There is a pressing need for an automatic road extraction method due to the continuous development of transportation networks. Free from the influence of weather, satellite-mounted synthetic-aperture radar (SAR) opens the way for such a road detection application. This study introduces an automatic discrimination method based on a deep neural network (DNN) adjusted for roads from dual-polarimetric (VV and VH) Sentinel-1 SAR imagery. In this proposed method, the U-Net extended the convolutional neural network (CNN), is adjusted for road extraction from SAR images. To investigate the potential of using the U-Net based fully convolutional neural network (FCN) for road extraction, LeNet-5, is applied as a preliminary DNN model. Additionally, several training optimizations are introduced to improve accuracy. To assess the performance of the different polarization modes used in road extraction, both single-polarimetric and dual-polarimetric data were investigated. Moreover, four machine learning algorithms have been compared for accuracy and speed. As a result, the outcome evaluation of Precision, Recall, and F₁ obtained by FCN is better than the original CNN, and the training time has been significantly reduced. The DNN model (CNN and FCN) is superior to machine learning methods in accuracy and elapsed computation time.

Soil salinity is a significant environmental indicator, directly reflecting the land quality and its productivity. In this work, dual-polarized synthetic aperture radar (PolSAR) data were exploited to retrieve the soil salinity in saline-affected fields based on the deep neural network (DNN) theory. Two polarimetric features gotten from Cloude polarization decomposition, together with six other features, were calculated and selected from ten features according to the feature importance. The DNN regression model for soil salinity (DNNR-S) based on one-dimensional convolutional neural network, quantifying the relationship between the eight feature parameters and soil salinity, was established to retrieve the soil salinity in northeastern China. Compared with other five traditional machine learning regression methods [logistic regression (LOR), random forest regression (RFR), support vector regression (SVR), decision tree regression (DTR), and multilayer perceptron regression (MPR)], DNNR-S is the best-performing model with the performance of root mean square error (RMSE) = 0.28, mean absolute error (MAE) = 0.21, and $r = 0.74$ . Using the proposed model, the soil salinity was retrieved, and 52.37% was found to be affected by salinization which was in general agreement with the government report. Due to the training criteria in the proposed model, it was a little more computationally intensive than all the others, but the DNNR-S had the advantage of easy spread to other study areas.

Background: Literature regarding the advantages of gasless vNOTES is insufficient. The aim of our study is to compare gasless vNOTES vs. traditional vNOTES on hemodynamic profiles and outcomes in patients with benign gynecological disease. We hypothesize that compared with those in the traditional vNOTES group, hemodynamic profiles will be changed less during gasless vNOTES, while safety can be promised. Methods: This is a single-center, prospective, single-blind, randomized controlled clinical trial, which has been approved by the Institutional Review Board of Chengdu Women’s and Children’s Hospital on September 27, 2022. One hundred and twenty patients will be recruited and randomly assigned to either the traditional vNOTES group or the gasless vNOTES group in a 1:1 ratio. For patients allocated to the traditional vNOTES group, after insertion of one port through the vagina, CO₂ gas is infused with a pressure of 12–14 mmHg; while for those allocated to the gasless vNOTES group, a special device is used as an abdominal wall-lifting device to facilitate gasless surgery. CO₂ pneumoperitoneum will not be used during the whole gasless vNOTES procedure. The primary outcome is vital signs at different time points. The secondary outcomes include surgical conversion rate, duration of surgery and anesthesia, anesthetic consumption, intraoperative estimated blood loss, VAS and PONV scores at postoperative 2 h and 24 h, administration of vasopressor drugs from the beginning of general anesthesia induction to 15 min after endotracheal intubation, including times, dosage, and type, intraoperative and postoperative complications, time of first getting out of bed after surgery, and time of first eating after surgery, including light drink. Discussion: This is the first randomized controlled trial to compare the impacts of gasless vNOTES vs. traditional vNOTES on hemodynamic profiles and outcomes in patients with benign gynecological disease. If a favorable effect and safety of gasless vNOTES for hemodynamic profiles and outcomes in patients are shown, gasless vNOTES would be an optimal treatment option for patients with benign gynecological disease. Trial registration: The trial was registered at https://www.chictr.org.cn/showproj.html?proj=182441 with registration No. ChiCTR2200064779 on Oct 17, 2022.