Advanced Computer Vision-Based Subsea Gas Leaks Monitoring: A Comparison of Two Approaches.

Recent years have witnessed the increasing risk of subsea gas leaks with the development of offshore gas exploration, which poses a potential threat to human life, corporate assets, and the environment. The optical imaging-based monitoring approach has become widespread in the field of monitoring underwater gas leakage, but the shortcomings of huge labor costs and severe false alarms exist due to related operators' operation and judgment. This study aimed to develop an advanced computer vision-based monitoring approach to achieve automatic and real-time monitoring of underwater gas leaks. A comparison analysis between the Faster Region Convolutional Neural Network (Faster R-CNN) and You Only Look Once version 4 (YOLOv4) was conducted. The results demonstrated that the Faster R-CNN model, developed with an image size of 1280 × 720 and no noise, was optimal for the automatic and real-time monitoring of underwater gas leakage. This optimal model could accurately classify small and large-shape leakage gas plumes from real-world datasets, and locate the area of these underwater gas plumes.

Probabilistic real-time natural gas jet fire consequence modeling of offshore platforms by hybrid deep learning approach.

Natural gas jet fire induced by igniting blowouts has the potential to cause critical structure damage and great casualties of offshore platforms. Real-time natural gas jet fire plume prediction is essential to support the emergency planning to mitigate subsequent damage consequence and ocean pollution. Deep learning based on a large amount of Computational fluid dynamics (CFD) simulations has recently been applied to real-time fire modeling. However, existing approaches based on point-estimation theory are 'over-confident' when prediction deficiency exists, which reduce robustness and accuracy for emergency planning support. This study proposes probabilistic deep learning approach for real-time natural gas jet fire consequence modeling by integrating variational Bayesian inference with deep learning. Numerical model of natural gas jet fire from offshore platform is built and the natural gas jet fire scenarios are simulated to construct the benchmark dataset. Sensitivity analysis of pre-defined parameters such as MC (Monte Carlo) sampling number m and dropout probability p is conducted to determine the trade-off between model's accuracy and efficiency. The results demonstrated our model exhibits competitive accuracy with R2 = 0.965 and real-time capacity with an inference time of 12 ms. In addition, the predicted spatial uncertainty corresponding to spatial jet fire flame plume provides more comprehensive and reliable support for the following mitigation decision-makings compared to the state-of-the-art point-estimation based deep learning model. This study provides a robust alternative for constructing a digital twin of fire and explosion associated emergency management on offshore platforms.

Development of video-assisted breast cancer surgery: Initial experience with a novel method for creating working space without prior liposuction.

Endoscopic techniques are promising in breast surgery. In order to create working space, liposuction is widely used in video-assisted breast surgery (VABS). However, the use of liposuction is likely associated with side effects that may partly limit the application of VABS. Therefore, a new technique of endoscopic axillary lymphadenectomy without prior liposuction was developed by our group. A total of 106 female patients underwent VABS, with special adaptation of the video-assisted surgical procedures previously described. Differing from other endoscopic surgery techniques, our adaptations of VABS included the selection of the working instruments, trocar placement, creation of working space, order of axillary lymph node dissection and method of mastectomy. The operative time was 50-180 min (mean, 85.5 min). The intraoperative blood loss ranged from 20 to 100 ml (mean, 48 ml). The mean lymph node number harvested was 11.5 (range, 6-31). No serious intra- or postoperative complications were recorded. There was no axillary tumor relapse, trocar site tumor implantation or upper limb edema. Without prior liposuction, our new technique of VABS reduced the blood loss volume, endoscopic surgery time, total volume of drainage fluid and, most importantly, the risk of port-site metastases. This new technique appears to have great clinical potential and good prospects for future endoscopic breast surgery development.