Echocardiography is a critical tool for diagnosing cardiovascular diseases, offering detailed insights into heart functions. However, its accessibility is currently limited by a shortage of trained sonographers, specific skill requirements, and the physical strain imposed on professionals during repetitive procedures. This article introduces a new robotic system designed to automate the acquisition of transthoracic echocardiography (TTE) images. The system autonomously adjusts the position and orientation of the ultrasound transducer based on analysing real-time ultrasound images, without relying on tomographic data or depth sensors. Initially, the transducer is manually placed on the subject’s skin, and the system uses a deep learning approach to grade the quality of ultrasound images captured at each position. The robot then adjusts its position by spiralling outwards from the starting point, moving to the location with the highest image quality score. Next, the system fine-tunes the transducer’s orientation in 5-degree increments along all three axes of rotation, informed by another deep learning module to identify the field of view. The robotic system was tested using a cardiac simulator, achieving approximately 80% accuracy in acquiring the A4Ch view when the probe was initially positioned randomly in a 6 by 6 cm area beneath the left nipple. The impact of this work would be rapid diagnostics in the Emergency Departments to reduce the length of stay in hospitals, a reduction of hospital admissions related to heart disease by accessing local healthcare communities, acceleration of clearing the post-Covid backlog, and improved quality of life and longevity of patients.
{"title":"Echo-Robot: Semi-Autonomous Cardiac Ultrasound Image Acquisition Using AI and Robotics","authors":"Eliott Laurent;Raska Soemantoro;Kathryn Jenner;Attila Kardos;Gilbert Tang;Yifan Zhao","doi":"10.1109/TMRB.2025.3590471","DOIUrl":"https://doi.org/10.1109/TMRB.2025.3590471","url":null,"abstract":"Echocardiography is a critical tool for diagnosing cardiovascular diseases, offering detailed insights into heart functions. However, its accessibility is currently limited by a shortage of trained sonographers, specific skill requirements, and the physical strain imposed on professionals during repetitive procedures. This article introduces a new robotic system designed to automate the acquisition of transthoracic echocardiography (TTE) images. The system autonomously adjusts the position and orientation of the ultrasound transducer based on analysing real-time ultrasound images, without relying on tomographic data or depth sensors. Initially, the transducer is manually placed on the subject’s skin, and the system uses a deep learning approach to grade the quality of ultrasound images captured at each position. The robot then adjusts its position by spiralling outwards from the starting point, moving to the location with the highest image quality score. Next, the system fine-tunes the transducer’s orientation in 5-degree increments along all three axes of rotation, informed by another deep learning module to identify the field of view. The robotic system was tested using a cardiac simulator, achieving approximately 80% accuracy in acquiring the A4Ch view when the probe was initially positioned randomly in a 6 by 6 cm area beneath the left nipple. The impact of this work would be rapid diagnostics in the Emergency Departments to reduce the length of stay in hospitals, a reduction of hospital admissions related to heart disease by accessing local healthcare communities, acceleration of clearing the post-Covid backlog, and improved quality of life and longevity of patients.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"7 3","pages":"1307-1316"},"PeriodicalIF":3.8,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144887735","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 : 2025-07-18DOI: 10.1109/TMRB.2025.3590488
Sixu Zhou;Hanjun Kim;Jairo Y. Maldonado-Contreras;Atli Örn Sverrisson;David Langlois;Kinsey R. Herrin;Aaron J. Young
Traditional tuning methods of assistance parameters rely on the experience of human experts but often fail to achieve optimal performance. Human-in-the-loop optimization improves parameter selection but requires extensive in-lab testing. In this study, we rigorously tested two control parameters, early stance knee flexion angle (5° to 12°) and swing initiation timing (55% to 65% of the gait cycle), with ten individuals with transfemoral amputation using a commercially available robotic prosthetic knee, Össur Power Knee, and a passive foot, Pro-Flex LP. We measured energy expenditure, joint work, and user preferences during treadmill walking. Results showed a 15.6% reduction in metabolic rate with stance flexion decreasing from 12° to 5° (p<0.05). User preferences favored lower stance flexion and personalized swing initiation. Personalized-best settings reduced the metabolic rate by 4.1% (stance flexion) and 9.8% (swing initiation) compared to the best-on-average settings (p<0.05). These reductions were also significant when compared to the device default and clinically tuned settings (p<0.05). We proposed an offline learning approach using anthropometric, gait, and prosthesis-related data to estimate optimal settings, yielding a 7.1% reduction in metabolic rate (p<0.05). Our results suggest that this approach achieves comparable energy efficiency without lengthy experiments, enabling automatic parameter tuning with initial measurements.
传统的辅助参数调优方法依赖于人类专家的经验，但往往无法达到最优的性能。人在环优化改进了参数选择，但需要大量的实验室测试。在这项研究中，我们严格测试了两个控制参数，早期站立膝关节弯曲角度（5°至12°）和摆动起始时间（55%至65%的步态周期），10例经股截肢患者使用市售机器人假膝Össur Power knee和被动足Pro-Flex LP。我们测量了在跑步机上行走时的能量消耗、关节工作和用户偏好。结果显示，当体位屈曲从12°减少到5°时，代谢率降低了15.6% （p<0.05）。用户偏好较低的姿态弯曲和个性化的挥拍开始。与平均最佳设置相比，个性化最佳设置可使代谢率降低4.1%（姿态弯曲）和9.8%（摇摆开始）（p<0.05）。与设备默认设置和临床调整设置相比，这些降低也很显著（p<0.05）。我们提出了一种离线学习方法，使用人体测量学、步态和假体相关数据来估计最佳设置，代谢率降低7.1% （p<0.05）。我们的研究结果表明，这种方法无需冗长的实验即可实现相当的能源效率，并且可以通过初始测量自动调整参数。
{"title":"An Anthropometry-Based Personalization of Powered Knee Prosthesis for Metabolic Efficiency","authors":"Sixu Zhou;Hanjun Kim;Jairo Y. Maldonado-Contreras;Atli Örn Sverrisson;David Langlois;Kinsey R. Herrin;Aaron J. Young","doi":"10.1109/TMRB.2025.3590488","DOIUrl":"https://doi.org/10.1109/TMRB.2025.3590488","url":null,"abstract":"Traditional tuning methods of assistance parameters rely on the experience of human experts but often fail to achieve optimal performance. Human-in-the-loop optimization improves parameter selection but requires extensive in-lab testing. In this study, we rigorously tested two control parameters, early stance knee flexion angle (5° to 12°) and swing initiation timing (55% to 65% of the gait cycle), with ten individuals with transfemoral amputation using a commercially available robotic prosthetic knee, Össur Power Knee, and a passive foot, Pro-Flex LP. We measured energy expenditure, joint work, and user preferences during treadmill walking. Results showed a 15.6% reduction in metabolic rate with stance flexion decreasing from 12° to 5° (p<0.05). User preferences favored lower stance flexion and personalized swing initiation. Personalized-best settings reduced the metabolic rate by 4.1% (stance flexion) and 9.8% (swing initiation) compared to the best-on-average settings (p<0.05). These reductions were also significant when compared to the device default and clinically tuned settings (p<0.05). We proposed an offline learning approach using anthropometric, gait, and prosthesis-related data to estimate optimal settings, yielding a 7.1% reduction in metabolic rate (p<0.05). Our results suggest that this approach achieves comparable energy efficiency without lengthy experiments, enabling automatic parameter tuning with initial measurements.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"7 3","pages":"1263-1274"},"PeriodicalIF":3.8,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144887791","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 this paper, an existing physiological muscle model that predicts muscular force in response to electrical stimulation is adapted to be compatible with gradient-based optimization, in particular with numerical optimal control/estimation problems. The objective is to integrate biomechanical models with those that correlate muscle force generation with electrical pulses from a physiological perspective, with the aim of achieving optimal stimulation patterns in activities assisted by functional electrical stimulation. To this end, the activation dynamics of the original model, initially constrained to a stimulation train of predefined and constant length, is reformulated to account for stimulation sequences that dynamically change over time. This is typically necessary to simulate complex motions, which would otherwise be impossible to achieve with the earliest formulation. To identify the model parameters, experimental torque data of 3 participants with spinal cord injury performing electrically evoked isometric quadriceps contractions at different knee angles are used. We then employ an optimal control framework to demonstrate the model’s ability to predict knee torques and the possibility of achieving optimized stimulation patterns in simulation for controlling muscle force and knee extension. Our results reveal that the identified model allows accurate prediction of knee torque and optimization of stimulation patterns while satisfying the system’s dynamics at the skeletal and physiological muscle levels. This proof of concept is a first step towards physiological muscle model-based control of functional electrical stimulation to achieve movements that best exploit an individual’s physiological and biomechanical characteristics.
{"title":"Numerical-Optimal-Control-Compliant Muscle Model for Electrically Evoked Contractions","authors":"Tiago Coelho-Magalhães;Christine Azevedo-Coste;François Bailly","doi":"10.1109/TMRB.2025.3590453","DOIUrl":"https://doi.org/10.1109/TMRB.2025.3590453","url":null,"abstract":"In this paper, an existing physiological muscle model that predicts muscular force in response to electrical stimulation is adapted to be compatible with gradient-based optimization, in particular with numerical optimal control/estimation problems. The objective is to integrate biomechanical models with those that correlate muscle force generation with electrical pulses from a physiological perspective, with the aim of achieving optimal stimulation patterns in activities assisted by functional electrical stimulation. To this end, the activation dynamics of the original model, initially constrained to a stimulation train of predefined and constant length, is reformulated to account for stimulation sequences that dynamically change over time. This is typically necessary to simulate complex motions, which would otherwise be impossible to achieve with the earliest formulation. To identify the model parameters, experimental torque data of 3 participants with spinal cord injury performing electrically evoked isometric quadriceps contractions at different knee angles are used. We then employ an optimal control framework to demonstrate the model’s ability to predict knee torques and the possibility of achieving optimized stimulation patterns in simulation for controlling muscle force and knee extension. Our results reveal that the identified model allows accurate prediction of knee torque and optimization of stimulation patterns while satisfying the system’s dynamics at the skeletal and physiological muscle levels. This proof of concept is a first step towards physiological muscle model-based control of functional electrical stimulation to achieve movements that best exploit an individual’s physiological and biomechanical characteristics.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"7 3","pages":"1297-1306"},"PeriodicalIF":3.8,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144887841","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 : 2025-07-18DOI: 10.1109/TMRB.2025.3590489
R. Heidari;M. Motaharifar;E. A. Khameneh;S. F. Mohammadi;M. Tavakoli;H. D. Taghirad
Ocular surgery demands exceptional precision due to the eye’s delicate anatomy, where errors, particularly by novice surgeons, can lead to severe complications. This underscores the critical need for advanced training and skill development methodologies. The integration of versatile AI/Robotic architectures into ophthalmic surgical training is revolutionizing how surgeons acquire and refine their skills. These specialized training tools provide a safe and realistic environment, crucial for deliberate practice, skill enhancement, and the delivery of personalized feedback. This paper offers a comprehensive review of such AI/Robotic architectures specifically designed for or adapted to ophthalmic surgery training. It examines these systems from multiple viewpoints: for ophthalmologists, it details how these technologies are reshaping training paradigms, improving skill acquisition, and enabling competency-based educational models. For control and robotic engineers, it provides an in-depth technical analysis of contemporary training systems, with a focus on their control architectures, simulation environments, haptic feedback mechanisms, and varying levels of autonomy within these educational platforms. Furthermore, by identifying emerging commercial training simulators and AI-driven educational tools, this review highlights new market opportunities in the domain of surgical education. Ultimately, this comprehensive overview identifies promising directions for future research and development, offering valuable guidance for advancing the field of AI and robotics in ophthalmic surgical training.
{"title":"A Survey of Versatile AI/Robotic Architectures for Ophthalmic Surgery Training","authors":"R. Heidari;M. Motaharifar;E. A. Khameneh;S. F. Mohammadi;M. Tavakoli;H. D. Taghirad","doi":"10.1109/TMRB.2025.3590489","DOIUrl":"https://doi.org/10.1109/TMRB.2025.3590489","url":null,"abstract":"Ocular surgery demands exceptional precision due to the eye’s delicate anatomy, where errors, particularly by novice surgeons, can lead to severe complications. This underscores the critical need for advanced training and skill development methodologies. The integration of versatile AI/Robotic architectures into ophthalmic surgical training is revolutionizing how surgeons acquire and refine their skills. These specialized training tools provide a safe and realistic environment, crucial for deliberate practice, skill enhancement, and the delivery of personalized feedback. This paper offers a comprehensive review of such AI/Robotic architectures specifically designed for or adapted to ophthalmic surgery training. It examines these systems from multiple viewpoints: for ophthalmologists, it details how these technologies are reshaping training paradigms, improving skill acquisition, and enabling competency-based educational models. For control and robotic engineers, it provides an in-depth technical analysis of contemporary training systems, with a focus on their control architectures, simulation environments, haptic feedback mechanisms, and varying levels of autonomy within these educational platforms. Furthermore, by identifying emerging commercial training simulators and AI-driven educational tools, this review highlights new market opportunities in the domain of surgical education. Ultimately, this comprehensive overview identifies promising directions for future research and development, offering valuable guidance for advancing the field of AI and robotics in ophthalmic surgical training.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"7 3","pages":"898-909"},"PeriodicalIF":3.8,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144887771","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 : 2025-07-16DOI: 10.1109/TMRB.2025.3589768
Yi Hu;Mahdi Tavakoli;Jun Jin
Training robots to acquire surgical skills poses significant challenges, primarily due to the limited availability of comprehensive datasets and safety constraints that restrict real-time trial-and-error learning. Although human Activities of Daily Living (ADL) tasks differ substantially from surgical tasks, they encompass fundamental motor skills that can serve as a foundation for robot learning. Notably, skilled surgeons often develop their advanced surgical abilities by building upon these basic motor skills acquired through daily activities. Inspired by this progressive learning trajectory, we propose a novel surgical skill training framework that enables robots to learn basic motor skills from the ADL dataset and quickly adapt to advanced surgical skills. Specifically, we propose a unified predictive representation space, constructed using probabilistic successor features, which capture the dynamic patterns of motion primitives common to both ADL and surgical tasks. To investigate the transferability of skills from human ADL tasks to robotic surgical tasks, we conducted a mathematical analysis to evaluate transferable policies and performed simulation experiments to assess transfer performance. Furthermore, we validated the practicality and effectiveness of our method through real-world experiments. Results show that our method significantly reduces the need for extensive surgical datasets, and enables efficient learning in robotic surgical tasks.
{"title":"Pretraining Using Comparable Human Activities of Daily Living Dataset in Robotic Surgical Task Learning","authors":"Yi Hu;Mahdi Tavakoli;Jun Jin","doi":"10.1109/TMRB.2025.3589768","DOIUrl":"https://doi.org/10.1109/TMRB.2025.3589768","url":null,"abstract":"Training robots to acquire surgical skills poses significant challenges, primarily due to the limited availability of comprehensive datasets and safety constraints that restrict real-time trial-and-error learning. Although human Activities of Daily Living (ADL) tasks differ substantially from surgical tasks, they encompass fundamental motor skills that can serve as a foundation for robot learning. Notably, skilled surgeons often develop their advanced surgical abilities by building upon these basic motor skills acquired through daily activities. Inspired by this progressive learning trajectory, we propose a novel surgical skill training framework that enables robots to learn basic motor skills from the ADL dataset and quickly adapt to advanced surgical skills. Specifically, we propose a unified predictive representation space, constructed using probabilistic successor features, which capture the dynamic patterns of motion primitives common to both ADL and surgical tasks. To investigate the transferability of skills from human ADL tasks to robotic surgical tasks, we conducted a mathematical analysis to evaluate transferable policies and performed simulation experiments to assess transfer performance. Furthermore, we validated the practicality and effectiveness of our method through real-world experiments. Results show that our method significantly reduces the need for extensive surgical datasets, and enables efficient learning in robotic surgical tasks.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"7 3","pages":"1111-1124"},"PeriodicalIF":3.8,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144887838","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}
Exoskeletons play a huge role in human body enhancement and physical rehabilitation. In this paper, a new modular exoskeleton driven by double-tendon-sheath variable stiffness actuator (DTS-VSA) is designed to achieve effective human power assistance. The modular and variable stiffness structure of exoskeleton enable the adaptation to different human joint, improving the characteristics of physical human-robot interaction. The DTS-VSA is designed based on the pulley-cable-spring preloading principle and tendon sheath transmission, and its stiffness model is developed through quasi-static force balance analysis. To realize coordinated and active power argumentation, a fuzzy adaptive assistive controller integrated with human joint torque and stiffness estimation is proposed based on surface electromyography. Feasibility is experimentally verified via three typical load-carrying experiments and ten volunteers. The experimental results show that the average assistance efficiencies of elbow motion and knee motion in different experiment conditions are higher than 44.72% and 38.41%.
{"title":"sEMG-Driven Assistive Control of a Modular Exoskeleton With Double-Tendon-Sheath Variable Stiffness Actuator","authors":"Qingcong Wu;Zijie Wang;Songshan Lu;Bai Chen;Hongtao Wu","doi":"10.1109/TMRB.2025.3589771","DOIUrl":"https://doi.org/10.1109/TMRB.2025.3589771","url":null,"abstract":"Exoskeletons play a huge role in human body enhancement and physical rehabilitation. In this paper, a new modular exoskeleton driven by double-tendon-sheath variable stiffness actuator (DTS-VSA) is designed to achieve effective human power assistance. The modular and variable stiffness structure of exoskeleton enable the adaptation to different human joint, improving the characteristics of physical human-robot interaction. The DTS-VSA is designed based on the pulley-cable-spring preloading principle and tendon sheath transmission, and its stiffness model is developed through quasi-static force balance analysis. To realize coordinated and active power argumentation, a fuzzy adaptive assistive controller integrated with human joint torque and stiffness estimation is proposed based on surface electromyography. Feasibility is experimentally verified via three typical load-carrying experiments and ten volunteers. The experimental results show that the average assistance efficiencies of elbow motion and knee motion in different experiment conditions are higher than 44.72% and 38.41%.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"7 3","pages":"1225-1236"},"PeriodicalIF":3.8,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144887839","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 : 2025-07-16DOI: 10.1109/TMRB.2025.3589795
Jonathan Wang;Hisashi Ishida;David Usevitch;Kesavan Venkatesh;Yi Wang;Mehran Armand;Rachel Bronheim;Amit Jain;Adnan Munawar
Surgical training remains a crucial milestone in modern medicine, with procedures such as laminectomy exemplifying the high risks involved. Laminectomy drilling requires precise manual control to mill bony tissue while preserving spinal segment integrity and avoiding breaches in the dura–the protective membrane surrounding the spinal cord. Despite unintended dural tears occurring in up to 11.3% of cases, no assistive tools are currently utilized to reduce this risk. Variability in patient anatomy further complicates learning for novice surgeons. This study introduces CAPTAiN, a critical anatomy-preserving and terrain-augmenting navigation system that provides layered, color-coded voxel guidance to enhance anatomical awareness during spinal drilling. CAPTAiN was evaluated against a standard non-navigated approach through 110 virtual laminectomies performed by 11 orthopedic residents and medical students. CAPTAiN significantly improved surgical completion rates of target anatomy (87.99% vs. 74.42%) and reduced cognitive load across multiple NASA-TLX domains. It also minimized performance gaps across experience levels, enabling novices to perform on par with advanced trainees. These findings highlight CAPTAiN’s potential to optimize surgical execution and support skill development across experience levels. Beyond laminectomy, it demonstrates potential for broader applications across various surgical and drilling procedures, including those in neurosurgery, otolaryngology, and other medical fields.
外科训练在现代医学中仍然是一个重要的里程碑，椎板切除术等手术是其中高风险的例证。椎板切除钻孔需要精确的人工控制来磨碎骨组织，同时保持脊柱节段的完整性，避免硬脑膜（脊髓周围的保护膜）断裂。尽管高达11.3%的病例发生意外硬脑膜撕裂，但目前没有使用辅助工具来降低这种风险。患者解剖结构的变化进一步使外科新手的学习复杂化。本研究介绍了CAPTAiN，这是一种关键的解剖保存和地形增强导航系统，可提供分层、彩色编码的体素指导，以增强脊柱钻孔过程中的解剖意识。通过11名骨科住院医师和医学生进行的110例虚拟椎板切除术，对CAPTAiN进行了标准的非导航入路评估。CAPTAiN显著提高了靶解剖的手术完成率（87.99% vs. 74.42%），并减少了多个NASA-TLX域的认知负荷。它还最大限度地减少了经验水平之间的绩效差距，使新手与高级学员的表现不相上下。这些发现突出了CAPTAiN在优化手术执行和支持不同经验水平的技能发展方面的潜力。除了椎板切除术，它还展示了在各种外科手术和钻孔手术中更广泛应用的潜力，包括神经外科、耳鼻喉科和其他医学领域。
{"title":"Critical Anatomy-Preserving and Terrain-Augmenting Navigation (CAPTAiN): Application to Laminectomy Surgical Education","authors":"Jonathan Wang;Hisashi Ishida;David Usevitch;Kesavan Venkatesh;Yi Wang;Mehran Armand;Rachel Bronheim;Amit Jain;Adnan Munawar","doi":"10.1109/TMRB.2025.3589795","DOIUrl":"https://doi.org/10.1109/TMRB.2025.3589795","url":null,"abstract":"Surgical training remains a crucial milestone in modern medicine, with procedures such as laminectomy exemplifying the high risks involved. Laminectomy drilling requires precise manual control to mill bony tissue while preserving spinal segment integrity and avoiding breaches in the dura–the protective membrane surrounding the spinal cord. Despite unintended dural tears occurring in up to 11.3% of cases, no assistive tools are currently utilized to reduce this risk. Variability in patient anatomy further complicates learning for novice surgeons. This study introduces CAPTAiN, a critical anatomy-preserving and terrain-augmenting navigation system that provides layered, color-coded voxel guidance to enhance anatomical awareness during spinal drilling. CAPTAiN was evaluated against a standard non-navigated approach through 110 virtual laminectomies performed by 11 orthopedic residents and medical students. CAPTAiN significantly improved surgical completion rates of target anatomy (87.99% vs. 74.42%) and reduced cognitive load across multiple NASA-TLX domains. It also minimized performance gaps across experience levels, enabling novices to perform on par with advanced trainees. These findings highlight CAPTAiN’s potential to optimize surgical execution and support skill development across experience levels. Beyond laminectomy, it demonstrates potential for broader applications across various surgical and drilling procedures, including those in neurosurgery, otolaryngology, and other medical fields.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"7 3","pages":"1125-1138"},"PeriodicalIF":3.8,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144887794","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}
Vascular interventional robot enables surgeons to perform percutaneous coronary interventions remotely from the cardiac catheterization room, significantly reducing their radiation exposure. However, the teleoperation mode inherently causes the loss of force perception, increasing surgical risks and limiting the clinical application of vascular interventional robots. Furthermore, existing robot systems lack the ability to enhance surgeons’ force perception and operational transparency. To address these limitations, we developed an intuitive interface with enhanced haptic feedback for vascular interventional robot. Our approach involved three key innovations: Firstly, we designed a magnetism-based feedback mechanism based on the equivalent magnetic charge method to provide high-precision and real-time force feedback. Secondly, we proposed a feedback enhancement model based on surgeons’ experience to reduce damage to vulnerable vascular areas. Thirdly, a dynamic feedback compensation strategy was presented, aiming at addressing the issue of vascular wall rupture resulted from the rapid decay of feedback force during instantaneous guidewire penetration through lesions in surgical procedures. Finally, we conducted a series of experiments to assess the accuracy, dynamic tracking ability, and overall effectiveness of our system. The results demonstrate the developed haptic interface not only improves surgical transparency but also reduces the risk of vascular injury and puncture, thereby advancing the clinical applicability of vascular interventional robots.
{"title":"A Novel Haptic Interface for Enhancing Operational Transparency in Robot-Assisted Vascular Interventional Surgery","authors":"Yu-Ze Feng;Shi-Qi Liu;Xiao-Liang Xie;Xiao-Hu Zhou;Jia-Xing Wang;Chen-Chen Fan;Zeng-Guang Hou;Xi-Yao Ma;Meng Song;Lin-Sen Zhang","doi":"10.1109/TMRB.2025.3583190","DOIUrl":"https://doi.org/10.1109/TMRB.2025.3583190","url":null,"abstract":"Vascular interventional robot enables surgeons to perform percutaneous coronary interventions remotely from the cardiac catheterization room, significantly reducing their radiation exposure. However, the teleoperation mode inherently causes the loss of force perception, increasing surgical risks and limiting the clinical application of vascular interventional robots. Furthermore, existing robot systems lack the ability to enhance surgeons’ force perception and operational transparency. To address these limitations, we developed an intuitive interface with enhanced haptic feedback for vascular interventional robot. Our approach involved three key innovations: Firstly, we designed a magnetism-based feedback mechanism based on the equivalent magnetic charge method to provide high-precision and real-time force feedback. Secondly, we proposed a feedback enhancement model based on surgeons’ experience to reduce damage to vulnerable vascular areas. Thirdly, a dynamic feedback compensation strategy was presented, aiming at addressing the issue of vascular wall rupture resulted from the rapid decay of feedback force during instantaneous guidewire penetration through lesions in surgical procedures. Finally, we conducted a series of experiments to assess the accuracy, dynamic tracking ability, and overall effectiveness of our system. The results demonstrate the developed haptic interface not only improves surgical transparency but also reduces the risk of vascular injury and puncture, thereby advancing the clinical applicability of vascular interventional robots.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"7 3","pages":"1051-1061"},"PeriodicalIF":3.8,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144887667","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 : 2025-07-08DOI: 10.1109/TMRB.2025.3585373
Joanna Jones;Dana D. Damian
Achieving compact and biocompatible advanced technologies with sensing capabilities is a key challenge for the safety critical and highly patient-specific biomedical field. In this study, a compact and versatile soft fluidic sensor-actuator (SA) capable of measuring both force and displacement in static and dynamic conditions is presented. Pressure and resistance are shown to be interchangeable, although best used in combination, when predicting the load on the SA, and show good repeatability and distinction between the loaded and constrained conditions. Using a single sensing medium and across the different diameters tested, the best estimated resolution of just under 4g and 0.07mm is achieved with the 12mm sensor, filled with 1.5mL using pressure sensing only. Furthermore, the SA is demonstrated in two probe applications and as part of a soft robotic implant for tissue-loading based tissue regeneration. The SA showed the ability to distinguish between different objects or areas of varying stiffness, as part of both a rigid-bodied and soft-bodied probe, as well as being able to predict force and displacement from the lengthening and retraction of a soft implant. Overall, this SA has the potential to be a key building block for biomedical robots’ monitoring of both displacement and force.
{"title":"A Soft Fluidic Sensor-Actuator for Active Sensing of Force and Displacement Applied to Tissue Probes and Implants","authors":"Joanna Jones;Dana D. Damian","doi":"10.1109/TMRB.2025.3585373","DOIUrl":"https://doi.org/10.1109/TMRB.2025.3585373","url":null,"abstract":"Achieving compact and biocompatible advanced technologies with sensing capabilities is a key challenge for the safety critical and highly patient-specific biomedical field. In this study, a compact and versatile soft fluidic sensor-actuator (SA) capable of measuring both force and displacement in static and dynamic conditions is presented. Pressure and resistance are shown to be interchangeable, although best used in combination, when predicting the load on the SA, and show good repeatability and distinction between the loaded and constrained conditions. Using a single sensing medium and across the different diameters tested, the best estimated resolution of just under 4g and 0.07mm is achieved with the 12mm sensor, filled with 1.5mL using pressure sensing only. Furthermore, the SA is demonstrated in two probe applications and as part of a soft robotic implant for tissue-loading based tissue regeneration. The SA showed the ability to distinguish between different objects or areas of varying stiffness, as part of both a rigid-bodied and soft-bodied probe, as well as being able to predict force and displacement from the lengthening and retraction of a soft implant. Overall, this SA has the potential to be a key building block for biomedical robots’ monitoring of both displacement and force.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"7 3","pages":"1329-1340"},"PeriodicalIF":3.8,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144887840","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 : 2025-07-07DOI: 10.1109/TMRB.2025.3583146
Peng Wang;Li Jiang;Yangjunjian Zhou;Baoshan Niu;Yiming Ji;Hong Liu
Minimally invasive surgery (MIS) is a widely adopted surgical approach in contemporary medicine, significantly reducing patient trauma. However, it imposes demands on the surgeon’s operation. To reduce the surgical complexity, this study developed a highly dexterous operative tool for MIS procedures. The tool utilizes the widely adopted radiofrequency ablation (RFA) technology in surgical to separate tissues by generating heat through high-frequency currents. It consists of three sets of grippers and radiofrequency (RF) transmitters at their tips. The tool enables intact capture and separation the lesion, thereby eliminating the need for an additional abdominal incision compared to traditional methods and reducing the complexity of liver tumor resection in confined spaces. To minimize the impact on healthy tissue, this paper proposed a calculation method that determines the tool’s key structural parameters and singularity position based on the lesion size, resulting in a lesion volume that constitutes approximately 48.4% of the excised area. Given the high-resistance lever mechanisms in the usage scenario, auxiliary tensiles utilizing RF transmitters are introduced. Simulation analysis confirms that this method reduces the tool’s maximum hinge forces and torques to one-quarter of its original value. Finally, comprehensive experiments validate the feasibility of the gripping tool in MIS.
{"title":"Intact Lesion Separation and Capture Tool: A Dual-Model Motion Mechanism for Simplifying Minimally Invasive Surgery","authors":"Peng Wang;Li Jiang;Yangjunjian Zhou;Baoshan Niu;Yiming Ji;Hong Liu","doi":"10.1109/TMRB.2025.3583146","DOIUrl":"https://doi.org/10.1109/TMRB.2025.3583146","url":null,"abstract":"Minimally invasive surgery (MIS) is a widely adopted surgical approach in contemporary medicine, significantly reducing patient trauma. However, it imposes demands on the surgeon’s operation. To reduce the surgical complexity, this study developed a highly dexterous operative tool for MIS procedures. The tool utilizes the widely adopted radiofrequency ablation (RFA) technology in surgical to separate tissues by generating heat through high-frequency currents. It consists of three sets of grippers and radiofrequency (RF) transmitters at their tips. The tool enables intact capture and separation the lesion, thereby eliminating the need for an additional abdominal incision compared to traditional methods and reducing the complexity of liver tumor resection in confined spaces. To minimize the impact on healthy tissue, this paper proposed a calculation method that determines the tool’s key structural parameters and singularity position based on the lesion size, resulting in a lesion volume that constitutes approximately 48.4% of the excised area. Given the high-resistance lever mechanisms in the usage scenario, auxiliary tensiles utilizing RF transmitters are introduced. Simulation analysis confirms that this method reduces the tool’s maximum hinge forces and torques to one-quarter of its original value. Finally, comprehensive experiments validate the feasibility of the gripping tool in MIS.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"7 3","pages":"1005-1016"},"PeriodicalIF":3.8,"publicationDate":"2025-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144887797","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：