Search

Introduction: While laparoscopic splenectomy (LS) has been widely used in benign splenic tumor, more concerns have been raised for postoperatively short-term and long-term complications. Laparoscopic partial splenectomy (LPS) is a surgical option, to preserve splenic function, and reduce postoperative complications. The aim of our study was to retrospectively identify the safety and feasibility of LPS compared with LS in patients with splenic benign tumor. Materials and methods: From 2014 to 2024, a total of 165 patients diagnosed with occupational splenic lesions underwent splenectomy, of whom 87 underwent LPS and 78 underwent LS. We compare the perioperative parameters and long term follow up between these two groups. Results: The etiology of splenic space-occupying lesions was nonparasitic splenic cysts, followed by splenic lymphangioma and splenic hemangioma. Of the patients with LPS, 55 underwent conventional surgery with blockage of the splenic arterial branch and resection along the ischemic line (RAIL), and 32 underwent with our modified total splenic blood supply blockade followed by resection alone the tumor edge (RATE). The tumor size, the operative time and estimated blood loss were comparable between the LPS and LS groups. One patient developed abnormal signs during the LPS procedure and was promptly referred for LS. The LPS group had fewer pancreatic leakage, incision infection, and pulmonary infection. As for different vascular types, patients with LS under all branches of the splenic artery had a longer time to resume postoperative feeding. As for the comparison of RAIL and RATE, estimated blood and operative time were significantly reduced in patients receiving RATE. Postoperative complications were the same in patients underwent each surgical procedures. Conclusion: LPS is a viable approach for patients with splenic benign tumor. We introduce the tumor artery supply types to indicate the resection region. Our RATE technique has proven to be clinically effective and safety.

Background: Laparoscopic pancreatoduodenectomy (LPD) is one of the most challenging operations and has a long learning curve. Artificial intelligence (AI) automated surgical phase recognition in intraoperative videos has many potential applications in surgical education, helping shorten the learning curve, but no study has made this breakthrough in LPD. Herein, we aimed to build AI models to recognize the surgical phase in LPD and explore the performance characteristics of AI models. Methods: Among 69 LPD videos from a single surgical team, we used 42 in the building group to establish the models and used the remaining 27 videos in the analysis group to assess the models’ performance characteristics. We annotated 13 surgical phases of LPD, including 4 key phases and 9 necessary phases. Two minimal invasive pancreatic surgeons annotated all the videos. We built two AI models for the key phase and necessary phase recognition, based on convolutional neural networks. The overall performance of the AI models was determined mainly by mean average precision (mAP). Results: Overall mAPs of the AI models in the test set of the building group were 89.7% and 84.7% for key phases and necessary phases, respectively. In the 27-video analysis group, overall mAPs were 86.8% and 71.2%, with maximum mAPs of 98.1% and 93.9%. We found commonalities between the error of model recognition and the differences of surgeon annotation, and the AI model exhibited bad performance in cases with anatomic variation or lesion involvement with adjacent organs. Conclusions: AI automated surgical phase recognition can be achieved in LPD, with outstanding performance in selective cases. This breakthrough may be the first step toward AI- and video-based surgical education in more complex surgeries.