Computer-based test-bed for clinical assessment of hand/wrist feed-forward neuroprosthetic controllers using artificial neural networks

Abstract

Neuroprosthestic systems can be used to restore hand grasp and wrist control in individuals with C5/C6 spinal cord injury. A computer-based system was developed for the implementation, tuning and clinical assessment of neuroprosthetic controllers, using off-the-shelf hardware and software. The computer system turned a Pentium III PC running Windows NT into a non-dedicated, real-time system for the control of neuroprostheses. Software execution (written using the high-level programming languages LabVIEW and MATLAB) was divided into two phases: training and real-time control. During the training phase, the computer system collected input/output data by stimulating the muscles and measuring the muscle outputs in real-time, analysed the recorded data, generated a set of training data and trained an artificial neural network (ANN)-based controller. During real-time control, the computer system stimulated the muscles using stimulus pulsewidths predicted by the ANN controller in response to a sampled input from an external command source, to provide independent control of hand grasp and wrist posture. System timing was stable, reliable and capable of providing muscle stimulation at frequencies up to 24Hz. To demonstrate the application of the test-bed, an ANN-based controller was implemented with three inputs and two independent channels of stimulation. The ANN controller's ability to control hand grasp and wrist angle independently was assessed by quantitative comparison of the outputs of the stimulated muscles with a set of desired grasp or wrist postures determined by the command signal. Controller performance results were mixed, but the platform provided the tools to implement and assess future controller designs.

A Systematic Review of Artificial Intelligence Applications in Plastic Surgery: Looking to the Future

“…The most frequently used algorithms were supervised machine learning (n = 11, 25%) 29 – 31 , 33 , 34 , 47 , 53 , 54 , 58 , 59 , 65 and artificial neural networks (n = 11, 25%). 36 , 40 , 42 , 43 , 50 , 57 , 60 – 64 Other algorithms used were convolutional neural networks (n = 8, 19%), 25 , 27 , 28 , 37 , 38 , 39 , 49 , 56 unsupervised machine learning (n = 4, 9%), 41 , 45 , 55 , 68 natural language processing (n = 4, 9%), 34 , 48 , 67 , 68 generative adversarial networks (n = 2, 5%), 17 , 26 computer vision (n = 2, 5%), 32 , 52 and combinations of models (combo; n = 2, 5%). 43 , 44 Input features were typically comprised of raw and preprocessed variables, such as subject characteristics (age, lapse time, comorbidities, vital signs, and laboratory values, anatomical and wound measurements, tissue reflectance spectrum), clinical images (facial photography, CT images, angiography, photoplethysmography, dermatoscopy, 3D cephalograms), surgical factors (surgical approach, intraoperative interactions with equipment), and synthetic or experimentally derived metrics (external muscle stimulation pulse widths, frequently asked questions).…”

Automated Optimal Coordination of Multiple-DOF Neuromuscular Actions in Feedforward Neuroprostheses

“…Briefly, we collected input-output data from a neuromuscular system, reversed the inputs and outputs, and trained an ANN based controller to invert the relationship. This, however, did not work adequately in experimental tests [20]. Subsequent simulation studies (unpublished) demonstrated that the inverse controller did not always select predictable patterns of coactivation because the training data contained redundant input-output data.…”

“…should depend on the functional objectives. Such criteria could be rapidly tested using software environments that allow rapid prototyping of different mathematical models [41] and controllers [20] appropriate for these objectives.…”

“…However, these studies have been limited to single degree-of-freedom systems acted upon by a pair of antagonists. On the other hand, studies incorporating mechanical coupling between degrees of freedom have been performed in simulation only [16–18], have not attempted to provide independent control of the multiple DOF [19], or have been limited by the lengthy data collection processes and by the need for an experimental platform that allowed rapid controller implementation, which has been presented elsewhere [20]. Thus, our objective was to develop and test experimentally a feedforward controller capable of decoupling multiple degrees of freedom and automating the design of the controller using clinically-measured input-output data.…”

Big Data and Machine Learning in Plastic Surgery: A New Frontier in Surgical Innovation

“…In light of this, artificial neural networks have been used to develop automated controllers for a variety of neuroprostheses, including those that are used to restore hand grasp and wrist control along with more proximal upper extremity function in patients with C5/C6 spinal cord injury. 18,19 Although the results of these initial investigations were mixed, they highlight the potential for artificial neural networks, along with other machine learning techniques, in the development of neuroprosthetic controllers for the hand and wrist.…”