Object detection in point clouds is an important aspect of many robotics applications such as autonomous driving. In this paper we consider the problem of encoding a point cloud into a format appropriate for a downstream detection pipeline. Recent literature suggests two types of encoders; fixed encoders tend to be fast but sacrifice accuracy, while encoders that are learned from data are more accurate, but slower. In this work we propose PointPillars, a novel encoder which utilizes PointNets to learn a representation of point clouds organized in vertical columns (pillars). While the encoded features can be used with any standard 2D convolutional detection architecture, we further propose a lean downstream network. Extensive experimentation shows that PointPillars outperforms previous encoders with respect to both speed and accuracy by a large margin. Despite only using lidar, our full detection pipeline significantly outperforms the state of the art, even among fusion methods, with respect to both the 3D and bird's eye view KITTI benchmarks. This detection performance is achieved while running at 62 Hz: a 2 -4 fold runtime improvement. A faster version of our method matches the state of the art at 105 Hz. These benchmarks suggest that PointPillars is an appropriate encoding for object detection in point clouds.

These data suggest a reduced tendency for monocyte/macrophage-driven inflammation with periodontal therapy and a potential impact on atherosclerosis-related complications in diabetic individuals.

Summary Background Previous studies have demonstrated the efficacy of apatinib and anlotinib for the treatment of sarcomas. However, more clinical data and evidence are needed to support clinical treatment selection and study design. Here, we evaluated the effectiveness and safety of these two drugs for the treatment of sarcomas. Methods We retrospectively reviewed the data of 110 patients with advanced osteosarcoma (n = 32) or soft tissue sarcoma (STS, n = 78) who received oral apatinib or anlotinib therapy during May 2016–February 2019 at two centers. Patients were divided into the apatinib and anlotinib groups. Results Among osteosarcoma patients, the objective response rates (ORRs) for the apatinib and anlotinib groups were 15.79% (3/19) and 7.69% (1/13), respectively. The disease control rates (DCRs) were 63.16% (12/19) and 30.77% (4/13), and the median progression-free survival (m-PFS) was 4.67 ± 3.01 and 2.67 ± 1.60 months, respectively. Among STS patients, ORRs for the apatinib and anlotinib groups were 12.24% (6/49) and 13.79% (4/29), respectively. The DCRs were 59.18% (29/49) and 55.17% (16/29), and m-PFS was 7.82 ± 6.90 and 6.03 ± 4.50 months, respectively. Regarding adverse events (AEs), apatinib was associated with a higher incidence of hair hypopigmentation and pneumothorax, while anlotinib was associated with a higher incidence of pharyngalgia or hoarseness. Conclusion Both apatinib and anlotinib were effective for the treatment of sarcomas. However, the effectiveness of the two drugs and associated AEs varied based on the histological type of sarcoma. These differences may be due to their different sensitivities to targets such as RET, warranting further study.