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}
Pub Date : 2025-06-25DOI: 10.1109/TMRB.2025.3583169
Michael Kam;Jiawei Ge;Naveed D. Riaziat;Justin D. Opfermann;Leila J. Mady;Jeremy D. Brown;Axel Krieger
Oral cavity cancer, a common head and neck cancer, is typically treated through precise tumor excision via electrosurgery. Autonomous robotic electrosurgery has demonstrated the potential to achieve more accurate and consistent resection margins compared to manual methods, thereby improving surgical outcomes. However, current autonomous systems face challenges in tracking tissue deformation during electrosurgical cutting due to unpredictable and complex soft tissue dynamics. Failure to monitor and adapt to tissue deformation can significantly compromise resection precision. This paper presents an autonomous closed-loop robotic electrosurgery system to enhance surgical precision via 3D tissue tracking and image-based feedback control utilizing a Red Green Blue – Depth (RGB-D) sensor. The developed 3D tissue tracker employs CoTracker, a deep learning-based model for markerless tracking, complemented by a tool-occlusion algorithm to achieve tissue deformation tracking with no prior knowledge of the tissue model. The estimated deformation is fed into a fuzzy logic controller, which dynamically adjusts the cutting velocity to minimize cutting error during electrosurgery. The system’s efficacy was validated using ex vivo porcine tongues, demonstrating a 55% reduction in average cutting error (from 1.2 mm to 0.54 mm, $plt 0.001$ ) in closed-loop operations (N=6) compared to open-loop cutting without feedback control (N=3). The results demonstrate the effectiveness of image-based closed-loop control in improving margin accuracy, a key factor in reducing the likelihood of cancer recurrence.
{"title":"Autonomous Closed-Loop Control for Robotic Soft Tissue Electrosurgery Using RGB-D Image Guidance","authors":"Michael Kam;Jiawei Ge;Naveed D. Riaziat;Justin D. Opfermann;Leila J. Mady;Jeremy D. Brown;Axel Krieger","doi":"10.1109/TMRB.2025.3583169","DOIUrl":"https://doi.org/10.1109/TMRB.2025.3583169","url":null,"abstract":"Oral cavity cancer, a common head and neck cancer, is typically treated through precise tumor excision via electrosurgery. Autonomous robotic electrosurgery has demonstrated the potential to achieve more accurate and consistent resection margins compared to manual methods, thereby improving surgical outcomes. However, current autonomous systems face challenges in tracking tissue deformation during electrosurgical cutting due to unpredictable and complex soft tissue dynamics. Failure to monitor and adapt to tissue deformation can significantly compromise resection precision. This paper presents an autonomous closed-loop robotic electrosurgery system to enhance surgical precision via 3D tissue tracking and image-based feedback control utilizing a Red Green Blue – Depth (RGB-D) sensor. The developed 3D tissue tracker employs CoTracker, a deep learning-based model for markerless tracking, complemented by a tool-occlusion algorithm to achieve tissue deformation tracking with no prior knowledge of the tissue model. The estimated deformation is fed into a fuzzy logic controller, which dynamically adjusts the cutting velocity to minimize cutting error during electrosurgery. The system’s efficacy was validated using ex vivo porcine tongues, demonstrating a 55% reduction in average cutting error (from 1.2 mm to 0.54 mm, <inline-formula> <tex-math>$plt 0.001$ </tex-math></inline-formula>) in closed-loop operations (N=6) compared to open-loop cutting without feedback control (N=3). The results demonstrate the effectiveness of image-based closed-loop control in improving margin accuracy, a key factor in reducing the likelihood of cancer recurrence.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"7 3","pages":"1041-1050"},"PeriodicalIF":3.8,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144887774","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 : 2025-06-25DOI: 10.1109/TMRB.2025.3583160
Aedan Mangan;Sukjun Kim;Noah Jones;Michael G. Brandel;Jeremy J. Heit;Alexander Norbash;John T. Hwang;Elliot Hawkes;Tania K. Morimoto
Endovascular surgeries generally rely on push-based catheters and guidewires, which require significant training to master and can still result in high stress being exerted on the anatomy, especially in tortuous paths. Because these procedures are so technically challenging to perform, many patients have limited access to high-quality treatment. Although various robotic systems have been developed to enhance navigation capabilities, they can also apply high stresses due to sliding against the vascular walls, impeding movement and raising the risk of vascular damage. Soft growing robots offer a promising alternative since their method of movement via eversion minimizes interaction forces with the environment and enables follow-the-leader navigation through tortuous paths. However, reliable steering of small-scale growing robots remains a significant challenge. We propose a robot architecture that combines a hydraulically-actuated, soft growing robot with a soft, tendon-driven notched continuum robot to overcome the challenges of steering for small-scale growing robots in endovascular procedures. The soft notched continuum robot successfully steers around the most difficult aortic arch type, and a 2.67 mm diameter growing robot—comparable in size to current catheters—deploys from the tip, pulling an aspiration catheter through extremely tortuous vessels. We present the design, manufacturing, and control of the notched continuum robot, growing robot, and proximal actuation subsystem. Overall, this robotic architecture facilitates active steering in proximal anatomy and navigation in tortuous distal vessels, with potential to reduce procedure times and expand access to care.
{"title":"Serially-Connected Soft Continuum Robots for Endovascular Emergencies","authors":"Aedan Mangan;Sukjun Kim;Noah Jones;Michael G. Brandel;Jeremy J. Heit;Alexander Norbash;John T. Hwang;Elliot Hawkes;Tania K. Morimoto","doi":"10.1109/TMRB.2025.3583160","DOIUrl":"https://doi.org/10.1109/TMRB.2025.3583160","url":null,"abstract":"Endovascular surgeries generally rely on push-based catheters and guidewires, which require significant training to master and can still result in high stress being exerted on the anatomy, especially in tortuous paths. Because these procedures are so technically challenging to perform, many patients have limited access to high-quality treatment. Although various robotic systems have been developed to enhance navigation capabilities, they can also apply high stresses due to sliding against the vascular walls, impeding movement and raising the risk of vascular damage. Soft growing robots offer a promising alternative since their method of movement via eversion minimizes interaction forces with the environment and enables follow-the-leader navigation through tortuous paths. However, reliable steering of small-scale growing robots remains a significant challenge. We propose a robot architecture that combines a hydraulically-actuated, soft growing robot with a soft, tendon-driven notched continuum robot to overcome the challenges of steering for small-scale growing robots in endovascular procedures. The soft notched continuum robot successfully steers around the most difficult aortic arch type, and a 2.67 mm diameter growing robot—comparable in size to current catheters—deploys from the tip, pulling an aspiration catheter through extremely tortuous vessels. We present the design, manufacturing, and control of the notched continuum robot, growing robot, and proximal actuation subsystem. Overall, this robotic architecture facilitates active steering in proximal anatomy and navigation in tortuous distal vessels, with potential to reduce procedure times and expand access to care.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"7 3","pages":"1029-1040"},"PeriodicalIF":3.8,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144887775","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 : 2025-06-25DOI: 10.1109/TMRB.2025.3583144
S. Hossein Sadat Hosseini;Arvin Samiei;Mojtaba Ahmadi
The increasing demand for responsive and intuitive assistive walking devices, driven by an aging population, underscores the need for intelligent systems powered by emerging machine learning (ML) technologies. This study introduces a novel feature fusion framework based on the Nondominated Sorting Genetic Algorithm II (NSGA-II) to fuse surface electromyography (sEMG) signals with inertial measurement unit (IMU) data and a high-level control architecture, enabling accurate and robust motion intention detection for robotic assistive walking systems. The proposed feature fusion method consistently outperformed statistical filter-based techniques such as mutual information (MI), minimum redundancy maximum relevance (MRMR), correlation coefficient (CC), and Fisher score (FS). It significantly improved the classification metrics of random forest (RF), K-nearest neighbour (KNN), and support vector machine (SVM) classifiers across varying feature counts. For example, the feature fusion algorithm improved RF’s accuracy by 6.74%, 7.67%, 6.35%, and 3.60% and enhanced precision by 6.77%, 7.67%, 6.36%, and 3.61% relative to FS, CC, MRMR, and MI, respectively. Similarly, the algorithm increased RF’s recall by 6.79%, 7.71%, 6.38%, and 3.62%. The proposed feature fusion and high-level and low-level control frameworks were implemented on SoloWalk for real-time interaction, enabling participants to perform daily walking activities. Real-time validation confirmed system stability across gait patterns and user variations, demonstrating its effectiveness in assistive walking robots.
{"title":"Genetic Algorithm-Optimized Feature Selection for sEMG-IMU Fusion Improves Intention Detection in AI-Driven Robotic Walking System","authors":"S. Hossein Sadat Hosseini;Arvin Samiei;Mojtaba Ahmadi","doi":"10.1109/TMRB.2025.3583144","DOIUrl":"https://doi.org/10.1109/TMRB.2025.3583144","url":null,"abstract":"The increasing demand for responsive and intuitive assistive walking devices, driven by an aging population, underscores the need for intelligent systems powered by emerging machine learning (ML) technologies. This study introduces a novel feature fusion framework based on the Nondominated Sorting Genetic Algorithm II (NSGA-II) to fuse surface electromyography (sEMG) signals with inertial measurement unit (IMU) data and a high-level control architecture, enabling accurate and robust motion intention detection for robotic assistive walking systems. The proposed feature fusion method consistently outperformed statistical filter-based techniques such as mutual information (MI), minimum redundancy maximum relevance (MRMR), correlation coefficient (CC), and Fisher score (FS). It significantly improved the classification metrics of random forest (RF), K-nearest neighbour (KNN), and support vector machine (SVM) classifiers across varying feature counts. For example, the feature fusion algorithm improved RF’s accuracy by 6.74%, 7.67%, 6.35%, and 3.60% and enhanced precision by 6.77%, 7.67%, 6.36%, and 3.61% relative to FS, CC, MRMR, and MI, respectively. Similarly, the algorithm increased RF’s recall by 6.79%, 7.71%, 6.38%, and 3.62%. The proposed feature fusion and high-level and low-level control frameworks were implemented on SoloWalk for real-time interaction, enabling participants to perform daily walking activities. Real-time validation confirmed system stability across gait patterns and user variations, demonstrating its effectiveness in assistive walking robots.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"7 3","pages":"1212-1224"},"PeriodicalIF":3.8,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144887795","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}
The development of procedure-specific surgical robots has become essential for tackling complex clinical challenges. Flexible bronchoscope robots (FBRs) have emerged over the past decade, revealing broad prospects for the safe, precise, and reliable diagnosis of peripheral pulmonary nodules (PPNs), which is crucial for enabling early lung cancer treatment. However, in advancing FBR development, roboticists sometimes stray from or overlook practical surgical considerations, which might impede its clinical implementation. This review aims to bridge this gap by offering an engineering-focused perspective enriched with critical medical insights to drive the clinical translation of next-generation FBRs. We begin by highlighting the medical significance and current state of FBR research. Then, we outline the “ambient environments” of FBRs: the supported procedure, robotic system, steering tools, and deployment modes. Subsequently, we summarize recent progress in FBR technology, focusing on two key areas: procedure-specific design and modeling to improve intervention capabilities, and autonomous navigation and control strategies to enhance autonomy. Based on the given analysis, we discuss the development directions of next-generation FBRs according to the current clinical challenges and the engineering approaches to their realization.
{"title":"A Review of Flexible Bronchoscope Robots for Peripheral Pulmonary Nodule Intervention","authors":"Yuzhou Duan;Jie Ling;Micky Rakotondrabe;Zuoqing Yu;Lei Zhang;Yuchuan Zhu","doi":"10.1109/TMRB.2025.3583172","DOIUrl":"https://doi.org/10.1109/TMRB.2025.3583172","url":null,"abstract":"The development of procedure-specific surgical robots has become essential for tackling complex clinical challenges. Flexible bronchoscope robots (FBRs) have emerged over the past decade, revealing broad prospects for the safe, precise, and reliable diagnosis of peripheral pulmonary nodules (PPNs), which is crucial for enabling early lung cancer treatment. However, in advancing FBR development, roboticists sometimes stray from or overlook practical surgical considerations, which might impede its clinical implementation. This review aims to bridge this gap by offering an engineering-focused perspective enriched with critical medical insights to drive the clinical translation of next-generation FBRs. We begin by highlighting the medical significance and current state of FBR research. Then, we outline the “ambient environments” of FBRs: the supported procedure, robotic system, steering tools, and deployment modes. Subsequently, we summarize recent progress in FBR technology, focusing on two key areas: procedure-specific design and modeling to improve intervention capabilities, and autonomous navigation and control strategies to enhance autonomy. Based on the given analysis, we discuss the development directions of next-generation FBRs according to the current clinical challenges and the engineering approaches to their realization.","PeriodicalId":73318,"journal":{"name":"IEEE transactions on medical robotics and bionics","volume":"7 3","pages":"845-862"},"PeriodicalIF":3.8,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144887776","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：