Image Guided Interpedicular Screw Placement Simulation System for Training and Skill Evaluation. Proof of Concept.

BACKGROUND: The SpineST-01 system is an image-guided vertebrae cannulation training system. During task execution, the computer calculates performance-based metrics displaying different visual perspectives (lateral view, axial view, anteroposterior view) with the position of the instrument inside the vertebra. Finally, a report with the metrics is generated as performance feedback. METHODS: A training box holds a 3D printed spine section. The computer works with 2 orthogonally disposed cameras, tracking passive markers placed on the instrument. Eight metrics were proposed to evaluate the execution of the surgical task. A preliminary study with 25 participants divided into 3 groups (12 novices, 10 intermediates, and 3 expert) was conducted to determine the feasibility of the system and to evaluate and assess the performance differences of each group using Kruskal-Wallis analysis and Mann-Whitney U analysis. In both analyses, a P value ≤ 0.05 was considered statistically significant. RESULTS: When comparing experts versus novices and all 3 groups, statistical analysis showed significant differences in 6 of the 8 metrics: axial angle error (°), lateral angle error (°), average speed (mm/second), progress between shots (mm), Time (seconds), and shots. The metrics that did not show any statistically significant difference were time between shots (seconds), and speed between shots (mm/second). Also, the average result comparison placed the experts as the best performance group. CONCLUSIONS: Initial testing of the SpineST-01 demonstrated potential for the system to practice image-guided cannulation tasks on lumbar vertebrae. Results showed objective differences between experts, intermediates, and novices in the proposed metrics, making this system a feasible option for developing basic navigation system skills without the risk of radiation exposure and objectively evaluating task performance.

Effect of three training programs on surgical performance in single-port laparoscopic surgery.

OBJECTIVE: The aim of this study was to evaluate the effect of three training methodologies on the acquisition of psychomotor skills for laparoendoscopic single-site surgery (LESS), using straight and articulating instruments. METHODS: A prospective study was conducted with subjects randomly divided into three groups, who performed a specific training for 12 days using three laparoscopic tasks in a laparoscopic simulator. Group-A trained in conventional laparoscopy setting using straight instruments and in LESS setting using both straight and articulating instruments. Group-B trained in LESS setting using straight and articulating instruments, whereas Group-C trained in LESS setting using articulating instruments. Participants' performance was recorded with a video-tracking system and evaluated with 12 motion analysis parameters (MAPs). RESULTS: All groups obtained significant differences in their performance in most of the MAPs. Group-C showed an improvement in nine MAPs, with a high level of technical competence. Group-A presented a marked improvement in bimanual dexterity skills. CONCLUSIONS: Training in LESS surgery using articulating laparoscopic instruments improves the quality of skills and allows smoother learning curves.

OBJETIVO: Evaluar el efecto de tres métodos de entrenamiento en la adquisición de habilidades psicomotrices para la cirugía laparoendoscópica por puerto único (LESS, laparoendoscopic single-site surgery) utilizando instrumental recto y articulado. MÉTODO: Se realizó un estudio prospectivo con sujetos divididos aleatoriamente en tres grupos, quienes realizaron un entrenamiento específico durante 12 días utilizando tres tareas laparoscópicas en un simulador laparoscópico. El grupo A entrenó en el entorno laparoscópico convencional con instrumentos rectos, y en el entorno LESS con instrumentos rectos y articulados. El grupo B entrenó en el entorno LESS con instrumentos rectos y articulados. El Grupo C entrenó en el entorno LESS con instrumentos articulados. El desempeño de los participantes se registró con un sistema de seguimiento en video y fue evaluado con 12 parámetros de análisis de movimiento (MAP, motion analysis parameters). RESULTADOS: Todos los grupos obtuvieron diferencias significativas en su desempeño para la mayoría de los MAP. El grupo C mostró una mejora en nueve MAP, con un alto nivel de competencia técnica. El grupo A mostró una marcada mejora en la habilidad de destreza bimanual. CONCLUSIONES: El entrenamiento en cirugía LESS con instrumentos articulados mejora la calidad de las habilidades adquiridas y permite curvas de aprendizaje más suaves.

Novices' learning curve in single-port surgery using three surgical training programs.

BACKGROUND: The objective of this study was to evaluate the novices' learning curves and proficiency level reached in laparoendoscopic single-site (LESS) surgery using three surgical training programs. MATERIAL AND METHODS: Participants were randomly divided into three groups, who trained in a specific practice regimen for 12 days using a laparoscopic box simulator and three tasks. Group A trained in three stages using conventional laparoscopic surgery (CLS) with straight instruments, and LESS with straight and articulating instruments for four days each. Group B trained in two stages in LESS with straight and articulating instruments for six days each. Group C trained only in LESS with articulating instruments exclusively for all 12 days. Performance was registered daily during the 12 days to evaluate the participants' progress. RESULTS: Pre- and post-training analysis of the three groups showed significant differences in performance, denoting the significant improvement in their LESS skills, with no difference between the groups. Group C reached a high level of technical competence with their specific training program in LESS, obtaining a lower asymptote and slow learning rate. CONCLUSION: Specific training programs in LESS settings using articulated instruments showed a slower learning rate than the other programs but better proficiency in the technique with the best surgical performance.

Objective Evaluation of Laparoscopic Experience Based on Muscle Electromyography and Accelerometry Performing Circular Pattern Cutting Tasks: A Pilot Study.

Purpose.The aim of this work is to present a new physical laparoscopy simulator with an electromyography (EMG)/accelerometry-based muscle activity recording system, EvalLap EMG-ACC, and perform objective evaluation of laparoscopic skills based on the quantification of muscle activity of participants with different levels of laparoscopic experience. Methods. EMG and ACC signals were obtained from 14 participants (6 experts, 8 medical students) performing circular pattern cutting tasks using a laparoscopic box trainer with the Trigno (Delsys Inc, Natick, MA) portable wireless system of 16 wireless sensors. Sensors were placed on the proximal and distal muscles of the upper extremities. Seven evaluation metrics were proposed and compared between skilled and novice surgeons. Results. The proximal and distal arm muscles (trapezius, deltoids, biceps, and forearms) were most active while executing laparoscopic tasks. Laparoscopic experience was associated with differences in EMG amplitude (Aavg), muscle activity (iEMG), hand acceleration (iACH), user movement (iAC), and muscle fatigue. For the cutting task, the deltoid, bicep, forearm EMG amplitude, and user movement significantly differed between experience groups. Conclusion. This pilot study demonstrates that different muscle groups are preferentially activated during laparoscopic tasks depending on the level of surgical experience. Expert surgeons showed less muscle activity compared with novices. EvalLap EMG-ACC represents a promising means to distinguish surgeons with basic cutting skills from those who have not yet developed these skills.

Objective psychomotor laparoscopic skills evaluation using a low-cost wearable device based on accelerometry: construct and concurrent validity study.

BACKGROUND: Motion analysis of surgical maneuvers provides useful quantitative information for the objective evaluation of the surgeons. However, surgical simulation laboratories for laparoscopic training do not usually integrate devices that help quantify the level of skills of the surgeons due to their limited resources and the high costs of new technologies. The purpose of this study is to present the construct and concurrent validity of a low-cost motion tracking system, based on a wireless triaxial accelerometer, employed to objectively evaluate psychomotor skills of surgeons during laparoscopic training. METHODS: An accelerometry system, a wireless three-axis accelerometer with appearance of wristwatch, was placed on the dominant hand of the surgeons to register the motion during the laparoscopy practice with the EndoViS simulator, which simultaneously recorded the motion of the laparoscopic needle driver. This study included the participation of 30 surgeons (6 experts, 14 intermediates and 10 novices) who performed the task of intracorporeal knot-tying suture. Using 11 motion analysis parameters (MAPs), the performance of each participant was assessed. Subsequently, the scores of the three groups of surgeons were statistically analyzed. In addition, a validity study was conducted comparing the metrics between the accelerometry-tracking system and the EndoViS hybrid simulator. RESULTS: Construct validity was achieved for 8 of the 11 metrics examined with the accelerometry system. Concurrent validity demonstrated that there is a strong correlation between the results of the accelerometry system and the EndoViS simulator in 9 of 11 parameters, showing reliability of the accelerometry system as an objective evaluation method. CONCLUSION: The accelerometry system was successfully validated. This method is potentially useful to complement the objective evaluation of surgeons during laparoscopic practice in training environments such as box-trainers and simulators.

Face, content, and construct validity of the virtual immersive operating room simulator for training laparoscopic procedures.

BACKGROUND: The aim of this work is to present the face, content, and construct validation of the virtual immersive operating room simulator (VIORS) for procedural training of surgeons' laparoscopic psychomotor skills and evaluate the immersive training experience. METHODS: The VIORS simulator consists of an HMD Oculus Rift 2016 with a visor on a 1080 × 1200 pixel OLED screen, two positioning sensors with two adapted controls to simulate laparoscopic instruments, and an acrylic base to simulate the conventional laparoscopic setup. The immersion consists of a 360° virtual operating room environment, based on the EndoSuite at Hospital Infantil de Mexico Federico Gomez, which reproduces a configuration of equipment, instruments, and common distractions in the operating room during a laparoscopic cholecystectomy procedure. Forty-five surgeons, residents, and medicine students participated in this study: 27 novices, 13 intermediates, and 5 experts. They completed a questionnaire on the realism and operating room immersion, as well as their capabilities for laparoscopic procedural training, scored in the 5-point Likert scale. The data of instrument movement were recorded and analyzed using 13 movement analysis parameters (MAPs). The experience during training with VIORS was evaluated through NASA-TLX. RESULTS: The participants were enthusiastic about the immersion and sensation levels of the VIORS simulator, with positive scores on the realism and its capabilities for procedural training using VIORS. The results proved that the VIORS simulator was able to differentiate between surgeons with different skill levels. Statistically significant differences were found in nine MAPs, demonstrating their construct validity for the objective assessment of the procedural laparoscopic performance. At cognitive level, the inversion experience proves a moderate mental workload when the laparoscopic procedure is carried out. CONCLUSION: The VIORS simulator has been successfully presented and validated. The VIORS simulator is a useful and effective device for the training of procedural laparoscopic psychomotor skills.

Protein Science Meets Artificial Intelligence: A Systematic Review and a Biochemical Meta-Analysis of an Inter-Field.

Proteins are some of the most fascinating and challenging molecules in the universe, and they pose a big challenge for artificial intelligence. The implementation of machine learning/AI in protein science gives rise to a world of knowledge adventures in the workhorse of the cell and proteome homeostasis, which are essential for making life possible. This opens up epistemic horizons thanks to a coupling of human tacit-explicit knowledge with machine learning power, the benefits of which are already tangible, such as important advances in protein structure prediction. Moreover, the driving force behind the protein processes of self-organization, adjustment, and fitness requires a space corresponding to gigabytes of life data in its order of magnitude. There are many tasks such as novel protein design, protein folding pathways, and synthetic metabolic routes, as well as protein-aggregation mechanisms, pathogenesis of protein misfolding and disease, and proteostasis networks that are currently unexplored or unrevealed. In this systematic review and biochemical meta-analysis, we aim to contribute to bridging the gap between what we call binomial artificial intelligence (AI) and protein science (PS), a growing research enterprise with exciting and promising biotechnological and biomedical applications. We undertake our task by exploring "the state of the art" in AI and machine learning (ML) applications to protein science in the scientific literature to address some critical research questions in this domain, including What kind of tasks are already explored by ML approaches to protein sciences? What are the most common ML algorithms and databases used? What is the situational diagnostic of the AI-PS inter-field? What do ML processing steps have in common? We also formulate novel questions such as Is it possible to discover what the rules of protein evolution are with the binomial AI-PS? How do protein folding pathways evolve? What are the rules that dictate the folds? What are the minimal nuclear protein structures? How do protein aggregates form and why do they exhibit different toxicities? What are the structural properties of amyloid proteins? How can we design an effective proteostasis network to deal with misfolded proteins? We are a cross-functional group of scientists from several academic disciplines, and we have conducted the systematic review using a variant of the PICO and PRISMA approaches. The search was carried out in four databases (PubMed, Bireme, OVID, and EBSCO Web of Science), resulting in 144 research articles. After three rounds of quality screening, 93 articles were finally selected for further analysis. A summary of our findings is as follows: regarding AI applications, there are mainly four types: 1) genomics, 2) protein structure and function, 3) protein design and evolution, and 4) drug design. In terms of the ML algorithms and databases used, supervised learning was the most common approach (85%). As for the databases used for the ML models, PDB and UniprotKB/Swissprot were the most common ones (21 and 8%, respectively). Moreover, we identified that approximately 63% of the articles organized their results into three steps, which we labeled pre-process, process, and post-process. A few studies combined data from several databases or created their own databases after the pre-process. Our main finding is that, as of today, there are no research road maps serving as guides to address gaps in our knowledge of the AI-PS binomial. All research efforts to collect, integrate multidimensional data features, and then analyze and validate them are, so far, uncoordinated and scattered throughout the scientific literature without a clear epistemic goal or connection between the studies. Therefore, our main contribution to the scientific literature is to offer a road map to help solve problems in drug design, protein structures, design, and function prediction while also presenting the "state of the art" on research in the AI-PS binomial until February 2021. Thus, we pave the way toward future advances in the synthetic redesign of novel proteins and protein networks and artificial metabolic pathways, learning lessons from nature for the welfare of humankind. Many of the novel proteins and metabolic pathways are currently non-existent in nature, nor are they used in the chemical industry or biomedical field.

Needle path planning in semiautonomous and teleoperated robot-assisted epidural anaesthesia procedure: A proof of concept.

BACKGROUND: Epidural anaesthesia is a Percutaneous Procedure (PP) which plays a crucial role in surgical procedures, where accurate needle insertion is still challenging. The objective of this work is to present a Tuohy needle path planning, which allows an anaesthesiologist to drive semiautonomously, with the assistance of a teleoperated robot, the tip of the needle during this PP. METHODS: We capture, analysed and modelled the anaesthetist hands' motion during the execution of this procedure, by synthetising, programing and simulating a parametrised and normalised kinematic constrains dependent on an insertion variable in a virtual robot. RESULTS: Two preoperative path planning models were obtained, which provide a teleoperated robot with kinematic constraints to semiautonomously drive a Tuohy needle in the epidural anaesthesia procedure. CONCLUSIONS: A semiautonomous robot can assist in the execution of this PP using the kinematic constraints obtained from the study of the movement of a specialist's hands.

Steerable Surgical Instrument for Conventional and Single-Site Minimally Invasive Surgery.

Background. This article aims to present an innovative design of a steerable surgical instrument for conventional and single-site minimally invasive surgery (MIS), which improves the dexterity and maneuverability of the surgeon while offering a solution to the limitations of current tools. Methods. The steerable MIS instrument consists of a deflection structure with a curved sliding joints design that articulates the distal tip in two additional degrees of freedom (DoFs), relative to the instrument shaft, using transmission by cables. A passive ball-joint mechanism articulates the handle relative to the instrument shaft, improves wrist posture, and prevents collision of instrument handles during single-site MIS procedures. The two additional DoFs of the articulating tip are activated by a thumb-controlled device, using a joystick design mounted on the handle. This steerable MIS instrument was developed by additive manufacturing in a 3D printer using PLA polymer. Results. Prototype testing showed a maximum tip deflection of 60° in the left and right directions, with a total deflection of 120°. With the passive ball-joint fully offset, the steerable tip achieved a deflection of 90° for the right and 40° for the left direction, with a total deflection of 130°. Furthermore, the passive ball-joint mechanism in the handle obtained a maximum range of motion of 60°. Conclusions. This steerable MIS instrument concept offers an alternative to enhance the application fields of conventional and single-site MIS, increasing manual dexterity of the surgeon and the ability to reach narrow anatomies from other directions.

Development of a 3D Motion Tracking System for the Analysis of Skills in Microsurgery.

Microsurgical skills of trainee surgeons have been subjectively evaluated due to the lack of technological tools. The objective of this investigation is to present the construct validity of the mitracks3D, which is a system designed to help in the objective evaluation of microsurgery trainees. To achieve this, a stereoscopic vision system records the 3D motion of two tweezers manipulated by surgeons during microsurgery training. Using motion analysis parameters (MAPs), quantitative information about their microsurgical skills and performance is obtained. For validation, 14 participants were enrolled and divided into two groups: expert microsurgeons (3 female, 2 male) and trainee surgeons (4 female, 5 male). The 3D motion tracking was acquired while the surgeons practiced with two training models: transferring objects and suture. Twelve MAPs were used to objective assessment the skill levels of each participant. Subsequent, statistical analysis was computed to compare the scores of both groups. Validation results showed statistically significant differences in 8 of the 12 MAPs and in 10 of the 12 MAPs using the transferring and the suturing models, respectively. The capability of mitracks3D to differentiate the performance of microsurgeons by analyzing their movements was shown. The mitracks3D system was successfully validated. With this system was possible to differentiate the psychomotor microsurgical skills between the two groups of surgeons. The mitracks3D system is a suitable device for the evaluation of microsurgical skills in a variety of surgical specialties that require it during the training of their residents.

Integration of Comprehensive Metrics into the PsT1 Neuroendoscopic Training System.

OBJECTIVE: Metric-based surgical training can be used to quantify the level and progression of neurosurgical performance to optimize and monitor training progress. Here we applied innovative metrics to a physical neurosurgery trainer to explore whether these metrics differentiate between different levels of experience across different tasks. METHODS: Twenty-four participants (9 experts, 15 novices) performed 4 tasks (dissection, spatial adaptation, depth adaptation, and the A-B-A task) using the PsT1 training system. Four performance metrics (collision, precision, dissected area, and time) and 6 kinematic metrics (dispersion, path length, depth perception, velocity, acceleration, and motion smoothness) were collected. RESULTS: For all tasks, the execution time (t) of the experts was significantly lower than that of novices (P < 0.05). The experts performed significantly better in all but 2 of the other metrics, dispersion and sectional area, corresponding to the A-B-A task and dissection task, respectively, for which they showed a nonsignificant trend towards better performance (P = 0.052 and P = 0.076, respectively). CONCLUSIONS: It is possible to differentiate between the skill levels of novices and experts according to parameters derived from the PsT1 platform, paving the way for the quantitative assessment of training progress using this system. During the current coronavirus disease 2019 pandemic, neurosurgical simulators that gather surgical performance metrics offer a solution to the educational needs of residents.

Construct validity of the SurgForce system for objective assessment of laparoscopic suturing skills.

BACKGROUND: Laparoscopic surgery requires a new set of skill to be learned by the surgeons, of which the most relevant is tissue manipulation. Excessive forces applied to the tissue can cause rupture during manipulation or ischemia when confronting both sides of the tissue. The aim of this study is to establish the construct validity of the SurgForce system for objective assessment of advanced laparoscopic skills, based on the force signal generated during suture tasks, and the development of force parameters for evaluating tissue handling interaction. METHODS: The SurgForce system, a tissue handling training device that measures dynamic force, was used to capture the force generated by surgeons with different levels of laparoscopic experience. For construct validity, 37 participants were enrolled in this study: 19 medical students, 12 residents of surgical specialties and 6 expert surgeons. All participants performed an intracorporeal knotting suture task over a synthetic tissue pad with a laparoscopic box-trainer. The force performance of the participants was analyzed using 11 force-based parameters with the application of the SurgForce system. Statistical analysis was performed between novice, intermediate, and expert groups using a Kruskal-Wallis test, and between the pairs of groups using a Mann-Whitney U-test. RESULTS: Overall, 9 of the 11 force-related parameters showed significant differences between the three study groups. Results between the pairs of groups presented significant differences in 5 force parameters proposed. Construct validity results demonstrated that the SurgForce system was able to differentiate force performance between surgeons with different levels of laparoscopic experience. CONCLUSION: The SurgForce system was successfully validated. This force system showed its potential to measure the force exerted on tissue for objective assessment of tissue handling skills in suturing tasks. Furthermore, its compact design allows the use of this device in conventional laparoscopic box-trainers.

Design of a Dynamic Force Measurement System for Training and Evaluation of Suture Surgical Skills.

The aim of this study is to present the SurgeForce system, a tissue handling training device for analysis of dynamic force applied to the tissue and objective assessment of basic surgical skills during the suture process. The SurgeForce system consists of a mechanical base formed by two platforms joint with three stainless steel springs and a three axial digital accelerometer attached to the upper platform, which detects the dynamic force caused by a surgeon when performing a suture task over a synthetic tissue pad. Accelerometer data is sent to a control unit where preprocessing to transform the raw data into a force signal is done, and then, the force signal is sent to a computer application, which register the force exerted over the synthetic tissue pad. For validation, 17 participants (6 surgeons and 11 medical students) performed three simple interrupted sutures with knot tying using the SurgeForce system. Ten force-based metrics were proposed to evaluate their performance during the suturing task. Results of the validation showed statistical differences in 8 of 10 force-based parameters for assessment of basic surgical skills during the suture task. The SurgeForce system demonstrated its capacity to differentiate force-based performance of surgeons and medical students. The SurgeForce system has been successfully validated. This system was able to distinguish force performance between experts and novices, showing its potential to distinguish surgeons with basic suture skills from those who are not yet prepared.

Objective classification of psychomotor laparoscopic skills of surgeons based on three different approaches.

BACKGROUND: The determination of surgeons' psychomotor skills in minimally invasive surgery techniques is one of the major concerns of the programs of surgical training in several hospitals. Therefore, it is important to assess and classify objectively the level of experience of surgeons and residents during their training process. The aim of this study was to investigate three classification methods for establishing automatically the level of surgical competence of the surgeons based on their psychomotor laparoscopic skills. METHODS: A total of 43 participants, divided into an experienced surgeons group with ten experts (> 100 laparoscopic procedures performed) and non-experienced surgeons group with 24 residents and nine medical students (< 10 laparoscopic procedures performed), performed three tasks in the EndoViS training system. Motion data of the instruments were captured with a video-tracking system built into the EndoViS simulator and analyzed using 13 motion analysis parameters (MAPs). Radial basis function networks (RBFNets), K-star (K*), and random forest (RF) were used for classifying surgeons based on the MAPs' scores of all participants. The performance of the three classifiers was examined using hold-out and leave-one-out validation techniques. RESULTS: For all three tasks, the K-star method was superior in terms of accuracy and AUC in both validation techniques. The mean accuracy of the classifiers was 93.33% for K-star, 87.58% for RBFNets, and 84.85% for RF in hold-out validation, and 91.47% for K-star, 89.92% for RBFNets, and 83.72% for RF in leave-one-out cross-validation. CONCLUSIONS: The three proposed methods demonstrated high performance in the classification of laparoscopic surgeons, according to their level of psychomotor skills. Together with motion analysis and three laparoscopic tasks of the Fundamental Laparoscopic Surgery Program, these classifiers provide a means for objectively classifying surgical competence of the surgeons for existing laparoscopic box trainers.

Development and Preliminary Validation of a Rabbit Model of Duodenal Atresia for Training in Pediatric Surgical Skills.

Duodenal atresia is a congenital defect that requires advanced surgical skills. The objective of this study is to present an anatomical defect of duodenal atresia using a rabbit model and evaluate the preliminary experience for the training of surgical skills with pediatric surgeons. Adult white New Zealand male rabbits weighing 3.0 to 4.5 kg were used to create the defect. To simulate the bottom of the dilated blind pouch, the gastric antrum of the rabbit was obliterated using a 2-0 Prolene suture, and the cecal appendix was dissected to simulate the continuation of the duodenum. Participants performed laparoscopic duodenal atresia repair in this animal model using the iPhone trainer. Thirteen pediatric surgeons with experience in laparoscopic duodenal atresia repair assessed this model with a questionnaire on 5-point Likert-type scale. Overall, the simulated model of duodenal atresia obtained a general average score of 4.39. The highest observed average was for its physical realism, whereas the lowest score was in surgical experience. The global opinion of the model obtained a score of 4.40. In addition, all surgeons answered that this rabbit model showed the same complexity as newborns and young children in the repair of this type of defect. The inclusion of new models through rabbits in pediatric surgery programs will allow the development of advanced skills of pediatric residents and surgeons.

Orthogonal cameras system for tracking of laparoscopic instruments in training environments.

INTRODUCTION: Motion analysis is a valuable tool for assessment of psychomotor skills in laparoscopy. Nonetheless, it requires technologies for tracking the activity of the laparoscopic instruments during training. This paper presents a sensor-free system to track the movements of laparoscopic instruments based on an orthogonal camera system and video image processing. METHODS: The movements of the laparoscopic instruments are tracked with two webcams placed in an orthogonal configuration. The position and orientation in the three-dimensional workspace are obtained using color markers placed on the tip of the instruments. RESULTS: Accuracy tests show a resolution of 0.14 mm for displacement, with 1694 cm3 of total workspace, and 0.54° in the angular movements. Mean relative errors of the tracking system were <1%. The orthogonal cameras show high precision, linearity, and repeatability of motion recording of the laparoscopic instruments. CONCLUSION: The proposed system offers unconstrained manipulation of the instruments and a low-cost alternative for traditional tracking technologies.

INTRODUCCIÓN: El análisis del movimiento es una valiosa herramienta para la evaluación de las habilidades psicomotrices en la laparoscopia. Sin embargo, requiere tecnologías para el seguimiento de la actividad de los instrumentos laparoscópicos durante el entrenamiento. En este artículo presentamos una técnica sin sensores para realizar el seguimiento de los movimientos de los instrumentos laparoscópicos basado en un sistema de cámara ortogonal y procesamiento de imágenes de video. MÉTODO: Los movimientos de los instrumentos laparoscópicos son capturados con dos cámaras web colocadas en configuración ortogonal. La posición y la orientación en el espacio de trabajo tridimensional se obtienen utilizando marcadores de color colocados en la punta de los instrumentos. RESULTADOS: Las pruebas de precisión mostraron una resolución de 0.14 mm para el desplazamiento, con 1694 cm3 de espacio de trabajo total y 0.54° en los movimientos angulares. Los errores relativos medios del sistema de seguimiento fueron <1%. Las cámaras ortogonales demostraron alta precisión, linealidad y repetibilidad de la captura de movimiento de los instrumentos laparoscópicos. CONCLUSIONES: El sistema propuesto ofrece una manipulación sin restricciones de los instrumentos laparoscópicos y una alternativa de bajo costo para las tecnologías tradicionales de captura de movimiento.

Development of a Laparoscopic Box Trainer Based on Open Source Hardware and Artificial Intelligence for Objective Assessment of Surgical Psychomotor Skills.

BACKGROUND: A trainer for online laparoscopic surgical skills assessment based on the performance of experts and nonexperts is presented. The system uses computer vision, augmented reality, and artificial intelligence algorithms, implemented into a Raspberry Pi board with Python programming language. METHODS: Two training tasks were evaluated by the laparoscopic system: transferring and pattern cutting. Computer vision libraries were used to obtain the number of transferred points and simulated pattern cutting trace by means of tracking of the laparoscopic instrument. An artificial neural network (ANN) was trained to learn from experts and nonexperts' behavior for pattern cutting task, whereas the assessment of transferring task was performed using a preestablished threshold. Four expert surgeons in laparoscopic surgery, from hospital "Raymundo Abarca Alarcón," constituted the experienced class for the ANN. Sixteen trainees (10 medical students and 6 residents) without laparoscopic surgical skills and limited experience in minimal invasive techniques from School of Medicine at Universidad Autónoma de Guerrero constituted the nonexperienced class. Data from participants performing 5 daily repetitions for each task during 5 days were used to build the ANN. RESULTS: The participants tend to improve their learning curve and dexterity with this laparoscopic training system. The classifier shows mean accuracy and receiver operating characteristic curve of 90.98% and 0.93, respectively. Moreover, the ANN was able to evaluate the psychomotor skills of users into 2 classes: experienced or nonexperienced. CONCLUSION: We constructed and evaluated an affordable laparoscopic trainer system using computer vision, augmented reality, and an artificial intelligence algorithm. The proposed trainer has the potential to increase the self-confidence of trainees and to be applied to programs with limited resources.

Construct validity of a video-tracking system based on orthogonal cameras approach for objective assessment of laparoscopic skills.

PURPOSE: This study was aimed to establish the construct validity of a video-tracking system based on orthogonal cameras approach for assessment of laparoscopic psychomotor skills in training environments. METHODS: The camera-tracking system consists of two webcams placed in orthogonal configuration at a distance of 13.5 cm. The orthogonal cameras employ a color segmentation algorithm to register the 3D motions of the laparoscopic instruments using colored tapes placed on the distal end. For construct validity, 31 participants (4 experts and 27 residents) performed three training tasks in a laparoscopic box trainer with the built-in orthogonal cameras system. Eleven motion-related parameters were used to evaluate their performance. Statistical analysis was performed, and results between two groups were compared using a Mann-Whitney U-test. RESULTS: Construct validity results showed statistical differences in almost all motion-related parameters for assessment of laparoscopic technical skills. Results demonstrated that the orthogonal video-based tracking system was able to differentiate laparoscopic experience between experts and trainees surgeons. CONCLUSION: The orthogonal cameras system was successfully validated in a laparoscopic box trainer. This video-based tracking system was able to distinguish performance between experts and trainees surgeons, showing its potential as a reliable tool to assess laparoscopic psychomotor skills. The orthogonal cameras allow incorporating the advantages of this video motion-tracking technology with the benefits of the traditional laparoscopic box trainers, creating realistic haptic feedback and allowing the evaluation of psychomotor skills of the surgeons.