There was no statistically significant difference in postoperative pain, pain site and analgesia requirement; however, patients who underwent SILC returned to their normal activity 1.8 days earlier than the LC patients. Larger RCTs are needed to compare postoperative outcomes between SILC and LC.

Introduction: Small gallbladder polyps (GBP) are usually asymptomatic and benign and are monitored with regular ultrasonography (US) surveillance. Although most centers repeat imaging within a year, there remains no consensus regarding appropriate scan intervals.Aims: To investigate the size stability of GBP and to review the need for close surveillance.Methods: All abdominal ultrasound scans performed in our hospital over 3-month period were reviewed. Patients with sonographic evidence of GBP and with subsequent surveillance were included. The demographics of patients, characteristics of polyps, and subsequent scans over the following five years were reviewed. Histological reports were obtained for patients who underwent cholecystectomy.Results: 96 patients were included in the study. Median age was 51 (range, 24-89) years with a male predominance (67.7%). Main indications for US were hepatitis follow-up (41.7%) and abdominal pain (20.8%). Most patients had multiple polyps (62.5%) and the median diameter of the largest polyp was 4 (range, 3-10) mm. An average of 4.5 scans were performed over five years following detection and most polyps remained stable in size, rarely growing beyond 10mm -only two patients had polyps beyond 10mm. No gallbladder carcinoma was detected during the follow-up period. Conclusion:GBP usually remain stable in size, seldom grow beyond 10mm, and are rarely malignant. Surveillance scans for polyps smaller than 10mm should not be performed at intervals less than a year.

Stochastic computing (SC) is an alternative computing domain for ubiquitous deterministic computing whereby a single logic gate can perform the arithmetic operation by exploiting the nature of probability math. SC was proposed in the 1960s when binary computing was expensive. However, presently, SC started to regain interest after the widespread of deep learning application, specifically the convolutional neural network (CNN) algorithm due to its practicality in hardware implementation. Although not all computing functions can translate to the SC domain, several useful function blocks related to the CNN algorithm had been proposed and tested by researchers. An evolution of CNN, namely, binarised neural network, had also gained attention in the edge computing due to its compactness and computing efficiency. This study reviews various SC CNN hardware implementation methodologies. Firstly, we review the fundamental concepts of SC and the circuit structure and then compare the advantages and disadvantages amongst different SC methods. Finally, we conclude the overview of SC in CNN and make suggestions for widespread implementation.

No abstract

Automatic License Plate Recognition (ALPR) is one of the applications that hugely benefited from Convolutional Neural Network (CNN) processing which has become the mainstream processing method for complex data. Many ALPR research proposed new CNN model designs and post-processing methods with various levels of performances in ALPR. However, good performing models such as YOLOv3 and SSD in more general object detection and recognition tasks could be effectively transferred to the license plate detection application with a small effort in model tuning. This paper focuses on the design of experiment (DOE) of training parameters in transferring YOLOv3 model design and optimising the training specifically for license plate detection tasks. The parameters are categorised to reduce the DOE run requirements while gaining insights on the YOLOv3 parameter interactions other than seeking optimized train settings. The result shows that the DOE effectively improve the YOLOv3 model to fit the vehicle license plate detection task.