No abstract

No abstract

The optimized graft for use in anterior cruciate ligament (ACL) reconstruction is still in controversy. The bone-patellar tendon-bone (BPTB) autograft has been accepted as the gold standard for ACL reconstruction. However, donor site morbidities cannot be avoided after this treatment. The artificial ligament of ligament advanced reinforcement system (LARS) has been recommended for ACL reconstruction. The purpose of this study is to compare the midterm outcome of ACL reconstruction using BPTB autografts or LARS ligaments. Between July 2004 and March 2006, the ACL reconstruction using BPTB autografts in 30 patients and LARS ligaments in 32 patients was performed. All patients were followed up for at least 4 years and evaluated using the Lysholm knee score, Tegner score, International Knee Documentation Committee (IKDC) score, and KT-1000 arthrometer test. There were no significant differences between the two groups with respect to the data of Lysholm scores, Tegner scores, IKDC scores, and KT-1000 arthrometer test at the latest follow-up. Our study demonstrates that the similarly good clinical results are obtained after ACL reconstruction using BPTB autografts or LARS ligaments at midterm follow-up. In addition to BPTB autografts, the LARS ligament may be a satisfactory treatment option for ACL rupture.

No abstract

Future trains will use more computer vision aids to help achieve fully autonomous driving. One of the most important parts of the train's visual function is the detection of railroad obstacles. This makes it important to identify and segment the railroad region within each video frame as it allows the train to identify the driving area so that it can do effective obstacle detection. Traditional railroad detection methods rely on hand-crafted features or highly specialized equipment such as lidar, which typically require expensive equipment to be maintained and are less reliable in scene changes. RailNet is a deep learning segmentation algorithm for railroad detection for videos captured by the front-view on-board cameras. RailNet provides an end-to-end solution that combines feature extraction and segmentation. We have modified the backbone network to extract multi-convolution features and use a pyramid structure to make the features have a top-tobottom propagation. Our model can detect the railroad without generating large numbers of regions, which greatly increases the detection speed. Tested on a railroad segmentation dataset (RSDS) which we have built, RailNet exhibits very good performance while achieving 20 frames per second processing speed.