TY - GEN
T1 - Computed tomography super-resolution using convolutional neural networks
AU - Yu, Haichao
AU - Liu, Ding
AU - Shi, Honghui
AU - Yu, Hanchao
AU - Wang, Zhangyang
AU - Wang, Xinchao
AU - Cross, Brent
AU - Bramler, Matthew
AU - Huang, Thomas S.
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/7/2
Y1 - 2017/7/2
N2 - 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 dataset1, and obtain competitive results both quantitatively and qualitatively.
AB - 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 dataset1, and obtain competitive results both quantitatively and qualitatively.
KW - Computed Tomography (CT)
KW - Convolutional Neural Network (CNN)
KW - Medical Image Analysis
KW - Residual Learning
KW - Super-resolution (SR)
UR - http://www.scopus.com/inward/record.url?scp=85045336920&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85045336920&partnerID=8YFLogxK
U2 - 10.1109/ICIP.2017.8297022
DO - 10.1109/ICIP.2017.8297022
M3 - Conference contribution
AN - SCOPUS:85045336920
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 3944
EP - 3948
BT - 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings
PB - IEEE Computer Society
T2 - 24th IEEE International Conference on Image Processing, ICIP 2017
Y2 - 17 September 2017 through 20 September 2017
ER -