviating radiologists' workload.
{"title":"Breast Cancer Detection on Dual-View Sonography via Data-Centric Deep Learning","authors":"Ting-Ruen Wei;Michele Hell;Aren Vierra;Ran Pang;Young Kang;Mahesh Patel;Yuling Yan","doi":"10.1109/OJEMB.2024.3454958","DOIUrl":"10.1109/OJEMB.2024.3454958","url":null,"abstract":"<italic>Goal:</i>\u0000 This study aims to enhance AI-assisted breast cancer diagnosis through dual-view sonography using a data-centric approach. \u0000<italic>Methods:</i>\u0000 We customize a DenseNet-based model on our exclusive dual-view breast ultrasound dataset to enhance the model's ability to differentiate between malignant and benign masses. Various assembly strategies are designed to integrate the dual views into the model input, contrasting with the use of single views alone, with a goal to maximize performance. Subsequently, we compare the model against the radiologist and quantify the improvement in key performance metrics. We further assess how the radiologist's diagnostic accuracy is enhanced with the assistance of the model. \u0000<italic>Results:</i>\u0000 Our experiments consistently found that optimal outcomes were achieved by using a channel-wise stacking approach incorporating both views, with one duplicated as the third channel. This configuration resulted in remarkable model performance with an area underthe receiver operating characteristic curve (AUC) of 0.9754, specificity of 0.96, and sensitivity of 0.9263, outperforming the radiologist by 50% in specificity. With the model's guidance, the radiologist's performance improved across key metrics: accuracy by 17%, precision by 26%, and specificity by 29%. \u0000<italic>Conclusions:</i>\u0000 Our customized model, withan optimal configuration for dual-view image input, surpassed both radiologists and existing model results in the literature. Integrating the model as a standalone tool or assistive aid for radiologists can greatly enhance specificity, reduce false positives, thereby minimizing unnecessary biopsies and alleviating radiologists' workload.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"100-106"},"PeriodicalIF":2.7,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10666269","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142200299","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: To accurately detect infections in Diabetic Foot Ulcers (DFUs) using photographs taken at the Point of Care (POC). Achieving high performance is critical for preventing complications and amputations, as well as minimizing unnecessary emergency department visits and referrals. Methods: This paper proposes the Guided Conditional Diffusion Classifier (ConDiff). This novel deep-learning framework combines guided image synthesis with a denoising diffusion model and distance-based classification. The process involves (1) generating guided conditional synthetic images by injecting Gaussian noise to a guide (input) image, followed by denoising the noise-perturbed image through a reverse diffusion process, conditioned on infection status and (2) classifying infections based on the minimum Euclidean distance between synthesized images and the original guide image in embedding space. Results: ConDiff demonstrated superior performance with an average accuracy of 81% that outperformed state-of-the-art (SOTA) models by at least 3%. It also achieved the highest sensitivity of 85.4%, which is crucial in clinical domains while significantly improving specificity to 74.4%, surpassing the best SOTA model. Conclusions: ConDiff not only improves the diagnosis of DFU infections but also pioneers the use of generative discriminative models for detailed medical image analysis, offering a promising approach for improving patient outcomes.
{"title":"Guided Conditional Diffusion Classifier (ConDiff) for Enhanced Prediction of Infection in Diabetic Foot Ulcers","authors":"Palawat Busaranuvong;Emmanuel Agu;Deepak Kumar;Shefalika Gautam;Reza Saadati Fard;Bengisu Tulu;Diane Strong","doi":"10.1109/OJEMB.2024.3453060","DOIUrl":"10.1109/OJEMB.2024.3453060","url":null,"abstract":"<italic>Goal:</i>\u0000 To accurately detect infections in Diabetic Foot Ulcers (DFUs) using photographs taken at the Point of Care (POC). Achieving high performance is critical for preventing complications and amputations, as well as minimizing unnecessary emergency department visits and referrals. \u0000<italic>Methods:</i>\u0000 This paper proposes the Guided Conditional Diffusion Classifier (ConDiff). This novel deep-learning framework combines guided image synthesis with a denoising diffusion model and distance-based classification. The process involves (1) generating guided conditional synthetic images by injecting Gaussian noise to a guide (input) image, followed by denoising the noise-perturbed image through a reverse diffusion process, conditioned on infection status and (2) classifying infections based on the minimum Euclidean distance between synthesized images and the original guide image in embedding space. \u0000<italic>Results:</i>\u0000 ConDiff demonstrated superior performance with an average accuracy of 81% that outperformed state-of-the-art (SOTA) models by at least 3%. It also achieved the highest sensitivity of 85.4%, which is crucial in clinical domains while significantly improving specificity to 74.4%, surpassing the best SOTA model. \u0000<italic>Conclusions:</i>\u0000 ConDiff not only improves the diagnosis of DFU infections but also pioneers the use of generative discriminative models for detailed medical image analysis, offering a promising approach for improving patient outcomes.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"20-27"},"PeriodicalIF":2.7,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10663215","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142225757","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}
Esophageal cancer (EC) poses a significant health concern, particularly among the elderly, warranting effective treatment strategies. While immunotherapy holds promise in activating the immune response against tumors, its specific impact and associated reactions in EC patients remain uncertain. Precise prognosis prediction becomes crucial for guiding appropriate interventions. This study, based on data from the First Affiliated Hospital of Xiamen University (January 2017 to May 2021), focuses on 113 EC patients undergoing immunotherapy. The primary objectives are to elucidate the effectiveness of immunotherapy in EC treatment and to introduce a stacking ensemble learning method for predicting the survival of EC patients who have undergone immunotherapy, in the context of small sample sizes, addressing the imperative of supporting clinical decision-making for healthcare professionals. Our method incorporates five sub-learners and one meta-learner. Leveraging optimal features from the training dataset, this approach achieved compelling accuracy (89.13%) and AUC (88.83%) in predicting three-year survival status, surpassing conventional techniques. The model proves efficient in guiding clinical decisions, especially in scenarios with small-size follow-up data.
{"title":"Prediction of Survival in Patients With Esophageal Cancer After Immunotherapy Based on Small-Size Follow-Up Data","authors":"Yuhan Su;Chaofeng Huang;Chen Yang;Qin Lin;Zhong Chen","doi":"10.1109/OJEMB.2024.3452983","DOIUrl":"10.1109/OJEMB.2024.3452983","url":null,"abstract":"Esophageal cancer (EC) poses a significant health concern, particularly among the elderly, warranting effective treatment strategies. While immunotherapy holds promise in activating the immune response against tumors, its specific impact and associated reactions in EC patients remain uncertain. Precise prognosis prediction becomes crucial for guiding appropriate interventions. This study, based on data from the First Affiliated Hospital of Xiamen University (January 2017 to May 2021), focuses on 113 EC patients undergoing immunotherapy. The primary objectives are to elucidate the effectiveness of immunotherapy in EC treatment and to introduce a stacking ensemble learning method for predicting the survival of EC patients who have undergone immunotherapy, in the context of small sample sizes, addressing the imperative of supporting clinical decision-making for healthcare professionals. Our method incorporates five sub-learners and one meta-learner. Leveraging optimal features from the training dataset, this approach achieved compelling accuracy (89.13%) and AUC (88.83%) in predicting three-year survival status, surpassing conventional techniques. The model proves efficient in guiding clinical decisions, especially in scenarios with small-size follow-up data.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"5 ","pages":"769-782"},"PeriodicalIF":2.7,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10663258","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142200300","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：