1066 results found
Troccaz J, Dagnino G, Yang G-Z, 2019, Frontiers of Medical Robotics: From Concept to Systems to Clinical Translation., Annu Rev Biomed Eng
Medical robotics is poised to transform all aspects of medicine-from surgical intervention to targeted therapy, rehabilitation, and hospital automation. A key area is the development of robots for minimally invasive interventions. This review provides a detailed analysis of the evolution of interventional robots and discusses how the integration of imaging, sensing, and robotics can influence the patient care pathway toward precision intervention and patient-specific treatment. It outlines how closer coupling of perception, decision, and action can lead to enhanced dexterity, greater precision, and reduced invasiveness. It provides a critical analysis of some of the key interventional robot platforms developed over the years and their relative merit and intrinsic limitations. The review also presents a future outlook for robotic interventions and emerging trends in making them easier to use, lightweight, ergonomic, and intelligent, and thus smarter, safer, and more accessible for clinical use. Expected final online publication date for the Annual Review of Biophysics Volume 48 is May 3, 2019. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.
Ros-Freixedes L, Gao A, Liu N, et al., 2019, Design optimization of a contact-aided continuum robot for endobronchial interventions based on anatomical constraints, International Journal of Computer Assisted Radiology and Surgery, ISSN: 1861-6429
PURPOSE: A laser-profiled continuum robot (CR) with a series of interlocking joints has been developed in our center to reach deeper areas of the airways. However, it deflects with constant curvature, which thus increases the difficulty of entering specific bronchi without relying on the tissue reaction forces. This paper aims to propose an optimization framework to find the best design parameters for nonconstant curvature CRs to reach distal targets while attempting to avoid the collision with the surrounding tissue. METHODS: First, the contact-aided compliant mechanisms (CCMs) are integrated with the continuum robot to achieve the nonconstant curvature. Second, forward kinematics considering CCMs is built. Third, inverse kinematics is implemented to steer the robot tip toward the desired targets within the confined anatomy. Finally, an optimization framework is proposed to find the best robot design to reach the target with the least collision to the bronchi walls. RESULTS: Experiments are carried out to verify the feasibility of CCMs to enable the nonconstant curvature deflection, and simulations demonstrate a lower cost function value to reach a target for the nonconstant curvature optimized design with respect to the standard constant curvature robot (0.11 vs. 2.66). In addition, the higher capacity of the optimized design to complete the task is validated by interventional experiments using fluoroscopy. CONCLUSION: Results demonstrate the effectiveness of the proposed framework to find an optimized CR with nonconstant curvature to perform safer interventions to reach distal targets.
Zhang D, Xiao B, Huang B, et al., 2019, A self-adaptive motion scaling framework for surgical robot remote control, IEEE Robotics and Automation Letters, Vol: 4, Pages: 359-366, ISSN: 2377-3766
Master-slave control is a common form of human-robot interaction for robotic surgery. To ensure seamless and intuitive control, a mechanism of self-adaptive motion scaling during teleoperaton is proposed in this letter. The operator can retain precise control when conducting delicate or complex manipulation, while the movement to a remote target is accelerated via adaptive motion scaling. The proposed framework consists of three components: 1) situation awareness, 2) skill level awareness, and 3) task awareness. The self-adaptive motion scaling ratio allows the operators to perform surgical tasks with high efficiency, forgoing the need of frequent clutching and instrument repositioning. The proposed framework has been verified on a da Vinci Research Kit to assess its usability and robustness. An in-house database is constructed for offline model training and parameter estimation, including both the kinematic data obtained from the robot and visual cues captured through the endoscope. Detailed user studies indicate that a suitable motion-scaling ratio can be obtained and adjusted online. The overall performance of the operators in terms of control efficiency and task completion is significantly improved with the proposed framework.
Gil B, Anastasova S, Yang GZ, 2019, A Smart Wireless Ear-Worn Device for Cardiovascular and Sweat Parameter Monitoring During Physical Exercise: Design and Performance Results, SENSORS, Vol: 19, ISSN: 1424-8220
Zhang D, Xiao B, Huang B, et al., 2019, A Self-Adaptive Motion Scaling Framework for Surgical Robot Remote Control, IEEE Robotics and Automation Letters, Vol: 4, Pages: 359-366
© 2016 IEEE. Master-slave control is a common form of human-robot interaction for robotic surgery. To ensure seamless and intuitive control, a mechanism of self-adaptive motion scaling during teleoperaton is proposed in this letter. The operator can retain precise control when conducting delicate or complex manipulation, while the movement to a remote target is accelerated via adaptive motion scaling. The proposed framework consists of three components: 1) situation awareness, 2) skill level awareness, and 3) task awareness. The self-adaptive motion scaling ratio allows the operators to perform surgical tasks with high efficiency, forgoing the need of frequent clutching and instrument repositioning. The proposed framework has been verified on a da Vinci Research Kit to assess its usability and robustness. An in-house database is constructed for offline model training and parameter estimation, including both the kinematic data obtained from the robot and visual cues captured through the endoscope. Detailed user studies indicate that a suitable motion-scaling ratio can be obtained and adjusted online. The overall performance of the operators in terms of control efficiency and task completion is significantly improved with the proposed framework.
Hu Y, Li W, Zhang L, et al., 2019, Designing, Prototyping, and Testing a Flexible Suturing Robot for Transanal Endoscopic Microsurgery, IEEE ROBOTICS AND AUTOMATION LETTERS, Vol: 4, Pages: 1669-1675, ISSN: 2377-3766
Zhou X-Y, Yang G-Z, 2019, Normalization in Training U-Net for 2-D Biomedical Semantic Segmentation, IEEE ROBOTICS AND AUTOMATION LETTERS, Vol: 4, Pages: 1792-1799, ISSN: 2377-3766
Gras G, Yang G-Z, 2019, Context-Aware Modeling for Augmented Reality Display Behaviour, IEEE ROBOTICS AND AUTOMATION LETTERS, Vol: 4, Pages: 562-569, ISSN: 2377-3766
Gu Y, Vyas K, Yang J, et al., 2019, Transfer Recurrent Feature Learning for Endomicroscopy Image Recognition, IEEE TRANSACTIONS ON MEDICAL IMAGING, Vol: 38, Pages: 791-801, ISSN: 0278-0062
Yang G-Z, 2019, Robot learning-Beyond imitation, SCIENCE ROBOTICS, Vol: 4, ISSN: 2470-9476
Hu Y, Zhang L, senici C, et al., Design, fabrication and testing a semi-automatic sewing device for personalized stent graft manufacturing, IEEE/ASME Transactions on Mechatronics, ISSN: 1083-4435
For the treatment of Abdominal Aortic Aneurysm (AAA), a personalised stent graft is used to ensure it fits tightly to the patients vessel geometry. A personalised stent graft is usually handmade which requires thousands of stitches and can take weeks or even months to complete. This delay may expose the patient to the risk of aneurysm rupture. This paper presents a robotic sewing device that can enhance the stent graft sewing speed by providing automated needle manipulation. It simplifies the sewing process and has the potential to achieve fully automated stent graft manufacturing via a vision-guided system. The device features a sewing probe that can switch a double pointed semi-circular needle between two movable jaws. This forgoes the need for manual needle handling including grasping, driving rotation, releasing and re-grasping, which requires a high level of manual dexterity and attention. This paper presents the design of the device, its mechanical synthesis and experimental validation. The focus of the paper is on the linkage parameter optimisation and needle locking mechanism design. The proposed device has been fabricated using 3D rapid prototyping techniques, and its performance has been compared with the conventional manual sewing method. The experimental results show that the device can achieve a 30% reduction of the completion time for a stitching task while achieving better consistency and quality of the stitches.
Hu Y, Zhang L, Li W, et al., Design and fabrication of a 3D printed metallic flexible joint for snake-like surgical robot, IEEE Robotics and Automation Letters, ISSN: 2377-3766
Snake-like robots have numerous applications in minimally invasive surgery (MIS). One important research topic of snake-like robots is the flexible joint mechanism and its actuation. This paper describes the design and fabrication of a new type of flexible joint mechanism which is enabled by metal powder bed additive manufacturing technique. Kinematics and static models of the flexible joint are presented, which can help in designing and controlling the flexible joint. As a compliant mechanism, the fatigue characteristics of the flexible joint is investigated. Finite Element Analysis (FEA) is also performed aiming for optimising the design process. In the experiment section, model estimation, FEA and experiment validation are conducted for further understanding the characteristics of the flexible joint. An example design that can survive after 100,000 full loading cycles is demonstrated. Finally, different design variations of the proposed method and a multisection flexible endoscope using the proposed design are introduced. The proposed flexible joint has the potential not only in reducing the cost of manufacturing and assembling a snake-like surgical robot, but also benefits for developing of more sophisticated 3D snake robotic structure which has an optimised space for embedded sensing and actuation.
Berthet-Rayne P, Leibrandt K, Kim K, et al., 2019, Rolling-Joint Design Optimization for Tendon Driven Snake-like Surgical Robots, 25th IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Publisher: IEEE, Pages: 4964-4971, ISSN: 2153-0858
Zhou X-Y, Riga C, Lee S-L, et al., 2019, Towards Automatic 3D Shape Instantiation for Deployed Stent Grafts: 2D Multiple-class and Class-imbalance Marker Segmentation with Equally-weighted Focal U-Net, 25th IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Publisher: IEEE, Pages: 1261-1267, ISSN: 2153-0858
Chi W, Liu J, Abdelaziz MEMK, et al., 2019, Trajectory Optimization of Robot-Assisted Endovascular Catheterization with Reinforcement Learning, 25th IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Publisher: IEEE, Pages: 3875-3881, ISSN: 2153-0858
Grammatikopoulou M, Zhang L, Yang G-Z, 2019, Depth Estimation of Optically Transparent Microrobots Using Convolutional and Recurrent Neural Networks, 25th IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Publisher: IEEE, Pages: 4895-4900, ISSN: 2153-0858
Gu Y, Hu Y, Zhang L, et al., 2019, Cross-Scene Suture Thread Parsing for Robot Assisted Anastomosis based on Joint Feature Learning, 25th IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Publisher: IEEE, Pages: 769-776, ISSN: 2153-0858
Fontanelli GA, Yang G-Z, Siciliano B, 2019, A comparison of assistive methods for suturing in MIRS, 25th IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Publisher: IEEE, Pages: 4389-4395, ISSN: 2153-0858
Fabelo H, Ortega S, Szolna A, et al., 2019, In-Vivo Hyperspectral Human Brain Image Database for Brain Cancer Detection, IEEE ACCESS, Vol: 7, Pages: 39098-39116, ISSN: 2169-3536
Li B, Tan H, Anastasova-Ivanova S, et al., 2019, A Bioinspired 3D micro-structure for graphene-based bacteria sensing, Biosensors and Bioelectronics, Vol: 123, Pages: 77-84, ISSN: 0956-5663
Nature is a great source of inspiration for the development of solutions for biomedical problems. We present a novel biosensor design utilizing two-photon polymerisation and graphene to fabricate an enhanced biosensing platform for the detection of motile bacteria. A cage comprising venous valve-inspired directional micro-structure is fabricated around graphene-based sensing electronics. The asymmetric 3D micro-structure promotes motile cells to swim from outside the cage towards the inner-most chamber, resulting in concentrated bacteria surrounding the central sensing region, thus enhancing the sensing signal. The concentrating effect is proved across a range of cell cultures - from 101 CFU/ml to 109 CFU/ml. Fluorescence analysis shows a 3.38–3.5 times enhanced signal. pH sensor presents a 2.14–3.08 times enhancement via the detection of cellar metabolite. Electrical measurements demonstrate an 8.8–26.7 times enhanced current. The proposed platform provides a new way of leveraging bio-inspired 3D printing and 2D materials for the development of sensing devices for biomedical applications.
Shen M, Gu Y, Liu N, et al., Context-aware depth and pose estimation for bronchoscopic navigation, IEEE Robotics and Automation Letters, ISSN: 2377-3766
Endobronchial intervention is increasingly used asa minimal invasive means of lung intervention. Vision-basedlocalization approaches are often sensitive to image artifacts inbronchoscopic videos. In this paper, a robust navigation systembased on a context-aware depth recovery approach for monocularvideo images is presented. To handle the artifacts, a conditionalgenerative adversarial learning framework is proposed for re-liable depth recovery. The accuracy of depth estimation andcamera localization is validated on anin vivodataset. Bothquantitative and qualitative results demonstrate that the depthrecovered with the proposed method preserves better structuralinformation of airway lumens in the presence of image artifacts,and the improved camera localization accuracy demonstrates itsclinical potential for bronchoscopic navigation.
Yun G, Shen M, Jie Y, et al., 2018, Reliable Label-Efficient Learning for Biomedical Image Recognition, IEEE Transactions on Biomedical Engineering, ISSN: 0018-9294
IEEE The use of deep neural networks for biomedical image analysis requires a sufficient number of labeled datasets. In order to acquire accurate labels as the gold standard, multiple clinicians with specific expertise are required for both annotation and proofreading. This process is time-consuming and labor-intensive, making high-quality and large-annotated biomedical datasets difficult. To address this problem, we propose a deep active learning framework which enables active selection of both informative queries and reliable experts. To measure the uncertainty of the unlabeled data, a dropout-based strategy is integrated with a similarity criterion for both data selection and random error elimination. To select the reliable labelers, we adopt the expertise estimator to learn the expertise levels of labelers via offline-testing and online consistency evaluation.The proposed method is applied to classification tasks on two types of medical images including confocal endomicroscopy images and gastrointestinal endoscopic images. The annotations are acquired from multiple labelers with diverse levels of expertise. The experiments demonstrate the efficiency and promising performance of the proposed method compared to a set of baseline methods.
Kassanos P, Anastasova S, Yang G-Z, 2018, Towards Low-Cost Cell Culturing Platforms with Integrated Sensing Capabilities, IEEE Biomedical Circuits and Systems Conference (BioCAS) - Advanced Systems for Enhancing Human Health, Publisher: IEEE, Pages: 327-330, ISSN: 2163-4025
Teachasrisaksakul K, Wu L, Yang G-Z, et al., 2018, Hand gesture recognition with inertial sensors, 40th International Conference of the IEEE Engineering in Medicine and Biology Society, Publisher: IEEE, Pages: 3517-3520, ISSN: 1558-4615
Dyscalculia is a learning difficulty hindering fundamental arithmetical competence. Children with dyscalculia often have difficulties in engaging in lessons taught with traditional teaching methods. In contrast, an educational game is an attractive alternative. Recent educational studies have shown that gestures could have a positive impact in learning. With the recent development of low cost wearable sensors, a gesture based educational game could be used as a tool to improve the learning outcomes particularly for children with dyscalculia. In this paper, two generic gesture recognition methods are proposed for developing an interactive educational game with wearable inertial sensors. The first method is a multilayered perceptron classifier based on the accelerometer and gyroscope readings to recognize hand gestures. As gyroscope is more power demanding and not all low-cost wearable device has a gyroscope, we have simplified the method using a nearest centroid classifier for classifying hand gestures with only the accelerometer readings. The method has been integrated into open-source educational games. Experimental results based on 5 subjects have demonstrated the accuracy of inertial sensor based hand gesture recognitions. The results have shown that both methods can recognize 15 different hand gestures with the accuracy over 93%.
Modi H, Singh H, Yang G, et al., 2018, Neural correlates of stress resilience in the operating room, Journal of The American College of Surgeons, Vol: 227, Pages: e208-e208, ISSN: 1072-7515
IntroductionIntraoperative stressors can increase surgeons’ mental demands, precipitating technical performance decline and risking patient safety. However, the neural signatures of stress resilience among surgeons remain unknown. We aimed to compare activation in the prefrontal cortex (PFC)–important for attention and concentration–between residents demonstrating performance stability and those exhibiting performance decline when operating under time pressure.MethodsThirty-three surgical residents [median age (range) = 33 years (29 to 56), 27 males] performed a laparoscopic suturing task under ‘self-paced’ (no time restriction) and ‘time pressure’ (2-minute per knot time restriction) conditions. A composite deterioration score was calculated based on between-condition differences in technical performance, and subjects were divided into quartiles reflecting performance stability (Q1) and decline (Q4). Changes in oxygenated haemoglobin concentration (HbO2) measured at 24 prefrontal locations using functional near-infrared spectroscopy were compared between Q1 and Q4. Subjective workload was quantified using the Surgical Task Load Index (SURG-TLX).ResultsUnder time pressure, Q1 residents demonstrated task-induced increases in HbO2 in the bilateral ventrolateral PFC (VLPFC), whereas Q4 residents demonstrated HbO2 decreases. The amplitude of activation (ΔHbO2) was significantly greater in Q1 than Q4 in the bilateral VLPFC (left VLPFC: Q1=0.44±1.36μM, Q4=-0.03±1.83μM; right VLPFC: Q1=0.49±1.70μM, Q4=-0.32±2.00μM). There were no significant between-group differences in SURG-TLX scores.ConclusionsResilience to intraoperative stress is associated with sustained prefrontal activation indicating preserved attention and concentration. In contrast, sensitivity to stress is marked by prefrontal deactivation suggesting task disengagement. Future work will aim to develop interventions that recr
Tudor A, Delaney C, Zhang H, et al., 2018, Fabrication of soft, stimulus-responsive structures with sub-micron resolution via two-photon polymerization of poly(ionic liquid)s, Materials Today, Vol: 21, Pages: 807-816, ISSN: 1369-7021
Soft, stimulus-responsive 3D structures created from crosslinked poly(ionic liquid)s (PILs) have been fabricated at unprecedented sub-micron resolution by direct laser writing (DLW). These structures absorb considerable quantities of solvent (e.g., water, alcohol, and acetone) to produce PIL hydrogels that exhibit stimulus-responsive behavior. Due to their flexibility and soft, responsive nature, these structures are much more akin to biological systems than the conventional, highly crosslinked, rigid structures typically produced using 2-photon polymerization (2-PP). These PIL gels expand/contract due to solvent uptake/release, and, by exploiting inherited properties of the ionic liquid monomer (ILM), thermo-responsive gels that exhibit reversible area change (30 ± 3%, n = 40) when the temperature is raised from 20 °C to 70 °C can be created. The effect is very rapid, with the response indistinguishable from the microcontroller heating rate of 7.4 °C s−1. The presence of an endoskeleton-like framework within these structures influences movement arising from expansion/contraction and assists the retention of structural integrity during actuation cycling.
Zheng H, Gu Y, Qin Y, et al., 2018, Small lesion classification in dynamic contrast enhancement MRI for breast cancer early detection, Medical Image Computing and Computer Assisted Intervention – MICCAI 2018, Publisher: Springer Nature Switzerland AG, Pages: 876-884, ISSN: 0302-9743
Classification of small lesions is of great importance for early detection of breast cancer. The small size of lesion makes handcrafted features ineffective for practical applications. Furthermore, the relatively small data sets also impose challenges on deep learning based classification methods. Dynamic Contrast Enhancement MRI (DCE-MRI) is widely-used for women at high risk of breast cancer, and the dynamic features become more important in the case of small lesion. To extract more dynamic information, we propose a method for processing sequence data to encode the DCE-MRI, and design a new structure, dense convolutional LSTM, by adding a dense block in convolutional LSTM unit. Faced with the huge number of parameters in deep neural network, we add some semantic priors as constrains to improve generalization performance. Four latent attributes are extracted from diagnostic reports and pathological results, and are predicted together with the classification of benign or malignant. Predicting the latent attributes as auxiliary tasks can help the training of deep neural network, which makes it possible to train complex network with small size dataset and achieve a satisfactory result. Our methods improve the accuracy from 0.625, acquired by ResNet, to 0.847.
Gu Y, Vyas K, Yang J, et al., 2018, Weakly supervised representation learning for endomicroscopy image analysis, Medical Image Computing and Computer Assisted Intervention – MICCAI 2018, Publisher: Springer, Pages: 326-334, ISSN: 0302-9743
This paper proposes a weakly-supervised representation learning framework for probe-based confocal laser endomicroscopy (pCLE). Unlike previous frame-based and mosaic-based methods, the proposed framework adopts deep convolutional neural networks and integrates frame-based feature learning, global diagnosis prediction and local tumor detection into a unified end-to-end model. The latent objects in pCLE mosaics are inferred via semantic label propagation and the deep convolutional neural networks are trained with a composite loss function. Experiments on 700 pCLE samples demonstrate that the proposed method trained with only global supervisions is able to achieve higher accuracy on global and local diagnosis prediction.
Liu N, Abdelaziz MEMK, Shen M, et al., 2018, Design and Kinematics Characterization of a Laser-Profiled Continuum Manipulator for the Guidance of Bronchoscopic Instruments, IEEE International Conference on Robotics and Automation (ICRA), Publisher: IEEE COMPUTER SOC, Pages: 25-31, ISSN: 1050-4729
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.