Abstract | ||
---|---|---|
The practical application of Computed Tomography (CT) faces the dilemma between higher image resolution and less X-ray exposure for patients, motivating the research on CT super-resolution (SR). In this paper, we apply state-of-the-art SR techniques to reconstruct CT images using two proposed advanced CT SR models based on Convolutional Neural Networks (CNNs) and residual learning: a single-slice CT SR network (S-CTSRN), and a multi-slice CT SR network (M-CTSRN). S-CTSRN improves the high-frequency feature extraction by incorporating the residual learning strategy, while M-CTSRN further utilizes the coherence between neighboring CT slices for better SR reconstruction. We evaluate both models on a large-scale CT dataset(1), and obtain competitive results both quantitatively and qualitatively. |
Year | Venue | Keywords |
---|---|---|
2017 | 2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | Super-resolution (SR), Medical Image Analysis, Computed Tomography (CT), Convolutional Neural Network (CNN), Residual Learning |
Field | DocType | ISSN |
Iterative reconstruction,Computer vision,Residual,Pattern recognition,Medical imaging,Convolutional neural network,Convolution,Computer science,Feature extraction,Coherence (physics),Artificial intelligence,Image resolution | Conference | 1522-4880 |
Citations | PageRank | References |
4 | 0.38 | 0 |
Authors | ||
9 |
Name | Order | Citations | PageRank |
---|---|---|---|
Haichao Yu | 1 | 16 | 3.02 |
Ding Liu | 2 | 611 | 32.97 |
Honghui Shi | 3 | 183 | 20.24 |
Haichao Yu | 4 | 82 | 2.87 |
Zhangyang Wang | 5 | 437 | 75.27 |
Xinchao Wang | 6 | 474 | 43.70 |
Brent Cross | 7 | 4 | 0.38 |
Matthew Bramler | 8 | 4 | 0.38 |
Thomas S. Huang | 9 | 27815 | 2618.42 |