Abstract
This paper presents an in-depth study and analysis of the 3D arterial centerline in spiral CT coronary angiography, and constructs its detection and extraction technique. The first time, the distance transform is used to complete the boundary search of the original figure; the second time, the distance transform is used to calculate the value of the distance transform of all voxels, and according to the value of the distance transform, unnecessary voxels are deleted, to complete the initial contraction of the vascular region and reduce the computational consumption in the next process; then, the nonwitnessed voxels are used to construct the maximum inner joint sphere model and find the skeletal voxels that can reflect the shape of the original figure. Finally, the skeletal lines were optimized on these initially extracted skeletal voxels using a dichotomous-like principle to obtain the final coronary artery centerline. Through the evaluation of the experimental results, the algorithm can extract the coronary centerline more accurately. In this paper, the segmentation method is evaluated on the test set data by two kinds of indexes: one is the index of segmentation result evaluation, including dice coefficient, accuracy, specificity, and sensitivity; the other is the index of clinical diagnosis result evaluation, which is to refine the segmentation result for vessel diameter detection. The results obtained in this paper were compared with the physicians' labeling results. In terms of network performance, the Dice coefficient obtained in this paper was 0.89, the accuracy was 98.36%, the sensitivity was 93.36%, and the specificity was 98.76%, which reflected certain advantages in comparison with the advanced methods proposed by previous authors. In terms of clinical evaluation indexes, by performing skeleton line extraction and diameter calculation on the results obtained by the segmentation method proposed in this paper, the absolute error obtained after comparing with the diameter of the labeled image was 0.382 and the relative error was 0.112, which indicates that the segmentation method in this paper can recover the vessel contour more accurately. Then, the results of coronary artery centerline extraction with and without fine branch elimination were evaluated, which proved that the coronary artery centerline has higher accuracy after fine branch elimination. The algorithm is also used to extract the centerline of the complete coronary artery tree, and the results prove that the algorithm has better results for the centerline extraction of the complete coronary vascular tree.
Highlights
Analyzing the data in the table, we can see that the TDTT algorithm proposed in this paper has improved the overlap rate by 5.4% compared with the MIBTT algorithm; the TDTT algorithm has reduced the average distance to the actual length by about 0.16 mm; the TDTT algorithm has improved the overlap rate before the first error by 63.3% compared with the MIBTT algorithm; the running time of the TDTT algorithm is about 9% of that of the MIBTT algorithm. e average running time of the MIBTT algorithm is 5.217 seconds, which can meet the design requirements of CAD systems in clinical practice
Comparing the results of centerline extraction based on the twenty-six directional topology refinement algorithm with the TDTT algorithm, we get to see that the overlap rate of the TDTT algorithm is 49.7% higher than that of the algorithm; the average distance is only 20% of that of the algorithm; the overlap rate before the first error is 3.24 times of that of the algorithm; and the extraction time is only 5% of that of the algorithm
The two algorithms proposed in this paper are compared, and the results show that the algorithm in this chapter has certain advantages; the algorithm proposed in this chapter is compared with the classical topology refinement algorithm based on twenty-six directions, and it is proved that the algorithm in this chapter is more suitable than this method for extracting the centerlines of coronary arteries
Summary
Since the imaging view of CT completely covers the heart side, the structures presented in the image include a variety of tissues such as bones, muscles, organs, and blood vessels; coupled with the fact that the dose of contrast agent required for imaging affects the picture quality, it makes it further difficult to extract the centerline of the coronary arteries [12]. E main method of convolutional neural networks applied to medical image processing is semantic segmentation, which is the pixel-level classification of images by different model classifiers. Convolutional neural network-based coronary angiography image vessel segmentation requires a large amount of real patient data to train the network, and it is very difficult to obtain sufficient sample sets, so image enhancement of existing data is required to lay a good foundation for the subsequent model training. Convolutional neural networks have automatic, fast, and accurate characteristics in processing large-scale image data, and have unparalleled advantages over traditional methods, and have achieved wide application in the field of image segmentation. It can be defined that its 26-neighbors in space can be split into F-neighbors, Edge-neighbors
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
