Search: onr:"swepub:oai:DiVA.org:kth-231206" >
Learned Primal-Dual...
Learned Primal-Dual Reconstruction
-
- Adler, Jonas (author)
- KTH,Matematik (Avd.),Elekta Instrument AB, Stockholm, Sweden
-
- Öktem, Ozan, 1969- (author)
- KTH,Matematik (Avd.)
-
KTH Matematik (Avd) (creator_code:org_t)
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 2018
- 2018
- English.
-
In: IEEE Transactions on Medical Imaging. - : IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC. - 0278-0062 .- 1558-254X. ; 37:6, s. 1322-1332
- Related links:
-
https://urn.kb.se/re...
-
show more...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- We propose the Learned Primal-Dual algorithm for tomographic reconstruction. The algorithm accounts for a (possibly non-linear) forward operator in a deep neural network by unrolling a proximal primal-dual optimization method, but where the proximal operators have been replaced with convolutional neural networks. The algorithm is trained end-to-end, working directly from raw measured data and it does not depend on any initial reconstruction such as filtered back-projection (FBP). We compare performance of the proposed method on low dose computed tomography reconstruction against FBP, total variation (TV), and deep learning based post-processing of FBP. For the Shepp-Logan phantom we obtain >6 dB peak signal to noise ratio improvement against all compared methods. For human phantoms the corresponding improvement is 6.6 dB over TV and 2.2 dB over learned post-processing along with a substantial improvement in the structural similarity index. Finally, our algorithm involves only ten forward-back-projection computations, making the method feasible for time critical clinical applications.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)
Keyword
- Inverse problems
- tomography
- deep learning
- primal-dual
- optimization
Publication and Content Type
- ref (subject category)
- art (subject category)
Find in a library
To the university's database