Pub Date : 2024-10-15DOI: 10.1109/TBME.2024.3480813
Qiongyan Wang;Hanrong Cheng;Wenjin Wang
Polysomnography (PSG) is the gold standard for sleep staging in clinics, but its skin-contact nature makes it uncomfortable and inconvenient to use for long-term sleep monitoring. As a complementary part of PSG, the video cameras are not utilized to their full potential, only for manual check of simple sleep events, thereby ignoring the potential for physiological and semantic measurement. This leads to a pivotal research question: Can camera be used for sleep staging, and to what extent? We developed a camera-based contactless sleep staging system in the Institute of Respiratory Diseases and created a clinical video dataset of 20 adults. The camera-based feature set, derived from both physiological signals (pulse and breath) and motions all measured from a video, was evaluated for 4-class sleep staging (Wake-REM-Light-Deep). Three optimization strategies were proposed to enhance the sleep staging accuracy: using motion metrics to prune measurement outliers, creating a more personalized model based on the baseline calibration of waking-stage physiological signals, and deriving a specialized feature for REM detection. It achieved the best accuracy of 73.1% (kappa = 0.62, F1-score = 0.74) in the benchmark of five sleep-staging classifiers. Notably, the system exhibited high accuracy in predicting the overall sleep structure and subtle changes between different sleep stages. The study demonstrates that camera-based contactless sleep staging is a new value stream for sleep medicine, which also provides clinical and technical insights for future optimization and implementation.
{"title":"Video-PSG: An Intelligent Contactless Monitoring System for Sleep Staging","authors":"Qiongyan Wang;Hanrong Cheng;Wenjin Wang","doi":"10.1109/TBME.2024.3480813","DOIUrl":"10.1109/TBME.2024.3480813","url":null,"abstract":"Polysomnography (PSG) is the gold standard for sleep staging in clinics, but its skin-contact nature makes it uncomfortable and inconvenient to use for long-term sleep monitoring. As a complementary part of PSG, the video cameras are not utilized to their full potential, only for manual check of simple sleep events, thereby ignoring the potential for physiological and semantic measurement. This leads to a pivotal research question: Can camera be used for sleep staging, and to what extent? We developed a camera-based contactless sleep staging system in the Institute of Respiratory Diseases and created a clinical video dataset of 20 adults. The camera-based feature set, derived from both physiological signals (pulse and breath) and motions all measured from a video, was evaluated for 4-class sleep staging (Wake-REM-Light-Deep). Three optimization strategies were proposed to enhance the sleep staging accuracy: using motion metrics to prune measurement outliers, creating a more personalized model based on the baseline calibration of waking-stage physiological signals, and deriving a specialized feature for REM detection. It achieved the best accuracy of 73.1% (kappa = 0.62, F1-score = 0.74) in the benchmark of five sleep-staging classifiers. Notably, the system exhibited high accuracy in predicting the overall sleep structure and subtle changes between different sleep stages. The study demonstrates that camera-based contactless sleep staging is a new value stream for sleep medicine, which also provides clinical and technical insights for future optimization and implementation.","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"72 3","pages":"965-977"},"PeriodicalIF":4.4,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142464209","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-15DOI: 10.1109/TBME.2024.3479910
Krzysztof Bartnik;Agnieszka Martychowiec;Norbert Kwietniewski;Paulina Musolf;Joanna Niedziółka-Jönsson;Marcin Koba;Mateusz Śmietana
Objective: Endovascular surgery requires accurate measurement of parameters such as pressure, temperature, and biomarkers within vessels for real-time tissue response monitoring and ensuring targeted therapeutic interventions. However, the availability of small tip-based sensors capable of precise application, for example, navigating an aneurysm's lumen, is limited. With their capabilities for real-time analysis, flexibility, and biocompatibility, optical fiber sensors (OFS) hold promise in addressing this need. This proof-of-concept study investigates the feasibility of OFS in endovascular surgery scenarios. Methods: The sensor is based on a single-mode silica fiber with an interferometric forward-facing thin-film tip. The thin-film materials may be tailored for detecting various physical parameters and, when functionalized, also specific analytes. Materials applied in this sensor are thin metal oxides deposited using magnetron sputtering. A full-scale 3D-printed vascular model was employed to simulate endovascular setup. Results: The experiments showed the high mechanical robustness of the approach, i.e., the sensor maintained functionality while being maneuvered through the endovascular model. The forward-facing tip remained intact and worked adequately, ensuring consistent and stable readouts. Moreover, the fiber showed sufficient flexibility, with no significant bending loss observed during simulations. Finally, the performance of the OFS in bovine serum samples was assessed. The sensor performed well in serum, and the results suggest that low-concentration serum may be used to reduce nonspecific surface interactions. Conclusion: Overall, this OFS system offers a promising solution for endovascular surgery and other biomedical applications, allowing for precise and on-the-spot analysis. Significance: Our study pioneers the feasibility of thin-film interferometric label-free OFS with a forward-facing sensitive area for sensing during endovascular procedures.
{"title":"Thin-Film-Based Optical Fiber Interferometric Sensor on the Fiber Tip for Endovascular Surgical Procedures","authors":"Krzysztof Bartnik;Agnieszka Martychowiec;Norbert Kwietniewski;Paulina Musolf;Joanna Niedziółka-Jönsson;Marcin Koba;Mateusz Śmietana","doi":"10.1109/TBME.2024.3479910","DOIUrl":"10.1109/TBME.2024.3479910","url":null,"abstract":"<italic>Objective:</i> Endovascular surgery requires accurate measurement of parameters such as pressure, temperature, and biomarkers within vessels for real-time tissue response monitoring and ensuring targeted therapeutic interventions. However, the availability of small tip-based sensors capable of precise application, for example, navigating an aneurysm's lumen, is limited. With their capabilities for real-time analysis, flexibility, and biocompatibility, optical fiber sensors (OFS) hold promise in addressing this need. This proof-of-concept study investigates the feasibility of OFS in endovascular surgery scenarios. <italic>Methods:</i> The sensor is based on a single-mode silica fiber with an interferometric forward-facing thin-film tip. The thin-film materials may be tailored for detecting various physical parameters and, when functionalized, also specific analytes. Materials applied in this sensor are thin metal oxides deposited using magnetron sputtering. A full-scale 3D-printed vascular model was employed to simulate endovascular setup. <italic>Results:</i> The experiments showed the high mechanical robustness of the approach, i.e., the sensor maintained functionality while being maneuvered through the endovascular model. The forward-facing tip remained intact and worked adequately, ensuring consistent and stable readouts. Moreover, the fiber showed sufficient flexibility, with no significant bending loss observed during simulations. Finally, the performance of the OFS in bovine serum samples was assessed. The sensor performed well in serum, and the results suggest that low-concentration serum may be used to reduce nonspecific surface interactions. <italic>Conclusion:</i> Overall, this OFS system offers a promising solution for endovascular surgery and other biomedical applications, allowing for precise and on-the-spot analysis. <italic>Significance:</i> Our study pioneers the feasibility of thin-film interferometric label-free OFS with a forward-facing sensitive area for sensing during endovascular procedures.","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"72 3","pages":"930-939"},"PeriodicalIF":4.4,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10719676","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142464208","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-14DOI: 10.1109/TBME.2024.3480362
Kathrin Bäumler;Malte Rolf-Pissarczyk;Richard Schussnig;Thomas-Peter Fries;Gabriel Mistelbauer;Martin R. Pfaller;Alison L. Marsden;Dominik Fleischmann;Gerhard A. Holzapfel
Aortic dissection leads to late complications due tochronic degeneration and dilatation of the false lumen. This study examines the interaction between hemodynamics and long-term remodeling of a patient's aortic dissection, tracked from pre-dissection to the chronic phase using CT angiography. Fluid–structure interaction models with tissue prestress, external support, and anisotropic properties were used to analyze hemodynamic markers. Each aortic wall layer had distinct thicknesses and material properties. The boundary conditions were guided by in vitro 4D-flow MRI and the patient's blood pressure. Aortic dilatation was most significant distal to the left subclavian artery, reaching 6 cm in the chronic phase. Simulations quantified the flow jet velocity through the entry tear, which peaked at 185 cm/s in the subacute phase and decreased to 123 to 133 cm/s in the chronic phase, corresponding to an increased entry tear size. Flow jet impingement on the false lumen resulted in a localized pressure increase of 11 and 2 mmHg in the subacute and chronic phases, with wall shear stress reaching 4 Pa. These hemodynamic changes appear to be the main drivers of aortic growth and morphological changes. Despite moderate overall flap movement, in-plane displacement increased from 0.6 to 1.8 mm as disease progressed, which was associated with an overall increase in aortic diameter. Simulations with a significant reduction in flap stiffness during the subacute phase resulted in increased flap motion up to 9.5 mm. Although these results are based on a single patient, they suggest a strong relationship between hemodynamics and aortic growth.
{"title":"Assessment of Aortic Dissection Remodeling With Patient-Specific Fluid–Structure Interaction Models","authors":"Kathrin Bäumler;Malte Rolf-Pissarczyk;Richard Schussnig;Thomas-Peter Fries;Gabriel Mistelbauer;Martin R. Pfaller;Alison L. Marsden;Dominik Fleischmann;Gerhard A. Holzapfel","doi":"10.1109/TBME.2024.3480362","DOIUrl":"10.1109/TBME.2024.3480362","url":null,"abstract":"Aortic dissection leads to late complications due tochronic degeneration and dilatation of the false lumen. This study examines the interaction between hemodynamics and long-term remodeling of a patient's aortic dissection, tracked from pre-dissection to the chronic phase using CT angiography. Fluid–structure interaction models with tissue prestress, external support, and anisotropic properties were used to analyze hemodynamic markers. Each aortic wall layer had distinct thicknesses and material properties. The boundary conditions were guided by <italic>in vitro</i> 4D-flow MRI and the patient's blood pressure. Aortic dilatation was most significant distal to the left subclavian artery, reaching 6 cm in the chronic phase. Simulations quantified the flow jet velocity through the entry tear, which peaked at 185 cm/s in the subacute phase and decreased to 123 to 133 cm/s in the chronic phase, corresponding to an increased entry tear size. Flow jet impingement on the false lumen resulted in a localized pressure increase of 11 and 2 mmHg in the subacute and chronic phases, with wall shear stress reaching 4 Pa. These hemodynamic changes appear to be the main drivers of aortic growth and morphological changes. Despite moderate overall flap movement, in-plane displacement increased from 0.6 to 1.8 mm as disease progressed, which was associated with an overall increase in aortic diameter. Simulations with a significant reduction in flap stiffness during the subacute phase resulted in increased flap motion up to 9.5 mm. Although these results are based on a single patient, they suggest a strong relationship between hemodynamics and aortic growth.","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"72 3","pages":"953-964"},"PeriodicalIF":4.4,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10716513","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142464203","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-14DOI: 10.1109/TBME.2024.3479938
Angelika S. Thalmayer;Lucas Fink;Georg Fischer
Introduction: Adjustable magnetic fields are essential for precisely steering drug-loaded magnetic nanoparticles in cancer therapy. Since electromagnets require high currents to achieve a strong magnetic force, this paper presents a new approach combining electromagnets and permanent magnets. Objective: The basic idea of the hybrid array is to use the strong and low-cost magnetic field of permanent magnets and superimpose them with the field of electromagnets via a Halbach arrangement. This results in a constructive and destructive superposition of the magnetic field, which can easily be reversed by the applied current's direction. Moreover, the current's magnitude can be reduced dramatically to 2 A, as the primary magnetic flux comes from the permanent magnets. Methods: To the authors' knowledge, this is the first paper proposing a magnetic hybrid array for steering magnetic nanoparticles in a velocity flow. The array was validated in simulations using COMSOL Multiphysics and measurements in a tube flow system. In contrast to state-of-the-art publications, the particle distribution was determined quantitatively. Results: In this proof of concept, the simulation and measurement results fit well. It was demonstrated that the magnetic force is adjustable via the current and that the magnetic field of permanent magnets can be eliminated by superimposing the field of electromagnets, also indicated by the particle distribution. Furthermore, gravitation has a significant influence on particle distribution. Significance: The proposed system combines the advantages of permanent magnets and electromagnets. Hence, the induced heat that damages tissue is decreased, which is crucial for bringing the setup into clinical treatments.
{"title":"Experimental and Simulative Characterization of a Hybrid Magnetic Array for Steering Superparamagnetic Nanoparticles in Drug Targeting","authors":"Angelika S. Thalmayer;Lucas Fink;Georg Fischer","doi":"10.1109/TBME.2024.3479938","DOIUrl":"10.1109/TBME.2024.3479938","url":null,"abstract":"<italic>Introduction:</i> Adjustable magnetic fields are essential for precisely steering drug-loaded magnetic nanoparticles in cancer therapy. Since electromagnets require high currents to achieve a strong magnetic force, this paper presents a new approach combining electromagnets and permanent magnets. <italic>Objective:</i> The basic idea of the hybrid array is to use the strong and low-cost magnetic field of permanent magnets and superimpose them with the field of electromagnets via a Halbach arrangement. This results in a constructive and destructive superposition of the magnetic field, which can easily be reversed by the applied current's direction. Moreover, the current's magnitude can be reduced dramatically to 2 A, as the primary magnetic flux comes from the permanent magnets. <italic>Methods:</i> To the authors' knowledge, this is the first paper proposing a magnetic hybrid array for steering magnetic nanoparticles in a velocity flow. The array was validated in simulations using COMSOL Multiphysics and measurements in a tube flow system. In contrast to state-of-the-art publications, the particle distribution was determined quantitatively. <italic>Results:</i> In this proof of concept, the simulation and measurement results fit well. It was demonstrated that the magnetic force is adjustable via the current and that the magnetic field of permanent magnets can be eliminated by superimposing the field of electromagnets, also indicated by the particle distribution. Furthermore, gravitation has a significant influence on particle distribution. <italic>Significance:</i> The proposed system combines the advantages of permanent magnets and electromagnets. Hence, the induced heat that damages tissue is decreased, which is crucial for bringing the setup into clinical treatments.","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"72 3","pages":"940-952"},"PeriodicalIF":4.4,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142464205","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Optical coherence tomography (OCT) is being widely applied in clinical studies to investigate insight into the retina under the retinal pigment epithelium. Optical coherence tomography angiography (OCTA) is one of the functional extensions of OCT, for visualizing retinal circulation. Due to obstruction of light propagation, such as vitreous floaters or pupil boundaries, OCTA remains challenged by shadow artifacts that can disrupt volumetric data. Detecting and removing these shadow artifacts are crucial when quantifying indicators of retinal disease progression. We simplified an optical attenuation model of shadow formation in OCTA to a linear illumination transformation. And learn its parameters using an adversarial neural network. Our framework also consists of a sub-network for shadows automatic detection. We experimented our method on 28 OCTA images of normal eyes and compared the non-perfusion area (NPA), an index to measure retinal vascularity. The results showed that the NPA adjusted to a reasonable range after image processing using our method. Furthermore, we tested 150 OCTA images of synthesis artifacts, and the mean absolute error(MAE) values reached 0.83 after shadow removal.
{"title":"Physics-Based Optical Coherence Tomography Angiography (OCTA) Image Correction for Shadow Compensation","authors":"Guangxu Li;Kang Wang;Yining Dai;Dongping Zheng;Kailu Wang;Lizhen Zhang;Tohru Kamiya","doi":"10.1109/TBME.2024.3478384","DOIUrl":"10.1109/TBME.2024.3478384","url":null,"abstract":"Optical coherence tomography (OCT) is being widely applied in clinical studies to investigate insight into the retina under the retinal pigment epithelium. Optical coherence tomography angiography (OCTA) is one of the functional extensions of OCT, for visualizing retinal circulation. Due to obstruction of light propagation, such as vitreous floaters or pupil boundaries, OCTA remains challenged by shadow artifacts that can disrupt volumetric data. Detecting and removing these shadow artifacts are crucial when quantifying indicators of retinal disease progression. We simplified an optical attenuation model of shadow formation in OCTA to a linear illumination transformation. And learn its parameters using an adversarial neural network. Our framework also consists of a sub-network for shadows automatic detection. We experimented our method on 28 OCTA images of normal eyes and compared the non-perfusion area (NPA), an index to measure retinal vascularity. The results showed that the NPA adjusted to a reasonable range after image processing using our method. Furthermore, we tested 150 OCTA images of synthesis artifacts, and the mean absolute error(MAE) values reached 0.83 after shadow removal.","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"72 3","pages":"891-898"},"PeriodicalIF":4.4,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142406373","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-11DOI: 10.1109/TBME.2024.3479232
Yuwen Ruan;Xiang Chen;Xu Zhang
Objective: Myoelectric control technology has important application value in rehabilitation medicine, prosthesis control, human-computer interaction (HCI) and other fields. However, the user dependence of electromyography (EMG) pattern recognition is one of the key problems hindering the implementation of robust myoelectric control applications. Aimed at solving the user dependence problem, this paper proposed a novel instruction gesture set determination scheme for EMG pattern recognition in user-independent mode. Methods: The scheme uses T-distributed stochastic neighbor embedding (T-SNE) dimensionality reduction to analyze high-dimensional surface EMG data from multiple users and gestures. This process can identify gesture combinations with minimal individual differences and high separability. Results: The proposed scheme was validated using two large-scale EMG gesture databases with different acquisition devices, subjects, and gestures. Optimal and inferior gesture sets of varying sizes were identified. In recognition experiments conducted in both user-independent and electrode-offset modes, the optimal gesture sets demonstrated significantly higher recognition accuracies compared to the inferior sets, with improvements ranging from 12.57% to 36.92%. Conclusion: The results demonstrated that the separability of the obtained optimal gesture sets was significantly superior to that of the inferior sets, confirming the effectiveness of the proposed scheme in reducing user dependence in EMG pattern recognition. Significance: The study has certain application value to promote the development of myoelectric control technology. Specifically, the scheme proposed can be used to determine instruction gesture sets with low user dependence and high separability for myoelectric control applications.
目的：肌电控制技术在康复医学、假肢控制、人机交互（HCI）等领域具有重要的应用价值。然而，肌电图（EMG）模式识别的用户依赖性是阻碍实现鲁棒性肌电控制应用的关键问题之一。为了解决用户依赖性问题，本文提出了一种新颖的指令手势集确定方案，用于用户无关模式下的肌电图模式识别：方法：该方案使用 T 分布随机邻域嵌入（T-SNE）降维技术分析来自多个用户和手势的高维表面肌电图数据。这一过程可以识别出个体差异最小、分离度高的手势组合：使用两个大型 EMG 手势数据库对所提出的方案进行了验证，这两个数据库具有不同的采集设备、研究对象和手势。确定了不同大小的最佳和次佳手势集。在用户独立模式和电极偏移模式下进行的识别实验中，最佳手势集的识别准确率明显高于劣质手势集，提高了 12.57% 至 36.92%：结论：研究结果表明，获得的最优手势集的可分离性明显优于劣质手势集，证实了所提出的方案在肌电模式识别中减少用户依赖性的有效性：研究对促进肌电控制技术的发展具有一定的应用价值。意义：该研究对促进肌电控制技术的发展具有一定的应用价值。具体而言，所提出的方案可用于确定用户依赖性低、可分离性高的指令手势集，以用于肌电控制应用。
{"title":"A Novel Instruction Gesture Set Determination Scheme for Robust Myoelectric Control Applications","authors":"Yuwen Ruan;Xiang Chen;Xu Zhang","doi":"10.1109/TBME.2024.3479232","DOIUrl":"10.1109/TBME.2024.3479232","url":null,"abstract":"<italic>Objective</i>: Myoelectric control technology has important application value in rehabilitation medicine, prosthesis control, human-computer interaction (HCI) and other fields. However, the user dependence of electromyography (EMG) pattern recognition is one of the key problems hindering the implementation of robust myoelectric control applications. Aimed at solving the user dependence problem, this paper proposed a novel instruction gesture set determination scheme for EMG pattern recognition in user-independent mode. <italic>Methods:</i> The scheme uses T-distributed stochastic neighbor embedding (T-SNE) dimensionality reduction to analyze high-dimensional surface EMG data from multiple users and gestures. This process can identify gesture combinations with minimal individual differences and high separability. <italic>Results:</i> The proposed scheme was validated using two large-scale EMG gesture databases with different acquisition devices, subjects, and gestures. Optimal and inferior gesture sets of varying sizes were identified. In recognition experiments conducted in both user-independent and electrode-offset modes, the optimal gesture sets demonstrated significantly higher recognition accuracies compared to the inferior sets, with improvements ranging from 12.57% to 36.92%. <italic>Conclusion:</i> The results demonstrated that the separability of the obtained optimal gesture sets was significantly superior to that of the inferior sets, confirming the effectiveness of the proposed scheme in reducing user dependence in EMG pattern recognition. <italic>Significance:</i> The study has certain application value to promote the development of myoelectric control technology. Specifically, the scheme proposed can be used to determine instruction gesture sets with low user dependence and high separability for myoelectric control applications.","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"72 3","pages":"909-920"},"PeriodicalIF":4.4,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142406372","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-10DOI: 10.1109/TBME.2024.3477708
Lexiu Xu;Yifang Li;Yuan Liu;Qinzhen Shi;Wenyu Xing;Tao Jiang;Gaobo Zhang;Ying Li;Dean Ta
Classic ultrasound bone imaging modalities usually demand either a prior knowledge or an advanced estimation on speed of sound (SoS), which not only renders to a burdensome imaging process but also supplies a limited resolution. To overcome these drawbacks, this article proposed a frequency-domain full-waveform inversion (FDFWI) modality using phased array tomography for high-accuracy cortical bone imaging. A transmission scenario of ultrasound wave in 2-D space was presented in the frequency domain to simulate the forward wavefield propagation. Iterations in the inversion process were performed by matching the simulation wavefield to the experimental one from low to high discrete frequency points. Moreover, the association between the maximum initial frequency and the initial SoS model was explored to prevent the occurrence of cycle-skipping phenomenon, which could lead to the outcomes being trapped in local minima. The feasibility and effectiveness of the proposed imaging scheme were testified by simulation, phantom, and ex-vivo studies, with mean relative errors of cortical part being 3.18%, 8.71%, and 9.36%, respectively. It is verified that the proposed FDFWI method is an effective way for parametric imaging of cortical bone without any prior knowledge of sound speed.
传统的超声骨成像模式通常需要先验知识或先进的声速（SoS）估计，这不仅造成成像过程繁琐，而且分辨率有限。为了克服这些缺点，本文提出了一种利用相控阵层析成像技术进行高精度皮质骨成像的频域全波形反转（FDFWI）模式。在频域中提出了超声波在二维空间中的传播情况，以模拟前向波场传播。反演过程中的迭代是通过将模拟波场与实验波场从低频点到高频点进行离散匹配。此外，还探讨了最大初始频率与初始 SoS 模型之间的关联，以防止出现周期跳跃现象，导致结果陷入局部极小值。模拟、模型和体外研究证明了拟议成像方案的可行性和有效性，皮质部分的平均相对误差分别为 3.18%、8.71% 和 9.36%。验证了所提出的 FDFWI 方法是在不预先了解声速的情况下对骨皮质进行参数成像的有效方法。
{"title":"Full-Waveform Inversion Imaging of Cortical Bone Using Phased Array Tomography","authors":"Lexiu Xu;Yifang Li;Yuan Liu;Qinzhen Shi;Wenyu Xing;Tao Jiang;Gaobo Zhang;Ying Li;Dean Ta","doi":"10.1109/TBME.2024.3477708","DOIUrl":"10.1109/TBME.2024.3477708","url":null,"abstract":"Classic ultrasound bone imaging modalities usually demand either a prior knowledge or an advanced estimation on speed of sound (SoS), which not only renders to a burdensome imaging process but also supplies a limited resolution. To overcome these drawbacks, this article proposed a frequency-domain full-waveform inversion (FDFWI) modality using phased array tomography for high-accuracy cortical bone imaging. A transmission scenario of ultrasound wave in 2-D space was presented in the frequency domain to simulate the forward wavefield propagation. Iterations in the inversion process were performed by matching the simulation wavefield to the experimental one from low to high discrete frequency points. Moreover, the association between the maximum initial frequency and the initial SoS model was explored to prevent the occurrence of cycle-skipping phenomenon, which could lead to the outcomes being trapped in local minima. The feasibility and effectiveness of the proposed imaging scheme were testified by simulation, phantom, and <italic>ex-vivo</i> studies, with mean relative errors of cortical part being 3.18%, 8.71%, and 9.36%, respectively. It is verified that the proposed FDFWI method is an effective way for parametric imaging of cortical bone without any prior knowledge of sound speed.","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"72 3","pages":"878-890"},"PeriodicalIF":4.4,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142400201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Objective: Develop a multi-functional imaging system that combines 1.7 µm optical coherence tomography/angiography (OCT/OCTA) to accurately interrogate Hereditary Hemorrhagic Telangiectasia (HHT) skin lesions. Methods: The study involved imaging HHT skin lesions on five subjects including lips, hands, and chest. We assessed the attributes of both HHT lesions and the healthy vasculature around them in these individuals, employing quantifiable measures such as vascular density and diameter. Additionally, we performed scans on an HHT patient who had undergone anti-angiogenic therapy, allowing us to observe changes in vasculature before and after treatment. Results: The results from this pilot study demonstrate the feasibility of evaluating the HHT lesion using this novel methodology and suggest the potential of OCTA to non-invasively track HHT lesions over time. The average percentage change in density between HHT patients’ lesions and control was 37%. The percentage increase in vessel diameter between lesion and control vessels in HHT patients was 23.21%. Conclusion: In this study, we demonstrated that OCTA, as a functional extension of OCT, can non-invasively scan HHT lesions in vivo. We scanned five subjects with HHT lesions in various areas (lip, ear, finger, and palm) and quantified vascular density and diameter in both the lesions and adjacent healthy tissue. This non-invasive method will permit a more comprehensive examination of HHT lesions. Significance: This method of non-invasive imaging could offer new insights into the physiology, management, and therapeutics of HHT-associated lesion development and bleeding.
{"title":"1.7-micron Optical Coherence Tomography Angiography for Diagnosis and Monitoring of Hereditary Hemorrhagic Telangiectasia - A Pilot Study","authors":"Raksha Sreeramachandra Murthy;Rachel Elsanadi;John Soliman;Yan Li;Li-Dek Chou;Dennis Sprecher;Kristen M. Kelly;Zhongping Chen","doi":"10.1109/TBME.2024.3473871","DOIUrl":"10.1109/TBME.2024.3473871","url":null,"abstract":"<italic>Objective:</i> Develop a multi-functional imaging system that combines 1.7 µm optical coherence tomography/angiography (OCT/OCTA) to accurately interrogate Hereditary Hemorrhagic Telangiectasia (HHT) skin lesions. <italic>Methods:</i> The study involved imaging HHT skin lesions on five subjects including lips, hands, and chest. We assessed the attributes of both HHT lesions and the healthy vasculature around them in these individuals, employing quantifiable measures such as vascular density and diameter. Additionally, we performed scans on an HHT patient who had undergone anti-angiogenic therapy, allowing us to observe changes in vasculature before and after treatment. <italic>Results:</i> The results from this pilot study demonstrate the feasibility of evaluating the HHT lesion using this novel methodology and suggest the potential of OCTA to non-invasively track HHT lesions over time. The average percentage change in density between HHT patients’ lesions and control was 37%. The percentage increase in vessel diameter between lesion and control vessels in HHT patients was 23.21%. <italic>Conclusion</i>: In this study, we demonstrated that OCTA, as a functional extension of OCT, can non-invasively scan HHT lesions in vivo. We scanned five subjects with HHT lesions in various areas (lip, ear, finger, and palm) and quantified vascular density and diameter in both the lesions and adjacent healthy tissue. This non-invasive method will permit a more comprehensive examination of HHT lesions. <italic>Significance:</i> This method of non-invasive imaging could offer new insights into the physiology, management, and therapeutics of HHT-associated lesion development and bleeding.","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"72 2","pages":"803-809"},"PeriodicalIF":4.4,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142400200","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Accurate extraction of heart rate from photoplethysmography (PPG) signals remains challenging due to motion artifacts and signal degradation. Although deep learning methods trained as a data-driven inference problem offer promising solutions, they often underutilize existing knowledge from the medical and signal processing community. In this paper, we address three shortcomings of deep learning models: motion artifact removal, degradation assessment, and physiologically plausible analysis of the PPG signal. We propose KID-PPG, a knowledge-informed deep learning model that integrates expert knowledge through adaptive linear filtering, deep probabilistic inference, and data augmentation. We evaluate KID-PPG on the PPGDalia dataset, achieving an average mean absolute error of 2.85 beats per minute, surpassing existing reproducible methods. Our results demonstrate a significant performance improvement in heart rate tracking through the incorporation of prior knowledge into deep learning models. This approach shows promise in enhancing various biomedical applications by incorporating existing expert knowledge in deep learning models.
{"title":"KID-PPG: Knowledge Informed Deep Learning for Extracting Heart Rate From a Smartwatch","authors":"Christodoulos Kechris;Jonathan Dan;Jose Miranda;David Atienza","doi":"10.1109/TBME.2024.3477275","DOIUrl":"10.1109/TBME.2024.3477275","url":null,"abstract":"Accurate extraction of heart rate from photoplethysmography (PPG) signals remains challenging due to motion artifacts and signal degradation. Although deep learning methods trained as a data-driven inference problem offer promising solutions, they often underutilize existing knowledge from the medical and signal processing community. In this paper, we address three shortcomings of deep learning models: motion artifact removal, degradation assessment, and physiologically plausible analysis of the PPG signal. We propose KID-PPG, a knowledge-informed deep learning model that integrates expert knowledge through adaptive linear filtering, deep probabilistic inference, and data augmentation. We evaluate KID-PPG on the PPGDalia dataset, achieving an average mean absolute error of 2.85 beats per minute, surpassing existing reproducible methods. Our results demonstrate a significant performance improvement in heart rate tracking through the incorporation of prior knowledge into deep learning models. This approach shows promise in enhancing various biomedical applications by incorporating existing expert knowledge in deep learning models.","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"72 3","pages":"870-877"},"PeriodicalIF":4.4,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142390148","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-09DOI: 10.1109/TBME.2024.3476930
Mehri Mehrnia;Eugene Kholmovski;Aggelos Katsaggelos;Daniel Kim;Rod Passman;Mohammed S. M. Elbaz
Myocardial fibrosis is a crucial marker of heart muscle injury in several heart disease like myocardial infarction, cardiomyopathies, and atrial fibrillation (AF). Fibrosis and associated scarring (dense fibrosis) are also vital for assessing heart muscle pre- and post-intervention, such as evaluating left atrial (LA) fibrosis/scarring in patients undergoing catheter ablation for AF. Although cardiac MRI is the gold standard for fibrosis assessment, current quantification methods are unreliable due to their reliance on variable thresholding and sensitivity to MRI uncertainties, lacking standardization and reproducibility. Importantly, current methods focus solely on quantifying fibrosis volume ignoring the unique MRI characteristics of fibrosis density and unique distribution, that could better inform on disease severity. To address these issues, we propose a novel threshold-free self-calibrating probabilistic method called “Fibrosis Signatures.” This method efficiently encodes ∼9 billion MRI intensity co-disparities per scan into standardized probability density functions, deriving a unique MRI fibrosis signature index (FSI). The FSI index quantitatively encodes fibrosis/scar extent, density, and distribution patterns simultaneously, providing a detailed assessment of burden/severity. Our self-calibrating design mitigates impacts of MRI uncertainties, ensuring robust evaluations pre- and post-intervention under varying MRI qualities. Extensively validated using a novel numerical phantom and 143 in vivo LA 3D MRIs of AF patients (pre- and post- ablation and serial post-ablation scans) and compared to 5 existing methods, our FSI index demonstrated strong correlations with traditional fibrosis measures and was able to quantify density and distribution pattern beyond entropy. FSI was up to 9 times more reliable and reproducible to MRI uncertainties (noise, segmentation, spatial resolution), highlighting its potential to improve cardiac MRI reliability and clinical utility.
{"title":"Novel Self-Calibrated Threshold-Free Probabilistic Fibrosis Signature Technique for 3D Late Gadolinium Enhancement MRI","authors":"Mehri Mehrnia;Eugene Kholmovski;Aggelos Katsaggelos;Daniel Kim;Rod Passman;Mohammed S. M. Elbaz","doi":"10.1109/TBME.2024.3476930","DOIUrl":"10.1109/TBME.2024.3476930","url":null,"abstract":"Myocardial fibrosis is a crucial marker of heart muscle injury in several heart disease like myocardial infarction, cardiomyopathies, and atrial fibrillation (AF). Fibrosis and associated scarring (dense fibrosis) are also vital for assessing heart muscle pre- and post-intervention, such as evaluating left atrial (LA) fibrosis/scarring in patients undergoing catheter ablation for AF. Although cardiac MRI is the gold standard for fibrosis assessment, current quantification methods are unreliable due to their reliance on variable thresholding and sensitivity to MRI uncertainties, lacking standardization and reproducibility. Importantly, current methods focus solely on quantifying fibrosis volume ignoring the unique MRI characteristics of fibrosis density and unique distribution, that could better inform on disease severity. To address these issues, we propose a novel threshold-free self-calibrating probabilistic method called “Fibrosis Signatures.” This method efficiently encodes ∼9 billion MRI intensity co-disparities per scan into standardized probability density functions, deriving a unique MRI fibrosis signature index (FSI). The FSI index quantitatively encodes fibrosis/scar extent, density, and distribution patterns simultaneously, providing a detailed assessment of burden/severity. Our self-calibrating design mitigates impacts of MRI uncertainties, ensuring robust evaluations pre- and post-intervention under varying MRI qualities. Extensively validated using a novel numerical phantom and 143 in vivo LA 3D MRIs of AF patients (pre- and post- ablation and serial post-ablation scans) and compared to 5 existing methods, our FSI index demonstrated strong correlations with traditional fibrosis measures and was able to quantify density and distribution pattern beyond entropy. FSI was up to 9 times more reliable and reproducible to MRI uncertainties (noise, segmentation, spatial resolution), highlighting its potential to improve cardiac MRI reliability and clinical utility.","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"72 3","pages":"856-869"},"PeriodicalIF":4.4,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10709867","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142390149","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","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：