Search

Background Surgical process modeling automatically identifies surgical phases, and further improvement in recognition accuracy is expected with deep learning. Surgical tool or time series information has been used to improve the recognition accuracy of a model. However, it is difficult to collect this information continuously intraoperatively. The present study aimed to develop a deep convolution neural network (CNN) model that correctly identifies the surgical phase during laparoscopic cholecystectomy (LC). Methods We divided LC into six surgical phases (P1–P6) and one redundant phase (P0). We prepared 115 LC videos and converted them to image frames at 3 fps. Three experienced doctors labeled the surgical phases in all image frames. Our deep CNN model was trained with 106 of the 115 annotation datasets and was evaluated with the remaining datasets. By depending on both the prediction probability and frequency for a certain period, we aimed for highly accurate surgical phase recognition in the operation room. Results Nine full LC videos were converted into image frames and were fed to our deep CNN model. The average accuracy, precision, and recall were 0.970, 0.855, and 0.863, respectively. Conclusion The deep learning CNN model in this study successfully identified both the six surgical phases and the redundant phase, P0, which may increase the versatility of the surgical process recognition model for clinical use. We believe that this model can be used in artificial intelligence for medical devices. The degree of recognition accuracy is expected to improve with developments in advanced deep learning algorithms.

Laparoscopic liver resection (LLR) is possible in many patients, but pure LLR is sometimes difficult to complete, and unplanned intraoperative hand-assisted laparoscopic surgery (HALS) or open conversion is sometimes necessary. However, appropriate indications and timing for conversion are unclear. This study aimed to clarify the indications for HALS and open conversion from pure LLR.We collected data from 208 patients who underwent LLR from January 2010 to February 2021 in our department. We retrospectively examined these data between cases of unplanned intraoperative HALS conversion, open conversion, and pure LLR, and clarified risk factors and indications for HALS or open conversion.There were 191 pure LLRs, nine HALS conversions, and eight open conversions. In the HALS conversion group versus pure LLR group, body mass index (BMI) (27.0 vs. 23.7 kg/mRisk factors for considering HALS during LLR were patients with a history of upper abdominal surgery including repeat hepatectomy, BMI ≥ 25 kg/m

Background: Laparoscopic sleeve gastrectomy (LSG) is a standard procedure due to its low complication rates and favorable outcomes. However, limited data are available regarding the optimal size of linear staplers in relation to gastric wall thickness (GWT)., Methods: Between August 2016 and December 2020, we performed LSG in 70 patients with an average age, body weight, and body mass index of 42 years, 107 kg, and 40 kg/m2, respectively. We measured the GWT at the antrum, body, and fundus using resected specimens. We used an endo-linear stapler, and the closed staple height (CSH) was 1.75 mm., Results: We found that the average GWT at the antrum was significantly thicker than the GWT at the body and fundus. There was a statistically significant relationship between body weight and the GWT at the antrum and body and obstructive sleep apnea and the GWT at the body. The average CSH/GWT ratios were 0.55, 0.62, and 0.90 at the antrum, body, and fundus, respectively. However, in 20 patients (29%), the CSH/GWT ratio at the fundus area was 〓1.0, and only preoperative body weight was a significant predictor for a CSH/GWT ratio of 〓1.0., Conclusion: A light body weight may be related to a CSH/GWT ratio of 〓1.0 at the fundus., Key Points: GWT at the antrum was significantly thicker than that at the body and fundus. GWT at the antrum and body statistically correlated with body weight. Preoperative body weight was a predictor for CSH/GWT ratio of 〓1.0 at the fundus

We have implemented Smart Endoscopic Surgery (SES), a surgical system that uses artificial intelligence (AI) to detect the anatomical landmarks that expert surgeons base on to perform certain surgical maneuvers. No report has verified the use of AI-based support systems for surgery in clinical practice, and no evaluation method has been established. To evaluate the detection performance of SES, we have developed and established a new evaluation method by conducting a clinical feasibility trial.A single-center prospective clinical feasibility trial was conducted on 10 cases of LC performed at Oita University hospital. Subsequently, an external evaluation committee (EEC) evaluated the AI detection accuracy for each landmark using five-grade rubric evaluation and DICE coefficient. We defined LM-CBD as the expert surgeon's "judge" of the cystic bile duct in endoscopic images.The average detection accuracy on the rubric by the EEC was 4.2 ± 0.8 for the LM-CBD. The DICE coefficient between the AI detection area of the LM-CBD and the EEC members' evaluation was similar to the mean value of the DICE coefficient between the EEC members. The DICE coefficient was high score for the case that was highly evaluated by the EEC on a five-grade scale.This is the first feasible clinical trial of an AI system designed for intraoperative use and to evaluate the AI system using an EEC. In the future, this concept of evaluation for the AI system would contribute to the development of new AI navigation systems for surgery.