Ying Hu

• Chinese Academy of Sciences

Ultrasound (US) examination is widely used to diagnose carotid artery plaque, which requires the sonographer to guide the probe to scan along a specific path for complete coverage of the carotid artery region. Meanwhile, stable probe-neck interaction is important for high-quality image acquisition. In this study, a robotic system for autonomous car...

Computer-aided ultrasound (US) imaging is an important prerequisite for early clinical diagnosis and treatment. Due to the harsh ultrasound (US) image quality and the blurry tumor area, recent memory-based video object segmentation models (VOS) achieve frame-level segmentation by performing intensive similarity matching among the past frames which...

Robot-assisted closed reduction surgery is recognized as the optimal approach for pelvic fractures. However, existing surgical robotic systems often lack the necessary output force to overcome soft tissue tension. To address this limitation, we propose a novel surgical robotic system to deliver high output force with required workspace. Our approac...

Automatic report generation has arisen as a significant research area in computer-aided diagnosis, aiming to alleviate the burden on clinicians by generating reports automatically based on medical images. In this work, we propose a novel framework for automatic ultrasound report generation, leveraging a combination of unsupervised and supervised le...

Blast lung injury (BLI) is a significant concern in cases of explosive events and can have severe consequences for victims. The injury is often irreversible, emphasizing the need for early symptom confirmation and intervention. Tele-ultrasound (Tele-US) is a novel approach that enables healthcare professionals to remotely interpret US images and pr...

Automatic report generation has arisen as a significant research area in computer-aided diagnosis, aiming to alleviate the burden on clinicians by generating reports automatically based on medical images. In this work, we propose a novel framework for automatic ultrasound report generation, leveraging a combination of unsupervised and supervised le...

Percutaneous puncture is a widely used procedure in the diagnosis and therapy of cancer such as biopsy and ablation operations, while the organs in the thoracic and abdominal cavities are significantly affected by patients' respiratory movement. In this study, a robotic puncture system with respiratory movement is firstly developed, which can simul...

Robotic breast ultrasound (RBUS) aims to standardize breast ultrasonography, reduce the workload of sonographers, and provide high-quality ultrasound (US) images for subsequent diagnosis. In the process of RBUS screening, adjusting the US probe correctly and efficiently to acquire high-quality US images is fundamental and significant. In this lette...

Objective: Computational model of bone healing can replace animal experiments to study the parameters affecting the bone healing process, thus reducing the damage to experimental animals and saving a lot of time. We propose a computational model for continuous simulation of four phases of bone healing to study the effects of mechanical environment...

Pelvic fracture reduction surgery (PFRS) has always been one of the most challenging procedures in trauma orthopedics. Excellent preoperative planning is crucial for surgery, especially with the increasingly mature robot-assisted surgical systems. However, current preoperative reduction planning heavily relies on surgeons’ experience. This paper pr...

Automatic and accurate segmentation and classification of esophageal lesions are two essential tasks to assist endoscopists in Upper Gastrointestinal Endoscopy. However, there is no intelligent system that can diagnose more lesion types, handle multiple tasks simultaneously, and be more accurate in clinical work. Therefore, we present an innovative...

Trauma orthopedic robotic systems play a crucial role in assisting surgeons with precise control and minimally invasive procedures. Nevertheless, key technologies such as output force, navigation, and operational performance in robot-assisted pelvic fracture reduction surgery require further development. This article introduces an improved serial-p...

The quality of breast ultrasound images has a significant impact on the accuracy of disease diagnosis. Existing image quality assessment (IQA) methods usually use pixel-level feature statistical methods or end-to-end deep learning methods, which focus on the global image quality but ignore the image quality of the lesion region. However, in clinica...

Deep learning networks have achieved remarkable progress in various tasks of medical imaging. Most of the recent success in computer vision highly depend on large amounts of carefully annotated data, whereas labelling is arduous, time-consuming and in need of expertise. In this paper, a semi-supervised learning method, Semi-XctNet, is proposed for...

Offline reinforcement learning (ORL) has been getting increasing attention in robot learning, benefiting from its ability to avoid hazardous exploration and learn policies directly from precollected samples. Approximate policy iteration (API) is one of the most commonly investigated ORL approaches in robotics, due to its linear representation of po...

Puncture robots pave a new way for stable, accurate and safe percutaneous liver tumor puncture operation. However, affected by respiratory motion, intraoperative accurate location of the tumor and its surrounding anatomical structures remains a difficult problem in existing robot-assisted puncture operations. In this paper, a dual-arm robotic needl...

Automatic radiology report generation is essential to computer-aided diagnosis. Through the success of image captioning, medical report generation has been achievable. However, the lack of annotated disease labels is still the bottleneck of this area. In addition, the image-text data bias problem and complex sentences make it more difficult to gene...

Autonomous ultrasound scanning robots have attracted the attention of researchers, and the real-time quality assessment of ultrasound images is the key technology of them. Existing robot systems usually use pixel-level feature statistical methods such as grayscale, confidence map, etc. However, in clinical practice doctors’ evaluation of ultrasound...

Automatic radiology report generation is essential to computer-aided diagnosis. Through the success of image captioning, medical report generation has been achievable. However, the lack of annotated disease labels is still the bottleneck of this area. In addition, the image-text data bias problem and complex sentences make it more difficult to gene...

Accurate segmentation of kidney in ultrasound images is a vital procedure in clinical diagnosis and interventional operation. In recent years, deep learning technology has demonstrated promising prospects in medical image analysis. However, due to the inherent problems of ultrasound images, data with annotations are scarce and arduous to acquire, h...

Needle insertion is widely used in modern clinical practice, and flexible needles enable surgeons to adjust the needle insertion path to avoid obstacles and compensate for target drift. To increase the accuracy and safety of the needle insertion procedure, a path planning and tracking control method for flexible needle steering in dynamic environme...

Conventional Computed Tomography (CT) produces volumetric images by computing inverse Radon transformation using X-ray projections from different angles, which results in high dose radiation, long reconstruction time and artifacts. Biologically, prior knowledge or experience can be utilized to identify volumetric information from 2D images to certa...

Ultrasound examination is widely used for diagnosis of breast cancer, which requires a full coverage scan of the whole organ and stable probe-breast interaction for high-quality image acquisition. In this study, a robotic system for automated breast ultrasound scanning is proposed. To avoid occlusion, point cloud of the breast is obtained from mult...

Background During percutaneous puncture procedure, breath holding is subjectively controlled by patients, and it is difficult to ensure consistent tumor position between the preoperative CT scanning phase and the intraoperative puncture phase. In addition, the manual registration process is time-consuming and has low accuracy. Methods We have prop...

Purpose Percutaneous image‐guided interventions are commonly used for the diagnosis and treatment of cancer. In practice, physiological breathing‐induced motion increases the difficulty of accurately inserting needles into tumors without impairing the surrounding vital structures. In this work, we propose a data‐driven patient‐specific hierarchical...

In order to achieve effective physical human–robot interaction, human dynamic characteristics needs to be considered in admittance control. This paper proposes a variable admittance control method for physical human–robot interaction based on trajectory prediction of human hand motion. By predicting the moving direction of the robot end tool under...

Natural orifice transluminal endoscopic surgery (NOTES) has received significant attentions due to its minimal incision trauma compared with traditional multi-port robot assisted surgery. Continuum robot can be used in NOTES due to its high flexibility which can adapt to circuitous paths. However, the modeling of continuum robot is complex due to i...

This paper proposes a rigid–flexible coupling parallel mechanism with variable stiffness based on a novel 3-5R parallel mechanism, which is derived from a special form of anti-parallelogram mechanism. A spring is used as the fourth limb of the 3-5R parallel mechanism to endow the mechanism with elasticity, and then the motion of the 3-5R parallel m...

Percutaneous needle insertion is a widely used technique in needle-based intervention; however, it is difficult to achieve high targeting accuracy due to needle deflection and the boundary effect in multilayered tissues. This paper presents a preoperative needle insertion trajectory planning method that includes needle deflection modeling, insertio...

In robot-assisted endoscopic nasal surgery, due to the narrow and complex nasal cavity and sinus anatomical structure, the nasal endoscope of robot end-effector is prone to injure surrounding tissues during surgical approaches. In order to improve the safety of endoscope movement in robot-assisted endoscopic nasal surgery, this paper proposes a pat...

In endoscopic nasal surgery, robots, rather than surgical assistants, can be introduced to hold endoscopes and act as the surgeon's third hand, which helps to reduce their operation burden. To address the problem of robot-assisted surgical field of view (FOV) acquisition in endoscopic nasal surgery, this letter proposes an automatic surgical FOV co...

Because the prior knowledge of spatially unknown moving targets is not available, it is a challenge to conduct on-orbit services, including tracking, approaching and arresting. This paper draws on the idea of the simultaneous localization and mapping (SLAM) of the traditional mobile robot and proposes a two-threaded algorithm framework combining a...

The traditional manual method for adolescent idiopathic scoliosis diagnosis suffers from observer variability. Doctors need an objective, accurate and fast detection method which would help to overcome the problem encountered by the traditional classification. This study introduces new techniques, including automatic radiograph segmentation, scolio...

Percutaneous needle puncture operation is widely used in the image-guided interventions, including biopsy and ablation. MRI guidance has the advantages of high-resolution soft tissue imaging and thermal monitoring during energy-based ablation. This paper proposes the design of a 5-DOF pneumatic needle puncture robot, with all the cylinders, sensors...

As an important instrument for air-to-ground communication, the large space deployable antenna plays an important role in driving technological innovation and has become a topic of interest for research scholars worldwide. A large-scale deployable ring truss is introduced in this paper, which is equipped with a complete rope-driven driving method a...

In endoscopic sinus surgery, the robot assists the surgeon in holding the endoscope and acts as the surgeon’s third hand, which helps to reduce the surgeon’s operating burden and improve the quality of the operation. This paper proposes a human–robot cooperative control method based on virtual fixture to realize accurate and safe human–robot intera...

When the spinal surgery robot assists the surgeon perform the surgery, the patient is prone on the operating table. However, due to the force of the surgical instruments on the spine, there is a corresponding deformation in the surgical field, which affects the accuracy of the operation. In order to improve the accuracy and safety of the operation,...

The lumbar spinal stenosis (LSS) is a kind of orthopedic disease which causes a series of neurological symptom. Vertebral lamina grinding operation is a key procedure in decompressive laminectomy for LSS treatment. With the help of image-guided navigation system, the robot-assisted technology is applied to reduce the burdens on surgeon and improve...

Robots play an increasingly important role in the development of minimally invasive surgery (MIS). In MIS assistant robot systems, the remote center of motion (RCM) mechanism is a key component, and is the primary choice as end-effector for such systems. In this paper, first, we propose a new type of synthesis method for RCM mechanisms, which is ba...

In some complicated tabletop object manipulation task for robotic system, demonstration based control is an efficient way to enhance the stability of execution. In this paper, we use a new optical hand tracking sensor, LeapMotion, to perform a non-contact demonstration for robotic systems. A Multi-LeapMotion hand tracking system is developed. The s...

Laminectomy is a typical high-risk surgical operation on the spine, during which milling is the key procedure to remove part of vertebral lamina and release the pressure on the spinal nerve. Because many important vessels and nerves surround the vertebral lamina, any incorrect maneuver can cause irreparable damage to patients. In this paper, a fuzz...

In real-time footstep planning for the humanoid robot, it is needed to obtain the accurate location of its foot placements. However, existing methods only needed to obtain the localization of the robot as a particle, which did not specifically consider the localization of its foot placements. This paper presents foot placement localization method f...

Spinal surgery is considered a high-risk surgery. To improve the accuracy, stability, and safety of such operations, we report the development of a novel six-degrees-of-freedom Robotic Spinal Surgical System that can assist surgeons in performing transpedicular surgery, one of the most common spinal surgeries. After optimization performed using Res...

Screw path drilling is an important process among many orthopedic surgeries. To guarantee the safety and correctness of this process, a model-based drilling state recognition method is proposed in this paper. The thrust force in the drilling process is modeled based on an accurate 3D bone model restructured by means of Micro-CT images. In theoretic...

Conflicts and deadlocks are key issues in a multiple automated guided vehicle system, especially in complicated and uncertain environments. They have been challenges for ensuring the reliability, security, and efficiency of the multiple automated guided vehicle system. In this paper, a traffic control model based on semaphores is proposed to resolv...

In this paper a medical robot based on a 3-RPS parallel platform is presented for providing correct screw path in transpedicular fixation surgery. For improving the accuracy of the robot, a calibration approach for 3-RPS with CMM (Coordinate Measuring Instrument) data is developed. Sensitivity analysis of the error source had been done with Monte-C...

A general framework of robot manipulation planning for door opening task is proposed in this paper. First grasp pattern, including grasp point and method for various door handles, is defined. Second door-opening pattern, including task planning and trajectory planning, is also proposed. This paper utilizes Kinect as a vision sensor to collect point...

A novel hierarchical function action behavior mechanism (FABM) modeling framework is proposed to conduct intelligent mapping from the overall function to the principle solution, according to the requirements of customers. Based on the hierarchical modeling framework, an object-oriented representation method is developed to express the inheritance a...

Robots in dynamic and uncertain environments are vulnerable to mission failures due to external perturbation or internal malfunctions. Diagnosis is the process to detect, locate or even assess the fault. Since robots rely on their function modules to sense the external environment, it is difficult to locate the fault under uncertainties of robot co...

Bone milling is one of the most common operations in various kinds of orthopedical surgeries, such as laminectomy surgery. For safety issue and efficacy, it is very important to recognize the states in milling operation. In this paper, an approach to recognize the states of bone milling is proposed, which identify the cortical tissue layer and canc...

Screw path drilling is one of the most common and high-risk operations in many kinds of orthopedic surgery, especially in spinal surgeries. During spinal surgery, the bone screws are inserted into the vertebral body from the narrow vertebral pedicles. Any failures in this process will hurt important vessels and nerves of the patient. In this paper...

Mobile parallel robots (MPR), which structurally configured a moving platform and several parallel limbs with an actuating wheel at the end of each limb, exhibit advantages in high mobility, high load capability and high flexibility in complex task environments. In this paper, a 6-DOF MPR with 3-PPUU (Prismatic-Prismatic Universal-Universal) limbs...

For most of the spinal surgeries, the pedicle screw insertion operation is a significant difficult procedure. To solve accurate position and keep the screw path in operation, a parallel guide device based on 3-RPS parallel mechanism is proposed in this paper. According to three degrees of freedom (Dofs), the inverse solution of the parallel mechani...

It has been shown in recent robot planning control research that planning with simplified domain models is efficient and can be robust by detecting execution failures and replanning online. In this work, we alter the traditional HTN planning by interleaving with execution and extend it with a geometric planner for mobile manipulation tasks. We also...

Object localization is a key issue of autonomous robots. RFID as a low cost, easy and effective technology has been widely used in localization and tracking situation. In this paper the ROS-based Simultaneous Localization and Mapping (SLAM) combined with Radio Frequency Identification (RFID) is used for a coarse position by our robot called RCT-M....

The current work environments for mobile robots tend to be complex and dynamic, which often causes difficulties in the execution of tasks due to incomplete and uncertain information. A number of experiments and applications have shown that it is an appropriate and efficient approach to handle this issue by integrating the AI method with plan-based...

This paper is based on a new Robotic Spinal Surgical System (RSSS) we have developed in last 2 years. This robotic surgical system focuses on pedicle screw implanting surgery, but can be used on some other orthopedic surgeries. Some safety design principles are presented during development of the RSSS. In this paper, two main aspects of them based...

The Mobile Parallel Robot (MPR) is a new type of robot which integrates the mechanical characteristics of Mobile Robot and Parallel Robot. It can adjust position and orientation to suit to many special situations. This paper firstly analyzes the kinematics characteristics of MPR, including the inverse kinematics and the forward kinematics using ana...

A novel master-slave robotic system has been proposed for minimally intravascular invasive surgery. The robotic system is composed of guide wire insertion mechanism with force feedback, catheter insertion mechanism and force feedback device. And the working principle and control system diagram are also introduced. This system can reduce the usage o...

To detect and localize objects in a scene is an essential step for many computer vision tasks. Many efforts have been done for detecting and localizing category-specific ojects. However, only few works focused on the generic objectness measure which is more common and important than category-specific object detection. Base on an existing method, in...

In this paper, the serial and parallel manipulator with RP-(2-RRU/1-RUU) Structure is developed. Firstly, we will establish the coordinate system for the serial and parallel manipulator and derive its spiral movement through the Spiral Principle. Then according to the spiral movement, we will get its DOF. Secondly, we will describe the solving proc...

The Pairwise Geometrical Histograms (PGH) is a generalization of Chain Code Histogram(CCH). It is a powerful shape descriptor that is applied to contours matching which is not affected by rotation. As we know, this method is seldom used for vehicle detection. Feature extraction is a very common and useful method of pattern recognition. In recent ye...

A novel high adaptability out-door mobile robot with diameter-variable wheels was proposed in this paper. The robot has advantages of good climbing obstacle capability, high terrain adaptability and stability for the self-adapting suspension and walking wheel combining the efficiency of wheels with the climbing mobility of legs. The mechanism struc...

navigation system in RSSS ensures high positioning accuracy, and structure of robot guarantees the safety and reliability of RSSS. Moreover, with new implements in surgery, procedure of surgery must be redesigned. In this paper, we discuss a new robotic surgical system for spinal surgery, including a complete system with tracing system, navigation...

In this paper, a robot simulation system which can accomplish multi-task planning is proposed. The system is based on Simbad - an autonomous robot simulation package. Compared to Simbad, our system can establishes the environment model, and enables robots to make proper planning under uncertainties. The main contributions of this paper are 1) integ...

Solving the vision problem using convex optimization theory is now a focus in computer vision and robot communities. Second Order Cone Programming (SOCP) is especially effective in these methods. This paper discusses homography estimation in omnidirectional vision under the L∞-norm, which provides a theoretical guarantee of global optimality and a...

A Pedicle Screws Surgical Robot (PSSR) can reduce the risk of spinal surgery and improve surgical precision, which plays an important role in promoting the medical care level of spinal surgery. A new type of PSSR is proposed in this paper, and the mechanical structure and its working principle are also introduced. The kinematics model of the robot...

In this paper, a novel type of parallel robot with four degree of freedoms is presented and investigated, which expends the family of few DOFs parallel robots. The parallel robot has two rotation and two translation degree of freedoms. The aspects about its configuration and kinematics analysis are discussed firstly, and a comparison of its singula...

In this paper, the Mobile Parallel Robot (MPR) with structural configurations of PPUU (Prismatic - Prismatic - Universal - Universal) is developed. The inverse kinematics is firstly derived and a specific control system is presented. The control system integrates the features of parallel robot and mobile robot. Five control modules are included in...

Compared with the existing mobile robot, the Mobile Parallel Robot (MPR) has more powerful climbing ability and more adaptive behaviors. This paper expands the complex agent using Deterministic Finite Automaton (DFA) from the wheeled mobile robot to a MPR successfully, and the monocular vision part is improved to stereo vision. The action status mo...

Flexibility of assembly systems is crucial to maintaining the competitiveness in the rapidly changing market. In this paper, a novel flexible fixturing system for sheet metal part assembly is presented, which utilizes parallel robots as reconfigurable fixture elements. The method of influence coefficients, combined with finite element analysis and...