RESUMEN

Objective: We present a general framework of simultaneous needle shape reconstruction and control input generation for robot-assisted spinal injection procedures, without continuous imaging feedback. Methods: System input-output mapping is generated with a real-time needle-tissue interaction simulation, and single-core FBG sensor readings are used as local needle shape feedback within the same simulation framework. FBG wavelength shifts due to temperature variation is removed by exploiting redundancy in fiber arrangement. Results: Targeting experiments performed on both plastisol lumbar phantoms as well as an ex vivo porcine lumbar section achieved in-plane tip errors of 0.6 ± 0.3 mm and 1.6 ± 0.9 mm , and total tip errors of 0.9 ± 0.7 mm and 2.1 ± 0.8 mm for the two testing environments. Significance: Our clinically inspired control strategy and workflow is self-contained and not dependent on the modality of imaging guidance. The generalizability of the proposed approach can be applied to other needle-based interventions where medical imaging cannot be reliably utilized as part of a closed-loop control system for needle guidance.

RESUMEN

This paper investigates the possibility of robotically performing in situ needle manipulations to correct the needle tip position in the setting of robot-assisted, MRI-guided spinal injections, where real time MRI images cannot be effectively used to guide the needle. Open-loop control of the needle tip is derived from finite element simulation, and the proposed method is tested with ex vivo animal muscle tissues and validated by cone beam computed tomography. Preliminary results have shown promise of performing needle tip correction in situ to improve needle insertion accuracy when real-time feedback is not readily available.

RESUMEN

The width of a neural network matters since increasing the width will necessarily increase the model capacity. However, the performance of a network does not improve linearly with the width and soon gets saturated. In this case, we argue that increasing the number of networks (ensemble) can achieve better accuracy-efficiency trade-offs than purely increasing the width. To prove it, one large network is divided into several small ones regarding its parameters and regularization components. Each of these small networks has a fraction of the original one's parameters. We then train these small networks together and make them see various views of the same data to increase their diversity. During this co-training process, networks can also learn from each other. As a result, small networks can achieve better ensemble performance than the large one with few or no extra parameters or FLOPs, i. e., achieving better accuracy-efficiency trade-offs. Small networks can also achieve faster inference speed than the large one by concurrent running. All of the above shows that the number of networks is a new dimension of model scaling. We validate our argument with 8 different neural architectures on common benchmarks through extensive experiments.

RESUMEN

Feature extraction of electrocardiogram (ECG) is the fundamental work of further automatic diagnosis. However, suffered from various kinds of noises with white, pink, and other colors, feature extraction is not a straightforward work but requires necessary signal processing techniques. In this paper, we propose an accurate and robust ECG feature extraction method based on mean shift algorithm which has the ability to remove noise involved in input signal by taking advantage of its embedded Gaussian filter and locate extremes of input signal using gradient optimization based on self-adaptive search steps. To demonstrate the availability and efficacy of the proposed method, we conduct experiments on signals contaminated by noises of white, pink and brown colors from 5dB to 15dB signal-noise ratios. Clean signals are produced by ECG synthesizer (ECGSyn) so that we can obtain the real features and quantitatively calculate feature extraction errors of the proposed method. Experiment results verify that our method can handle various kinds of noises and achieve satisfactory feature extraction performance.

Asunto(s)

RESUMEN

In this paper, we presents a novel approach for tracking and catching operation of space robots using learning and transferring human control strategies (HCS). We firstly use an efficient support vector machine (SVM) to parametrize the model of HCS. Then we develop a new SVM-based learning structure to better implement human control strategy learning in tracking and capturing control. The approach is fundamentally valuable in dealing with some problems such as small sample data and local minima, and so on. Therefore this approach is efficient in modeling, understanding and transferring its learning process. The simulation results attest that this approach is useful and feasible in generating tracking trajectory and catching objects autonomously.

Asunto(s)

RESUMEN

Surgical training systems using virtual reality simulation techniques offer a cost-effective alternative to traditional training methods. In this sense, techniques for interactive visualization and virtual reality surgery have been one of the very important research areas. We describe various techniques we have used in developing a virtual reality system for anatomic visualization and training arthroscopic knee surgeons. Virtual models used in our systems are constructed from the Visible Human Project and Chinese Visible Human data sets. We present our various developments in segmentation, personal-computer-based real-time volume visualization, soft tissue deformation with topological change in real-time using finite element analysis, and soft tissue cutting with tactile feedback.

Asunto(s)

RESUMEN

We are developing a novel robot concept called the wearable robot. Wearable robots are mobile information devices capable of supporting remote communication and intelligent interaction between networked entities. In this paper, we explore the possible functions of such a robotic network and will present a distributed network architecture based on service components. In order to support the interaction and communication between the components in the wearable robot system, we have developed an intelligent network architecture. This service-based architecture involves three major mechanisms. The first mechanism involves the use of a task coordinator service such that the execution of the services can be managed using a priority queue. The second mechanism enables the system to automatically push the required service proxy to the client intelligently based on certain system-related conditions. In the third mechanism, we allow the system to automatically deliver services based on contextual information. Using a fuzzy-logic-based decision making system, the matching service can determine whether the service should be automatically delivered utilizing the information provided by the service, client, lookup service, and context sensors. An application scenario has been implemented to demonstrate the feasibility of this distributed service-based robot architecture. The architecture is implemented as extensions to the Jini network model.

Asunto(s)

RESUMEN

Surgical training systems based on virtual-reality (VR) simulation techniques offer a cost-effective and efficient alternative to traditional training methods. This paper describes a VR system for training arthroscopic knee surgery. Virtual models used in this system are constructed from the Visual Human Project dataset. Our system simulates soft tissue deformation with topological change in real-time using finite-element analysis. To offer realistic tactile feedback, we build a tailor-made force feedback hardware.

Asunto(s)