ABSTRACT
BACKGROUND: Many surgical adverse events, such as bile duct injuries during laparoscopic cholecystectomy (LC), occur due to errors in visual perception and judgment. Artificial intelligence (AI) can potentially improve the quality and safety of surgery, such as through real-time intraoperative decision support. GoNoGoNet is a novel AI model capable of identifying safe ("Go") and dangerous ("No-Go") zones of dissection on surgical videos of LC. Yet, it is unknown how GoNoGoNet performs in comparison to expert surgeons. This study aims to evaluate the GoNoGoNet's ability to identify Go and No-Go zones compared to an external panel of expert surgeons. METHODS: A panel of high-volume surgeons from the SAGES Safe Cholecystectomy Task Force was recruited to draw free-hand annotations on frames of prospectively collected videos of LC to identify the Go and No-Go zones. Expert consensus on the location of Go and No-Go zones was established using Visual Concordance Test pixel agreement. Identification of Go and No-Go zones by GoNoGoNet was compared to expert-derived consensus using mean F1 Dice Score, and pixel accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV). RESULTS: A total of 47 frames from 25 LC videos, procured from 3 countries and 9 surgeons, were annotated simultaneously by an expert panel of 6 surgeons and GoNoGoNet. Mean (± standard deviation) F1 Dice score were 0.58 (0.22) and 0.80 (0.12) for Go and No-Go zones, respectively. Mean (± standard deviation) accuracy, sensitivity, specificity, PPV and NPV for the Go zones were 0.92 (0.05), 0.52 (0.24), 0.97 (0.03), 0.70 (0.21), and 0.94 (0.04) respectively. For No-Go zones, these metrics were 0.92 (0.05), 0.80 (0.17), 0.95 (0.04), 0.84 (0.13) and 0.95 (0.05), respectively. CONCLUSIONS: AI can be used to identify safe and dangerous zones of dissection within the surgical field, with high specificity/PPV for Go zones and high sensitivity/NPV for No-Go zones. Overall, model prediction was better for No-Go zones compared to Go zones. This technology may eventually be used to provide real-time guidance and minimize the risk of adverse events.
Subject(s)
Cholecystectomy, Laparoscopic , Surgeons , Humans , Cholecystectomy, Laparoscopic/adverse effects , Artificial Intelligence , Data Collection , CholecystectomyABSTRACT
Background: Benign biliary strictures (BBS) befall in â¼7%-23% after hepaticojejunostomy and in 0.3%-0.6% after cholecystectomies. Their treatment options include surgical, endoscopic, and percutaneous management. The percutaneous approach is an excellent mini-invasive option including balloon dilation, biodegradable stents, and sustained dilation, a procedure born endoscopically. However, when the endoscopic approach fails or it is not available, it is possible to perform it percutaneously. Aim: To estimate the technical and clinical success of sustained percutaneous dilation with multiple catheters (SPDMC) in hepaticojejunostomy strictures and the percentage of complications and recurrence. Materials and Methods: We conducted a retrospective study, from a prospective database from January 2010 to March 2019, of 17 patients with postoperative BBS who failed to percutaneous pneumatic balloon dilation and underwent SPDMC with a mean follow-up of 2 years. Results: Seventeen patients between 28 and 71 years of age underwent SPMDC with technical success of 100%; the average number of catheters used was 5.59 (95% confidence interval [CI] 5.12-6.06) achieving a dilatation diameter of 16.15 mm (95% CI 14.71-17.60), and the therapeutic success rate was 71%, with recurrences of stricture and complications of 29% and 18%, respectively. The mean time with SPMDC was 7.06 months (95% CI 5.56-8.56). The median follow-up after dilation was 16 months, with an average of 27.75 months (95% CI 14.15-41.34). Conclusion: SPMDC is a feasible technique with a high technical success rate, therapeutic success rate, and low morbidity and mortality.