Early-stage clinical evaluation of real-time artificial intelligence assistance for laparoscopic cholecystectomy.

The growing availability of surgical digital data and developments in analytics such as artificial intelligence (AI) are being harnessed to improve surgical care. However, technical and cultural barriers to real-time intraoperative AI assistance exist. This early-stage clinical evaluation shows the technical feasibility of concurrently deploying several AIs in operating rooms for real-time assistance during procedures. In addition, potentially relevant clinical applications of these AI models are explored with a multidisciplinary cohort of key stakeholders.

Characterisation and mitigation of gas leaks at laparoscopy: an international prospective, multi-center cohort clinical trial.

INTRODUCTION: Gas leaks polluting the operating room are common in laparoscopy. Studies defining methods for sensitive leak characterisation and mechanical mitigation in real world settings are, however, lacking. METHODS: Mobile optical gas imagers (both a miniaturised Schlieren system and sensitive tripod-mounted near-infrared carbon dioxide camera (GF343, FLIR)) prospectively defined trocar-related gas leaks occurring either spontaneously or with instrumentation during planned laparoscopic surgery at three hospitals. A boutique Matlab-based analyser using sequential frame subtraction categorised leaks (class 0-no observable leak; class 1-marginally detectable leak; class 2-short-lived plume; class 3-energetic, turbulent jet). Concurrently, the usefulness of a novel vacuum-ring device (LeakTrap™, Palliare, Ireland) designed as a universal adjunct for existing standard laparoscopic ports at both abdominal wall and port valve level was determined similarly in a phase I/11 clinical trial along with the device's useability through procedural observation and surgeon questionnaire. RESULTS: With ethical and regulatory approval, 40 typical patients (mean age 58.6 years, 20 males) undergoing planned laparoscopic cholecystectomy (n = 36) and hernia repair (n = 4) were studied comprising both control (n = 20) and intervention (n = 20) cohorts. Dual optical gas imaging was successfully performed across all procedures with minimal impact on procedural flow. In total, 1643 trocar instrumentations were examined, 819 in the control group (mean 41 trocar instrumentations/procedure) and 824 in the intervention group (mean 41.2 trocar instrumentations/procedure). Gas leaks were detected during 948(62.6%) visualised trocar instrumentations (in 129-7.8%-the imaging was obscured). 14.8% (110/742) and 60% (445/742) of leaks in control patients were class 0 and 3, respectively, versus 59.1% (456/770) and 8.7% (67/772) in the interventional group (class 3 v non-class 3, p < 0.0001, χ2). The Leaktrap proved surgically acceptable without significant workflow disruption. CONCLUSION: Laparoscopic gas leaks can be sensitively detected and consistently, effectively mitigated using straightforward available-now technology with most impact on the commonest, highest energy instrument exchange leaks.

Stepwise training program: A novel practice schedule for laparoscopic suturing.

Purpose: We establish stepwise training program in which laparoscopic suturing is broken down to discrete steps. The purpose is to evaluate the learning outcomes of stepwise training program. Materials and methods: Volunteer participants were enrolled from medical students and surgical trainees. Students took two courses of 2-h stepwise training, and a post-course (1st & 2nd) test was taken after each course; trainees took one course of stepwise training with a pre-course (1st) and a post-course (2nd) test. Attending surgeons took the test as control. Learning outcomes were assessed with laparoscopic suturing competency assessment tool (LS-CAT) and suturing time. Results: There were 10 students, 8 trainees and 6 surgeon controls. Suturing time and LS-CAT scores significantly improved between the 1st and 2nd test (p < 0.01). In the both tests, suturing time and LS-CAT scores of students and trainees were similar. In the 1st test, surgeons had significantly better performance in suturing time and LS-CAT score than students and trainees; in the 2nd test, the LS-CAT scores of students and trainees were similar to the surgeon controls. Conclusions: Stepwise program effectively enhances laparoscopic suturing skill for medical students and surgical trainees. Catch-up effect was demonstrated in medical students with stepwise training.

Educational Scoring System in Laparoscopic Cholecystectomy: Is It the Right Time to Standardize?

Background and Objectives: Laparoscopic cholecystectomy (LC) is one of the most performed surgeries worldwide. Procedure difficulty and patient outcomes depend on several factors which are not considered in the current literature, including the learning curve, generating confusing and subjective results. This study aims to create a scoring system to calculate the learning curve of LC based on hepatobiliopancreatic (HPB) experts' opinions during an educational course. Materials and Methods: A questionnaire was submitted to the panel of experts attending the HPB course at Research Institute against Digestive Cancer-IRCAD (Strasbourg, France) from 27-29 October 2022. Experts scored the proposed variables according to their degree of importance in the learning curve using a Likert scale from 1 (not useful) to 5 (very useful). Variables were included in the composite scoring system only if more than 75% of experts ranked its relevance in the learning curve assessment ≥4. A positive or negative value was assigned to each variable based on its effect on the learning curve. Results: Fifteen experts from six different countries attended the IRCAD HPB course and filled out the questionnaire. Ten variables were finally included in the learning curve scoring system (i.e., patient body weight/BMI, patient previous open surgery, emergency setting, increased inflammatory levels, presence of anatomical bile duct variation(s), and appropriate critical view of safety (CVS) identification), which were all assigned positive values. Minor or major intraoperative injuries to the biliary tract, development of postoperative complications related to biliary injuries, and mortality were assigned negative values. Conclusions: This is the first scoring system on the learning curve of LC based on variables selected through the experts' opinions. Although the score needs to be validated through future studies, it could be a useful tool to assess its efficacy within educational programs and surgical courses.

Towards automatic verification of the critical view of the myopectineal orifice with artificial intelligence.

BACKGROUND: Visualization of key anatomical landmarks is required during surgical Trans Abdominal Pre Peritoneal repair (TAPP) of inguinal hernia. The Critical View of the MyoPectineal Orifice (CVMPO) was proposed to ensure correct dissection. An artificial intelligence (AI) system that automatically validates the presence of key and marks during the procedure is a critical step towards automatic dissection quality assessment and video-based competency evaluation. The aim of this study was to develop an AI system that automatically recognizes the TAPP key CVMPO landmarks in hernia repair videos. METHODS: Surgical videos of 160 TAPP procedures were used in this single-center study. A deep neural network-based object detector was developed to automatically recognize the pubic symphysis, direct hernia orifice, Cooper's ligament, the iliac vein, triangle of Doom, deep inguinal ring, and iliopsoas muscle. The system was trained using 130 videos, annotated and verified by two board-certified surgeons. Performance was evaluated in 30 videos of new patients excluded from the training data. RESULTS: Performance was validated in 2 ways: first, single-image validation where the AI model detected landmarks in a single laparoscopic image (mean average precision (MAP) of 51.2%). The second validation is video evaluation where the model detected landmarks throughout the myopectineal orifice visual inspection phase (mean accuracy and F-score of 77.1 and 75.4% respectively). Annotation objectivity was assessed between 2 surgeons in video evaluation, showing a high agreement of 88.3%. CONCLUSION: This study establishes the first AI-based automated recognition of critical structures in TAPP surgical videos, and a major step towards automatic CVMPO validation with AI. Strong performance was achieved in the video evaluation. The high inter-rater agreement confirms annotation quality and task objectivity.

International survey among surgeons on the perioperative management of rectal cancer.

BACKGROUND: Several pivotal studies and international guidelines on the perioperative management of rectal cancer have been published. However, little is known about the current state of perioperative management of rectal cancer patients in clinical practice worldwide. METHODS: An online survey including 13 questions focusing on key topics related to the perioperative management of patients with rectal cancer was conducted among colorectal surgeons registered within the database of the Research Institute Against Digestive Cancer (IRCAD). RESULTS: A total of 535 respondents from 89 countries participated in the survey. Most surgeons worked in the European region (40.9%). Two hundred and fifty-four respondents (47.5%) performed less than 25% of surgical procedures laparoscopically. The most commonly used definition of the upper limit of the rectum was a fixed distance from the anal verge (23.4%). Magnetic resonance imaging was used to define the upper limit of the rectum by 258 respondents (48.2%). During total mesorectal excision (TME), 301 respondents (56.3%) used a high-tie technique. The most commonly constructed anastomosis was an end-to-end anastomosis (68.2%) with the majority of surgeons performing a leak test intraoperatively (88.9%). A total of 355 respondents (66.4%) constructed a diverting ostomy, and the majority of these surgeons constructed an enterostomy (82%). A total of 208 respondents (39.3%) closed a stoma within 8 weeks. Lastly, 135 respondents (25.2%) introduced a solid diet on postoperative day 1. CONCLUSION: There is considerable heterogeneity in the perioperative management of rectal cancer patients worldwide with several discrepancies between current international practice and recommendations from international guidelines. To achieve worldwide standardization in rectal cancer care, further research is needed to elucidate the cause of this heterogeneity and find ways of improved implementation of best practice recommendations.

Democratizing Flexible Endoscopy Training: Noninferiority Randomized Trial Comparing a Box-Trainer vs a Virtual Reality Simulator to Prepare for the Fundamental of Endoscopic Surgery Exam.

BACKGROUND: A considerable number of surgical residents fail the mandated endoscopy exam despite having completed the required clinical cases. Low-cost endoscopy box trainers (BTs) could democratize training; however, their effectiveness has never been compared with higher-cost virtual reality simulators (VRSs). STUDY DESIGN: In this randomized noninferiority trial, endoscopy novices trained either on the VRS used in the Fundamental of Endoscopic Surgery manual skills (FESms) exam or a validated BT-the Basic Endoscopic Skills Training (BEST) box. Trainees were tested at fixed timepoints on the FESms and on standardized ex vivo models. The primary endpoint was FESms improvement at 1 week. Secondary endpoints were FESms improvement at 2 weeks, FESms pass rates, ex vivo tests performance, and trainees' feedback. RESULTS: Seventy-seven trainees completed the study. VRS and BT trainees showed comparable FESms improvements (25.16 ± 14.29 vs 25.58 ± 11.75 FESms points, respectively; p = 0.89), FESms pass rates (76.32% vs 61.54%, respectively; p = 0.16) and total ex vivo tasks completion times (365.76 ± 237.56 vs 322.68 ± 186.04 seconds, respectively; p = 0.55) after 1 week. Performances were comparable also after 2 weeks of training, but FESms pass rates increased significantly only in the first week. Trainees were significantly more satisfied with the BT platform (3.97 ± 1.20 vs 4.81 ± 0.40 points on a 5-point Likert scale for the VRS and the BT, respectively; p < 0.001). CONCLUSIONS: Simulation-based training is an effective means to develop competency in endoscopy, especially at the beginning of the learning curve. Low-cost BTs like the BEST box compare well with high-tech VRSs and could help democratize endoscopy training.

Multicentric validation of EndoDigest: a computer vision platform for video documentation of the critical view of safety in laparoscopic cholecystectomy.

BACKGROUND: A computer vision (CV) platform named EndoDigest was recently developed to facilitate the use of surgical videos. Specifically, EndoDigest automatically provides short video clips to effectively document the critical view of safety (CVS) in laparoscopic cholecystectomy (LC). The aim of the present study is to validate EndoDigest on a multicentric dataset of LC videos. METHODS: LC videos from 4 centers were manually annotated with the time of the cystic duct division and an assessment of CVS criteria. Incomplete recordings, bailout procedures and procedures with an intraoperative cholangiogram were excluded. EndoDigest leveraged predictions of deep learning models for workflow analysis in a rule-based inference system designed to estimate the time of the cystic duct division. Performance was assessed by computing the error in estimating the manually annotated time of the cystic duct division. To provide concise video documentation of CVS, EndoDigest extracted video clips showing the 2 min preceding and the 30 s following the predicted cystic duct division. The relevance of the documentation was evaluated by assessing CVS in automatically extracted 2.5-min-long video clips. RESULTS: 144 of the 174 LC videos from 4 centers were analyzed. EndoDigest located the time of the cystic duct division with a mean error of 124.0 ± 270.6 s despite the use of fluorescent cholangiography in 27 procedures and great variations in surgical workflows across centers. The surgical evaluation found that 108 (75.0%) of the automatically extracted short video clips documented CVS effectively. CONCLUSIONS: EndoDigest was robust enough to reliably locate the time of the cystic duct division and efficiently video document CVS despite the highly variable workflows. Training specifically on data from each center could improve results; however, this multicentric validation shows the potential for clinical translation of this surgical data science tool to efficiently document surgical safety.

International survey among surgeons on laparoscopic right hemicolectomy: the gap between guidelines and reality.

INTRODUCTION: To assess the current approaches and perioperative treatments of laparoscopic right hemicolectomy (LRHC) and to highlight similarities and differences with international guidelines and scientific evidence, we conducted a survey for surgeons across the globe. METHODS: All digestive and colorectal surgeons registered with the database of the Research Institute against Digestive Cancer (IRCAD) were invited to take part in the survey via email and through the social media networks of IRCAD. RESULTS: There were a total of 440 respondents from 78 countries. Most surgeons worked in the European region (38.6%) followed by the Americas (34.1%), the Eastern Mediterranean region (13.0%), the South-East Asian region (5.9%), the Western Pacific region (4.8%), and Africa (3.2%) respectively. Over half of the respondents performed less than 25% of right hemicolectomies laparoscopically where 4 ports are usually used by 68% of the surgeons. The medial-to-lateral, vessel-first approach is the approach most commonly used (74.1%). The most common extraction site was through a midline incision (53%) and an abdominal drain tube is routinely used by 52% of the surgeons after surgery. A total of 68.6% of the responding surgeons perform the majority of the anastomoses extracorporeally. Finally, we found that the majority of responders (60.7%) routinely used mechanical bowel preparations prior to LRHC. CONCLUSION: Regarding several topics related to LRHC care, a discrepancy was observed between the current medical practice and the recommendations from RCTs and international guidelines and significant regional differences were observed.

Artificial Intelligence for Surgical Safety: Automatic Assessment of the Critical View of Safety in Laparoscopic Cholecystectomy Using Deep Learning.

OBJECTIVE: To develop a deep learning model to automatically segment hepatocystic anatomy and assess the criteria defining the critical view of safety (CVS) in laparoscopic cholecystectomy (LC). BACKGROUND: Poor implementation and subjective interpretation of CVS contributes to the stable rates of bile duct injuries in LC. As CVS is assessed visually, this task can be automated by using computer vision, an area of artificial intelligence aimed at interpreting images. METHODS: Still images from LC videos were annotated with CVS criteria and hepatocystic anatomy segmentation. A deep neural network comprising a segmentation model to highlight hepatocystic anatomy and a classification model to predict CVS criteria achievement was trained and tested using 5-fold cross validation. Intersection over union, average precision, and balanced accuracy were computed to evaluate the model performance versus the annotated ground truth. RESULTS: A total of 2854 images from 201 LC videos were annotated and 402 images were further segmented. Mean intersection over union for segmentation was 66.6%. The model assessed the achievement of CVS criteria with a mean average precision and balanced accuracy of 71.9% and 71.4%, respectively. CONCLUSIONS: Deep learning algorithms can be trained to reliably segment hepatocystic anatomy and assess CVS criteria in still laparoscopic images. Surgical-technical partnerships should be encouraged to develop and evaluate deep learning models to improve surgical safety.

Technical Performance of Continuous Pressure Insufflators Versus Traditional Insufflators in the Presence of Leaks During Laparoscopic Surgery.

Background. New insufflators have been developed to manage leaks emanating from the working cavity during laparoscopic surgery. Little data have been published to show the performance of these insufflators. This study evaluates the performance of 2 modern continuous pressure insufflators in various leak conditions. Methods. Performance of a new continuous pressure insufflator, EVA15 (Palliare, Galway, Ireland), was compared with that of a continuous pressure insufflator, Airseal intelligent Flow System (iFS) (CONMED, Utica, NY), and a traditional intermittent pressure insufflator, Endoflator 40 (KARL STORZ, Tuttlingen, Germany). Six different leak scenarios were created in a swine model to create different dynamic leak profiles of between 5 and 15 L/min. Pressure deviation from setting was measured for each insufflator tested. The following were calculated: (a) mean absolute difference of measured insufflation pressure vs. the insufflator pressure setting for the 50 second measurement period (MAD) and (b) standard deviation of the absolute differences (SD). Results. The average mean absolute pressure difference between the EVA15 and Airseal is .27 mmHg. However, the average mean absolute pressure difference between the EVA15 and Endoflator 40 is 2.62 mmHg. Conclusions. Continuous pressure insufflators provide superior pressure delivery performance in leak situations when compared against a traditional intermittent pressure insufflator. No clinically significant performance difference was observed when comparing the EVA15 and Airseal iFS insufflators in the tested leak situations.

Robotic endoscopic cooperative surgery for colorectal tumors: a feasibility study (with video).

BACKGROUND: Laparoscopic endoscopic cooperative colorectal surgery (LECS-CR) is a promising technique to achieve full-thickness resection of colorectal tumors. This approach has shown good rates of complete resection and low local recurrence, especially for large laterally spreading tumors, which are difficult to remove via endoscopy alone. However, it is often difficult to prevent peritoneal leakage of intestinal content, causing infections and risks of cancer spreading. It was hypothesized that a robotic assistance could make the procedure easier and decrease intestinal fluid leakage. This preclinical trial aims to assess the feasibility of robotic and endoscopic cooperative colorectal surgery (RECS-CR). METHODS: LECS-CR was performed in five female pigs and RECS-CR was also performed in five female pigs. With the animal under general anesthesia, pseudotumors were created on the colonic mucosa at a distance comprised between 20 and 25 cm from the anal verge. Desired resection margins were marked endoscopically and two stay sutures were placed either robotically or laparoscopically. A mucosa-to-submucosa dissection was performed endoscopically along the markings. Complete full-thickness dissection was performed cooperatively. The specimen was withdrawn endoscopically. The colon was closed using a self-fixating running suture. Abdominal contaminations, operating times, complications, and complete resections were evaluated and compared between LECS-CR and RECS-CR. RESULTS: The mean number of colonies of Escherichia coli in the RECS group was significantly lower than in the LECS group (36.7 ± 30.2 vs. 142.2 ± 78.4, respectively, p < 0.05). Operating time was comparable (118 ± 11.2 vs. 98.6 ± 25.7, respectively, p = 0.22). Two stenoses occurred in the LECS group. R0 resection was achieved in all cases. CONCLUSION: This study suggests that RECS-CR is feasible and has the potential to reduce intestinal content leakage, potentially preventing postoperative infections.

Impact of surgical repair on type IV paraesophageal hernias (PEHs).

BACKGROUND: Paraesophageal hernias (PEHs; types II-III-IV) account for about 5% of all hiatal hernias (HHs). The peculiarity of PEHs is the presence of a herniated sac which contains a more or less important part of the stomach, along with other abdominal organs in type IV PEHs. Surgical treatment is more complex since it requires a reduction not only of the herniated content but also of the "container," namely the sac adherent to mediastinal structures. Since type III and IV PEHs are mostly grouped together as large PEHs, there is a lack of articles in the literature with regards to clear surgical outcomes, as well as management algorithms in type IV PEHs. This study aims to compare outcomes in type IV vs. type III PEHs after surgical repair. METHODS: A retrospective study of patients who underwent laparoscopic PEH hernia repair (LPEHR) was conducted in a single institution between 2006 and 2020. Patient baseline characteristics and surgical outcomes were analyzed. RESULTS: A total of 103 patients were included in the analysis. Patients presenting with type IV PEHs (12/103) were significantly older than patients with type III PEHs (91/104) (75.25 ± 7.15 vs. 66.91 ± 13.58 respectively (p = 0.039), and more fragile with a higher Charlson Comorbidity Index (CCI) (4.25 ± 1.48 vs. 2.96 ± 1.72, p = 0.016). Operative time was significantly longer (243 ± 101.73 vs. 133.38 ± 61.76, p = 0.002), and postoperative morbidity was significantly higher in type IV PEH repair (50% vs. 8.8% type III, p = 0.000). CONCLUSION: Patients with type IV PEHs appear to be older and frailer. The higher incidence of postoperative complications in patients with type IV PEHs should advocate for a precise indication for surgical treatment, which should be performed in centers of expertise.

Statistical models to preoperatively predict operative difficulty in laparoscopic cholecystectomy: A systematic review.

BACKGROUND: Laparoscopic cholecystectomy operative difficulty is highly variable and influences outcomes. This systematic review analyzes the performance and clinical value of statistical models to preoperatively predict laparoscopic cholecystectomy operative difficulty. METHODS: PRISMA guidelines were followed. PubMed, Embase, and the Cochrane Library were searched until June 2020. Primary studies developing or validating preoperative models predicting laparoscopic cholecystectomy operative difficulty in cohorts of >100 patients were included. Studies not reporting performance metrics or enough information for clinical implementation were excluded. Data were extracted according to CHARMS, and study quality was assessed using the PROBAST tool. RESULTS: In total, 2,654 articles were identified, and 22 met eligibility criteria. Eighteen were model development, whereas 4 were validation studies. Eighteen studies were at high risk of bias. However, 11 studies showed low concern for applicability. Identified models predict 9 definitions of laparoscopic cholecystectomy operative difficulty, the most common being conversion to open surgery and operating time. The most validated models predict an intraoperative difficulty scale and procedures >90 minutes with an area under the curve of >0.70 and >0.76, respectively. Commonly used predictors include demographic variables such as age and gender (9/18 models) and ultrasound findings such as gallbladder wall thickness (11/18). Clinical implementation was never studied. CONCLUSION: There is a longstanding interest in estimating laparoscopic cholecystectomy operative difficulty. Models to preoperatively predict laparoscopic cholecystectomy operative difficulty have generally good performance and seem applicable. However, an unambiguous definition of operative difficulty, validations, and clinical studies are needed to implement patients' stratification in laparoscopic cholecystectomy.

Intraoperative Time-Out to Promote the Implementation of the Critical View of Safety in Laparoscopic Cholecystectomy: A Video-Based Assessment of 343 Procedures.

BACKGROUND: The critical view of safety (CVS) is poorly adopted in surgical practices, although it is recommended ubiquitously to prevent major bile duct injuries during laparoscopic cholecystectomy (LC). This study aimed to investigate whether performing a short intraoperative time-out can improve CVS implementation. STUDY DESIGN: In this before vs after study, surgeons performing LCs at an academic center were invited to use a 5-second long time-out to verify CVS before dividing the cystic duct (5-second rule). The primary aim was to compare the rate of CVS achievement for LC performed in the year before vs the year after implementation of the 5-second rule. The CVS achievement rate was computed after exclusion of bailout procedures using a mediated video-based assessment made by 2 independent reviewers. Clinical outcomes, LC workflows, and postoperative reports were also compared. RESULTS: Three hundred and forty-three of 381 LC performed between December 2017 and November 2019 (171 before and 172 after implementation of the 5-second rule) were analyzed. The 5-second rule was associated with a significantly increased rate of CVS achievement (15.9% vs 44.1% before vs after the 5-second rule, respectively; p < 0.001). Significant differences were also observed with respect to the rate of bailout procedures (8.2% vs 15.7%; p = 0.04), median time (hours:minutes:seconds) to clip the cystic duct or artery (00:17:26; interquartile range 00:11:48 to 00:28:35 vs 00:23:12; interquartile range 00:14:29 to 00:31:45 duration; p = 0.007), and the rate of postoperative CVS reporting (1.3% vs 28.8%; p < 0.001). Postoperative morbidity was comparable (1.8% vs 2.3%; p = 0.68). CONCLUSIONS: Performing a short intraoperative time-out was associated with an improved CVS achievement rate. Systematic intraoperative cognitive aids should be studied to sustain the uptake of guidelines.

A Computer Vision Platform to Automatically Locate Critical Events in Surgical Videos: Documenting Safety in Laparoscopic Cholecystectomy.

OBJECTIVE: The aim of this study was to develop a computer vision platform to automatically locate critical events in surgical videos and provide short video clips documenting the critical view of safety (CVS) in laparoscopic cholecystectomy (LC). BACKGROUND: Intraoperative events are typically documented through operator-dictated reports that do not always translate the operative reality. Surgical videos provide complete information on surgical procedures, but the burden associated with storing and manually analyzing full-length videos has so far limited their effective use. METHODS: A computer vision platform named EndoDigest was developed and used to analyze LC videos. The mean absolute error (MAE) of the platform in automatically locating the manually annotated time of the cystic duct division in full-length videos was assessed. The relevance of the automatically extracted short video clips was evaluated by calculating the percentage of video clips in which the CVS was assessable by surgeons. RESULTS: A total of 155 LC videos were analyzed: 55 of these videos were used to develop EndoDigest, whereas the remaining 100 were used to test it. The time of the cystic duct division was automatically located with a MAE of 62.8 ±â€Š130.4 seconds (1.95% of full-length video duration). CVS was assessable in 91% of the 2.5 minutes long video clips automatically extracted from the considered test procedures. CONCLUSIONS: Deep learning models for workflow analysis can be used to reliably locate critical events in surgical videos and document CVS in LC. Further studies are needed to assess the clinical impact of surgical data science solutions for safer laparoscopic cholecystectomy.

Image-Guided Surgical Training in Percutaneous Hepatobiliary Procedures: Development of a Realistic and Meaningful Bile Duct Dilatation Porcine Model.

Background: Malignant or benign biliary obstructions can be successfully managed with minimally invasive percutaneous interventions. Since percutaneous approaches are challenging, extensive training using relevant models is fundamental to improve the proficiency of percutaneous physicians. The aim of this experimental study was to develop an in vivo training model in pigs to simulate bile duct dilatation to be used during percutaneous biliary interventions. Materials and Methods: Twenty-eight large white pigs were involved and procedures were performed in an experimental hybrid operating room. Under general anesthesia, animals underwent a preoperative magnetic resonance cholangiography (MRC). Afterward, the common bile duct was isolated and ligated laparoscopically. A postoperative MRC was performed 72 hours after the procedure to evaluate bile duct dilatation. The In vivo models presenting an effective dilatation model were included in the hands-on part of a percutaneous surgery training course. Animals were euthanized at the end of the training session. Results: Postoperative MRC confirmed the presence of bile duct dilatation in the survival pigs (n = 25). No intraoperative complications occurred and mean operative time was 15.8 ± 5.27 minutes. During the course, 27 trainees could effectively perform percutaneous transhepatic cholangiography, bile duct drainage, biliary duct dilatation, and stent placement, with a > 90% success rate, thereby validating the experimental model. All animals survived during the training procedures and complications occurred in 28.3% of cases. Conclusion: The creation of an in vivo bile duct dilatation animal model is feasible with a low short-term mortality. It provides a realistic and meaningful training model in percutaneous biliary procedures.