1. Multi-Scale Dilated Convolution Neural Network for Image Artifact Correction of Limited-Angle Tomography
- Author
-
Yining Zhu, Huitao Zhang, Yingying Dong, Jinqiu Xu, Qian Wang, Haichuan Zhou, Ge Li, and Defeng Chen
- Subjects
0209 industrial biotechnology ,General Computer Science ,Computer science ,multi-scale ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,Scale (descriptive set theory) ,artifact correction ,02 engineering and technology ,Convolutional neural network ,Image (mathematics) ,Convolution ,020901 industrial engineering & automation ,0202 electrical engineering, electronic engineering, information engineering ,Preprocessor ,General Materials Science ,Computer vision ,Artifact (error) ,business.industry ,Deep learning ,General Engineering ,Process (computing) ,dilated convolution ,Limited-angle tomography ,020201 artificial intelligence & image processing ,Artificial intelligence ,lcsh:Electrical engineering. Electronics. Nuclear engineering ,business ,lcsh:TK1-9971 - Abstract
Limited-angle computed tomography (CT) has arisen in some medical and industrial applications. It is also a challenging problem since some scan views are missing and the directly reconstructed images often suffer from severe distortions. For such kind of problems, we analyze the features of limited-angle CT images and propose a multi-scale dilated convolution neural network (MSD-CNN) to correct the artifacts and to restore the image. In this network, the dilated convolution layer and multi-scale pooling layer are combined to form a group and exited in the whole encoder-decoder process. Since the dilated convolutions support an exponential expansion of the receptive field without losing resolution and coverage, the obtained artifact features possess the multi-scale characteristic. Furthermore, to improve the effectiveness and accuracy of the training step, we employ a preprocessing method, which extracts image patches. Numerical experiments verify the out-performance of the proposed method compared with some conventional methods, such as Unet based deep learning,TV- and L0 -based optimization methods.
- Published
- 2020