Sparse-view computed tomography (CT) holds great promise for speeding up data acquisition and reducing radiation dose in CT scans. Recent advances in reconstruction algorithms for sparse-view CT, such as iterative reconstruction algorithms, obtained high-quality image while requiring advanced computing power. Lately, deep learning (DL) has been widely used in various applications and has obtained many remarkable outcomes. In this paper, we propose a new method for sparse-view CT reconstruction based on the DL approach. The method can be divided into two steps. First, filter backprojection (FBP) was used to reconstruct the CT image from sparsely sampled sinogram. Then, the FBP results were fed to a DL neural network, which is a DenseNet and deconvolution-based network (DD-Net). The DD-Net combines the advantages of DenseNet and deconvolution and applies shortcut connections to concatenate DenseNet and deconvolution to accelerate the training speed of the network; all of those operations can greatly increase the depth of network while enhancing the expression ability of the network. After the training, the proposed DD-Net achieved a competitive performance relative to the state-of-the-art methods in terms of streaking artifacts removal and structure preservation. Compared with the other state-of-the-art reconstruction methods, the DD-Net method can increase the structure similarity by up to 18% and reduce the root mean square error by up to 42%. These results indicate that DD-Net has great potential for sparse-view CT image reconstruction.

A Sparse-View CT Reconstruction Method Based on Combination of DenseNet and Deconvolution

Emotion recognition represents the position and motion of facial muscles. It contributes significantly in many fields. Current approaches have not obtained good results. This paper aimed to propose a new emotion recognition system based on facial expression images. We enrolled 20 subjects and let each subject pose seven different emotions: happy, sadness, surprise, anger, disgust, fear, and neutral. Afterward, we employed biorthogonal wavelet entropy to extract multiscale features, and used fuzzy multiclass support vector machine to be the classifier. The stratified cross validation was employed as a strict validation model. The statistical analysis showed our method achieved an overall accuracy of 96.77±0.10%. Besides, our method is superior to three state-of-the-art methods. In all, this proposed method is efficient.

Facial Emotion Recognition Based on Biorthogonal Wavelet Entropy, Fuzzy Support Vector Machine, and Stratified Cross Validation

Accurate fruit classification is difficult to accomplish because of the similarities among the various categories. In this paper, we proposed a novel fruit-classification system, with the goal of recognizing fruits in a more efficient way. Our methodology included the following steps. First, a four-step pre-processing was employed. Second, the features colour, shape, and texture were extracted. Third, we utilized principal component analysis to remove excessive features. Fourth, a novel fruit-classification system based on biogeography-based optimization BBO and feedforward neural network FNN was proposed, with the short name of BBO-FNN. The experiment employed over 1653 chromatic fruit images 18 categories by fivefold stratified cross-validation. The results showed that the proposed BBO-FNN yielded an overall accuracy of 89.11%, which was higher than the five state-of-the-art methods: genetic algorithm-FNN, artificial bee colony-FNN, particle swarm optimization-FNN, kernel support vector machine, and ant colony optimization-FNN. Also, the BBO-FNN achieved the same accuracy as fitness-scaling chaotic artificial bee colony-FNN, but it performed much faster than the latter. The proposed BBO-FNN was effective in fruit-classification in terms of classification accuracy and computation time. This indicated that it can be applied in credible use.

Fruit classification by biogeography-based optimization and feedforward neural network

17th International Conference on Medical Image Computing and Computer-Assisted Intervention

Minimal path techniques can efficiently extract geometrically curve-like structures by finding the path with minimal accumulated cost between two given endpoints. Though having found wide practical applications (e.g., line identification, crack detection, and vascular centerline extraction), minimal path techniques suffer from some notable problems. The first one is that they require setting two endpoints for each line to be extracted (endpoint problem). The second one is that the connection might fail when the geodesic distance between the two points is much shorter than the desirable minimal path (shortcut problem). In addition, when connecting two distant points, the minimal path connection might become inefficient as the accumulated cost increases over the propagation and results in leakage into some non-feature regions near the starting point (accumulation problem). To address these problems, this paper proposes an approach termed minimal path propagation with backtracking. We found that the information in the process of backtracking from reached points can be well utilized to overcome the above problems and improve the extraction performance. The whole algorithm is robust to parameter setting and allows a coarse setting of the starting point. Extensive experiments with both simulated and realistic data are performed to validate the performance of the proposed method.

Curve-Like Structure Extraction Using Minimal Path Propagation With Backtracking

Dictionary learning based sinogram inpainting for CT sparse reconstruction

An automatic coronary artery tree labeling algorithm is described to identify the anatomical segments of the extracted centerlines from coronary computed tomography angiography (CCTA) images. This method will facilitate the automatic lesion reporting and risk stratification of cardiovascular disease. Three-dimensional (3D) models for both right dominant (RD) and left dominant (LD) coronary circulations were built. All labels in the model were matched with their possible candidates in the extracted tree to find the optimal labeling result. In total, 83 CCTA datasets with 1149 segments were included in the testing of the algorithm. The results of the automatic labeling were compared with those by two experts. In all cases, the proximal parts of main branches including LM were labeled correctly. The automatic labeling algorithm was able to identify and assign labels to 89.2% RD and 83.6% LD coronary tree segments in comparison with the agreements of the two experts (97.6% RD, 87.6% LD). The average precision of start and end points of segments was 92.0% for RD and 90.7% for LD in comparison with the manual identification by two experts while average differences in experts is 1.0% in RD and 2.2% in LD cases. All cases got similar clinical risk scores as the two experts. The presented fully automatic labeling algorithm can identify and assign labels to the extracted coronary centerlines for both RD and LD circulations.

/pdf/automatic-identification-of-coronary-tree-anatomy-in-3sg3z7e7qe.pdf

Automatic identification of coronary tree anatomy in coronary computed tomography angiography

Vessel segmentation takes a key step toward accurate visualization, diagnosis and quantification of vascular pathologies. This paper proposes a Centerline Constrained Minimal Path Propagation (CCMPP) algorithm for vascular extraction. The proposed CCMPP method includes two minimal path propagations. In the first minimal path propagation, a novel back-tracing accumulation strategy is used to extract vessel centerlines, then the centerline information serves as a constraint for the vessel extraction in the second minimal path propagation. For the proposed approach, only one start point is needed to be set, and no input of start and end points is required for the whole centerline and vessel extraction. We validate the utility of the proposed approach by using 3-D angiography data.

Centerline constrained minimal path propagation for vessel extraction

Automatically extracted coronary artery trees (CATs) from coronary computed tomography angiography images could contain incorrect extractions which require manual corrections before they can be used in clinical practice. A model-guided method for improving the extracted CAT is described to automatically detect potential incorrect extractions and improve them. The proposed method is a coarse-to-fine approach. A coarse improvement is first applied on all vessels in the extracted CAT, and then a fine improvement is applied only on vessels with higher clinical significance. Based upon a decision tree, the proposed method automatically and iteratively performs improvement operations for the entire extracted CAT until it meets the stop criteria. The improvement in the extraction quality obtained by the proposed method is measured using a scoring system. 18 datasets were used to determine optimal values for the parameters involved in the model-guided method and 122 datasets were used for evaluation. Compared to the initial automatic extractions, the proposed method improves the CATs for 122 datasets from an average quality score of 87 ± 6 to 93 ± 4. The developed method is able to run within 2 min on a typical workstation. The difference in extraction quality after automatic improvement is negatively correlated with the initial extraction quality (R = − 0.694, P < 0.001). Without deteriorating the initially extracted CATs, the presented method automatically detects incorrect extractions and improves the CATs to an average quality score of 93 guided by anatomical statistical models.

/pdf/a-model-guided-method-for-improving-coronary-artery-tree-2jbap42n9k.pdf

Qing Cao

Papers

Curve-Like Structure Extraction Using Minimal Path Propagation With Backtracking

Dictionary learning based sinogram inpainting for CT sparse reconstruction

Automatic identification of coronary tree anatomy in coronary computed tomography angiography

Centerline constrained minimal path propagation for vessel extraction

A model-guided method for improving coronary artery tree extractions from CCTA images.