A morphing-Based 3D point cloud reconstruction framework for medical image processing

Scattered Train Bolt Point Cloud Segmentation Based on Hierarchical Multi-Scale Feature Learning

In view of the difficulty of using raw 3D point clouds for component detection in the railway field, this paper designs a point cloud segmentation model based on deep learning together with a point cloud preprocessing mechanism. First, a special preprocessing algorithm is designed to resolve the problems of noise points, acquisition errors, and large data volume in the actual point cloud model of the bolt. The algorithm uses the point cloud adaptive weighted guided filtering for noise smoothing according to the noise characteristics. Then retaining the key points of the point cloud, this algorithm uses the octree to partition the point cloud and carries out iterative farthest point sampling in each partition for obtaining the standard point cloud model. The standard point cloud model is then subjected to hierarchical multi-scale feature extraction to obtain global features, which are combined with local features through a self-attention mechanism, while linear interpolation is used to further expand the perceptual field of local features of the model as a basis for segmentation, and finally the segmentation is completed. Experiments show that the proposed algorithm could deal with the scattered bolt point cloud well, realize the segmentation of train bolt and background, and could achieve high segmentation accuracy, which has important practical significance for train safety detection.

Artificial Intelligence-Based Spiral CT 3D Reconstruction in Transcatheter Aortic Valve Implantation

To evaluate the clinical application effect of spiral computed tomography (CT) three-dimensional (3D) reconstruction based on artificial intelligence in transcatheter aortic valve implantation (TAVI), a CT 3D reconstruction model based on deep convolutional neural networks (DCNN) was established in this research, which was compared with the model-based iterative reconstruction (MBIR) and used in clinical practice. Then, 62 patients with aortic stenosis (AS) who underwent TAVI surgery were recruited as the research objects. The accuracy, sensitivity, and specificity of the multislice spiral CT scan (MSCT) and transthoracic echocardiography (TTE) in predicting the type of TAVI surgical valve were compared and analyzed. The results showed that the mean absolute error (MAE) (0.01) and root mean square error (RMSE) (0.086) of the MBIR model were higher than the reconstruction model in this research. The structural similarity (SSIM) (0.831) and peak signal-to noise ratio (PSNR) (32.77 dB) of the MBIR model were lower than the reconstruction model, and the differences were considerable ( $P<0.05$ ). Of the valve models selected based on the TTE measurement results, 35 cases were accurately predicted and 27 cases were incorrectly predicted. The accuracy of MSCT was 87.1%, the specificity was 98.84%, and the sensitivity was 92.87%; all of which were significantly higher than TTE ( $P<0.05$ ). In summary, compared with the MBIR reconstruction model, the imaging results of the model established in this research were closer to the real image. Compared with TTE, MSCT had higher accuracy, sensitivity, and specificity and can provide more accurate preoperative predictions for patients undergoing TAVI surgery.

State Estimation of Axisymmetric Target Based on Beacon Linear Features and View Relation

In order to realize state estimation for axisymmetric targets and improve the accuracy and robustness of state estimation, a state estimation method for axisymmetric targets based on beacon linear features and view relation is proposed in this paper. The depth camera is used to collect the image and depth information of the object, and the features of the beacon line are extracted by the thinning process and Hough transform. Then, the rotation matrix model based on view relation is constructed to solve the target state. Finally, an axisymmetric shore power plug is taken as the experimental object and the L–V (linear features and view relation) state estimation method is compared with the C–H and C–IPPE state estimation methods. The experimental results show that the L–V state estimation method has higher accuracy and robustness.

Depth-Image Segmentation Based on Evolving Principles for 3D Sensing of Structured Indoor Environments

This paper presents an approach of depth image segmentation based on the Evolving Principal Component Clustering (EPCC) method, which exploits data locality in an ordered data stream. The parameters of linear prototypes, which are used to describe different clusters, are estimated in a recursive manner. The main contribution of this work is the extension and application of the EPCC to 3D space for recursive and real-time detection of flat connected surfaces based on linear segments, which are all detected in an evolving way. To obtain optimal results when processing homogeneous surfaces, we introduced two-step filtering for outlier detection within a clustering framework and considered the noise model, which allowed for the compensation of characteristic uncertainties that are introduced into the measurements of depth sensors. The developed algorithm was compared with well-known methods for point cloud segmentation. The proposed approach achieves better segmentation results over longer distances for which the signal-to-noise ratio is low, without prior filtering of the data. On the given database, an average rate higher than 90% was obtained for successfully detected flat surfaces, which indicates high performance when processing huge point clouds in a non-iterative manner.