Large-scale point clouds scanned by light detection and ranging (lidar) sensors provide detailed geometric characteristics of the indoor and outdoor scenes due to the provision of 3D structural data colored by intensity/reflectance information. The semantic segmentation of large-scale point clouds is a crucial step for an in-depth understanding of complex scenes. Of late, although a large number of point cloud semantic segmentation algorithms have been proposed, semantic segmentation methods are still far from being satisfactory in terms of precision and accuracy of large-scale point clouds. For machine learning (ML) and deep learning (DL) methodologies, the semantic segmentation is largely influenced by the quality of training sets and methods themselves. Therefore, we construct a new point cloud dataset, namely CSPC-Dataset (Complex Scene Point Cloud Dataset) for large-scale scene semantic segmentation. CSPC-Dataset point clouds are acquired by a wearable laser mobile mapping robot. It covers five complex urban and rural scenes and mainly includes six types of objects, i.e., ground, car, building, vegetation, bridge, and pole. It provides large-scale outdoor scenes, which has advantages such as the scene more complete, point density relatively uniform, diversity and complexity of objects and the high discrepancy between different scenes. Based on the CSPC-Dataset, we construct a new benchmark, which includes approximately 68 million points with explicit semantic labels. To extend the dataset into a wide range of applications, this paper provides the semantic segmentation results and comparative analysis of 7 baseline methods based on CSPC-Dataset. In the experiment part, three groups of experiments are conducted for benchmarking, which offers an effective way to make comparisons with different point-labeling algorithms. The labeling results have shown that the highest Intersection over Union (IoU) of pole, ground, building, car, vegetation, and bridge for all benchmarks is 36.0%, 97.8%, 93.7%, 65.6%, 92.0%, and 69.6%.

Background: For patients with locally advanced rectal cancer (LARC), it is unclear whether neoadjuvant chemoradiotherapy-induced pathologic complete response (pCR) individuals would further benefit from adjuvant chemotherapy (ACT). Methods: The pCR individuals who received different ACT cycles were paired by propensity score matching. Overall survival (OS), disease-free survival (DFS), local recurrence-free survival (LRFS), and distant metastasis-free survival (DMFS) were calculated by Kaplan–Meier and log-rank test. Results: In total, 1041 pCR individuals were identified from 5567 LARC cases. Specifically, 303 pCR cases had no ACT treatment, and 738 pCR patients received fluoropyrimidine-based ACT (median, 4 cycles) treatment. After 1:3 propensity score matching, 297 cases without ACT treatment were matched to 712 cases who received ACT treatment. Kaplan–Meier analysis showed that pCR individuals treated with or without ACT had the similar 3-year outcome (OS, DFS, LRFS and DMFS) (all P > 0.05). Moreover, the pCR patients received different ACT cycle(s) (0 vs. 1–4 cycles, 0 vs. ≥5 cycles) had comparable 3-year OS, DFS, LRFS and DMFS (all P > 0.05). In stratified analysis, ACT treatment did not improve 3-year survival (OS, DFS, LRFS and DMFS) for the baseline high-risk (cT3–4/cN1–2) subgroup patients (all P > 0.05). Conclusion: ACT, which did not improve survival, is unnecessary to neoadjuvant treatment-induced pCR LARC patients. Trial registration: 2019ZSLYEC-136 (24-6-2019).

Due to the disorder, sparsity and irregularity of point clouds, the accurate classification of large-scale point clouds is a challenging problem. Voxelization-based deep learning methods have been applied to point cloud classification and have achieved good performances. However, there are some problems in the methods such as voxels lacking color information, single receptive fields being considered only at the same voxel scale, and only the global features of voxels being considered in the classification. This study proposes a deep learning-based algorithm for large-scale point cloud classification through the fusion of multiscale voxels and features (MVF-CNN). First, the point cloud is transformed into voxels of two different sizes. Then, the voxels are input into the 3D convolution neural network (3D CNN) with three different scale receptive fields for the feature extraction. Next, the output features of the 3D CNN are input into the proposed global and local feature fusion classification network (GLNet), which fuses the global features of the voxels at the main branch and the local features of each voxel at the auxiliary branch. Finally, the multiscale features of the main branch are fused, and its classification results are obtained. We have conducted experiments on five point cloud scenes. The experimental results show that the proposed algorithm accurately classifies large-scale point clouds. Compared with several semisupervised/supervised learning methods, the proposed algorithm obtains better classification results. In addition, the experimental results also demonstrate that the proposed algorithm has a strong generalization ability and obviously has better classification performance than the compared algorithms.