Abstract | ||
---|---|---|
The development of fast and accurate image reconstruction algorithms is a central aspect of computed tomography. In this paper, we investigate this issue for the sparse data problem in photoacoustic tomography (PAT). We develop a direct and highly efficient reconstruction algorithm based on deep learning. In our approach, image reconstruction is performed with a deep convolutional neural network (CNN), whose weights are adjusted prior to the actual image reconstruction based on a set of training data. The proposed reconstruction approach can be interpreted as a network that uses the PAT filtered backprojection algorithm for the first layer, followed by the U-net architecture for the remaining layers. Actual image reconstruction with deep learning consists in one evaluation of the trained CNN, which does not require time-consuming solution of the forward and adjoint problems. At the same time, our numerical results demonstrate that the proposed deep learning approach reconstructs images with a quality comparable to state of the art iterative approaches for PAT from sparse data. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1080/17415977.2018.1518444 | INVERSE PROBLEMS IN SCIENCE AND ENGINEERING |
Keywords | Field | DocType |
Photoacoustic tomography, sparse data, image reconstruction, deep learning, convolutional neural networks, inverse problems | Iterative reconstruction,Training set,Photoacoustic tomography,Pattern recognition,Computer science,Convolutional neural network,Reconstruction algorithm,Computed tomography,Artificial intelligence,Deep learning,Sparse matrix | Journal |
Volume | Issue | ISSN |
27 | 7 | 1741-5977 |
Citations | PageRank | References |
16 | 0.92 | 28 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Stephan Antholzer | 1 | 16 | 1.26 |
Markus Haltmeier | 2 | 74 | 14.16 |
Johannes Schwab | 3 | 17 | 1.32 |