REBOA as a rescue strategy for catastrophic vascular injury during robotic surgery

Experience sharing on perioperative clinical management of gastric cancer patients based on the "China Robotic Gastric Cancer Surgery Guidelines"

BACKGROUND

With the popularization of robotic surgical systems in the field of surgery, robotic gastric cancer surgery has also been fully applied and promoted in China. The Chinese Guidelines for Robotic Gastric Cancer Surgery was published in the Chinese Journal of General Surgery in August 2021.

METHODS

We have made a detailed interpretation of the process of robotic gastric cancer surgery regarding the indications, contraindications, perioperative preparation, surgical steps, complication, and postoperative management based on the recommendations of China's Guidelines for Robotic Gastric Cancer Surgery and supplemented by other surgical guidelines, consensus, and single-center experience.

RESULTS

Twenty experiences of perioperative clinical management of robotic gastric cancer surgery were described in detail.

CONCLUSION

We hope to bring some clinical reference values to the front-line clinicians in treating robotic gastric cancer surgery.

TRIAL REGISTRATION

The guidelines were registered on the International Practice Guideline Registration Platform ( http://www.guidelines-registry.cn ) (registration number: IPGRP-2020CN199).

Short: Prediction of fetal blood oxygen content in response to partial occlusion of maternal aorta

Acute hemorrhage in pregnancy may lead to maternal and/or fetal morbidity or mortality. In emergency medicine, blockage of the aorta via an inflatable endovascular balloon, technically referred to Resuscitative Endovascular Balloon Occlusion of the Aorta (REBOA), is used to manage hemorrhage. However, the application of REBOA in pregnancy needs to strike a balance between two competing objectives of limiting maternal blood loss and ensuring fetal wellness, for which one would need to predict the impact of regulated blood pressure on fetal wellness. To address this problem, we propose an efficient machine learning-based method to predict the temporal impact of the distal Mean Arterial Blood Pressure (dMAP) controlled by the REBOA on the oxygen content in the fetal blood. Evaluation of the algorithm on data collected from in-vivo experiments from pregnant ewe animal models exhibits mean absolute error of 0.61, 1.09, 1.42, 1.70 mmHg, and coefficient of determination of 0.95, 0.86, 0.76, 0.64 for prediction of partial pressure of oxygen in fetal arterial blood, a key predictor of fetal wellness, in 2.5, 5, 7.5, 10-minute prediction horizons, respectively.

Challenges of Conversion from Robotic Surgery for Vascular Complications

A 67-year-old woman with endometrial adenocarcinoma had sustained an aortic injury during robotically assisted retroperitoneal lymphadenectomy. Repair could not be performed laparoscopically; however, graspers were used to maintain hemostasis while conversion to open surgery was initiated. Safety mechanisms locked the graspers in place, preventing tissue release, but resulting in additional aortic injury. Forceful removal of the graspers was eventually successful, and definitive aortic repair was then performed. Vascular surgeons who are not familiar with robotic surgery techniques should be aware that removal of robotic hardware requires the use of stepwise algorithms, which, if performed out of order, can introduce significant challenges.

Expert surgeons and deep learning models can predict the outcome of surgical hemorrhage from 1 min of video

Major vascular injury resulting in uncontrolled bleeding is a catastrophic and often fatal complication of minimally invasive surgery. At the outset of these events, surgeons do not know how much blood will be lost or whether they will successfully control the hemorrhage (achieve hemostasis). We evaluate the ability of a deep learning neural network (DNN) to predict hemostasis control ability using the first minute of surgical video and compare model performance with human experts viewing the same video. The publicly available SOCAL dataset contains 147 videos of attending and resident surgeons managing hemorrhage in a validated, high-fidelity cadaveric simulator. Videos are labeled with outcome and blood loss (mL). The first minute of 20 videos was shown to four, blinded, fellowship trained skull-base neurosurgery instructors, and to SOCALNet (a DNN trained on SOCAL videos). SOCALNet architecture included a convolutional network (ResNet) identifying spatial features and a recurrent network identifying temporal features (LSTM). Experts independently assessed surgeon skill, predicted outcome and blood loss (mL). Outcome and blood loss predictions were compared with SOCALNet. Expert inter-rater reliability was 0.95. Experts correctly predicted 14/20 trials (Sensitivity: 82%, Specificity: 55%, Positive Predictive Value (PPV): 69%, Negative Predictive Value (NPV): 71%). SOCALNet correctly predicted 17/20 trials (Sensitivity 100%, Specificity 66%, PPV 79%, NPV 100%) and correctly identified all successful attempts. Expert predictions of the highest and lowest skill surgeons and expert predictions reported with maximum confidence were more accurate. Experts systematically underestimated blood loss (mean error - 131 mL, RMSE 350 mL, R² 0.70) and fewer than half of expert predictions identified blood loss > 500 mL (47.5%, 19/40). SOCALNet had superior performance (mean error - 57 mL, RMSE 295 mL, R² 0.74) and detected most episodes of blood loss > 500 mL (80%, 8/10). In validation experiments, SOCALNet evaluation of a critical on-screen surgical maneuver and high/low-skill composite videos were concordant with expert evaluation. Using only the first minute of video, experts and SOCALNet can predict outcome and blood loss during surgical hemorrhage. Experts systematically underestimated blood loss, and SOCALNet had no false negatives. DNNs can provide accurate, meaningful assessments of surgical video. We call for the creation of datasets of surgical adverse events for quality improvement research.

Operating on the Mesentery in Robotic Colonic Surgery—General Techniques

During colorectal surgery the mesentery is the organ on which the greatest amount of operating time is focused. It has recently gained increasing attention. This technical review focuses on the mesentery during robotic colonic procedures. Specifically, we focus upon how to access, dissect, and divide the mesentery using the robotic platform. We also touch on the management of bleeding and some specific disease etiologies.

Utility of the Simulated Outcomes Following Carotid Artery Laceration Video Data Set for Machine Learning Applications

IMPORTANCE

Surgical data scientists lack video data sets that depict adverse events, which may affect model generalizability and introduce bias. Hemorrhage may be particularly challenging for computer vision-based models because blood obscures the scene.

OBJECTIVE

To assess the utility of the Simulated Outcomes Following Carotid Artery Laceration (SOCAL)-a publicly available surgical video data set of hemorrhage complication management with instrument annotations and task outcomes-to provide benchmarks for surgical data science techniques, including computer vision instrument detection, instrument use metrics and outcome associations, and validation of a SOCAL-trained neural network using real operative video.

DESIGN, SETTING, AND PARTICIPANTS

For this quailty improvement study, a total of 75 surgeons with 1 to 30 years' experience (mean, 7 years) were filmed from January 1, 2017, to December 31, 2020, managing catastrophic surgical hemorrhage in a high-fidelity cadaveric training exercise at nationwide training courses. Videos were annotated from January 1 to June 30, 2021.

INTERVENTIONS

Surgeons received expert coaching between 2 trials.

MAIN OUTCOMES AND MEASURES

Hemostasis within 5 minutes (task success, dichotomous), time to hemostasis (in seconds), and blood loss (in milliliters) were recorded. Deep neural networks (DNNs) were trained to detect surgical instruments in view. Model performance was measured using mean average precision (mAP), sensitivity, and positive predictive value.

RESULTS

SOCAL contains 31 443 frames with 65 071 surgical instrument annotations from 147 trials with associated surgeon demographic characteristics, time to hemostasis, and recorded blood loss for each trial. Computer vision-based instrument detection methods using DNNs trained on SOCAL achieved a mAP of 0.67 overall and 0.91 for the most common surgical instrument (suction). Hemorrhage control challenges standard object detectors: detection of some surgical instruments remained poor (mAP, 0.25). On real intraoperative video, the model achieved a sensitivity of 0.77 and a positive predictive value of 0.96. Instrument use metrics derived from the SOCAL video were significantly associated with performance (blood loss).

CONCLUSIONS AND RELEVANCE

Hemorrhage control is a high-stakes adverse event that poses unique challenges for video analysis, but no data sets of hemorrhage control exist. The use of SOCAL, the first data set to depict hemorrhage control, allows the benchmarking of data science applications, including object detection, performance metric development, and identification of metrics associated with outcomes. In the future, SOCAL may be used to build and validate surgical data science models.