Goal: In this study, we demonstrate that a deep neural network (DNN) can be trained to reconstruct high-contrast images, resembling those produced by the multistatic Synthetic Aperture (SA) method using a 128-element array, leveraging pre-beamforming radiofrequency (RF) signals acquired through the monostatic SA approach. Methods : A U-net was trained using 27200 pairs of RF signals, simulated considering a monostatic SA architecture, with their corresponding delay-and-sum beamformed target images in a multistatic 128-element SA configuration. The contrast was assessed on 500 simulated test images of anechoic/hyperechoic targets. The DNN's performance in reconstructing experimental images of a phantom and different in vivo scenarios was tested too. Results : The DNN, compared to the simple monostatic SA approach used to acquire pre-beamforming signals, generated better-quality images with higher contrast and reduced noise/artifacts. Conclusions : The obtained results suggest the potential for the development of a single-channel setup, simultaneously providing good-quality images and reducing hardware complexity.
目标：在本研究中，我们证明了深度神经网络（DNN）可以通过训练来重建高对比度图像，类似于使用 128 元阵列的多静态合成孔径（SA）方法生成的图像，并利用通过单静态 SA 方法获取的预波束成形射频（RF）信号。方法：使用 27200 对射频信号训练 U-网络，模拟单静态 SA 架构，以及多静态 128 元 SA 配置中相应的延迟和波束成形目标图像。对比度在 500 幅模拟测试图像上进行了评估，测试图像为消声/低消声目标。此外，还测试了 DNN 在重建幻影实验图像和不同活体场景中的性能。测试结果与用于获取波束成形前信号的简单单静态 SA 方法相比，DNN 生成的图像质量更好，对比度更高，噪声/伪影更少。结论获得的结果表明，开发单通道设置具有潜力，可同时提供高质量图像并降低硬件复杂性。
{"title":"A Deep Learning Approach for Beamforming and Contrast Enhancement of Ultrasound Images in Monostatic Synthetic Aperture Imaging: A Proof-of-Concept","authors":"Edoardo Bosco;Edoardo Spairani;Eleonora Toffali;Valentino Meacci;Alessandro Ramalli;Giulia Matrone","doi":"10.1109/OJEMB.2024.3401098","DOIUrl":"10.1109/OJEMB.2024.3401098","url":null,"abstract":"<italic>Goal:</i>\u0000 In this study, we demonstrate that a deep neural network (DNN) can be trained to reconstruct high-contrast images, resembling those produced by the multistatic Synthetic Aperture (SA) method using a 128-element array, leveraging pre-beamforming radiofrequency (RF) signals acquired through the monostatic SA approach. \u0000<italic>Methods</i>\u0000: A U-net was trained using 27200 pairs of RF signals, simulated considering a monostatic SA architecture, with their corresponding delay-and-sum beamformed target images in a multistatic 128-element SA configuration. The contrast was assessed on 500 simulated test images of anechoic/hyperechoic targets. The DNN's performance in reconstructing experimental images of a phantom and different \u0000<italic>in vivo</i>\u0000 scenarios was tested too. \u0000<italic>Results</i>\u0000: The DNN, compared to the simple monostatic SA approach used to acquire pre-beamforming signals, generated better-quality images with higher contrast and reduced noise/artifacts. \u0000<italic>Conclusions</i>\u0000: The obtained results suggest the potential for the development of a single-channel setup, simultaneously providing good-quality images and reducing hardware complexity.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"5 ","pages":"376-382"},"PeriodicalIF":5.8,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10531023","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141063459","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 : 2024-03-12DOI: 10.1109/OJEMB.2024.3374966
Kele Xu;Kang You;Boqing Zhu;Ming Feng;Dawei Feng;Cheng Yang
Recently, deep learning-based methods have emerged as the preferred approach for ultrasound data analysis. However, these methods often require large-scale annotated datasets for training deep models, which are not readily available in practical scenarios. Additionally, the presence of speckle noise and other imaging artifacts can introduce numerous hard examples for ultrasound data classification. In this paper, drawing inspiration from self-supervised learning techniques, we present a pre-training method based on mask modeling specifically designed for ultrasound data. Our study investigates three different mask modeling strategies: random masking, vertical masking, and horizontal masking. By employing these strategies, our pre-training approach aims to predict the masked portion of the ultrasound images. Notably, our method does not rely on externally labeled data, allowing us to extract representative features without the need for human annotation. Consequently, we can leverage unlabeled datasets for pre-training. Furthermore, to address the challenges posed by hard samples in ultrasound data, we propose a novel hard sample mining strategy. To evaluate the effectiveness of our proposed method, we conduct experiments on two datasets. The experimental results demonstrate that our approach outperforms other state-of-the-art methods in ultrasound image classification. This indicates the superiority of our pre-training method and its ability to extract discriminative features from ultrasound data, even in the presence of hard examples.
{"title":"Masked Modeling-Based Ultrasound Image Classification via Self-Supervised Learning","authors":"Kele Xu;Kang You;Boqing Zhu;Ming Feng;Dawei Feng;Cheng Yang","doi":"10.1109/OJEMB.2024.3374966","DOIUrl":"10.1109/OJEMB.2024.3374966","url":null,"abstract":"Recently, deep learning-based methods have emerged as the preferred approach for ultrasound data analysis. However, these methods often require large-scale annotated datasets for training deep models, which are not readily available in practical scenarios. Additionally, the presence of speckle noise and other imaging artifacts can introduce numerous hard examples for ultrasound data classification. In this paper, drawing inspiration from self-supervised learning techniques, we present a pre-training method based on mask modeling specifically designed for ultrasound data. Our study investigates three different mask modeling strategies: random masking, vertical masking, and horizontal masking. By employing these strategies, our pre-training approach aims to predict the masked portion of the ultrasound images. Notably, our method does not rely on externally labeled data, allowing us to extract representative features without the need for human annotation. Consequently, we can leverage unlabeled datasets for pre-training. Furthermore, to address the challenges posed by hard samples in ultrasound data, we propose a novel hard sample mining strategy. To evaluate the effectiveness of our proposed method, we conduct experiments on two datasets. The experimental results demonstrate that our approach outperforms other state-of-the-art methods in ultrasound image classification. This indicates the superiority of our pre-training method and its ability to extract discriminative features from ultrasound data, even in the presence of hard examples.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"5 ","pages":"226-237"},"PeriodicalIF":5.8,"publicationDate":"2024-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10463101","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140114732","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 : 2024-03-10DOI: 10.1109/OJEMB.2024.3399469
M. Rubega;E. Passarotto;M. Paramento;E. Formaggio;S. Masiero
The pathophysiology of Adolescent Idiopathic Scoliosis (AIS) is not yet fully understood, but multifactorial hypotheses have been proposed that include defective central nervous system (CNS) control of posture, biomechanics, and body schema alterations. To deepen CNS control of posture in AIS, electroencephalographic (EEG) activity during a simple balance task in adolescents with and without AIS was parsed into EEG microstates. Microstates are quasi-stable spatial distributions of the electric potential of the brain that last tens of milliseconds. The spatial distribution of the EEG characterised by the orientation from left-frontal to right-posterior remains stable for a greater amount of time in AIS compared to controls. This spatial distribution of EEG, commonly named in the literature as class B, has been found to be correlated with the visual resting state network. Both vision and proprioception networks provide critical information in mapping the extrapersonal environment. This neurophysiological marker probably unveils an alteration in the postural control mechanism in AIS, suggesting a higher information processing load due to the increased postural demands caused by scoliosis.
青少年特发性脊柱侧弯症（AIS）的病理生理学尚不完全清楚，但已提出了多因素假说，包括中枢神经系统（CNS）对姿势的控制缺陷、生物力学和身体图式的改变。为了加深中枢神经系统对 AIS 患者姿势的控制，我们将患有和未患有 AIS 的青少年在完成简单平衡任务时的脑电图（EEG）活动解析为 EEG 微状态。微状态是大脑电位的准稳定空间分布，持续时间为数十毫秒。与对照组相比，AIS 患者脑电图的空间分布特点是从左前方到右后方，在更长的时间内保持稳定。这种脑电图的空间分布在文献中通常被称为 B 类，已被发现与视觉静息状态网络相关。视觉和本体感觉网络都为绘制人外环境图提供了关键信息。这一神经生理学标记可能揭示了AIS患者姿势控制机制的改变，表明由于脊柱侧弯导致姿势需求增加，信息处理负荷加重。
{"title":"EEG Microstate as a Marker of Adolescent Idiopathic Scoliosis","authors":"M. Rubega;E. Passarotto;M. Paramento;E. Formaggio;S. Masiero","doi":"10.1109/OJEMB.2024.3399469","DOIUrl":"10.1109/OJEMB.2024.3399469","url":null,"abstract":"The pathophysiology of Adolescent Idiopathic Scoliosis (AIS) is not yet fully understood, but multifactorial hypotheses have been proposed that include defective central nervous system (CNS) control of posture, biomechanics, and body schema alterations. To deepen CNS control of posture in AIS, electroencephalographic (EEG) activity during a simple balance task in adolescents with and without AIS was parsed into EEG microstates. Microstates are quasi-stable spatial distributions of the electric potential of the brain that last tens of milliseconds. The spatial distribution of the EEG characterised by the orientation from left-frontal to right-posterior remains stable for a greater amount of time in AIS compared to controls. This spatial distribution of EEG, commonly named in the literature as class B, has been found to be correlated with the visual resting state network. Both vision and proprioception networks provide critical information in mapping the extrapersonal environment. This neurophysiological marker probably unveils an alteration in the postural control mechanism in AIS, suggesting a higher information processing load due to the increased postural demands caused by scoliosis.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"5 ","pages":"339-344"},"PeriodicalIF":5.8,"publicationDate":"2024-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10528670","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140938885","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 : 2024-03-08DOI: 10.1109/OJEMB.2024.3397965
Pragya Gupta;Tamas Heffter;Muhammad Zubair;I-Chow Hsu;E. Clif Burdette;Chris J. Diederich
Purpose: To develop patient-specific 3D models using Finite-Difference Time-Domain (FDTD) simulations and pre-treatment planning tools for the selective thermal ablation of prostate cancer with interstitial ultrasound. This involves the integration with a FDA 510(k) cleared catheter-based ultrasound interstitial applicators and delivery system. Methods: A 3D generalized “prostate” model was developed to generate temperature and thermal dose profiles for different applicator operating parameters and anticipated perfusion ranges. A priori planning, based upon these pre-calculated lethal thermal dose and iso-temperature clouds, was devised for iterative device selection and positioning. Full 3D patient-specific anatomic modeling of actual placement of single or multiple applicators to conformally ablate target regions can be applied, with optional integrated pilot-point temperature-based feedback control and urethral/rectum cooling. These numerical models were verified against previously reported ex-vivo experimental results obtained in soft tissues. Results: For generic prostate tissue, 360 treatment schemes were simulated based on the number of transducers (1-4), applied power (8-20 W/cm2), heating time (5, 7.5, 10 min), and blood perfusion (0, 2.5, 5 kg/m3/s) using forward treatment modelling. Selectable ablation zones ranged from 0.8-3.0 cm and 0.8-5.3 cm in radial and axial directions, respectively. 3D patient-specific thermal treatment modeling for 12 Cases of T2/T3 prostate disease demonstrate applicability of workflow and technique for focal, quadrant and hemi-gland ablation. A temperature threshold (e.g., Tthres = 52 °C) at the treatment margin, emulating placement of invasive temperature sensing, can be applied for pilot-point feedback control to improve conformality of thermal ablation. Also, binary power control (e.g., Treg = 45 °C) can be applied which will regulate the applied power level to maintain the surrounding temperature to a safe limit or maximum threshold until the set heating time. Conclusions: Prostate-specific simulations of interstitial ultrasound applicators were used to generate a library of thermal-dose distributions to visually optimize and set applicator positioning and directivity during a priori treatment planning pre-procedure. Anatomic 3D forward treatment planning in patient-specific models, along with optional temperature-based feedback control, demonstrated single and multi-applicator implant strategies to effectively ablate focal disease while affording protection of normal tissues.
{"title":"Treatment Planning Strategies for Interstitial Ultrasound Ablation of Prostate Cancer","authors":"Pragya Gupta;Tamas Heffter;Muhammad Zubair;I-Chow Hsu;E. Clif Burdette;Chris J. Diederich","doi":"10.1109/OJEMB.2024.3397965","DOIUrl":"10.1109/OJEMB.2024.3397965","url":null,"abstract":"Purpose: To develop patient-specific 3D models using Finite-Difference Time-Domain (FDTD) simulations and pre-treatment planning tools for the selective thermal ablation of prostate cancer with interstitial ultrasound. This involves the integration with a FDA 510(k) cleared catheter-based ultrasound interstitial applicators and delivery system. Methods: A 3D generalized “prostate” model was developed to generate temperature and thermal dose profiles for different applicator operating parameters and anticipated perfusion ranges. A priori planning, based upon these pre-calculated lethal thermal dose and iso-temperature clouds, was devised for iterative device selection and positioning. Full 3D patient-specific anatomic modeling of actual placement of single or multiple applicators to conformally ablate target regions can be applied, with optional integrated pilot-point temperature-based feedback control and urethral/rectum cooling. These numerical models were verified against previously reported ex-vivo experimental results obtained in soft tissues. Results: For generic prostate tissue, 360 treatment schemes were simulated based on the number of transducers (1-4), applied power (8-20 W/cm2), heating time (5, 7.5, 10 min), and blood perfusion (0, 2.5, 5 kg/m3/s) using forward treatment modelling. Selectable ablation zones ranged from 0.8-3.0 cm and 0.8-5.3 cm in radial and axial directions, respectively. 3D patient-specific thermal treatment modeling for 12 Cases of T2/T3 prostate disease demonstrate applicability of workflow and technique for focal, quadrant and hemi-gland ablation. A temperature threshold (e.g., Tthres = 52 °C) at the treatment margin, emulating placement of invasive temperature sensing, can be applied for pilot-point feedback control to improve conformality of thermal ablation. Also, binary power control (e.g., Treg = 45 °C) can be applied which will regulate the applied power level to maintain the surrounding temperature to a safe limit or maximum threshold until the set heating time. Conclusions: Prostate-specific simulations of interstitial ultrasound applicators were used to generate a library of thermal-dose distributions to visually optimize and set applicator positioning and directivity during a priori treatment planning pre-procedure. Anatomic 3D forward treatment planning in patient-specific models, along with optional temperature-based feedback control, demonstrated single and multi-applicator implant strategies to effectively ablate focal disease while affording protection of normal tissues.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"5 ","pages":"362-375"},"PeriodicalIF":5.8,"publicationDate":"2024-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10522889","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140942326","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: The network representation is becoming increasingly popular for the description of cardiovascular interactions based on the analysis of multiple simultaneously collected variables. However, the traditional methods to assess network links based on pairwise interaction measures cannot reveal high-order effects involving more than two nodes, and are not appropriate to infer the underlying network topology. To address these limitations, here we introduce a framework which combines the assessment of high-order interactions with statistical inference for the characterization of the functional links sustaining physiological networks. Methods: The framework develops information-theoretic measures quantifying how two nodes interact in a redundant or synergistic way with the rest of the network, and employs these measures for reconstructing the functional structure of the network. The measures are implemented for both static and dynamic networks mapped respectively by random variables and random processes using plug-in and model-based entropy estimators. Results: The validation on theoretical and numerical simulated networks documents the ability of the framework to represent high-order interactions as networks and to detect statistical structures associated to cascade, common drive and common target effects. The application to cardiovascular networks mapped by the beat-to-beat variability of heart rate, respiration, arterial pressure, cardiac output and vascular resistance allowed noninvasive characterization of several mechanisms of cardiovascular control operating in resting state and during orthostatic stress. Conclusion: Our approach brings to new comprehensive assessment of physiological interactions and complements existing strategies for the classification of pathophysiological states.
{"title":"Assessing High-Order Links in Cardiovascular and Respiratory Networks via Static and Dynamic Information Measures","authors":"Gorana Mijatovic;Laura Sparacino;Yuri Antonacci;Michal Javorka;Daniele Marinazzo;Sebastiano Stramaglia;Luca Faes","doi":"10.1109/OJEMB.2024.3374956","DOIUrl":"10.1109/OJEMB.2024.3374956","url":null,"abstract":"<italic>Goal:</i>\u0000 The network representation is becoming increasingly popular for the description of cardiovascular interactions based on the analysis of multiple simultaneously collected variables. However, the traditional methods to assess network links based on pairwise interaction measures cannot reveal high-order effects involving more than two nodes, and are not appropriate to infer the underlying network topology. To address these limitations, here we introduce a framework which combines the assessment of high-order interactions with statistical inference for the characterization of the functional links sustaining physiological networks. \u0000<italic>Methods:</i>\u0000 The framework develops information-theoretic measures quantifying how two nodes interact in a redundant or synergistic way with the rest of the network, and employs these measures for reconstructing the functional structure of the network. The measures are implemented for both static and dynamic networks mapped respectively by random variables and random processes using plug-in and model-based entropy estimators. \u0000<italic>Results:</i>\u0000 The validation on theoretical and numerical simulated networks documents the ability of the framework to represent high-order interactions as networks and to detect statistical structures associated to cascade, common drive and common target effects. The application to cardiovascular networks mapped by the beat-to-beat variability of heart rate, respiration, arterial pressure, cardiac output and vascular resistance allowed noninvasive characterization of several mechanisms of cardiovascular control operating in resting state and during orthostatic stress. \u0000<italic>Conclusion:</i>\u0000 Our approach brings to new comprehensive assessment of physiological interactions and complements existing strategies for the classification of pathophysiological states.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"5 ","pages":"846-858"},"PeriodicalIF":2.7,"publicationDate":"2024-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10463144","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140074941","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 : 2024-03-08DOI: 10.1109/OJEMB.2024.3398444
Sicong Huang;Roozbeh Jafari;Bobak J. Mortazavi
Goal: To establish Pulse2AI as a reproducible data preprocessing framework for pulsatile signals that generate high-quality machine-learning-ready datasets from raw wearable recordings. Methods: We proposed an end-to-end data preprocessing framework that adapts multiple pulsatile signal modalities and generates machine-learning-ready datasets agnostic to downstream medical tasks. Results: a dataset preprocessed by Pulse2AI improved systolic blood pressure estimation by 29.58%, from 11.41 to 8.03 mmHg in root-mean-square-error (RMSE) and its diastolic counterpart by 26.01%, from 7.93 to 5.87 mmHg in RMSE. For respiration rate (RR) estimation, Pulse2AI boosted performance by 19.69%, from 1.47 to 1.18 breaths per minute (BrPM) in mean-absolute-error (MAE). Conclusion: Pulse2AI turns pulsatile signals into machine learning (ML) ready datasets for arbitrary remote health monitoring tasks. We tested Pulse2AI on multiple pulsatile modalities and demonstrated its efficacy in two medical applications. This work bridges valuable assets in remote sensing and internet of medical things to ML-ready datasets for medical modeling.
{"title":"Pulse2AI: An Adaptive Framework to Standardize and Process Pulsatile Wearable Sensor Data for Clinical Applications","authors":"Sicong Huang;Roozbeh Jafari;Bobak J. Mortazavi","doi":"10.1109/OJEMB.2024.3398444","DOIUrl":"10.1109/OJEMB.2024.3398444","url":null,"abstract":"<italic>Goal:</i>\u0000 To establish Pulse2AI as a reproducible data preprocessing framework for pulsatile signals that generate high-quality machine-learning-ready datasets from raw wearable recordings. \u0000<italic>Methods:</i>\u0000 We proposed an end-to-end data preprocessing framework that adapts multiple pulsatile signal modalities and generates machine-learning-ready datasets agnostic to downstream medical tasks. \u0000<italic>Results:</i>\u0000 a dataset preprocessed by Pulse2AI improved systolic blood pressure estimation by 29.58%, from 11.41 to 8.03 mmHg in root-mean-square-error (RMSE) and its diastolic counterpart by 26.01%, from 7.93 to 5.87 mmHg in RMSE. For respiration rate (RR) estimation, Pulse2AI boosted performance by 19.69%, from 1.47 to 1.18 breaths per minute (BrPM) in mean-absolute-error (MAE). \u0000<italic>Conclusion:</i>\u0000 Pulse2AI turns pulsatile signals into machine learning (ML) ready datasets for arbitrary remote health monitoring tasks. We tested Pulse2AI on multiple pulsatile modalities and demonstrated its efficacy in two medical applications. This work bridges valuable assets in remote sensing and internet of medical things to ML-ready datasets for medical modeling.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"5 ","pages":"330-338"},"PeriodicalIF":5.8,"publicationDate":"2024-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10522883","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140927331","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Two-Dimensional Array Sinusoidal Waves Conductor for Biometric Measurements","authors":"Homare Yamada, Risa Kawai, Risako Niwa, Kosuke Tsukada","doi":"10.1109/ojemb.2024.3374975","DOIUrl":"https://doi.org/10.1109/ojemb.2024.3374975","url":null,"abstract":"","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"28 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2024-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140074618","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Goal: REM Sleep Behavior Disorder (RBD) is a REM parasomnia that is associated to high risk of developing α-synucleinopathies, as Parkinson's disease (PD) or dementia with Lewy bodies, over time. This study aims at investigating the presence of autonomic dysfunctions in RBD subjects, with and without PD, by assessing their sleep structure and autonomous nervous system activity along the different sleep stages. Methods: To this aim, an innovative framework combining a sleep transition model, by Markov chains, with an instantaneous assessment of autonomic state dynamics by statistical modeling of heart rate variability (HRV) dynamics through a point-process approach, was introduced. Results: In general, RBD groups showed lower HRV than controls across all sleep stages, as well as higher probabilities of transitioning towards lighter sleep stages. Subjects also affected by PD present an even lower HRV, but better sleep continuity. Conclusions: RBD patients suffer from sleep fragmentation and overall autonomic dysfunction, mainly due to lower autonomic activation across all sleep stages. Coexistence of PD seems to improve sleep quality, possibly due to a sleep-related relief of their symptoms.
{"title":"Characterization of Sleep Structure and Autonomic Dysfunction in REM Sleep Behavior Disorder","authors":"Nicla Mandas;Maximiliano Mollura;Giulia Baldazzi;Parisa Sattar;Maria Mura;Elisa Casaglia;Michela Figorilli;Laura Giorgetti;Pietro Mattioli;Francesco Calizzano;Francesco Famà;Dario Arnaldi;Monica Puligheddu;Danilo Pani;Riccardo Barbieri","doi":"10.1109/OJEMB.2024.3397550","DOIUrl":"10.1109/OJEMB.2024.3397550","url":null,"abstract":"<italic>Goal:</i>\u0000 REM Sleep Behavior Disorder (RBD) is a REM parasomnia that is associated to high risk of developing α-synucleinopathies, as Parkinson's disease (PD) or dementia with Lewy bodies, over time. This study aims at investigating the presence of autonomic dysfunctions in RBD subjects, with and without PD, by assessing their sleep structure and autonomous nervous system activity along the different sleep stages. \u0000<italic>Methods:</i>\u0000 To this aim, an innovative framework combining a sleep transition model, by Markov chains, with an instantaneous assessment of autonomic state dynamics by statistical modeling of heart rate variability (HRV) dynamics through a point-process approach, was introduced. \u0000<italic>Results:</i>\u0000 In general, RBD groups showed lower HRV than controls across all sleep stages, as well as higher probabilities of transitioning towards lighter sleep stages. Subjects also affected by PD present an even lower HRV, but better sleep continuity. \u0000<italic>Conclusions:</i>\u0000 RBD patients suffer from sleep fragmentation and overall autonomic dysfunction, mainly due to lower autonomic activation across all sleep stages. Coexistence of PD seems to improve sleep quality, possibly due to a sleep-related relief of their symptoms.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"5 ","pages":"859-866"},"PeriodicalIF":2.7,"publicationDate":"2024-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10521879","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140927472","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 : 2024-03-07DOI: 10.1109/OJEMB.2024.3397623
David Jozef Hresko;Peter Drotar
Goal: In recent years, deep neural networks have consistently outperformed previously proposed methods in the domain of medical segmentation. However, due to their nature, these networks often struggle to delineate desired structures in data that fall outside their training distribution. The goal of this study is to address the challenges associated with domain generalization in CT segmentation by introducing a novel method called BucketAugment for deep neural networks. Methods: BucketAugment leverages principles from the Q-learning algorithm and employs validation loss to search for an optimal policy within a search space comprised of distributed stacks of 3D volumetric augmentations, termed ‘buckets.’ These buckets have tunable parameters and can be seamlessly integrated into existing neural network architectures, offering flexibility for customization. Results: In our experiments, we focus on segmenting kidney and liver structures across three distinct medical datasets, each containing CT scans of the abdominal region collected from various clinical institutions and scanner vendors. Our results indicate that BucketAugment significantly enhances domain generalization across diverse medical datasets, requiring only minimal modifications to existing network architectures. Conclusions: The introduction of BucketAugment provides a promising solution to the challenges of domain generalization in CT segmentation. By leveraging Q-learning principles and distributed stacks of 3D augmentations, this method improves the performance of deep neural networks on medical segmentation tasks, demonstrating its potential to enhance the applicability of such models across different datasets and clinical scenarios.
{"title":"BucketAugment: Reinforced Domain Generalisation in Abdominal CT Segmentation","authors":"David Jozef Hresko;Peter Drotar","doi":"10.1109/OJEMB.2024.3397623","DOIUrl":"10.1109/OJEMB.2024.3397623","url":null,"abstract":"<italic>Goal:</i>\u0000 In recent years, deep neural networks have consistently outperformed previously proposed methods in the domain of medical segmentation. However, due to their nature, these networks often struggle to delineate desired structures in data that fall outside their training distribution. The goal of this study is to address the challenges associated with domain generalization in CT segmentation by introducing a novel method called BucketAugment for deep neural networks. \u0000<italic>Methods:</i>\u0000 BucketAugment leverages principles from the Q-learning algorithm and employs validation loss to search for an optimal policy within a search space comprised of distributed stacks of 3D volumetric augmentations, termed ‘buckets.’ These buckets have tunable parameters and can be seamlessly integrated into existing neural network architectures, offering flexibility for customization. \u0000<italic>Results:</i>\u0000 In our experiments, we focus on segmenting kidney and liver structures across three distinct medical datasets, each containing CT scans of the abdominal region collected from various clinical institutions and scanner vendors. Our results indicate that BucketAugment significantly enhances domain generalization across diverse medical datasets, requiring only minimal modifications to existing network architectures. \u0000<italic>Conclusions:</i>\u0000 The introduction of BucketAugment provides a promising solution to the challenges of domain generalization in CT segmentation. By leveraging Q-learning principles and distributed stacks of 3D augmentations, this method improves the performance of deep neural networks on medical segmentation tasks, demonstrating its potential to enhance the applicability of such models across different datasets and clinical scenarios.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"5 ","pages":"353-361"},"PeriodicalIF":5.8,"publicationDate":"2024-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10521822","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140942154","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 : 2024-03-06DOI: 10.1109/OJEMB.2024.3397208
Daniel Krauss;Lukas Engel;Tabea Ott;Johanna Bräunig;Robert Richer;Markus Gambietz;Nils Albrecht;Eva M. Hille;Ingrid Ullmann;Matthias Braun;Peter Dabrock;Alexander Kölpin;Anne D. Koelewijn;Bjoern M. Eskofier;Martin Vossiek
Radio detection and ranging-based (radar) sensing offers unique opportunities for biomedical monitoring and can help overcome the limitations of currently established solutions. Due to its contactless and unobtrusive measurement principle, it can facilitate the longitudinal recording of human physiology and can help to bridge the gap from laboratory to real-world assessments. However, radar sensors typically yield complex and multidimensional data that are hard to interpret without domain expertise. Machine learning (ML) algorithms can be trained to extract meaningful information from radar data for medical experts, enhancing not only diagnostic capabilities but also contributing to advancements in disease prevention and treatment. However, until now, the two aspects of radar-based data acquisition and ML-based data processing have mostly been addressed individually and not as part of a holistic and end-to-end data analysis pipeline. For this reason, we present a tutorial on radar-based ML applications for biomedical monitoring that equally emphasizes both dimensions. We highlight the fundamentals of radar and ML theory, data acquisition and representation and outline categories of clinical relevance. Since the contactless and unobtrusive nature of radar-based sensing also raises novel ethical concerns regarding biomedical monitoring, we additionally present a discussion that carefully addresses the ethical aspects of this novel technology, particularly regarding data privacy, ownership, and potential biases in ML algorithms.
基于无线电探测和测距（雷达）的传感技术为生物医学监测提供了独特的机会，有助于克服现有解决方案的局限性。由于其非接触式和非侵入式测量原理，它可以促进对人体生理的纵向记录，并有助于缩小从实验室到真实世界评估之间的差距。然而，雷达传感器通常会产生复杂的多维数据，如果没有相关领域的专业知识，很难对其进行解读。通过训练机器学习（ML）算法，医学专家可以从雷达数据中提取有意义的信息，不仅能提高诊断能力，还能促进疾病预防和治疗的进步。然而，迄今为止，基于雷达的数据采集和基于 ML 的数据处理这两个方面大多是单独处理的，而不是作为整体和端到端数据分析管道的一部分。因此，我们将介绍基于雷达的 ML 应用于生物医学监测的教程，同样强调这两个方面。我们重点介绍了雷达和 ML 理论、数据采集和表示的基本原理，并概述了与临床相关的类别。由于基于雷达的传感具有非接触和非侵入性的特点，这也引发了有关生物医学监测的新的伦理问题，因此我们还进行了讨论，仔细探讨了这项新技术的伦理问题，特别是数据隐私、所有权和 ML 算法中的潜在偏差。
{"title":"A Review and Tutorial on Machine Learning-Enabled Radar-Based Biomedical Monitoring","authors":"Daniel Krauss;Lukas Engel;Tabea Ott;Johanna Bräunig;Robert Richer;Markus Gambietz;Nils Albrecht;Eva M. Hille;Ingrid Ullmann;Matthias Braun;Peter Dabrock;Alexander Kölpin;Anne D. Koelewijn;Bjoern M. Eskofier;Martin Vossiek","doi":"10.1109/OJEMB.2024.3397208","DOIUrl":"10.1109/OJEMB.2024.3397208","url":null,"abstract":"Radio detection and ranging-based (radar) sensing offers unique opportunities for biomedical monitoring and can help overcome the limitations of currently established solutions. Due to its contactless and unobtrusive measurement principle, it can facilitate the longitudinal recording of human physiology and can help to bridge the gap from laboratory to real-world assessments. However, radar sensors typically yield complex and multidimensional data that are hard to interpret without domain expertise. Machine learning (ML) algorithms can be trained to extract meaningful information from radar data for medical experts, enhancing not only diagnostic capabilities but also contributing to advancements in disease prevention and treatment. However, until now, the two aspects of radar-based data acquisition and ML-based data processing have mostly been addressed individually and not as part of a holistic and end-to-end data analysis pipeline. For this reason, we present a tutorial on radar-based ML applications for biomedical monitoring that equally emphasizes both dimensions. We highlight the fundamentals of radar and ML theory, data acquisition and representation and outline categories of clinical relevance. Since the contactless and unobtrusive nature of radar-based sensing also raises novel ethical concerns regarding biomedical monitoring, we additionally present a discussion that carefully addresses the ethical aspects of this novel technology, particularly regarding data privacy, ownership, and potential biases in ML algorithms.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"5 ","pages":"680-699"},"PeriodicalIF":2.7,"publicationDate":"2024-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10520876","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140886921","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：