Pub Date : 2024-06-03DOI: 10.1109/OJEMB.2024.3408078
Sevgi Z. Gurbuz;Mohammad Mahbubur Rahman;Zahra Bassiri;Dario Martelli
Current methods for fall risk assessment rely on Quantitative Gait Analysis (QGA) using costly optical tracking systems, which are often only available at specialized laboratories that may not be easily accessible to rural communities. Radar placed in a home or assisted living facility can acquire continuous ambulatory recordings over extended durations of a subject's natural gait and activity. Thus, radar-based QGA has the potential to capture day-to-day variations in gait, is time efficient and removes the burden for the subject to come to a clinic, providing a more realistic picture of older adults’ mobility. Although there has been research on gait-related health monitoring, most of this work focuses on classification-based methods, while only a few consider gait parameter estimation. On the one hand, metrics that are accurately and easily computable from radar data have not been demonstrated to have an established correlation with fall risk or other medical conditions; on the other hand, the accuracy of radar-based estimates of gait parameters that are well-accepted by the medical community as indicators of fall risk have not been adequately validated. This paper provides an overview of emerging radar-based techniques for gait parameter estimation, especially with emphasis on those relevant to fall risk. A pilot study that compares the accuracy of estimating gait parameters from different radar data representations – in particular, the micro-Doppler signature and skeletal point estimates – is conducted based on validation against an 8-camera, marker-based optical tracking system. The results of pilot study are discussed to assess the current state-of-the-art in radar-based QGA and potential directions for future research that can improve radar-based gait parameter estimation accuracy.
{"title":"Overview of Radar-Based Gait Parameter Estimation Techniques for Fall Risk Assessment","authors":"Sevgi Z. Gurbuz;Mohammad Mahbubur Rahman;Zahra Bassiri;Dario Martelli","doi":"10.1109/OJEMB.2024.3408078","DOIUrl":"10.1109/OJEMB.2024.3408078","url":null,"abstract":"Current methods for fall risk assessment rely on Quantitative Gait Analysis (QGA) using costly optical tracking systems, which are often only available at specialized laboratories that may not be easily accessible to rural communities. Radar placed in a home or assisted living facility can acquire continuous ambulatory recordings over extended durations of a subject's natural gait and activity. Thus, radar-based QGA has the potential to capture day-to-day variations in gait, is time efficient and removes the burden for the subject to come to a clinic, providing a more realistic picture of older adults’ mobility. Although there has been research on gait-related health monitoring, most of this work focuses on classification-based methods, while only a few consider gait parameter estimation. On the one hand, metrics that are accurately and easily computable from radar data have not been demonstrated to have an established correlation with fall risk or other medical conditions; on the other hand, the accuracy of radar-based estimates of gait parameters that are well-accepted by the medical community as indicators of fall risk have not been adequately validated. This paper provides an overview of emerging radar-based techniques for gait parameter estimation, especially with emphasis on those relevant to fall risk. A pilot study that compares the accuracy of estimating gait parameters from different radar data representations – in particular, the micro-Doppler signature and skeletal point estimates – is conducted based on validation against an 8-camera, marker-based optical tracking system. The results of pilot study are discussed to assess the current state-of-the-art in radar-based QGA and potential directions for future research that can improve radar-based gait parameter estimation accuracy.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10546280","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141948752","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: A biological system's internal morphological structure or function can be changed as a result of the mechanical effect of focused ultrasound. Pulsed low-intensity focused ultrasound (LIFU) has mechanical effects that might induce follicle development with less damage to ovarian tissue. The potential development of LIFU as a non-invasive method for the treatment of female infertility is being considered, and this study sought to explore and confirm that LIFU can activate ovarian follicles. Results: We found a 50% increase in ovarian weight and in the number of mature follicles on the ultrasound-stimulated side with pulsed LIFU and intraperitoneal injection of 10 IU PMSG in 10-day-old rats. After ultrasound stimulation, the PCOS-like rats had a decrease in androgen levels, restoration of regular estrous cycle and increase in the number of mature follicles and corpora lutea, and the ratio of M1 and M2 type macrophages was altered in antral follicles of PCOS-like rats, consequently promoting further development and maturation of antral follicles. Conclusion: LIFU treatment could trigger actin changes in ovarian cells, which might disrupt the Hippo signal pathway to promote follicle formation, and the mechanical impact on the ovaries of PCOS-like rats improved antral follicle development.
{"title":"Pulsed Low-Intensity Focused Ultrasound (LIFU) Activation of Ovarian Follicles","authors":"Yan Xiao;Lixia Yang;Yicong Wang;Yu Wang;Yuning Chen;Wenhan Lu;Zhenle Pei;Ruonan Zhang;Yao Ye;Xiaowei Ji;Suying Liu;Xi Dong;Yonghua Xu;Yi Feng","doi":"10.1109/OJEMB.2024.3391939","DOIUrl":"10.1109/OJEMB.2024.3391939","url":null,"abstract":"<italic>Objective:</i>\u0000 A biological system's internal morphological structure or function can be changed as a result of the mechanical effect of focused ultrasound. Pulsed low-intensity focused ultrasound (LIFU) has mechanical effects that might induce follicle development with less damage to ovarian tissue. The potential development of LIFU as a non-invasive method for the treatment of female infertility is being considered, and this study sought to explore and confirm that LIFU can activate ovarian follicles. \u0000<italic>Results:</i>\u0000 We found a 50% increase in ovarian weight and in the number of mature follicles on the ultrasound-stimulated side with pulsed LIFU and intraperitoneal injection of 10 IU PMSG in 10-day-old rats. After ultrasound stimulation, the PCOS-like rats had a decrease in androgen levels, restoration of regular estrous cycle and increase in the number of mature follicles and corpora lutea, and the ratio of M1 and M2 type macrophages was altered in antral follicles of PCOS-like rats, consequently promoting further development and maturation of antral follicles. \u0000<italic>Conclusion:</i>\u0000 LIFU treatment could trigger actin changes in ovarian cells, which might disrupt the Hippo signal pathway to promote follicle formation, and the mechanical impact on the ovaries of PCOS-like rats improved antral follicle development.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":null,"pages":null},"PeriodicalIF":5.8,"publicationDate":"2024-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10508955","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140803921","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: Parkinson's disease (PD) can lead to gait impairment and Freezing of Gait (FoG). Recent advances in cueing technologies have enhanced mobility in PD patients. While sensor technology and machine learning offer real-time detection for on-demand cueing, existing systems are limited by the usage of smartphones between the sensor(s) and cueing device(s) for data processing. By avoiding this we aim at improving usability, robustness, and detection delay. Methods: We present a new technical solution, that runs detection and cueing algorithms directly on the sensing and cueing devices, bypassing the smartphone. This solution relies on edge computing on the devices' hardware. The wearable system consists of a single inertial sensor to control a stimulator and enables machine-learning-based FoG detection by classifying foot motion phases as either normal or FoG-affected. We demonstrate the system's functionality and safety during on-demand gait-synchronous electrical cueing in two patients, performing freezing of gait assessments. As references, motion phases and FoG episodes have been video-annotated. Results: The analysis confirms adequate gait phase and FoG detection performance. The mobility assistant detected foot motions with a rate above 94 % and classified them with an accuracy of 84 % into normal or FoG-affected. The FoG detection delay is mainly defined by the foot-motion duration, which is below the delay in existing sliding-window approaches. Conclusions: Direct computing on the sensor and cueing devices ensures robust detection of FoG-affected motions for on demand cueing synchronized with the gait. The proposed solution can be easily adopted to other sensor and cueing modalities.
目标：帕金森病（PD）可导致步态障碍和步态冻结（FoG）。提示技术的最新进展提高了帕金森病患者的行动能力。虽然传感器技术和机器学习为按需提示提供了实时检测功能，但现有系统却受限于在传感器和提示设备之间使用智能手机进行数据处理。通过避免这种情况，我们的目标是提高可用性、鲁棒性和检测延迟。方法：我们提出了一种新的技术解决方案，绕过智能手机，直接在传感和提示设备上运行检测和提示算法。该解决方案依赖于设备硬件上的边缘计算。该可穿戴系统由一个惯性传感器组成，用于控制一个刺激器，并通过将脚部运动阶段分类为正常或受 FoG 影响，实现基于机器学习的 FoG 检测。我们在两名患者身上演示了该系统的功能性和安全性，在按需进行步态同步电提示的过程中，对步态进行了冻结评估。作为参考，我们对运动阶段和 FoG 事件进行了视频标注。结果分析证实，步态相位和 FoG 检测性能良好。助行器对足部运动的检测率超过 94%，对正常或受 FoG 影响足部运动的分类准确率为 84%。FoG 检测延迟主要由脚部运动持续时间决定，低于现有滑动窗口方法的延迟。结论传感器和提示设备上的直接计算可确保对受 FoG 影响的运动进行稳健检测，从而实现与步态同步的按需提示。所提出的解决方案可轻松应用于其他传感器和提示模式。
{"title":"On-Demand Gait-Synchronous Electrical Cueing in Parkinson's Disease Using Machine Learning and Edge Computing: A Pilot Study","authors":"Ardit Dvorani;Constantin Wiesener;Christina Salchow-Hömmen;Magdalena Jochner;Lotta Spieker;Matej Skrobot;Hanno Voigt;Andrea Kühn;Nikolaus Wenger;Thomas Schauer","doi":"10.1109/OJEMB.2024.3390562","DOIUrl":"10.1109/OJEMB.2024.3390562","url":null,"abstract":"<italic>Goal:</i>\u0000 Parkinson's disease (PD) can lead to gait impairment and Freezing of Gait (FoG). Recent advances in cueing technologies have enhanced mobility in PD patients. While sensor technology and machine learning offer real-time detection for on-demand cueing, existing systems are limited by the usage of smartphones between the sensor(s) and cueing device(s) for data processing. By avoiding this we aim at improving usability, robustness, and detection delay. \u0000<italic>Methods:</i>\u0000 We present a new technical solution, that runs detection and cueing algorithms directly on the sensing and cueing devices, bypassing the smartphone. This solution relies on edge computing on the devices' hardware. The wearable system consists of a single inertial sensor to control a stimulator and enables machine-learning-based FoG detection by classifying foot motion phases as either normal or FoG-affected. We demonstrate the system's functionality and safety during on-demand gait-synchronous electrical cueing in two patients, performing freezing of gait assessments. As references, motion phases and FoG episodes have been video-annotated. \u0000<italic>Results:</i>\u0000 The analysis confirms adequate gait phase and FoG detection performance. The mobility assistant detected foot motions with a rate above 94 % and classified them with an accuracy of 84 % into normal or FoG-affected. The FoG detection delay is mainly defined by the foot-motion duration, which is below the delay in existing sliding-window approaches. \u0000<italic>Conclusions:</i>\u0000 Direct computing on the sensor and cueing devices ensures robust detection of FoG-affected motions for on demand cueing synchronized with the gait. The proposed solution can be easily adopted to other sensor and cueing modalities.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":null,"pages":null},"PeriodicalIF":5.8,"publicationDate":"2024-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10504963","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140625436","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 : 2024-04-05DOI: 10.1109/OJEMB.2024.3377461
Youngbin Kim;Kunlun Wang;Roberta I. Lock;Trevor R. Nash;Sharon Fleischer;Bryan Z. Wang;Barry M. Fine;Gordana Vunjak-Novakovic
Goal: Contractile response and calcium handling are central to understanding cardiac function and physiology, yet existing methods of analysis to quantify these metrics are often time-consuming, prone to mistakes, or require specialized equipment/license. We developed BeatProfiler, a suite of cardiac analysis tools designed to quantify contractile function, calcium handling, and force generation for multiple in vitro cardiac models and apply downstream machine learning methods for deep phenotyping and classification. Methods: We first validate BeatProfiler's accuracy, robustness, and speed by benchmarking against existing tools with a fixed dataset. We further confirm its ability to robustly characterize disease and dose-dependent drug response. We then demonstrate that the data acquired by our automatic acquisition pipeline can be further harnessed for machine learning (ML) analysis to phenotype a disease model of restrictive cardiomyopathy and profile cardioactive drug functional response. To accurately classify between these biological signals, we apply feature-based ML and deep learning models (temporal convolutional-bidirectional long short-term memory model or TCN-BiLSTM). Results: Benchmarking against existing tools revealed that BeatProfiler detected and analyzed contraction and calcium signals better than existing tools through improved sensitivity in low signal data, reduction in false positives, and analysis speed increase by 7 to 50-fold. Of signals accurately detected by published methods (PMs), BeatProfiler's extracted features showed high correlations to PMs, confirming that it is reliable and consistent with PMs. The features extracted by BeatProfiler classified restrictive cardiomyopathy cardiomyocytes from isogenic healthy controls with 98% accuracy and identified relax90 as a top distinguishing feature in congruence with previous findings. We also show that our TCN-BiLSTM model was able to classify drug-free control and 4 cardiac drugs with different mechanisms of action at 96% accuracy. We further apply Grad-CAM on our convolution-based models to identify signature regions of perturbations by these drugs in calcium signals. Conclusions: We anticipate that the capabilities of BeatProfiler will help advance in vitro studies in cardiac biology through rapid phenotyping, revealing mechanisms underlying cardiac health and disease, and enabling objective classification of cardiac disease and responses to drugs.
{"title":"BeatProfiler: Multimodal In Vitro Analysis of Cardiac Function Enables Machine Learning Classification of Diseases and Drugs","authors":"Youngbin Kim;Kunlun Wang;Roberta I. Lock;Trevor R. Nash;Sharon Fleischer;Bryan Z. Wang;Barry M. Fine;Gordana Vunjak-Novakovic","doi":"10.1109/OJEMB.2024.3377461","DOIUrl":"https://doi.org/10.1109/OJEMB.2024.3377461","url":null,"abstract":"<italic>Goal:</i>\u0000 Contractile response and calcium handling are central to understanding cardiac function and physiology, yet existing methods of analysis to quantify these metrics are often time-consuming, prone to mistakes, or require specialized equipment/license. We developed BeatProfiler, a suite of cardiac analysis tools designed to quantify contractile function, calcium handling, and force generation for multiple in vitro cardiac models and apply downstream machine learning methods for deep phenotyping and classification. \u0000<italic>Methods:</i>\u0000 We first validate BeatProfiler's accuracy, robustness, and speed by benchmarking against existing tools with a fixed dataset. We further confirm its ability to robustly characterize disease and dose-dependent drug response. We then demonstrate that the data acquired by our automatic acquisition pipeline can be further harnessed for machine learning (ML) analysis to phenotype a disease model of restrictive cardiomyopathy and profile cardioactive drug functional response. To accurately classify between these biological signals, we apply feature-based ML and deep learning models (temporal convolutional-bidirectional long short-term memory model or TCN-BiLSTM). \u0000<italic>Results:</i>\u0000 Benchmarking against existing tools revealed that BeatProfiler detected and analyzed contraction and calcium signals better than existing tools through improved sensitivity in low signal data, reduction in false positives, and analysis speed increase by 7 to 50-fold. Of signals accurately detected by published methods (PMs), BeatProfiler's extracted features showed high correlations to PMs, confirming that it is reliable and consistent with PMs. The features extracted by BeatProfiler classified restrictive cardiomyopathy cardiomyocytes from isogenic healthy controls with 98% accuracy and identified relax90 as a top distinguishing feature in congruence with previous findings. We also show that our TCN-BiLSTM model was able to classify drug-free control and 4 cardiac drugs with different mechanisms of action at 96% accuracy. We further apply Grad-CAM on our convolution-based models to identify signature regions of perturbations by these drugs in calcium signals. \u0000<italic>Conclusions:</i>\u0000 We anticipate that the capabilities of BeatProfiler will help advance in vitro studies in cardiac biology through rapid phenotyping, revealing mechanisms underlying cardiac health and disease, and enabling objective classification of cardiac disease and responses to drugs.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":null,"pages":null},"PeriodicalIF":5.8,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10490213","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140351488","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 : 2024-04-03DOI: 10.1109/OJEMB.2024.3384488
Youngro Lee;Jongae Park;Sungjoon Park;Jongmo Seo;Hae-Young Lee
Recent advancements in smartwatch technology have introduced photoplethysmography (PPG)-based blood pressure (BP) estimation, enabling convenient and continuous monitoring of BP. However, concerns about accuracy and validation for clinical use persist. This study uses real-world data from a Samsung Galaxy Watch campaign to assess smartwatch-based BP measurements. The approach examines calibration stability by comparing average systolic BP (SBP) before and after calibration, identifying factors affecting stability through regression analysis. User-level strategies are suggested to mitigate calibration instability and emphasize guideline adherence. Notably, calibration instability is found to decrease during night-time measurements and when averaging multiple readings in the same time frame. Guideline adherence is vital, particularly for the elderly, females, and individuals with hypertension. The research enhances measurement reliability through extensive datasets, shedding light on calibration stability.
{"title":"Stability of Watch-Based Blood Pressure Measurements Analyzed by Pre-Post Calibration Differences","authors":"Youngro Lee;Jongae Park;Sungjoon Park;Jongmo Seo;Hae-Young Lee","doi":"10.1109/OJEMB.2024.3384488","DOIUrl":"10.1109/OJEMB.2024.3384488","url":null,"abstract":"Recent advancements in smartwatch technology have introduced photoplethysmography (PPG)-based blood pressure (BP) estimation, enabling convenient and continuous monitoring of BP. However, concerns about accuracy and validation for clinical use persist. This study uses real-world data from a Samsung Galaxy Watch campaign to assess smartwatch-based BP measurements. The approach examines calibration stability by comparing average systolic BP (SBP) before and after calibration, identifying factors affecting stability through regression analysis. User-level strategies are suggested to mitigate calibration instability and emphasize guideline adherence. Notably, calibration instability is found to decrease during night-time measurements and when averaging multiple readings in the same time frame. Guideline adherence is vital, particularly for the elderly, females, and individuals with hypertension. The research enhances measurement reliability through extensive datasets, shedding light on calibration stability.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10490153","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140585424","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 evaluate the usability of different technologies designed for a remote assessment of knee osteoarthritis. Methods: We recruited eleven patients affected by mild or moderate knee osteoarthritis, eleven caregivers, and eleven clinicians to assess the following technologies: a wristband for monitoring physical activity, an examination chair for measuring leg extension, a thermal camera for acquiring skin thermographic data, a force balance for measuring center of pressure, an ultrasound imaging system for remote echographic acquisition, a mobile app, and a clinical portal software. Specific questionnaires scoring usability were filled out by patients, caregivers and clinicians. Results: The questionnaires highlighted a good level of usability and user-friendliness for all the technologies, obtaining an average score of 8.7 provided by the patients, 8.8 by the caregivers, and 8.5 by the clinicians, on a scale ranging from 0 to 10. Such average scores were calculated by putting together the scores obtained for the single technologies under evaluation and averaging them. Conclusions: This study demonstrates a high level of acceptability for the tested portable technologies designed for a potentially remote and frequent assessment of knee osteoarthritis.
{"title":"Usability Assessment of Technologies for Remote Monitoring of Knee Osteoarthritis","authors":"Andrea Cafarelli;Angela Sorriento;Giorgia Marola;Denise Amram;Fabien Rabusseau;Hervé Locteau;Paolo Cabras;Erik Dumont;Sam Nakhaei;Ake Jernberger;Pär Bergsten;Paolo Spinnato;Alessandro Russo;Leonardo Ricotti","doi":"10.1109/OJEMB.2024.3407961","DOIUrl":"10.1109/OJEMB.2024.3407961","url":null,"abstract":"<italic>Goal</i>\u0000: To evaluate the usability of different technologies designed for a remote assessment of knee osteoarthritis. \u0000<italic>Methods:</i>\u0000 We recruited eleven patients affected by mild or moderate knee osteoarthritis, eleven caregivers, and eleven clinicians to assess the following technologies: a wristband for monitoring physical activity, an examination chair for measuring leg extension, a thermal camera for acquiring skin thermographic data, a force balance for measuring center of pressure, an ultrasound imaging system for remote echographic acquisition, a mobile app, and a clinical portal software. Specific questionnaires scoring usability were filled out by patients, caregivers and clinicians. \u0000<italic>Results:</i>\u0000 The questionnaires highlighted a good level of usability and user-friendliness for all the technologies, obtaining an average score of 8.7 provided by the patients, 8.8 by the caregivers, and 8.5 by the clinicians, on a scale ranging from 0 to 10. Such average scores were calculated by putting together the scores obtained for the single technologies under evaluation and averaging them. \u0000<italic>Conclusions:</i>\u0000 This study demonstrates a high level of acceptability for the tested portable technologies designed for a potentially remote and frequent assessment of knee osteoarthritis.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":null,"pages":null},"PeriodicalIF":5.8,"publicationDate":"2024-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10543164","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141191644","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}
Background: Deep learning models for patch classification in whole-slide images (WSIs) have shown promise in assisting follicular lymphoma grading. However, these models often require pathologists to identify centroblasts and manually provide refined labels for model optimization. Objective: To address this limitation, we propose PseudoCell , an object detection framework for automated centroblast detection in WSI, eliminating the need for extensive pathologist's refined labels. Methods: PseudoCell leverages a combination of pathologist-provided centroblast labels and pseudo-negative labels generated from undersampled false-positive predictions based on cell morphology features. This approach reduces the reliance on time-consuming manual annotations. Results: Our framework significantly reduces the workload for pathologists by accurately identifying and narrowing down areas of interest containing centroblasts. Depending on the confidence threshold, PseudoCell can eliminate 58.18-99.35% of irrelevant tissue areas on WSI, streamlining the diagnostic process. Conclusion: This study presents PseudoCell as a practical and efficient prescreening method for centroblast detection, eliminating the need for refined labels from pathologists. The discussion section provides detailed guidance for implementing PseudoCell in clinical practice.
背景：用于全切片图像（WSI）斑块分类的深度学习模型在辅助滤泡性淋巴瘤分级方面大有可为。然而，这些模型通常需要病理学家识别中心母细胞，并手动提供用于模型优化的精细标签。目的：为了解决这一局限性，我们提出了一个对象检测框架--PseudoCell，用于自动检测 WSI 中的成中心细胞，无需病理学家提供大量的精细标签。方法PseudoCell 综合利用了病理学家提供的中心母细胞标签和根据细胞形态特征从采样不足的假阳性预测中生成的伪阴性标签。这种方法减少了对耗时的人工注释的依赖。结果我们的框架能准确识别并缩小含有中心母细胞的感兴趣区，从而大大减轻了病理学家的工作量。根据置信度阈值的不同，PseudoCell 可以消除 WSI 上 58.18-99.35% 的无关组织区域，从而简化诊断过程。结论本研究提出的伪细胞是一种实用、高效的成中心细胞检测预筛选方法，无需病理学家进行精细标记。讨论部分为在临床实践中使用伪细胞提供了详细指导。
{"title":"PseudoCell: Hard Negative Mining as Pseudo Labeling for Deep Learning-Based Centroblast Cell Detection","authors":"Narongrid Seesawad;Piyalitt Ittichaiwong;Thapanun Sudhawiyangkul;Phattarapong Sawangjai;Peti Thuwajit;Paisarn Boonsakan;Supasan Sripodok;Kanyakorn Veerakanjana;Komgrid Charngkaew;Ananya Pongpaibul;Napat Angkathunyakul;Narit Hnoohom;Sumeth Yuenyong;Chanitra Thuwajit;Theerawit Wilaiprasitporn","doi":"10.1109/OJEMB.2024.3407351","DOIUrl":"10.1109/OJEMB.2024.3407351","url":null,"abstract":"<italic>Background:</i>\u0000 Deep learning models for patch classification in whole-slide images (WSIs) have shown promise in assisting follicular lymphoma grading. However, these models often require pathologists to identify centroblasts and manually provide refined labels for model optimization. \u0000<italic>Objective:</i>\u0000 To address this limitation, we propose \u0000<italic>PseudoCell</i>\u0000, an object detection framework for automated centroblast detection in WSI, eliminating the need for extensive pathologist's refined labels. \u0000<italic>Methods:</i>\u0000 \u0000<italic>PseudoCell</i>\u0000 leverages a combination of pathologist-provided centroblast labels and pseudo-negative labels generated from undersampled false-positive predictions based on cell morphology features. This approach reduces the reliance on time-consuming manual annotations. \u0000<italic>Results:</i>\u0000 Our framework significantly reduces the workload for pathologists by accurately identifying and narrowing down areas of interest containing centroblasts. Depending on the confidence threshold, \u0000<italic>PseudoCell</i>\u0000 can eliminate 58.18-99.35% of irrelevant tissue areas on WSI, streamlining the diagnostic process. \u0000<italic>Conclusion:</i>\u0000 This study presents \u0000<italic>PseudoCell</i>\u0000 as a practical and efficient prescreening method for centroblast detection, eliminating the need for refined labels from pathologists. The discussion section provides detailed guidance for implementing \u0000<italic>PseudoCell</i>\u0000 in clinical practice.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10542389","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141191635","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: FetSAM represents a cutting-edge deep learning model aimed at revolutionizing fetal head ultrasound segmentation, thereby elevating prenatal diagnostic precision. Methods: Utilizing a comprehensive dataset–the largest to date for fetal head metrics–FetSAM incorporates prompt-based learning. It distinguishes itself with a dual loss mechanism, combining Weighted DiceLoss and Weighted Lovasz Loss, optimized through AdamW and underscored by class weight adjustments for better segmentation balance. Performance benchmarks against prominent models such as U-Net, DeepLabV3, and Segformer highlight its efficacy. Results: FetSAM delivers unparalleled segmentation accuracy, demonstrated by a DSC of 0.90117, HD of 1.86484, and ASD of 0.46645. Conclusion: FetSAM sets a new benchmark in AI-enhanced prenatal ultrasound analysis, providing a robust, precise tool for clinical applications and pushing the envelope of prenatal care with its groundbreaking dataset and segmentation capabilities.
{"title":"FetSAM: Advanced Segmentation Techniques for Fetal Head Biometrics in Ultrasound Imagery","authors":"Mahmood Alzubaidi;Uzair Shah;Marco Agus;Mowafa Househ","doi":"10.1109/OJEMB.2024.3382487","DOIUrl":"10.1109/OJEMB.2024.3382487","url":null,"abstract":"<italic>Goal:</i>\u0000 FetSAM represents a cutting-edge deep learning model aimed at revolutionizing fetal head ultrasound segmentation, thereby elevating prenatal diagnostic precision. \u0000<italic>Methods:</i>\u0000 Utilizing a comprehensive dataset–the largest to date for fetal head metrics–FetSAM incorporates prompt-based learning. It distinguishes itself with a dual loss mechanism, combining Weighted DiceLoss and Weighted Lovasz Loss, optimized through AdamW and underscored by class weight adjustments for better segmentation balance. Performance benchmarks against prominent models such as U-Net, DeepLabV3, and Segformer highlight its efficacy. \u0000<italic>Results:</i>\u0000 FetSAM delivers unparalleled segmentation accuracy, demonstrated by a DSC of 0.90117, HD of 1.86484, and ASD of 0.46645. \u0000<italic>Conclusion:</i>\u0000 FetSAM sets a new benchmark in AI-enhanced prenatal ultrasound analysis, providing a robust, precise tool for clinical applications and pushing the envelope of prenatal care with its groundbreaking dataset and segmentation capabilities.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":null,"pages":null},"PeriodicalIF":5.8,"publicationDate":"2024-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10480532","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140312995","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 : 2024-03-27DOI: 10.1109/OJEMB.2024.3405666
Meng Jiao;Changyue Song;Xiaochen Xian;Shihao Yang;Feng Liu
Sleep Apnea (SA) is a prevalent sleep disorder with multifaceted etiologies that can have severe consequences for patients. Diagnosing SA traditionally relies on the in-laboratory polysomnogram (PSG), which records various human physiological activities overnight. SA diagnosis involves manual scoring by qualified physicians. Traditional machine learning methods for SA detection depend on hand-crafted features, making feature selection pivotal for downstream classification tasks. In recent years, deep learning has gained popularity in SA detection due to its capability for automatic feature extraction and superior classification accuracy. This study introduces a Deep Attention Network with Multi-Temporal Information Fusion (DAN-MTIF) for SA detection using single-lead electrocardiogram (ECG) signals. This framework utilizes three 1D convolutional neural network (CNN) blocks to extract features from R-R intervals and R-peak amplitudes using segments of varying lengths. Recognizing that features derived from different temporal scales vary in their contribution to classification, we integrate a multi-head attention module with a self-attention mechanism to learn the weights for each feature vector. Comprehensive experiments and comparisons between two paradigms of classical machine learning approaches and deep learning approaches are conducted. Our experiment results demonstrate that (1) compared with benchmark methods, the proposed DAN-MTIF exhibits excellent performance with 0.9106 accuracy, 0.9396 precision, 0.8470 sensitivity, 0.9588 specificity, and 0.8909 $F_{1}$ score at per-segment level; (2) DAN-MTIF can effectively extract features with a higher degree of discrimination from ECG segments of multiple timescales than those with a single time scale, ensuring a better SA detection performance; (3) the overall performance of deep learning methods is better than the classical machine learning algorithms, highlighting the superior performance of deep learning approaches for SA detection.
睡眠呼吸暂停（SA）是一种普遍存在的睡眠障碍，其病因是多方面的，可对患者造成严重后果。睡眠呼吸暂停的诊断传统上依赖于实验室多导睡眠图（PSG），它记录了人体在一夜之间的各种生理活动。SA 诊断需要由合格的医生进行人工评分。用于 SA 检测的传统机器学习方法依赖于手工创建的特征，因此特征选择对于下游分类任务至关重要。近年来，深度学习因其自动提取特征的能力和出色的分类准确性，在 SA 检测中越来越受欢迎。本研究介绍了利用单导联心电图（ECG）信号进行 SA 检测的多时空信息融合深度注意力网络（DAN-MTIF）。该框架利用三个一维卷积神经网络（CNN）块，使用不同长度的片段从 R-R 间期和 R 峰振幅中提取特征。由于从不同时间尺度提取的特征对分类的贡献各不相同，我们将多头注意模块与自我注意机制相结合，以学习每个特征向量的权重。我们在经典机器学习方法和深度学习方法的两种范例之间进行了全面的实验和比较。实验结果表明：(1) 与基准方法相比，DAN-MTIF 的准确度为 0.9106、精确度为 0.9396、灵敏度为 0.8470、特异度为 0.9588 和 0.8909 $F_{1}$ 的得分；（2）DAN-MTIF 能有效地从多个时间尺度的心电图片段中提取比单一时间尺度的心电图片段具有更高辨别度的特征，保证了更好的 SA 检测性能；（3）深度学习方法的整体性能优于经典的机器学习算法，凸显了深度学习方法在 SA 检测中的优越性能。
{"title":"Deep Attention Networks With Multi-Temporal Information Fusion for Sleep Apnea Detection","authors":"Meng Jiao;Changyue Song;Xiaochen Xian;Shihao Yang;Feng Liu","doi":"10.1109/OJEMB.2024.3405666","DOIUrl":"10.1109/OJEMB.2024.3405666","url":null,"abstract":"Sleep Apnea (SA) is a prevalent sleep disorder with multifaceted etiologies that can have severe consequences for patients. Diagnosing SA traditionally relies on the in-laboratory polysomnogram (PSG), which records various human physiological activities overnight. SA diagnosis involves manual scoring by qualified physicians. Traditional machine learning methods for SA detection depend on hand-crafted features, making feature selection pivotal for downstream classification tasks. In recent years, deep learning has gained popularity in SA detection due to its capability for automatic feature extraction and superior classification accuracy. This study introduces a Deep Attention Network with Multi-Temporal Information Fusion (DAN-MTIF) for SA detection using single-lead electrocardiogram (ECG) signals. This framework utilizes three 1D convolutional neural network (CNN) blocks to extract features from R-R intervals and R-peak amplitudes using segments of varying lengths. Recognizing that features derived from different temporal scales vary in their contribution to classification, we integrate a multi-head attention module with a self-attention mechanism to learn the weights for each feature vector. Comprehensive experiments and comparisons between two paradigms of classical machine learning approaches and deep learning approaches are conducted. Our experiment results demonstrate that (1) compared with benchmark methods, the proposed DAN-MTIF exhibits excellent performance with 0.9106 accuracy, 0.9396 precision, 0.8470 sensitivity, 0.9588 specificity, and 0.8909 \u0000<inline-formula><tex-math>$F_{1}$</tex-math></inline-formula>\u0000 score at per-segment level; (2) DAN-MTIF can effectively extract features with a higher degree of discrimination from ECG segments of multiple timescales than those with a single time scale, ensuring a better SA detection performance; (3) the overall performance of deep learning methods is better than the classical machine learning algorithms, highlighting the superior performance of deep learning approaches for SA detection.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10539178","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141170429","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: In patients with coronary artery disease, the prediction of future cardiac events such as myocardial infarction (MI) remains a major challenge. In this work, we propose a novel anatomy-informed multimodal deep learning framework to predict future MI from clinical data and Invasive Coronary Angiography (ICA) images. Methods: The images are analyzed by Convolutional Neural Networks (CNNs) guided by anatomical information, and the clinical data by an Artificial Neural Network (ANN). Embeddings from both sources are then merged to provide a patient-level prediction. Results: The results of our framework on a clinical study of 445 patients admitted with acute coronary syndromes confirms that multimodal learning increases the predictive power and achieves good performance (AUC: $0.67pm 0.04$ & F1-Score: $0.36pm 0.12$ ), which outperforms the prediction obtained by each modality independently as well as that of interventional cardiologists (AUC: 0.54 & F1-Score: 0.18). Conclusions: To the best of our knowledge, this is the first attempt towards combining multimodal data through a deep learning framework for future MI prediction. Although it demonstrates the superiority of multi-modal approaches over single modality, the results do not yet meet the necessary criteria for practical application.
{"title":"Anatomy-Informed Multimodal Learning for Myocardial Infarction Prediction","authors":"Ivan-Daniel Sievering;Ortal Senouf;Thabo Mahendiran;David Nanchen;Stephane Fournier;Olivier Muller;Pascal Frossard;Emmanuel Abbé;Dorina Thanou","doi":"10.1109/OJEMB.2024.3403948","DOIUrl":"10.1109/OJEMB.2024.3403948","url":null,"abstract":"<italic>Goal:</i>\u0000 In patients with coronary artery disease, the prediction of future cardiac events such as myocardial infarction (MI) remains a major challenge. In this work, we propose a novel anatomy-informed multimodal deep learning framework to predict future MI from clinical data and Invasive Coronary Angiography (ICA) images. \u0000<italic>Methods:</i>\u0000 The images are analyzed by Convolutional Neural Networks (CNNs) guided by anatomical information, and the clinical data by an Artificial Neural Network (ANN). Embeddings from both sources are then merged to provide a patient-level prediction. \u0000<italic>Results:</i>\u0000 The results of our framework on a clinical study of 445 patients admitted with acute coronary syndromes confirms that multimodal learning increases the predictive power and achieves good performance (AUC: \u0000<inline-formula><tex-math>$0.67pm 0.04$</tex-math></inline-formula>\u0000 & F1-Score: \u0000<inline-formula><tex-math>$0.36pm 0.12$</tex-math></inline-formula>\u0000), which outperforms the prediction obtained by each modality independently as well as that of interventional cardiologists (AUC: 0.54 & F1-Score: 0.18). \u0000<italic>Conclusions:</i>\u0000 To the best of our knowledge, this is the first attempt towards combining multimodal data through a deep learning framework for future MI prediction. Although it demonstrates the superiority of multi-modal approaches over single modality, the results do not yet meet the necessary criteria for practical application.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2024-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10540036","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141170475","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：