Pub Date : 2024-06-03DOI: 10.1109/TMRB.2024.3408892
Ryan S. Pollard;David S. Hollinger;Iván E. Nail-Ulloa;Michael E. Zabala
Elevated runtimes of machine learning algorithms and neural networks make their inclusion in near-future joint angle estimation difficult. The purpose of this study was to develop simple, analytical models that prioritize historical joint kinematics when estimating near-future joint angles. Five kinematically-informed and extrapolation-based methods were developed for joint angle estimation at three near-future estimation horizons: $t_{pred} = 50$ ms, 75 ms, and 100 ms. The estimation error and required runtimes of each prediction algorithm were evaluated on the sagittal-plane ankle angles of 24 individual subjects who performed three level-ground walking trials. Results showed that the kinematically-informed models had significantly faster estimation runtimes than Random Forest (RF) machine learning models trained and tested on identical datasets (kinematic models: $t_{run}lt 0.62$ ms, RF models: $t_{run}gt 8.19$ ms for all estimation horizons). The RF models exhibited significantly lower prediction errors than the kinematic models for estimation horizons of $t_{pred} = 75$ ms and 100 ms, but no significance was found between the top-performing kinematic model and RF models for a $t_{pred} = 50$ ms. These results indicate that a kinematically-informed approach to joint angle estimation can serve as a simple alternative to complex machine learning models for very near-future applications ( $t_{pred} leq 50$ ms) while serving as a comparison baseline for more distant estimation horizons ( $t_{pred} geq 75$ ms).
机器学习算法和神经网络的运行时间较长，因此很难将其纳入近未来关节角度估算中。本研究旨在开发简单的分析模型，在估算近未来关节角度时优先考虑历史关节运动学。研究开发了五种以运动学为基础的外推法，用于在三个近未来估计视角下估计关节角度：$t_{pred} = 50$ ms、75 ms 和 100 ms。对 24 名受试者进行了三次平地行走试验，评估了每种预测算法的估计误差和所需运行时间。结果表明，在相同的数据集上训练和测试的运动学模型的估计运行时间明显快于随机森林（RF）机器学习模型（运动学模型：$t_{run}lt 0.62$ms，RF模型：$t_{run}gt 8.19$ms，适用于所有估计范围）。射频模型在 $t_{pred} = 75$ ms 和 $t_{pred} = 100 ms 时的预测误差明显低于运动学模型，但在 $t_{pred} = 50$ ms 时，表现最好的运动学模型与射频模型之间没有显著差异。这些结果表明，在非常接近未来的应用中（$t_{pred} leq 50$ms），以运动学为基础的关节角度估计方法可以作为复杂机器学习模型的简单替代方法，同时也可以作为更远估计范围（$t_{pred} geq 75$ms）的比较基线。
{"title":"A Kinematically Informed Approach to Near-Future Joint Angle Estimation at the Ankle","authors":"Ryan S. Pollard;David S. Hollinger;Iván E. Nail-Ulloa;Michael E. Zabala","doi":"10.1109/TMRB.2024.3408892","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3408892","url":null,"abstract":"Elevated runtimes of machine learning algorithms and neural networks make their inclusion in near-future joint angle estimation difficult. The purpose of this study was to develop simple, analytical models that prioritize historical joint kinematics when estimating near-future joint angles. Five kinematically-informed and extrapolation-based methods were developed for joint angle estimation at three near-future estimation horizons: \u0000<inline-formula> <tex-math>$t_{pred} = 50$ </tex-math></inline-formula>\u0000 ms, 75 ms, and 100 ms. The estimation error and required runtimes of each prediction algorithm were evaluated on the sagittal-plane ankle angles of 24 individual subjects who performed three level-ground walking trials. Results showed that the kinematically-informed models had significantly faster estimation runtimes than Random Forest (RF) machine learning models trained and tested on identical datasets (kinematic models: \u0000<inline-formula> <tex-math>$t_{run}lt 0.62$ </tex-math></inline-formula>\u0000 ms, RF models: \u0000<inline-formula> <tex-math>$t_{run}gt 8.19$ </tex-math></inline-formula>\u0000 ms for all estimation horizons). The RF models exhibited significantly lower prediction errors than the kinematic models for estimation horizons of \u0000<inline-formula> <tex-math>$t_{pred} = 75$ </tex-math></inline-formula>\u0000 ms and 100 ms, but no significance was found between the top-performing kinematic model and RF models for a \u0000<inline-formula> <tex-math>$t_{pred} = 50$ </tex-math></inline-formula>\u0000 ms. These results indicate that a kinematically-informed approach to joint angle estimation can serve as a simple alternative to complex machine learning models for very near-future applications (\u0000<inline-formula> <tex-math>$t_{pred} leq 50$ </tex-math></inline-formula>\u0000 ms) while serving as a comparison baseline for more distant estimation horizons (\u0000<inline-formula> <tex-math>$t_{pred} geq 75$ </tex-math></inline-formula>\u0000 ms).","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"6 3","pages":"1125-1134"},"PeriodicalIF":3.4,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141965570","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}
Dynamic factors, like limb position changes and electrode shifting, significantly impact the performance of EMG-based hand gesture classification as the transition is made from a laboratory-controlled environment to real-life scenarios. Traditionally, researchers have employed conventional wavelet transform methods to improve classification performance. This study compares a tempo-spatial technique that utilizes the wavelet multiresolution method and compares it with the conventional wavelet transform using eight machine learning algorithms. Two public datasets are utilized. DB1 comprising ideal conditions with a range of limb positions, while DB2 incorporates dynamic factors like electrode shifting and muscle fatigue. The training/testing involves two cases: one using single-position data and other with multiple positions. Results demonstrate that the Deep Neural Network (DNN) classifier outperforms others in classification accuracy. Proposed technique achieves mean accuracies of 84.07% (DB1) and 68.15% (DB2), while conventional wavelet transform methods achieve 79.39% (DB1) and 53.48% (DB2) for single-position DNN training. For multiple positions, particularly two limb positions, the proposed technique achieves mean accuracies of 94.43% (DB1) and 73.79% (DB2), compared to conventional wavelet transform, which achieves 84.38% (DB1) and 51.98% (DB2) with DNN. Paired t-tests (p-value<0.001) show significant improvement over conventional wavelet transformation, indicating the proposed technique’s potential to enhance gesture classification in real-world scenarios.
{"title":"Enhanced EMG-Based Hand Gesture Classification in Real-World Scenarios: Mitigating Dynamic Factors With Tempo-Spatial Wavelet Transform and Deep Learning","authors":"Parul Rani;Sidharth Pancholi;Vikash Shaw;Manfredo Atzori;Sanjeev Kumar","doi":"10.1109/TMRB.2024.3408896","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3408896","url":null,"abstract":"Dynamic factors, like limb position changes and electrode shifting, significantly impact the performance of EMG-based hand gesture classification as the transition is made from a laboratory-controlled environment to real-life scenarios. Traditionally, researchers have employed conventional wavelet transform methods to improve classification performance. This study compares a tempo-spatial technique that utilizes the wavelet multiresolution method and compares it with the conventional wavelet transform using eight machine learning algorithms. Two public datasets are utilized. DB1 comprising ideal conditions with a range of limb positions, while DB2 incorporates dynamic factors like electrode shifting and muscle fatigue. The training/testing involves two cases: one using single-position data and other with multiple positions. Results demonstrate that the Deep Neural Network (DNN) classifier outperforms others in classification accuracy. Proposed technique achieves mean accuracies of 84.07% (DB1) and 68.15% (DB2), while conventional wavelet transform methods achieve 79.39% (DB1) and 53.48% (DB2) for single-position DNN training. For multiple positions, particularly two limb positions, the proposed technique achieves mean accuracies of 94.43% (DB1) and 73.79% (DB2), compared to conventional wavelet transform, which achieves 84.38% (DB1) and 51.98% (DB2) with DNN. Paired t-tests (p-value<0.001) show significant improvement over conventional wavelet transformation, indicating the proposed technique’s potential to enhance gesture classification in real-world scenarios.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"6 3","pages":"1202-1211"},"PeriodicalIF":3.4,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141965576","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}
Safe capsule-colon interaction for magnetically driven robotic capsules is important in clinical applications. This work presents a solution based on the amplitude information of the magnetic field to adjust the distance between the interacting magnets, in order to prevent the magnetic forces exerted on the capsule robot and the pressure on the intestine walls from being overlarge, which may cause large deformation of the colon. As the first step, the geometry of the internal magnet embedded in the capsule is optimized to approach a near-spherical amplitude of the magnetic field based on the dipole model. Next, mathematical mapping from magnetic field amplitude to the interaction distance between the magnets is presented with constraint derivation and implementation. Then, a strategy to adjust the distance between the interacting magnets is provided based on the mapping using the magnetic field information. Finally, experiments are designed to validate the pose-independent interaction distance adjustment. Compared with the previous work, the proposed solution enables the quick interaction distance adjustment between the magnets to enhance the safety of capsule-colon interaction in the magnetically driven capsule endoscopies, since the interaction distance is derived straightforwardly from the magnetic field signals, without requiring the prerequisite implementation of capsule localization.
{"title":"Pose-Independent Interaction Distance Adjustment for Magnetically Driven Robotic Capsules","authors":"Guoqing Li;Jing Li;Gastone Ciuti;Paolo Dario;Qiang Huang","doi":"10.1109/TMRB.2024.3408324","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3408324","url":null,"abstract":"Safe capsule-colon interaction for magnetically driven robotic capsules is important in clinical applications. This work presents a solution based on the amplitude information of the magnetic field to adjust the distance between the interacting magnets, in order to prevent the magnetic forces exerted on the capsule robot and the pressure on the intestine walls from being overlarge, which may cause large deformation of the colon. As the first step, the geometry of the internal magnet embedded in the capsule is optimized to approach a near-spherical amplitude of the magnetic field based on the dipole model. Next, mathematical mapping from magnetic field amplitude to the interaction distance between the magnets is presented with constraint derivation and implementation. Then, a strategy to adjust the distance between the interacting magnets is provided based on the mapping using the magnetic field information. Finally, experiments are designed to validate the pose-independent interaction distance adjustment. Compared with the previous work, the proposed solution enables the quick interaction distance adjustment between the magnets to enhance the safety of capsule-colon interaction in the magnetically driven capsule endoscopies, since the interaction distance is derived straightforwardly from the magnetic field signals, without requiring the prerequisite implementation of capsule localization.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"6 3","pages":"961-970"},"PeriodicalIF":3.4,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141965166","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}
Pub Date : 2024-06-03DOI: 10.1109/TMRB.2024.3408325
Vaibhav Koshta;Bikesh Kumar Singh;Ajoy K. Behera;Ranganath T. G.
Subjective discrimination of asthma and Chronic Obstructive Pulmonary Disease (COPD) is challenging as they share overlapping symptoms and are subject to personal interpretation. Hence, there is a demand for an alternative diagnostic system devoid of any subjective interference. The current study introduces Fourier Decomposition Method (FDM) based models utilizing Discrete Cosine Transform (DCT) and Discrete Fourier Transform (DFT) to identify patients with asthma and COPD by analyzing lung sound signals. The signals were decomposed into Fourier intrinsic band functions (FIBF) using three filter banks: dyadic, equal energy, and uniform band. Four statistical attributes, namely: Shannon entropy, log entropy, median absolute deviation and kurtosis, are calculated from relevant FIBF. Support vector machine (SVM), k-nearest neighbor (kNN) and ensemble classifier (EC) optimized with Bayesian optimization are used for classification of asthma vs COPD and normal vs adventitious sound, respectively. The highest accuracies achieved using DCT with 10-fold cross-validation are as follows: 99.4% (Asthma vs COPD), 99.1% (Asthma vs COPD vs Normal), 99.4% (COPD vs Normal) and 99.7% (Asthma vs Normal). Similarly, the highest accuracies reported by DFT with 10-fold cross-validation are: 99.4% (Asthma vs COPD), 99.6% (Asthma vs COPD vs Normal), 99.4% (COPD vs Normal) and 99.8% (Asthma vs Normal).
对哮喘和慢性阻塞性肺病（COPD）进行主观判别具有挑战性，因为这两种疾病的症状有重叠之处，而且会受到个人解释的影响。因此，需要一种没有任何主观干扰的替代诊断系统。本研究介绍了基于傅立叶分解法（FDM）的模型，利用离散余弦变换（DCT）和离散傅立叶变换（DFT），通过分析肺部声音信号来识别哮喘和慢性阻塞性肺病患者。使用三个滤波器组将信号分解为傅里叶本征频带函数（FIBF），这三个滤波器组分别是：二元滤波器组、等能滤波器组和均一滤波器组。四个统计属性，即根据相关的 FIBF 计算出香农熵、对数熵、中位数绝对偏差和峰度。支持向量机（SVM）、k-近邻（kNN）和经贝叶斯优化的集合分类器（EC）分别用于哮喘与慢性阻塞性肺病和正常与临近声的分类。使用 DCT 和 10 倍交叉验证取得的最高准确率如下：99.4%（哮喘 vs 慢性阻塞性肺病）、99.1%（哮喘 vs 慢性阻塞性肺病 vs 正常）、99.4%（慢性阻塞性肺病 vs 正常）和 99.7%（哮喘 vs 正常）。同样，DFT 通过 10 倍交叉验证报告的最高准确率为99.4%（哮喘与慢性阻塞性肺病）、99.6%（哮喘与慢性阻塞性肺病与正常）、99.4%（慢性阻塞性肺病与正常）和 99.8%（哮喘与正常）。
{"title":"Fourier Decomposition-Based Automated Classification of Healthy, COPD, and Asthma Using Single-Channel Lung Sounds","authors":"Vaibhav Koshta;Bikesh Kumar Singh;Ajoy K. Behera;Ranganath T. G.","doi":"10.1109/TMRB.2024.3408325","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3408325","url":null,"abstract":"Subjective discrimination of asthma and Chronic Obstructive Pulmonary Disease (COPD) is challenging as they share overlapping symptoms and are subject to personal interpretation. Hence, there is a demand for an alternative diagnostic system devoid of any subjective interference. The current study introduces Fourier Decomposition Method (FDM) based models utilizing Discrete Cosine Transform (DCT) and Discrete Fourier Transform (DFT) to identify patients with asthma and COPD by analyzing lung sound signals. The signals were decomposed into Fourier intrinsic band functions (FIBF) using three filter banks: dyadic, equal energy, and uniform band. Four statistical attributes, namely: Shannon entropy, log entropy, median absolute deviation and kurtosis, are calculated from relevant FIBF. Support vector machine (SVM), k-nearest neighbor (kNN) and ensemble classifier (EC) optimized with Bayesian optimization are used for classification of asthma vs COPD and normal vs adventitious sound, respectively. The highest accuracies achieved using DCT with 10-fold cross-validation are as follows: 99.4% (Asthma vs COPD), 99.1% (Asthma vs COPD vs Normal), 99.4% (COPD vs Normal) and 99.7% (Asthma vs Normal). Similarly, the highest accuracies reported by DFT with 10-fold cross-validation are: 99.4% (Asthma vs COPD), 99.6% (Asthma vs COPD vs Normal), 99.4% (COPD vs Normal) and 99.8% (Asthma vs Normal).","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"6 3","pages":"1270-1284"},"PeriodicalIF":3.4,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141965687","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}
Pub Date : 2024-06-03DOI: 10.1109/TMRB.2024.3408308
Qiang Chen;Jiaxin Wang;Qian Xiang;Shijie Guo
Relevant research highlights humans’ capacity to continuously adapt their walking speed to minimize metabolic energy consumption during overground free walking. Past studies have shown that soft exosuits assisting in hip flexion and extension can reduce metabolic costs and regulate gait parameters during human locomotion. This emphasizes the need to fine-tune hip exosuit parameters to align with walking speed, thereby enhancing metabolic efficiency. This study aims to optimize assistive force parameters of hip exosuits across different walking speeds, providing insights for optimizing force profiles in outdoor walking. We employed a human-in-the-loop approach with Bayesian optimization to determine optimal force profiles for hip assistance. Six subjects performed treadmill walking at four fixed speeds (0.84, 1.16, 1.48, and 1.8 m/s), optimizing control parameters for each speed and establishing a Bayesian experience (BXE) linking walking speed to optimal parameters. Furthermore, we developed a real-time force optimization controller based on the BXE for adjusting the force parameters of assistance. Outdoor walking experiments with the same subjects showed that BXE-optimized profiles significantly reduced metabolic costs compared to fixed profiles. This study underscores the importance of optimizing assistive forces for varying walking speeds in humans.
{"title":"Bayesian Algorithm-Based Force Profiles Optimization of Hip-Assistive Soft Exosuits Under Variable Walking Speeds","authors":"Qiang Chen;Jiaxin Wang;Qian Xiang;Shijie Guo","doi":"10.1109/TMRB.2024.3408308","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3408308","url":null,"abstract":"Relevant research highlights humans’ capacity to continuously adapt their walking speed to minimize metabolic energy consumption during overground free walking. Past studies have shown that soft exosuits assisting in hip flexion and extension can reduce metabolic costs and regulate gait parameters during human locomotion. This emphasizes the need to fine-tune hip exosuit parameters to align with walking speed, thereby enhancing metabolic efficiency. This study aims to optimize assistive force parameters of hip exosuits across different walking speeds, providing insights for optimizing force profiles in outdoor walking. We employed a human-in-the-loop approach with Bayesian optimization to determine optimal force profiles for hip assistance. Six subjects performed treadmill walking at four fixed speeds (0.84, 1.16, 1.48, and 1.8 m/s), optimizing control parameters for each speed and establishing a Bayesian experience (BXE) linking walking speed to optimal parameters. Furthermore, we developed a real-time force optimization controller based on the BXE for adjusting the force parameters of assistance. Outdoor walking experiments with the same subjects showed that BXE-optimized profiles significantly reduced metabolic costs compared to fixed profiles. This study underscores the importance of optimizing assistive forces for varying walking speeds in humans.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"6 3","pages":"1232-1244"},"PeriodicalIF":3.4,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141965684","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}
Pub Date : 2024-04-18DOI: 10.1109/TMRB.2024.3391048
Hui Liu;Ning Li;Shuai Li;Gregory J. Mancini;Jindong Tan
In single-incision laparoscopic surgery (SILS), magnetic anchoring and guidance system (MAGS) is a promising technique to prevent clutter in the surgical workspace and provide a larger vision field. Existing camera designs mainly rely on a rigid structure and sliding motion, which may cause stress concentration and tissue damage on curved abdominal walls. Meanwhile, the insertion procedure is also challenging. In this paper, we proposed a wireless MAGS consisting of soft material and wheel structure design. The camera can passively bend and adapt to the curved tissue surface to relieve stress concentration. The wheel structure transfers the sliding motion to rolling motion when the camera tilts and translates, avoiding tissue rupture due to dry friction and facilitating smooth motion. The experiments show the novel laparoscope has dexterous locomotion and bendability with 20° in bending angle and $16.4mm$ in displacement. The maximum stress is reduced by 64% compared with rigid designs. An easy and safe insertion procedure based on soft property is also introduced, which takes less than 2 minutes on average without the assistance of additional instruments.
{"title":"Design and Evaluation for a Soft Intra-Abdominal Wireless Laparoscope","authors":"Hui Liu;Ning Li;Shuai Li;Gregory J. Mancini;Jindong Tan","doi":"10.1109/TMRB.2024.3391048","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3391048","url":null,"abstract":"In single-incision laparoscopic surgery (SILS), magnetic anchoring and guidance system (MAGS) is a promising technique to prevent clutter in the surgical workspace and provide a larger vision field. Existing camera designs mainly rely on a rigid structure and sliding motion, which may cause stress concentration and tissue damage on curved abdominal walls. Meanwhile, the insertion procedure is also challenging. In this paper, we proposed a wireless MAGS consisting of soft material and wheel structure design. The camera can passively bend and adapt to the curved tissue surface to relieve stress concentration. The wheel structure transfers the sliding motion to rolling motion when the camera tilts and translates, avoiding tissue rupture due to dry friction and facilitating smooth motion. The experiments show the novel laparoscope has dexterous locomotion and bendability with 20° in bending angle and \u0000<inline-formula> <tex-math>$16.4mm$ </tex-math></inline-formula>\u0000 in displacement. The maximum stress is reduced by 64% compared with rigid designs. An easy and safe insertion procedure based on soft property is also introduced, which takes less than 2 minutes on average without the assistance of additional instruments.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"6 3","pages":"940-950"},"PeriodicalIF":3.4,"publicationDate":"2024-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141965168","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}
Pub Date : 2024-04-16DOI: 10.1109/TMRB.2024.3389490
Haipeng Liang;Wanli Zuo;Dimitri Kessler;Tristan Barrett;Zion Tsz Ho Tse
Under the guidance of high-resolution Magnetic Resonance Imaging (MRI), robotic devices offer a great advantage for prostate intervention. This paper presents an MR-safe robot, where a needle is attached to the needle guide to obtain prostate biopsies during surgeries. The robot is powered by three actuators, two of them are customized to function as a work plane that allows the needle to move horizontally and vertically, and the third actuator controls the rotation of the work plane, allowing the needle to be inserted into the prostate from different directions. All the actuators are pneumatically actuated to allow them to work in a Magnetic Resonance (MR) environment. The kinematics and mechanism of the robot are analyzed. A user interface developed using LabView is created to calculate the target position and generate a control signal for the valves. In the open-air test, the needle can reach the target with an accuracy of 1.3 mm. The signal-to-noise ratio (SNR) variation was measured below 5% under a 3T MR scanner.
{"title":"A Pneumatic Driven MRI-Guided Robot System for Prostate Interventions","authors":"Haipeng Liang;Wanli Zuo;Dimitri Kessler;Tristan Barrett;Zion Tsz Ho Tse","doi":"10.1109/TMRB.2024.3389490","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3389490","url":null,"abstract":"Under the guidance of high-resolution Magnetic Resonance Imaging (MRI), robotic devices offer a great advantage for prostate intervention. This paper presents an MR-safe robot, where a needle is attached to the needle guide to obtain prostate biopsies during surgeries. The robot is powered by three actuators, two of them are customized to function as a work plane that allows the needle to move horizontally and vertically, and the third actuator controls the rotation of the work plane, allowing the needle to be inserted into the prostate from different directions. All the actuators are pneumatically actuated to allow them to work in a Magnetic Resonance (MR) environment. The kinematics and mechanism of the robot are analyzed. A user interface developed using LabView is created to calculate the target position and generate a control signal for the valves. In the open-air test, the needle can reach the target with an accuracy of 1.3 mm. The signal-to-noise ratio (SNR) variation was measured below 5% under a 3T MR scanner.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"6 3","pages":"951-960"},"PeriodicalIF":3.4,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141965167","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}
Pub Date : 2024-04-10DOI: 10.1109/TMRB.2024.3387040
Heng Zhang;Yehui Li;Xinfa Shi;Yichong Sun;Jixiu Li;Yisen Huang;Wing Yin Ng;Chengxiang Liu;Philip Wai Yan Chiu;Chi-Kwan Lee;Zheng Li
Stomach cancer remains one of the primary health challenges with a high incidence and motility. Magnetically actuated capsule endoscope (MACE) provides a noninvasive and practical solution for stomach screening, due to its contactless actuation and high maneuverability. In this work, with an aim of shortening procedure duration and lowering surgeon workload, we propose an automatic stomach screening strategy by using a MACE to automatically detect and capture specific gastric features for mapping the whole stomach. To achieve this, an electromagnetic actuation system and a wireless MACE with real-time video transmission and orientation feedback are developed. Magnetic actuation modeling and kinematics analysis of the MACE are conducted, based on which an optimization-based position controller and a visual-servo-based orientation controller are designed. Simulative and experimental validation are conducted for proof-of-concept, with attractive results showing that the MACE can be accurately and stably controlled with a mean absolute position error of around 2.56 mm and an average convergent time of about 1.1 s for visual servoing and that automatic stomach screening is successfully demonstrated in a stomach phantom. The proposed stomach screening strategy using a MACE indicates high potential in clinical practice.
{"title":"Toward Automatic Stomach Screening Using a Wireless Magnetically Actuated Capsule Endoscope","authors":"Heng Zhang;Yehui Li;Xinfa Shi;Yichong Sun;Jixiu Li;Yisen Huang;Wing Yin Ng;Chengxiang Liu;Philip Wai Yan Chiu;Chi-Kwan Lee;Zheng Li","doi":"10.1109/TMRB.2024.3387040","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3387040","url":null,"abstract":"Stomach cancer remains one of the primary health challenges with a high incidence and motility. Magnetically actuated capsule endoscope (MACE) provides a noninvasive and practical solution for stomach screening, due to its contactless actuation and high maneuverability. In this work, with an aim of shortening procedure duration and lowering surgeon workload, we propose an automatic stomach screening strategy by using a MACE to automatically detect and capture specific gastric features for mapping the whole stomach. To achieve this, an electromagnetic actuation system and a wireless MACE with real-time video transmission and orientation feedback are developed. Magnetic actuation modeling and kinematics analysis of the MACE are conducted, based on which an optimization-based position controller and a visual-servo-based orientation controller are designed. Simulative and experimental validation are conducted for proof-of-concept, with attractive results showing that the MACE can be accurately and stably controlled with a mean absolute position error of around 2.56 mm and an average convergent time of about 1.1 s for visual servoing and that automatic stomach screening is successfully demonstrated in a stomach phantom. The proposed stomach screening strategy using a MACE indicates high potential in clinical practice.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"6 2","pages":"512-523"},"PeriodicalIF":0.0,"publicationDate":"2024-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140820245","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}
In surgical robotics, accurate characterization of the dynamic model is crucial. It serves as a foundation for developing robust control algorithms that effectively handle the complex dynamics of the robot and its interactions with the environment. Additionally, an accurate dynamic model aids in estimating external forces and disturbances, enhancing the safety and stability of the control. Among surgical robots, the da Vinci Research Kit (dVRK) is one of the most used, and it has been a crucial instrument in removing a barrier to entry for new research groups in surgical robotics by facilitating the development of improved control algorithms. This paper presents a method for dynamic model identification of the dVRK *psm robot that employs a novel friction model definition. The model formulation has been modified by including the Stribeck effect at low velocities, and the friction has been estimated using the superposition method. The dynamic parameters are identified utilizing a restricted optimization method with physical consistency requirements in an Augmented Lagrangian Particle Swarm Algorithm (ALPSO) methodology. The identified model is thoroughly evaluated, and the results are compared with existing literature methods. Also, a model-based sensorless force estimation method was used to test the dynamic model.
{"title":"daVinci Research Kit Patient Side Manipulator Dynamic Model Using Augmented Lagrangian Particle Swarm Optimization","authors":"Omer Faruk Argin;Rocco Moccia;Cristina Iacono;Fanny Ficuciello","doi":"10.1109/TMRB.2024.3387070","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3387070","url":null,"abstract":"In surgical robotics, accurate characterization of the dynamic model is crucial. It serves as a foundation for developing robust control algorithms that effectively handle the complex dynamics of the robot and its interactions with the environment. Additionally, an accurate dynamic model aids in estimating external forces and disturbances, enhancing the safety and stability of the control. Among surgical robots, the da Vinci Research Kit (dVRK) is one of the most used, and it has been a crucial instrument in removing a barrier to entry for new research groups in surgical robotics by facilitating the development of improved control algorithms. This paper presents a method for dynamic model identification of the dVRK *psm robot that employs a novel friction model definition. The model formulation has been modified by including the Stribeck effect at low velocities, and the friction has been estimated using the superposition method. The dynamic parameters are identified utilizing a restricted optimization method with physical consistency requirements in an Augmented Lagrangian Particle Swarm Algorithm (ALPSO) methodology. The identified model is thoroughly evaluated, and the results are compared with existing literature methods. Also, a model-based sensorless force estimation method was used to test the dynamic model.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"6 2","pages":"589-599"},"PeriodicalIF":0.0,"publicationDate":"2024-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140820396","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}
Pub Date : 2024-04-10DOI: 10.1109/TMRB.2024.3387114
Yanding Qin;Yueyang Shi;Longxin Wang;Hongpeng Wang;Jianda Han
In neurosurgery, magnetic resonance (MR) imaging is extensively utilized for preoperative diagnosis and postoperative evaluation due to its superior soft tissue contrast. However, the strong magnetic field poses a challenge to the real-time utilization of MR for intraoperative navigation. To facilitate neurosurgery in the MR environment, this paper develops a MR conditional robot featuring nonferrous materials and ultrasonic motor actuation. The robot consists of a 3-degree-of-freedom (3-DOF) translational module and a 3-DOF remote center of motion (RCM) module. The RCM module incorporates a 3-RRR spherical parallel mechanism. The mechanical design and kinematic modeling of the RCM module is completed. This paper further conducts the optimization for the RCM module. Additionally, a path-planning algorithm, focusing on the maximization of dexterity, is introduced, and the feasible workspace of the optimized RCM module is evaluated. A prototype is fabricated, and the orientation repeatability of the RCM module is measured to be 0.055±0.0016°, and the absolute orientation error is 2.05±0.019°. Needle insertion experiments are performed on an agarose phantom to evaluate the feasibility of the robot. The impact on signal-to-noise ratio in MRI images caused by the robot is less than 4%, indicating a highly promising applicability in MR conditional neurosurgery.
{"title":"Design, Modeling and Optimization of a Magnetic Resonance Conditional 3-RRR Spherical Parallel Robot for Neurosurgery","authors":"Yanding Qin;Yueyang Shi;Longxin Wang;Hongpeng Wang;Jianda Han","doi":"10.1109/TMRB.2024.3387114","DOIUrl":"https://doi.org/10.1109/TMRB.2024.3387114","url":null,"abstract":"In neurosurgery, magnetic resonance (MR) imaging is extensively utilized for preoperative diagnosis and postoperative evaluation due to its superior soft tissue contrast. However, the strong magnetic field poses a challenge to the real-time utilization of MR for intraoperative navigation. To facilitate neurosurgery in the MR environment, this paper develops a MR conditional robot featuring nonferrous materials and ultrasonic motor actuation. The robot consists of a 3-degree-of-freedom (3-DOF) translational module and a 3-DOF remote center of motion (RCM) module. The RCM module incorporates a 3-RRR spherical parallel mechanism. The mechanical design and kinematic modeling of the RCM module is completed. This paper further conducts the optimization for the RCM module. Additionally, a path-planning algorithm, focusing on the maximization of dexterity, is introduced, and the feasible workspace of the optimized RCM module is evaluated. A prototype is fabricated, and the orientation repeatability of the RCM module is measured to be 0.055±0.0016°, and the absolute orientation error is 2.05±0.019°. Needle insertion experiments are performed on an agarose phantom to evaluate the feasibility of the robot. The impact on signal-to-noise ratio in MRI images caused by the robot is less than 4%, indicating a highly promising applicability in MR conditional neurosurgery.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"6 2","pages":"556-566"},"PeriodicalIF":0.0,"publicationDate":"2024-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140820254","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}
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：