Skill-level classification and performance evaluation for endoscopic sleeve gastroplasty.

BACKGROUND: We previously developed grading metrics for quantitative performance measurement for simulated endoscopic sleeve gastroplasty (ESG) to create a scalar reference to classify subjects into experts and novices. In this work, we used synthetic data generation and expanded our skill level analysis using machine learning techniques. METHODS: We used the synthetic data generation algorithm SMOTE to expand and balance our dataset of seven actual simulated ESG procedures using synthetic data. We performed optimization to seek optimum metrics to classify experts and novices by identifying the most critical and distinctive sub-tasks. We used support vector machine (SVM), AdaBoost, K-nearest neighbors (KNN) Kernel Fisher discriminant analysis (KFDA), random forest, and decision tree classifiers to classify surgeons as experts or novices after grading. Furthermore, we used an optimization model to create weights for each task and separate the clusters by maximizing the distance between the expert and novice scores. RESULTS: We split our dataset into a training set of 15 samples and a testing dataset of five samples. We put this dataset through six classifiers, SVM, KFDA, AdaBoost, KNN, random forest, and decision tree, resulting in 0.94, 0.94, 1.00, 1.00, 1.00, and 1.00 accuracy, respectively, for training and 1.00 accuracy for the testing results for SVM and AdaBoost. Our optimization model maximized the distance between the expert and novice groups from 2 to 53.72. CONCLUSION: This paper shows that feature reduction, in combination with classification algorithms such as SVM and KNN, can be used in tandem to classify endoscopists as experts or novices based on their results recorded using our grading metrics. Furthermore, this work introduces a non-linear constraint optimization to separate the two clusters and find the most important tasks using weights.

Objective metrics for hand-sewn bowel anastomoses can differentiate novice from expert surgeons.

BACKGROUND: Assessing performance automatically in a virtual reality trainer or from recorded videos is advantageous but needs validated objective metrics. The purpose of this study is to obtain expert consensus and validate task-specific metrics developed for assessing performance in double-layered end-to-end anastomosis. MATERIALS AND METHODS: Subjects were recruited into expert (PGY 4-5, colorectal surgery residents, and attendings) and novice (PGY 1-3) groups. Weighted average scores of experts for each metric item, completion time, and the total scores computed using global and task-specific metrics were computed for assessment. RESULTS: A total of 43 expert surgeons rated our task-specific metric items with weighted averages ranging from 3.33 to 4.5 on a 5-point Likert scale. A total of 20 subjects (10 novices and 10 experts) participated in validation study. The novice group completed the task significantly more slowly than the experienced group (37.67 ± 7.09 vs 25.47 ± 7.82 min, p = 0.001). In addition, both the global rating scale (23.47 ± 4.28 vs 28.3 ± 3.85, p = 0.016) and the task-specific metrics showed a significant difference in performance between the two groups (38.77 ± 2.83 vs 42.58 ± 4.56 p = 0.027) following partial least-squares (PLS) regression. Furthermore, PLS regression showed that only two metric items (Stay suture tension and Tool handling) could reliably differentiate the performance between the groups (20.41 ± 2.42 vs 24.28 ± 4.09 vs, p = 0.037). CONCLUSIONS: Our study shows that our task-specific metrics have significant discriminant validity and can be used to evaluate the technical skills for this procedure.

Hierarchical task analysis of endoscopic sleeve gastroplasty.

BACKGROUND: Endoscopic sleeve gastroplasty (ESG) is a minimally invasive endoscopic weight loss procedure used to treat obesity. The long-term goal of this project is to develop a Virtual Bariatric Endoscopy (ViBE) simulator for training and assessment of the ESG procedure. The objectives of this current work are to: (a) perform a task analysis of ESG and (b) create metrics to be validated in the created simulator. METHODS: We performed a hierarchical task analysis (HTA) by identifying the significant tasks of the ESG procedure. We created the HTA to show the breakdown and connection of the tasks of the procedure. Utilizing the HTA and input from ESG experts, performance metrics were derived for objective measurement of the ESG procedure. Three blinded video raters analyzed seven recorded ESG procedures according to the proposed performance metrics. RESULTS: Based on the seven videos, there was a positive correlation between total task times and total performance scores (R = 0.886, P = 0.008). Endoscopists expert were found to be more skilled in reducing the area of the stomach compared to endoscopists novice (34.6% reduction versus 9.4% reduction, P = 0.01). The mean novice performance score was significantly lower than the mean expert performance score (34.7 vs. 23.8, P = 0.047). The inter-rater reliability test showed a perfect agreement among three raters for all tasks except for the suturing task. The suturing task had a significant agreement (Inter-rater Correlation = 0.84, Cronbach's alpha = 0.88). Suturing was determined to be a critical task that is positively correlated with the total score (R = 0.962, P = 0.0005). CONCLUSION: The task analysis and metrics development are critical for the development of the ViBE simulator. This preliminary assessment demonstrates that the performance metrics provide an accurate assessment of the endoscopist's performance. Further validation testing and refinement of the performance metrics are anticipated.

Surgeons With Five or More Actual Cricothyrotomies Perform Significantly Better on a Virtual Reality Simulator.

BACKGROUND: Discriminating performance of learners with varying experience is essential to developing and validating a surgical simulator. For rare and emergent procedures such as cricothyrotomy (CCT), the criteria to establish such groups are unclear. This study is to investigate the impact of surgeons' actual CCT experience on their virtual reality simulator performance and to determine the minimum number of actual CCTs that significantly discriminates simulator scores. Our hypothesis is that surgeons who performed more actual CCT cases would perform better on a virtual reality CCT simulator. METHODS: 47 clinicians were recruited to participate in this study at the 2018 annual conference of the Society of American Gastrointestinal and Endoscopic Surgeons. We established groups based on three different experience thresholds, that is, the minimal number of CCT cases performed (1, 5, and 10), and compared simulator performance between these groups. RESULTS: Participants who had performed more clinical cases manifested higher mean scores in completing CCT simulation tasks, and those reporting at least 5 actual CCTs had significantly higher (P = 0.014) simulator scores than those who had performed fewer cases. Another interesting finding was that classifying participants based on experience level, that is, attendings, fellows, and residents, did not yield statistically significant differences in skills related to CCT. CONCLUSIONS: The simulator was sensitive to prior experience at a threshold of 5 actual CCTs performed.

Endoscopic submucosal dissection: a cognitive task analysis framework toward training design.

BACKGROUND: One of the major impediments to the proliferation of endoscopic submucosal dissection (ESD) training in Western countries is the lack of sufficient experts as instructors. One way to address this gap is to develop didactic systems, such as surgical simulators, to support the role of trainers. Cognitive task analysis (CTA) has been used in healthcare for the design and improvement of surgical training programs, and therefore can potentially be used for design of similar systems for ESD. OBJECTIVE: The aim of the study was to apply a CTA-based approach to identify the cognitive aspects of performing ESD, and to generate qualitative insights for training. MATERIALS AND METHODS: Semi-structured interviews were designed based on the CTA framework to elicit knowledge of ESD practitioners relating to the various tasks involved in the procedure. Three observations were conducted of expert ESD trainers either while they performed actual ESD procedures or at a training workshop. Interviews were either conducted over the phone or in person. Interview participants included four experts and four novices. The observation notes and interviews were analyzed for emergent qualitative themes and relationships. RESULTS: The qualitative analysis yielded thematic insights related to four main cognition-related categories: learning goals/principles, challenges/concerns, strategies, and decision-making. The specific insights under each of these categories were systematically mapped to the various tasks inherent to the ESD procedure. CONCLUSIONS: The CTA approach was applied to identify cognitive themes related to ESD procedural tasks. Insights developed based on the qualitative analysis of interviews and observations of ESD practitioners can be used to inform the design of ESD training systems, such as virtual reality-based simulators.

Partition-based optimization model for generative anatomy modeling language (POM-GAML).

BACKGROUND: This paper presents a novel approach for Generative Anatomy Modeling Language (GAML). This approach automatically detects the geometric partitions in 3D anatomy that in turn speeds up integrated non-linear optimization model in GAML for 3D anatomy modeling with constraints (e.g. joints). This integrated non-linear optimization model requires the exponential execution time. However, our approach effectively computes the solution for non-linear optimization model and reduces computation time from exponential to linear time. This is achieved by grouping the 3D geometric constraints into communities. METHODS: Various community detection algorithms (k-means clustering, Clauset Newman Moore, and Density-Based Spatial Clustering of Applications with Noise) were used to find communities and partition the non-linear optimization problem into sub-problems. GAML was used to create a case study for 3D shoulder model to benchmark our approach with up to 5000 constraints. RESULTS: Our results show that the computation time was reduced from exponential time to linear time and the error rate between the partitioned and non-partitioned approach decreases with the increasing number of constraints. For the largest constraint set (5000 constraints), speed up was over 2689-fold whereas error was computed as low as 2.2%. CONCLUSION: This study presents a novel approach to group anatomical constraints in 3D human shoulder model using community detection algorithms. A case study for 3D modeling for shoulder models developed for arthroscopic rotator cuff simulation was presented. Our results significantly reduced the computation time in conjunction with a decrease in error using constrained optimization by linear approximation, non-linear optimization solver.

Local edge-enhanced active contour for accurate skin lesion border detection.

BACKGROUND: Dermoscopy is one of the common and effective imaging techniques in diagnosis of skin cancer, especially for pigmented lesions. Accurate skin lesion border detection is the key to extract important dermoscopic features of the skin lesion. In current clinical settings, border delineation is performed manually by dermatologists. Operator based assessments lead to intra- and inter-observer variations due to its subjective nature. Moreover it is a tedious process. Because of aforementioned hurdles, the automation of lesion boundary detection in dermoscopic images is necessary. In this study, we address this problem by developing a novel skin lesion border detection method with a robust edge indicator function, which is based on a meshless method. RESULT: Our results are compared with the other image segmentation methods. Our skin lesion border detection algorithm outperforms other state-of-the-art methods. Based on dermatologist drawn ground truth skin lesion borders, the results indicate that our method generates reasonable boundaries than other prominent methods having Dice score of 0.886 ±0.094 and Jaccard score of 0.807 ±0.133. CONCLUSION: We prove that smoothed particle hydrodynamic (SPH) kernels can be used as edge features in active contours segmentation and probability map can be employed to avoid the evolving contour from leaking into the object of interest.

A task and performance analysis of endoscopic submucosal dissection (ESD) surgery.

BACKGROUND: ESD is an endoscopic technique for en bloc resection of gastrointestinal lesions. ESD is a widely-used in Japan and throughout Asia, but not as prevalent in Europe or the US. The procedure is technically challenging and has higher adverse events (bleeding, perforation) compared to endoscopic mucosal resection. Inadequate training platforms and lack of established training curricula have restricted its wide acceptance in the US. Thus, we aim to develop a Virtual Endoluminal Surgery Simulator (VESS) for objective ESD training and assessment. In this work, we performed task and performance analysis of ESD surgeries. METHODS: We performed a detailed colorectal ESD task analysis and identified the critical ESD steps for lesion identification, marking, injection, circumferential cutting, dissection, intraprocedural complication management, and post-procedure examination. We constructed a hierarchical task tree that elaborates the order of tasks in these steps. Furthermore, we developed quantitative ESD performance metrics. We measured task times and scores of 16 ESD surgeries performed by four different endoscopic surgeons. RESULTS: The average time of the marking, injection, and circumferential cutting phases are 203.4 (σ: 205.46), 83.5 (σ: 49.92), 908.4 s. (σ: 584.53), respectively. Cutting the submucosal layer takes most of the time of overall ESD procedure time with an average of 1394.7 s (σ: 908.43). We also performed correlation analysis (Pearson's test) among the performance scores of the tasks. There is a moderate positive correlation (R = 0.528, p = 0.0355) between marking scores and total scores, a strong positive correlation (R = 0.7879, p = 0.0003) between circumferential cutting and submucosal dissection and total scores. Similarly, we noted a strong positive correlation (R = 0.7095, p = 0.0021) between circumferential cutting and submucosal dissection and marking scores. CONCLUSIONS: We elaborated ESD tasks and developed quantitative performance metrics used in analysis of actual surgery performance. These ESD metrics will be used in future validation studies of our VESS simulator.

Texture based skin lesion abruptness quantification to detect malignancy.

BACKGROUND: Abruptness of pigment patterns at the periphery of a skin lesion is one of the most important dermoscopic features for detection of malignancy. In current clinical setting, abrupt cutoff of a skin lesion determined by an examination of a dermatologist. This process is subjective, nonquantitative, and error-prone. We present an improved computational model to quantitatively measure abruptness of a skin lesion over our previous method. To achieve this, we quantitatively analyze the texture features of a region within the lesion boundary. This region is bounded by an interior border line of the lesion boundary which is determined using level set propagation (LSP) method. This method provides a fast border contraction without a need for extensive boolean operations. Then, we build feature vectors of homogeneity, standard deviation of pixel values, and mean of the pixel values of the region between the contracted border and the original border. These vectors are then classified using neural networks (NN) and SVM classifiers. RESULTS: As lower homogeneity indicates sharp cutoffs, suggesting melanoma, we carried out our experiments on two dermoscopy image datasets, which consist of 800 benign and 200 malignant melanoma cases. LSP method helped produce better results than Kaya et al., 2016 study. By using texture homogeneity at the periphery of a lesion border determined by LSP, as a classification results, we obtained 87% f1-score and 78% specificity; that we obtained better results than in the previous study. We also compared the performances of two different NN classifiers and support vector machine classifier. The best results obtained using combination of RGB color spaces with the fully-connected multi-hidden layer NN. CONCLUSIONS: Computational results also show that skin lesion abrupt cutoff is a reliable indicator of malignancy. Results show that computational model of texture homogeneity along the periphery of skin lesion borders based on LSP is an effective way of quantitatively measuring abrupt cutoff of a lesion.

Abrupt skin lesion border cutoff measurement for malignancy detection in dermoscopy images.

BACKGROUND: Automated skin lesion border examination and analysis techniques have become an important field of research for distinguishing malignant pigmented lesions from benign lesions. An abrupt pigment pattern cutoff at the periphery of a skin lesion is one of the most important dermoscopic features for detection of neoplastic behavior. In current clinical setting, the lesion is divided into a virtual pie with eight sections. Each section is examined by a dermatologist for abrupt cutoff and scored accordingly, which can be tedious and subjective. METHODS: This study introduces a novel approach to objectively quantify abruptness of pigment patterns along the lesion periphery. In the proposed approach, first, the skin lesion border is detected by the density based lesion border detection method. Second, the detected border is gradually scaled through vector operations. Then, along gradually scaled borders, pigment pattern homogeneities are calculated at different scales. Through this process, statistical texture features are extracted. Moreover, different color spaces are examined for the efficacy of texture analysis. RESULTS: The proposed method has been tested and validated on 100 (31 melanoma, 69 benign) dermoscopy images. Analyzed results indicate that proposed method is efficient on malignancy detection. More specifically, we obtained specificity of 0.96 and sensitivity of 0.86 for malignancy detection in a certain color space. The F-measure, harmonic mean of recall and precision, of the framework is reported as 0.87. CONCLUSIONS: The use of texture homogeneity along the periphery of the lesion border is an effective method to detect malignancy of the skin lesion in dermoscopy images. Among different color spaces tested, RGB color space's blue color channel is the most informative color channel to detect malignancy for skin lesions. That is followed by YCbCr color spaces Cr channel, and Cr is closely followed by the green color channel of RGB color space.

Graphic and haptic simulation for transvaginal cholecystectomy training in NOTES.

BACKGROUND: Natural Orifice Transluminal Endoscopic Surgery (NOTES) provides an emerging surgical technique which usually needs a long learning curve for surgeons. Virtual reality (VR) medical simulators with vision and haptic feedback can usually offer an efficient and cost-effective alternative without risk to the traditional training approaches. Under this motivation, we developed the first virtual reality simulator for transvaginal cholecystectomy in NOTES (VTEST™). METHODS: This VR-based surgical simulator aims to simulate the hybrid NOTES of cholecystectomy. We use a 6DOF haptic device and a tracking sensor to construct the core hardware component of simulator. For software, an innovative approach based on the inner-spheres is presented to deform the organs in real time. To handle the frequent collision between soft tissue and surgical instruments, an adaptive collision detection method based on GPU is designed and implemented. To give a realistic visual performance of gallbladder fat tissue removal by cautery hook, a multi-layer hexahedral model is presented to simulate the electric dissection of fat tissue. RESULTS: From the experimental results, trainees can operate in real time with high degree of stability and fidelity. A preliminary study was also performed to evaluate the realism and the usefulness of this hybrid NOTES simulator. CONCLUSIONS: This prototyped simulation system has been verified by surgeons through a pilot study. Some items of its visual performance and the utility were rated fairly high by the participants during testing. It exhibits the potential to improve the surgical skills of trainee and effectively shorten their learning curve.

Face and content validation of a Virtual Translumenal Endoscopic Surgery Trainer (VTEST™).

BACKGROUND: Natural orifice translumenal endoscopic surgery (NOTES) is an emerging surgical paradigm, where peritoneal access is achieved through one of the natural orifices of the body. It is being reported as a safe and feasible surgical technique with significantly reduced external scarring. Virtual Translumenal Endoscopic Surgical Trainer (VTEST™) is the first virtual reality simulator for the NOTES. The VTEST™ simulator was developed to train surgeons in the hybrid transvaginal NOTES cholecystectomy procedure. The initial version of the VTEST™ simulator underwent face validation at the 2013 Natural Orifice Surgery Consortium for Assessment and Research (NOSCAR) summit. Several areas of improvement were identified as a result, and the corresponding modifications were implemented in the simulator. This manuscript outlines the results of the subsequent evaluation study, performed in order to assess the face and content validity of the latest VTEST™ simulator. METHODS: Twelve subjects participated in an institutional review board-approved study that took place at the 2014 NOSCAR summit. Six of the 12 subjects, who are experts with NOTES experience, were used for face and content validation. The subjects performed the hybrid transvaginal NOTES cholecystectomy procedure on VTEST™ that included identifying the Calot's triangle, clipping and cutting the cystic duct/artery, and detaching the gallbladder. The subjects then answered five-point Likert scale feedback questionnaires for face and content validity. RESULTS: Overall, subjects rated 12/15 questions as 3.0 or greater (60 %), for face validity questions regarding the realism of the anatomical features, interface, and the tasks. Subjects also highly rated the usefulness of the simulator in learning the fundamental NOTES technical skills (3.50 ± 0.84). Content validity results indicate a high level of usefulness of the VTEST™ for training prior to operating room experience (4.17 ± 0.75).

Density-based parallel skin lesion border detection with webCL.

BACKGROUND: Dermoscopy is a highly effective and noninvasive imaging technique used in diagnosis of melanoma and other pigmented skin lesions. Many aspects of the lesion under consideration are defined in relation to the lesion border. This makes border detection one of the most important steps in dermoscopic image analysis. In current practice, dermatologists often delineate borders through a hand drawn representation based upon visual inspection. Due to the subjective nature of this technique, intra- and inter-observer variations are common. Because of this, the automated assessment of lesion borders in dermoscopic images has become an important area of study. METHODS: Fast density based skin lesion border detection method has been implemented in parallel with a new parallel technology called WebCL. WebCL utilizes client side computing capabilities to use available hardware resources such as multi cores and GPUs. Developed WebCL-parallel density based skin lesion border detection method runs efficiently from internet browsers. RESULTS: Previous research indicates that one of the highest accuracy rates can be achieved using density based clustering techniques for skin lesion border detection. While these algorithms do have unfavorable time complexities, this effect could be mitigated when implemented in parallel. In this study, density based clustering technique for skin lesion border detection is parallelized and redesigned to run very efficiently on the heterogeneous platforms (e.g. tablets, SmartPhones, multi-core CPUs, GPUs, and fully-integrated Accelerated Processing Units) by transforming the technique into a series of independent concurrent operations. Heterogeneous computing is adopted to support accessibility, portability and multi-device use in the clinical settings. For this, we used WebCL, an emerging technology that enables a HTML5 Web browser to execute code in parallel for heterogeneous platforms. We depicted WebCL and our parallel algorithm design. In addition, we tested parallel code on 100 dermoscopy images and showed the execution speedups with respect to the serial version. Results indicate that parallel (WebCL) version and serial version of density based lesion border detection methods generate the same accuracy rates for 100 dermoscopy images, in which mean of border error is 6.94%, mean of recall is 76.66%, and mean of precision is 99.29% respectively. Moreover, WebCL version's speedup factor for 100 dermoscopy images' lesion border detection averages around ~491.2. CONCLUSIONS: When large amount of high resolution dermoscopy images considered in a usual clinical setting along with the critical importance of early detection and diagnosis of melanoma before metastasis, the importance of fast processing dermoscopy images become obvious. In this paper, we introduce WebCL and the use of it for biomedical image processing applications. WebCL is a javascript binding of OpenCL, which takes advantage of GPU computing from a web browser. Therefore, WebCL parallel version of density based skin lesion border detection introduced in this study can supplement expert dermatologist, and aid them in early diagnosis of skin lesions. While WebCL is currently an emerging technology, a full adoption of WebCL into the HTML5 standard would allow for this implementation to run on a very large set of hardware and software systems. WebCL takes full advantage of parallel computational resources including multi-cores and GPUs on a local machine, and allows for compiled code to run directly from the Web Browser.

Optimization Model for Web Based Multimodal Interactive Simulations.

This paper presents a technique for optimizing the performance of web based multimodal interactive simulations. For such applications where visual quality and the performance of simulations directly influence user experience, overloading of hardware resources may result in unsatisfactory reduction in the quality of the simulation and user satisfaction. However, optimization of simulation performance on individual hardware platforms is not practical. Hence, we present a mixed integer programming model to optimize the performance of graphical rendering and simulation performance while satisfying application specific constraints. Our approach includes three distinct phases: identification, optimization and update. In the identification phase, the computing and rendering capabilities of the client device are evaluated using an exploratory proxy code. This data is utilized in conjunction with user specified design requirements in the optimization phase to ensure best possible computational resource allocation. The optimum solution is used for rendering (e.g. texture size, canvas resolution) and simulation parameters (e.g. simulation domain) in the update phase. Test results are presented on multiple hardware platforms with diverse computing and graphics capabilities to demonstrate the effectiveness of our approach.

Endoscopic sleeve gastroplasty: stomach location and task classification for evaluation using artificial intelligence.

PURPOSE: We have previously developed grading metrics to objectively measure endoscopist performance in endoscopic sleeve gastroplasty (ESG). One of our primary goals is to automate the process of measuring performance. To achieve this goal, the repeated task being performed (grasping or suturing) and the location of the endoscopic suturing device in the stomach (Incisura, Anterior Wall, Greater Curvature, or Posterior Wall) need to be accurately recorded. METHODS: For this study, we populated our dataset using screenshots and video clips from experts carrying out the ESG procedure on ex vivo porcine specimens. Data augmentation was used to enlarge our dataset, and synthetic minority oversampling (SMOTE) to balance it. We performed stomach localization for parts of the stomach and task classification using deep learning for images and computer vision for videos. RESULTS: Classifying the stomach's location from the endoscope without SMOTE for images resulted in 89% and 84% testing and validation accuracy, respectively. For classifying the location of the stomach from the endoscope with SMOTE, the accuracies were 97% and 90% for images, while for videos, the accuracies were 99% and 98% for testing and validation, respectively. For task classification, the accuracies were 97% and 89% for images, while for videos, the accuracies were 100% for both testing and validation, respectively. CONCLUSION: We classified the four different stomach parts manipulated during the ESG procedure with 97% training accuracy and classified two repeated tasks with 99% training accuracy with images. We also classified the four parts of the stomach with a 99% training accuracy and two repeated tasks with a 100% training accuracy with video frames. This work will be essential in automating feedback mechanisms for learners in ESG.

Pattern cutting and ligating loop simulation in Virtual Basic Laparoscopic Skill Trainer (VBLaST.

This paper presents the pattern cutting and ligating loop simulation in the Virtual Basic Laparoscopic Skill Trainer (VBLaST©). In the simulation, the gauze, tubular foam, and ligating loop thread are modeled by the mass-spring method and constraint projection for the inextensible characteristics. Discrete simulation states defined based on the tool-object interaction types are utilized to efficiently and accurately manages the physics simulation, collision processing, and haptic feedback in real-time. An automated scoring system provides quantitative measurement for evaluation of trainees' skills. The simulation results show advanced visual realism and real-time performances.

Performance optimization of web-based medical simulation.

This paper presents a technique for performance optimization of multimodal interactive web-based medical simulation. A web-based simulation framework is promising for easy access and wide dissemination of medical simulation. However, the real-time performance of the simulation highly depends on hardware capability on the client side. Providing consistent simulation in different hardware is critical for reliable medical simulation. This paper proposes a non-linear mixed integer programming model to optimize the performance of visualization and physics computation while considering hardware capability and application specific constraints. The optimization model identifies and parameterizes the rendering and computing capabilities of the client hardware using an exploratory proxy code. The parameters are utilized to determine the optimized simulation conditions including texture sizes, mesh sizes and canvas resolution. The test results show that the optimization model not only achieves a desired frame per second but also resolves visual artifacts due to low performance hardware.

GPU based Position Based Dynamics for Surgical Simulators.

Position Based Dynamics is the most popular approach for simulating dynamic systems in computer graphics. However, volume rendering with linear deformation times is still a challenge in virtual scenes. In this work, we implemented Graphics Processing Unit (GPU)-based Position-Based Dynamics to iMSTK, an open-source toolkit for rapid prototyping interactive multi-modal surgical simulation. We utilized NVIDIA's CUDA toolkit for this implementation and carried out vector calculations on GPU kernels while ensuring that threads do not overwrite the data used in other calculations. We compared our results with an available GPU-based Position-Based Dynamics solver. We gathered results on two computers with different specifications using affordable GPUs. The vertex (959 vertices) and tetrahedral mesh element (2591 elements) counts were kept the same for all calculations. Our implementation was able to speed up physics calculations by nearly 10x. For the size of 128x128, the CPU implementation carried out physics calculations in 7900ms while our implementation carried out the same physics calculations in 820ms.

Evaluation of WebRTC in the Cloud for Surgical Simulations: A case study on Virtual Rotator Cuff Arthroscopic Skill Trainer (ViRCAST).

Web Real-Time Communication (WebRTC) is an open-source technology which enables remote peer-to-peer video and audio connection. It has quickly become the new standard for real-time communications over the web and is commonly used as a video conferencing platform. In this study, we present a different application domain which may greatly benefit from WebRTC technology, that is virtual reality (VR) based surgical simulations. Virtual Rotator Cuff Arthroscopic Skill Trainer (ViRCAST) is our testing platform that we completed preliminary feasibility studies for WebRTC. Since the elasticity of cloud computing provides the ability to meet possible future hardware/software requirements and demand growth, ViRCAST is deployed in a cloud environment. Additionally, in order to have plausible simulations and interactions, any VR-based surgery simulator must have haptic feedback. Therefore, we implemented an interface to WebRTC for integrating haptic devices. We tested ViRCAST on Google cloud through haptic-integrated WebRTC at various client configurations. Our experiments showed that WebRTC with cloud and haptic integrations is a feasible solution for VR-based surgery simulators. From our experiments, the WebRTC integrated simulation produced an average frame rate of 33 fps, and the hardware integration produced an average lag of 0.7 milliseconds in real-time.

Multimodal Approach to Assess a Virtual Reality-based Surgical Training Platform.

Virtual reality (VR) can bring numerous benefits to the learning process. Combining a VR environment with physiological sensors can be beneficial in skill assessment. We aim to investigate trainees' physiological (ECG) and behavioral differences during the virtual reality-based surgical training environment. Our finding showed a significant association between the VR-Score and all participants' total NASA-TLX workload score. The extent of the NASA-TLX workload score was negatively correlated with VR-Score (R2 =0.15, P < 0.03). In time-domain ECG analysis, we found that RMSSD (R2 =0.16, P < 0.05) and pNN50 (R2 =0.15, P < 0.05) scores correlated with significantly higher VR-score of all participants. In this study, we used SVM (linear kernel) and Logistic Regression classification techniques to classify the participants as gamers and non-gamers using data from VR headsets. Both SVM and Logistic Regression accurately classified the participants as gamers and non-gamers with 83% accuracy. For both SVM and Linear Regression, precision was noted as 88%, recall as 83%, and f1-score as 83%. There is increasing interest in characterizing trainees' physiological and behavioral activity profiles in a VR environment, aiming to develop better training and assessment methodologies.