TY - GEN
T1 - Variational Deep Learning for Low-Dose Computed Tomography
AU - Kobler, Erich
AU - Muckley, Matthew
AU - Chen, Baiyu
AU - Knoll, Florian
AU - Hammernik, Kerstin
AU - Pock, Thomas
AU - Sodickson, Daniel
AU - Otazo, Ricardo
N1 - Funding Information:
We acknowledge support from the Austrian Science Fund (FWF) under the START project BIVISION, No. Y729, the European Research Council under the Horizon 2020 program, ERC starting grant HOMOVIS, No. 640156. and the National Institutes of Health (NIH) grants U01-EB018760 and P41-EB017183.
Publisher Copyright:
© 2018 IEEE.
PY - 2018/9/10
Y1 - 2018/9/10
N2 - In this work, we propose a learning-based variational network (VN) approach for reconstruction of low-dose 3D computed tomography data. We focus on two methods to decrease the radiation dose: (1) x-ray tube current reduction, which reduces the signal-to-noise ratio, and (2) x-ray beam interruption, which undersamples data and results in images with aliasing artifacts. While the learned VN denoises the current-reduced images in the first case, it reconstructs the undersampled data in the second case. Different VNs for denoising and reconstruction are trained on a single clinical 3D abdominal data set. The VNs are compared against state-of-the-art model-based denoising and sparse reconstruction techniques on a different clinical abdominal 3D data set with 4-fold dose reduction. Our results suggest that the proposed VNs enable higher radiation dose reductions and/or increase the image quality for a given dose.
AB - In this work, we propose a learning-based variational network (VN) approach for reconstruction of low-dose 3D computed tomography data. We focus on two methods to decrease the radiation dose: (1) x-ray tube current reduction, which reduces the signal-to-noise ratio, and (2) x-ray beam interruption, which undersamples data and results in images with aliasing artifacts. While the learned VN denoises the current-reduced images in the first case, it reconstructs the undersampled data in the second case. Different VNs for denoising and reconstruction are trained on a single clinical 3D abdominal data set. The VNs are compared against state-of-the-art model-based denoising and sparse reconstruction techniques on a different clinical abdominal 3D data set with 4-fold dose reduction. Our results suggest that the proposed VNs enable higher radiation dose reductions and/or increase the image quality for a given dose.
KW - Compressed sensing
KW - Computed tomography
KW - Machine learning
KW - Medical imaging
KW - Variational networks
UR - http://www.scopus.com/inward/record.url?scp=85054201849&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85054201849&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2018.8462312
DO - 10.1109/ICASSP.2018.8462312
M3 - Conference contribution
AN - SCOPUS:85054201849
SN - 9781538646588
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 6687
EP - 6691
BT - 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018
Y2 - 15 April 2018 through 20 April 2018
ER -