Search

Abstract Using the intelligent image recognition method to recognize the reading of the unintelligent manual reading meter is an important approach to expand the sensing means and reduce the cost of transformation of the Industrial Internet of Things. Traditional methods based on morphology and back propagation neural networks are difficult to solve the problems of shadow, deflection, and dimness in the industrial environment. In this article, the deep learning‐based capsule networks for pointer instruments and digital display instruments were proposed to implement unintelligent manual reading meter recognition using. Due to the complex structure and a large number of parameters, the basic capsule network is difficult to run on devices with low computing resources. To overcome this issue, the improved capsule network model was designed to reduce the parameters of the model. The experimental results show that the improved capsule network improves the recognition accuracy by 13% and reduces the parameters by 23%.

Background. Colorectal endoscopic submucosal dissection (ESD) is a complex operation. Effective traction is crucial. We have successfully used an orthodontic rubber band (ORB) combined with the clip traction method to assist ESD (ORB-ESD). The aim of this retrospective study is to describe the method and to compare the efficacy and safety of ORB-ESD versus conventional ESD in the treatment of superficial colorectal tumors. Methods. We retrospectively analyzed the data of patients with superficial colorectal tumor (with diameter≥20 mm) who received either ORB-ESD (n=34) or conventional ESD (n=90) between January 2019 and September 2020. Propensity score matching (PSM) was used to match the clinical data of 31 pairs of patients in each group. Results. Operation time was significantly shorter for ORB-ESD than for conventional ESD (34.5 minutes vs. 56 minutes, P≤0.001). In the propensity-matched cohorts, the operation time remained significantly shorter in the ORB-ESD patients (35 minutes vs. 50 minutes, P=0.001). Postoperative adverse events, en bloc resection rate, and R0 resection rate were comparable between the two groups (P>0.05), both before and after propensity score matching. In the ORB subgroup analysis, the trainee and expert ESD operation times were similar (37 (26–53) vs. 33.5 (26–37) minutes, respectively; P=0.274). Conclusion. ORB-ESD appears to be an effective technique for ESD of colorectal cancer. Our findings need to be confirmed in large prospective multicenter studies.