Using Deep Learning for Task and Tremor Type Classification in People with Parkinson's Disease.

Hand tremor is one of the dominating symptoms of Parkinson's disease (PD), which significantly limits activities of daily living. Along with medications, wearable devices have been proposed to suppress tremor. However, suppressing tremor without interfering with voluntary motion remains challenging and improvements are needed. The main goal of this work was to design algorithms for the automatic identification of the tremor type and voluntary motions, using only surface electromyography (sEMG) data. Towards this goal, a bidirectional long short-term memory (BiLSTM) algorithm was implemented that uses sEMG data to identify the motion and tremor type of people living with PD when performing a task. Moreover, in order to automate the training process, hyperparamter selection was performed using a regularized evolutionary algorithm. The results show that the accuracy of task classification among 15 people living with PD was 84±8%, and the accuracy of tremor classification was 88±5%. Both models performed significantly above chance levels (20% and 33% for task and tremor classification, respectively). Thus, it was concluded that the trained models, based on using purely sEMG signals, could successfully identify the task and tremor types.

Real-Time Performance Assessment of High-Order Tremor Estimators Used in a Wearable Tremor Suppression Device.

The side effects and complications of traditional treatments for treating pathological tremor have led to a growing research interest in wearable tremor suppression devices (WTSDs) as an alternative approach. Similar to how the human brain coordinates the function of the human system, a tremor estimator determines how a WTSD functions. Although many tremor estimation algorithms have been developed and validated, whether they can be implemented on a cost-effective embedded system has not been studied; furthermore, their effectiveness on tremor signals with multiple harmonics has not been investigated. Therefore, in this study, four tremor estimators were implemented, evaluated, and compared: Weighted-frequency Fourier Linear Combiner (WFLC), WFLC-based Kalman Filter (WFLC-KF), Band-limited Multiple FLC, and enhanced High-order WFLC-KF (eHWFLC-KF). This study aimed to evaluate the performance of each algorithm on a bench-top tremor suppression system with 18 recorded tremor motion datasets; and compare the performance of each estimator. The experimental evaluation showed that the eHWFLC-KF-based WTSD achieved the best performance when suppressing tremor with an average of 89.3% reduction in tremor power, and an average error when tracking voluntary motion of 6.6°/s. Statistical analysis indicated that the eHWFLC-KF-based WTSD is able to reduce the power of tremor better than the WFLC and WFLC-KF, and the BMFLC-based WTSD is better than the WFLC. The performance when tracking voluntary motion is similar among all systems. This study has proven the feasibility of implementing various tremor estimators in a cost-effective embedded system, and provided a real-time performance assessment of four tremor estimators.

Scalp-Targeted Haptic Proprioception for Upper-Limb Prosthetics.

In this paper, a head-worn wearable haptic feedback device (WHFD) is developed to communicate sensory information from an upper-limb prosthesis. A 14-week, 6-stage, between-subjects study was created to investigate the learning trajectory as participants were stimulated with haptic patterns conveying joint proprioception. Healthy participants were divided into three groups, with each group using a different haptic stimulation methods. 18 participants completed the study within 7-14 weekly sessions, demonstrating that participants were, in fact, learning to interpret the haptic information. Participants in the spatiotemporal stimulation group had some advantages in interpreting the haptic information over the others; however, each stimulation method has advantages that can be exploited and hybridized for future models of the WHFD. Overall, the proposed WHFD is an effective non-invasive device that can promote greater sensory awareness for wearers of prostheses.

Multi-modal Prosthesis Control using sEMG, FMG and IMU Sensors.

In this work, a novel multi-modal device that allows data to simultaneously be collected from three noninva-sive sensor modalities was created. Force myography (FMG), surface electromyography (sEMG), and inertial measurement unit (IMU) sensors were integrated into a wearable armband and used to collect signal data while subjects performed gestures important for the activities of daily living (ADL). An established machine learning algorithm was used to decipher the signals to predict the user's intent/gesture being held, which could be used to control a prosthetic device. Using all three modalities provided statistically-significant improvements over most other modality combinations, as it provided the most accurate and consistent classification results. Clinical relevance-The use of three sensing modalities can improve gesture-based control of upper-limb prosthetics.

Preliminary Assessment of the Safety of a Fault-Tolerant Control-based Wearable Tremor Suppression Glove.

The advent of wearable tremor suppression de-vices (WTSDs) has provided a promising alternative approach for parkinsonian tremor management, especially for individuals whose tremors are not managed by conventional treatment options. Currently, research in WTSDs has shown successful results with a tremor suppression ratio of up to 99 %; however, the user safety of WTSDs has not been properly considered, especially in the occurrence of unexpected events, such as faults and disturbances. In this study, a fault-tolerant control system was developed and integrated into the control system of a WTSD for the first time. The safety and tremor suppression performance of the proposed system under the influence of a measurement loss fault were tested and evaluated on 18 tremor motion datasets, specifically by quantifying the tremor power suppression ratio and the error when tracking voluntary motion. The experimental evaluation showed that the proposed system could remain functional and safe to use in the existence of the fault, with an average user motion tracking error of 1.5º. It was also found that the proposed system achieved significantly improved performance in both metrics when compared to the system without a fault-tolerant controller. Clinical Relevance-This work improves the safety and robustness of WTSDs making them more suitable for use as an additional treatment for parkinsonian tremor.

Survey-based identification of design requirements and constraints for a wearable tremor suppression device.

Introduction: Parkinsonian tremor has severely impacted the lives of 65% of individuals with Parkinson's disease, and nearly 25% do not respond to traditional treatments. Although wearable tremor suppression devices (WTSDs) have become a promising alternative approach, this technology is still in the early stages of development, and no studies have reported the stakeholders' opinions on this technology and their desired design requirements. Methods: An online survey was distributed to affected Canadians and Canadian movement disorder specialists (MDS) to acquire information on demographics, the current state of treatments, opinions on the WTSDs, and the desired design requirements of future WTSDs. Results: A total of 101 affected individuals and 24 MDS completed the survey. It was found that both groups are generally open to using WTSDs to manage tremor. The most important design requirement to end users is the adaptability to lifestyle, followed by weight and size, accurate motion, comfort, safety, quick response, and cost. Lastly, most of the participants (65%) think that the device should cost under $500. Conclusions: The findings from this study can be used as guidelines for the development of future WTSDs, such that the future generations could be evaluated and accepted by the end users.

Texture-based Intraoperative Image Guidance for Tumor Localization in Minimally Invasive Surgery.

Intraoperative tumor localization in a deflated lung in minimally invasive surgery (MIS) is challenging as the lung cannot be manually palpated through small incisions. To do so remotely, an articulated multisensory imaging device combining tactile and ultrasound sensors was developed. It visualizes the surface tactile map and the depth of the tissue. However, with little maneuverability in MIS, localizing tumors using instrumented palpation is both tedious and inefficient. In this paper, a texture- based image guidance system that classifies tactile-guided ultrasound texture regions and provides beliefs on their types is proposed. The resulting interactive feedback allows directed palpation in MIS. A k-means classifier is used to first cluster gray-level co-occurrence matrix (GLCM)-based texture features of the ultrasound regions, followed by hidden Markov model-based belief propagation to establish confidence about the clustered features observing repeated patterns. When the beliefs converge, the system autonomously detects tumor and nontumor textures. The approach was tested on 20 ex vivo soft tissue specimens in a staged MIS. The results showed that with guidance, tumors in MIS could be localized with 98% accuracy, 99% sensitivity, and 97% specificity.Clinical Relevance- Texture-based image guidance adds efficiency and control to instrumented palpation in MIS. It renders fluidity and accuracy in image acquisition using a hand-held device where fatigue from prolonged handling affects imaging quality.

Real-Time Voluntary Motion Prediction and Parkinson's Tremor Reduction Using Deep Neural Networks.

Wearable tremor suppression devices (WTSD) have been considered as a viable solution to manage parkinsonian tremor. WTSDs showed their ability to improve the quality of life of individuals suffering from parkinsonian tremor, by helping them to perform activities of daily living (ADL). Since parkinsonian tremor has been shown to be nonstationary, nonlinear, and stochastic in nature, the performance of the tremor models used by WTSDs is affected by their inability to adapt to the nonlinear behaviour of tremor. Another drawback that the models have is their limitation to estimate or predict one step ahead, which introduces delay when used in real time with WTSDs, which compromises performance. To address these issues, this work proposes a deep neural network model that learns the correlations and nonlinearities of tremor and voluntary motion, and is capable of multi-step prediction with minimal delay. A generalized model that is task and user-independent is presented. The model achieved an average estimation percentage accuracy of 99.2%. The average future voluntary motion prediction percentage accuracy with 10, 20, 50, and 100 steps ahead was 97.0%, 94.0%, 91.6%, and 89.9%, respectively, with prediction time as low as 1.5 ms for 100 steps ahead. The proposed model also achieved an average of 93.8% ± 1.5% in tremor reduction when it was tested in an experimental setup in real time. The tremor reduction showed an improvement of 25% over the Weighted Fourier Linear Combiner (WFLC), an estimator commonly used with WTSDs.

Design and Preliminary Performance Assessment of a Wearable Tremor Suppression Glove.

OBJECTIVE: Approximately 25% of individualsliving with parkinsonian tremor do not respond to traditional treatments. Wearable tremor suppression devices (WTSD) provide an alternative approach, however, tremor in the fingers has not been given as much attention as tremor in the elbow and the wrist. Therefore, the objective of this study is to design a wearable tremor suppression glove that can suppress tremor simultaneously, but independently, in multiple hand joints without restricting the user's voluntary motion. METHODS: A WTSD was designed for managing tremor in the index finger metacarpophalangeal (MCP) joint, thumb MCP joint, and the wrist. The prototype was tested and assessed on a participant living with parkinsonian tremor. RESULTS: The experimental evaluation showed an overall suppression of 73.1%, 80.7%, and 85.5% in resting tremor, 70.2%, 79.5%, and 81% in postural tremor, and 60.0%, 58.7%, and 65.0% in kinetic tremor in the index finger MCP joint, the thumb MCP joint, and the wrist, respectively. CONCLUSION: This first assessment of a WTSD for people living with Parkinson's disease provides confirmation of the feasibility of the approach. The next step requires a comprehensive validation on a broader population in order to evaluate the performance of the WTSD. SIGNIFICANCE: This study demonstrates the feasibility of using a WTSD to manage hand and finger tremor. The device enriches the field of upper-limb tremor management, as the first WTSD for multiple joints of the hand.

The Design of a Parkinson's Tremor Predictor and Estimator Using a Hybrid Convolutional-Multilayer Perceptron Neural Network.

Parkinson's Disease (PD) is considered to be the second most common age-related neuroegenerative disorder, and it is estimated that seven to ten million people worldwide have PD. One of the symptoms of PD is tremor, and studies have shown that wearable assistive devices have the potential to assist in suppressing it. However, despite the progress in the development of these devices, their performance is limited by the tremor estimators they use. Thus, a need for a tremor model that helps the wearable assistive devices to increase tremor suppression without impeding voluntary motion remains. In this work, a user-independent and task-independent tremor and voluntary motion detection method based on neural networks is proposed. Inertial measurement units (IMUs) were used to measure acceleration and angular velocity from participants with PD, these data were then used to train the neural network. The achieved estimation percentage accuracy of voluntary motion was 99.0%, and the future prediction percentage accuracy was 97.3%, 93.7%, 91.4% and 90.3% for 10 ms, 20 ms, 50 ms and 100 ms ahead, respectively. The root mean squared error (RMSE) achieved for tremor estimation was an average of 0.00087°/s on new unseen data, and the future prediction average RMSE across the different tasks achieved was 0.001°/s, 0.002°/s, 0.020°/s and 0.049°/s for 1 ms, 2 ms, 5 ms, and 10 ms ahead, respectively. Therefore, the proposed method shows promise for use in wearable suppression devices.

Development of a physical shoulder simulator for the training of basic arthroscopic skills.

BACKGROUND: Orthopaedic training programs are incorporating arthroscopic simulations into their residency curricula. There is a need for a physical shoulder simulator that accommodates lateral decubitus and beach chair positions, has realistic anatomy, allows for an objective measure of performance and provides feedback to trainees. METHODS: A physical shoulder simulator was developed for training basic arthroscopic skills. Sensors were embedded in the simulator to provide a means to assess performance. Subjects of varying skill level were invited to use the simulator and their performance was objectively assessed. RESULTS: Novice subjects improved their performance after practice with the simulator. A survey completed by experts recognized the simulator as a valuable tool for training basic arthroscopic skills. CONCLUSIONS: The physical shoulder simulator helps train novices in basic arthroscopic skills and provides objective measures of performance. By using the physical shoulder simulator, residents could improve their basic arthroscopic skills, resulting in improved patient safety.

Analysis of Energy-Based Metrics for Laparoscopic Skills Assessment.

OBJECTIVE: The complexity of minimally invasive surgery (MIS) requires that trainees practice MIS skills in numerous training sessions. The goal of these training sessions is to learn how to move the instruments smoothly without damaging the surrounding tissue and achieving operative tasks with accuracy. In order to enhance the efficiency of these training sessions, the proficiency of the trainees should be assessed using an objective assessment method. Several performance metrics have been proposed and analyzed for MIS tasks. The differentiation of various levels of expertise is limited without the presence of an external evaluator. METHODS: In this study, novel objective performance metrics are proposed based on mechanical energy expenditure and work. The three components of these metrics are potential energy, kinetic energy, and work. These components are optimally combined through both one-step and two-step methods. Evaluation of these metrics is accomplished for suturing and knot-tying tasks based on the performance of 30 subjects across four levels of experience. RESULTS: The results of this study show that the one-step combined metric provides 47 and 60 accuracy in determining the level of expertise of subjects for the suturing and knot-tying tasks, respectively. The two-step combined metric provided 67 accuracy for both of the tasks studied. CONCLUSION: The results indicate that energy expenditure is a useful metric for developing objective and efficient assessment methods. SIGNIFICANCE: These metrics can be used to evaluate and determine the proficiency levels of trainees, provide feedback and, consequently, enhance surgical simulators.

Energy-Based Metrics for Arthroscopic Skills Assessment.

Minimally invasive skills assessment methods are essential in developing efficient surgical simulators and implementing consistent skills evaluation. Although numerous methods have been investigated in the literature, there is still a need to further improve the accuracy of surgical skills assessment. Energy expenditure can be an indication of motor skills proficiency. The goals of this study are to develop objective metrics based on energy expenditure, normalize these metrics, and investigate classifying trainees using these metrics. To this end, different forms of energy consisting of mechanical energy and work were considered and their values were divided by the related value of an ideal performance to develop normalized metrics. These metrics were used as inputs for various machine learning algorithms including support vector machines (SVM) and neural networks (NNs) for classification. The accuracy of the combination of the normalized energy-based metrics with these classifiers was evaluated through a leave-one-subject-out cross-validation. The proposed method was validated using 26 subjects at two experience levels (novices and experts) in three arthroscopic tasks. The results showed that there are statistically significant differences between novices and experts for almost all of the normalized energy-based metrics. The accuracy of classification using SVM and NN methods was between 70% and 95% for the various tasks. The results show that the normalized energy-based metrics and their combination with SVM and NN classifiers are capable of providing accurate classification of trainees. The assessment method proposed in this study can enhance surgical training by providing appropriate feedback to trainees about their level of expertise and can be used in the evaluation of proficiency.

Mastery Learning - does the method of learning make a difference in skills acquisition for robotic surgery?

BACKGROUND: Few studies compare the effectiveness of blocked vs random practice conditions in minimally invasive surgery training, and none have evaluated these in robotic surgery training. METHODS: The dV-Trainer® and the da Vinci® Surgical System (dVSS) were used to compare practice conditions. Forty-two participants were randomized into blocked and random practice groups. Each participant performed five tasks: Ring Walk, Thread the Rings, Needle Targeting, Suture Sponge and Tubes Level 2. Transfer to the dVSS was also assessed. RESULTS: No significant differences were observed between the two groups, except for a few instances. For example, during Ring Walk, the random group performed significantly faster than the blocked group (100.78 ± 5.26 s vs 121.59 ± 5.26 s, p < 0.01). CONCLUSIONS: The study results do not follow the current evidence presented in the education literature. This is the first time that blocked versus random practice was tested for robotic surgery training.

Energy-based metrics for laparoscopic skills assessment.

The growing popularity of minimally invasive surgery (MIS) can be attributed to its advantages, which include reduced post-operative pain, a shorter hospital stay, and faster recovery. However, MIS requires extensive training for surgeons to become experts in their field of practice. Different assessment methods have been proposed for evaluating the performance of surgeons and residents on surgical simulators. Nonetheless, optimal objective performance measures are still lacking. In this study, three metrics for minimally invasive skills assessment are proposed based on energy expenditure: work, potential energy and kinetic energy. In order to evaluate these metrics, two laparoscopic tasks consisting of suturing and knot-tying are investigated, involving expert and novice subjects. This study shows that measures based on energy expenditure can be used for skills assessment: all three metrics can discriminate between experts and novices for the two tasks investigated here. These measures can also reflect the efficiency of subjects when performing MIS tasks. Further modification and investigation of these metrics can extend their use to different tasks and for discriminating between various levels of experience.

An autoclavable wireless palpation instrument for minimally invasive surgery.

Minimally invasive surgery prevents surgeons from manually palpating organs to locate subsurface tumors and other structures. One solution is to use ultrasound; however, it is not always reliable. Various minimally invasive surgery instruments that provide tactile feedback have been proposed to augment ultrasound sensing for tumor localization; however, current designs have limitations such as cumbersome wiring, difficulty in manipulation, lack of sterilizability and high cost. This paper presents a novel, autoclavable, wireless, hand-held palpation instrument that uses a custom, low-cost, disposable tactile sensor to provide tactile and kinesthetic force feedback. The use of a replaceable, disposable tactile sensor avoids deterioration in sensor performance due to repeated autoclaving. The instrument features a passive joint in the end effector that allows the sensor to self-align to the palpation surface in a wide range of orientations. All of the electronics are packaged in a removable module that allows the rest of the instrument to be easily cleaned and autoclaved. Two versions of the tactile sensor, using piezoresistive sensing and capacitive sensing respectively, have been designed for use with this instrument. The instrument is shown to be able to detect 6 mm diameter spherical tumors at a depth of 9-10 mm in ex vivo tissue samples.

Randomized control trial for evaluation of a hands-free pointer for surgical instruction during laparoscopic cholecystectomy.

INTRODUCTION: Training surgeons in minimally invasive surgery (MIS) requires surgical residents to operate under the direction of a consultant. The inability of the instructing surgeon to point at the laparoscopic monitor without releasing the instruments remains a barrier to effective instruction. The wireless hands-free surgical pointer (WHaSP) has been developed to aid instruction during MIS. METHODS: The objective of this study was to evaluate the effectiveness and likeability of the WHaSP as an instructional tool compared with the conventional methods. Data were successfully collected during 103 laparoscopic cholecystectomy procedures, which had been randomized to use or not use the WHaSP as a teaching tool. Audio and video from the surgeries were recorded and analyzed. Instructing surgeons, operating surgeons, and camera assistants provided feedback through a post-operative questionnaire that used a five-level Likert scale. The questionnaire results were analyzed using a Mann-Whitney U test. RESULTS: There were no negative effects on surgery completion time or instruction practice due to the use of the WHaSP. The number of times an instructor surgeon pointed to the laparoscopic screen with their hand was significantly reduced when the WHaSP was utilized (p < 0.001). The questionnaires showed that WHaSP users found it to be comfortable, easy to use, and easy to control. Compared to when the WHaSP was not used, users found that communication was more effective (p = 0.002), locations were easier to communicate (p < 0.001), and instructions were easier to follow (p = 0.005). CONCLUSIONS: The WHaSP system was successfully used in surgery. It integrated seamlessly into existing equipment within the operating room and did not affect flow. The positive outcomes of utilizing the WHaSP were improved communication in the OR, improved efficiency and safety of the surgery, easy to use, and comfortable to wear. The surgeons showed a preference for utilizing the WHaSP if given a choice.

A chance-constrained programming approach to preoperative planning of robotic cardiac surgery under task-level uncertainty.

In this paper, a novel formulation for robust surgical planning of robotics-assisted minimally invasive cardiac surgery based on patient-specific preoperative images is proposed. In this context, robustness is quantified in terms of the likelihood of intraoperative collisions and of joint limit violations. The proposed approach provides a more accurate and complete formulation than existing deterministic approaches in addressing uncertainty at the task level. Moreover, it is demonstrated that the dexterity of robotic arms can be quantified as a cross-entropy term. The resulting planning problem is rendered as a chance-constrained entropy maximization problem seeking a plan with the least susceptibility toward uncertainty at the task level, while maximizing the dexterity (cross-entropy term). By such treatment of uncertainty at the task level, spatial uncertainty pertaining to mismatches between the patient-specific anatomical model and that of the actual intraoperative situation is also indirectly addressed. As a solution method, the unscented transform is adopted to efficiently transform the resulting chance-constrained entropy maximization problem into a constrained nonlinear program without resorting to computationally expensive particle-based methods.

A knee arthroscopy simulator: design and validation.

Many challenges exist when teaching and learning arthroscopic surgery, carrying a high risk of damaging the joint during the learning process. To minimize risk, the use of arthroscopy simulators allows trainees to learn basic skills in a risk-free environment before entering the operating room. A high-fidelity physical knee arthroscopy simulator is proposed to bridge the gap between surgeons and residents. The simulator is composed of modular and replaceable elements and can measure applied forces, instrument position and hand motion, in order to assess performance in real time. A construct validity study was conducted in order to assess the performance improvement of novices after practicing with the simulator. In addition, a face validity study involving expert surgeons indicated that the simulator provides a realistic scenario suitable for teaching basic skills. Future work involves the development of better metrics to assess user performance.

Force sensing-based simulator for arthroscopic skills assessment in orthopaedic knee surgery.

The complexity of knee arthroscopy makes it difficult to teach and assess skill level during real surgery. Simulator-based training is ideal for this complex procedure. To address the limitations of existing systems, a physical simulator, capable of providing skills assessment and feedback has been developed. The simulator measures the forces applied on the femur and acting on the tools. An experimental evaluation was conducted to assess the differences in task completion time and applied forces for fourteen tasks performed by trainees and expert surgeons. Initial results show that the simulator, together with well-chosen tasks, can potentially be used to assess user performance.