Real-time detection of active bleeding in laparoscopic colectomy using artificial intelligence.

BACKGROUND: Most intraoperative adverse events (iAEs) result from surgeons' errors, and bleeding is the majority of iAEs. Recognizing active bleeding timely is important to ensure safe surgery, and artificial intelligence (AI) has great potential for detecting active bleeding and providing real-time surgical support. This study aimed to develop a real-time AI model to detect active intraoperative bleeding. METHODS: We extracted 27 surgical videos from a nationwide multi-institutional surgical video database in Japan and divided them at the patient level into three sets: training (n = 21), validation (n = 3), and testing (n = 3). We subsequently extracted the bleeding scenes and labeled distinctively active bleeding and blood pooling frame by frame. We used pre-trained YOLOv7_6w and developed a model to learn both active bleeding and blood pooling. The Average Precision at an Intersection over Union threshold of 0.5 (AP.50) for active bleeding and frames per second (FPS) were quantified. In addition, we conducted two 5-point Likert scales (5 = Excellent, 4 = Good, 3 = Fair, 2 = Poor, and 1 = Fail) questionnaires about sensitivity (the sensitivity score) and number of overdetection areas (the overdetection score) to investigate the surgeons' assessment. RESULTS: We annotated 34,117 images of 254 bleeding events. The AP.50 for active bleeding in the developed model was 0.574 and the FPS was 48.5. Twenty surgeons answered two questionnaires, indicating a sensitivity score of 4.92 and an overdetection score of 4.62 for the model. CONCLUSIONS: We developed an AI model to detect active bleeding, achieving real-time processing speed. Our AI model can be used to provide real-time surgical support.

The safety and feasibility of laparoscopic gastrectomy for gastric cancer in very elderly patients: short-and long-term outcomes.

PURPOSE: It remains unclear whether laparoscopic gastrectomy (LG) for gastric cancer is a suitable treatment for very elderly (VE) patients. We aimed to assess the safety and feasibility of LG for gastric cancer in VE patients. METHODS: We reviewed 226 consecutive patients who underwent LG between January 2010 and December 2016. We compared VE patients (age ≥ 80, n = 38) with non-elderly patients (age ≤ 79, n = 188). RESULTS: An ASA-PS score ≥ 2 was more common in VE group (86.8 vs. 48.9%; P < 0.01). There were no significant differences in the operating time, blood loss, postoperative hospital stay, or postoperative morbidity between the groups. The 3-year survival rate and 3-year disease-specific survival rate were lower in the VE group (53.7 vs. 85.6%; P < 0.0001, 78.5 vs. 92.4%; P = 0.0116). A univariate analysis showed that PS scores ≥ 2, Charlson comorbidity index ≥ 4, and pN stage were independent predictors of decreased overall survival rates in the VE group. A multivariate analysis showed total gastrectomy, a Charlson comorbidity index ≥ 4, and the pN stage to be independent predictors in the VE group. CONCLUSION: LG for gastric cancer is, thus, considered to be safe for patients aged 80 years or older. Total gastrectomy, a Charlson comorbidity index ≥ 4, and the pN stage were independent risk factors for a poor prognosis in these patients.

A novel technique of laparoscopic reduction of incarcerated internal supravesical hernia via peritoneal incision: A case report.

INTRODUCTION: Laparoscopic reduction techniques for internal supravesical hernia have not been discussed much in literature. CASE PRESENTATION: A 90-year old woman was admitted for symptoms of intestinal obstruction. She was diagnosed with small bowel strangulation by CT scan and laparoscopy was performed. Laparoscopy revealed a mass medial to the medial inguinal fold with tightly incarcerated small bowel. The bowel could not be reduced by traction or external compression, and required incision of the hernia ring. The tight incarceration posed a risk of bowel injury and so we performed peritoneal incision in a similar manner to the TAPP approach for loosening and precise incision of the hernia ring. The bowel was successfully reduced and the hernia was repaired by partial sac resection. DISCUSSION: Surgical methods as well as reduction technique were reviewed from previous literature. Procedures with open laparotomy, laparoscopy and anterior approach have been described, but details of reduction were not seen in many of these reports. Various methods have been described for bowel reduction in other hernias, but none involving peritoneal incision. This is the first report describing bowel reduction via the peritoneal incision technique. CONCLUSION: Internal supravesical hernia may pose difficulty in bowel reduction, but the peritoneal incision technique allows safe incision of the hernia ring under laparoscopic situations.

Protective effect of pre-recovery surfactant inhalation on lungs donated after cardiac death in a canine lung transplantation model.

BACKGROUND: Warm ischemia-reperfusion injury related to donation after cardiac death is a crucial issue in transplantation. Because surfactant function deteriorates in lungs during warm ischemia, we hypothesized pre-recovery surfactant inhalation would mitigate warm ischemia-reperfusion injury. METHODS: We rendered donor dogs cardiac dead and left them at room temperature. All animals received ventilation for 60 minutes starting at 240 minutes after cardiac arrest. The animals were divided into 2 groups: NS (normal saline, n = 7) group, which received aerosolized normal saline, and SF (surfactant; n = 5), which received aerosolized surfactant. The lungs were flushed and procured, and the left lung was transplanted into recipient dogs. At 45 minutes of reperfusion, the right pulmonary artery was ligated, and the left transplanted lung function was evaluated. RESULTS: In the NS group, 2 of 7 dogs died at 75 minutes after reperfusion, whereas all 5 animals in the SF group survived for 240 minutes after reperfusion. The SF group showed significantly better dynamic compliance, oxygenation, and wet-to-dry weight ratio. Furthermore, the SF group had higher levels of high-energy phosphates in the lung tissues and lower levels of interleukin-8, tumor necrosis factor-α, and protein in the bronchoalveolar lavage fluid. Histologically, the lungs in the SF group showed fewer signs of interstitial edema and hemorrhage and significantly less neutrophilic sequestration than those of the NS group. CONCLUSIONS: Our results indicated pre-recovery surfactant inhalation improved graft function, maintained adenine nucleotide levels, and prevented alveolar-capillary barrier leakage, resulting in the attenuation of warm ischemia-reperfusion injury.