Deep Learning Computed Tomography: Learning Projection-Domain Weights From Image Domain in Limited Angle Problems
Top Cited Papers
- 7 May 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 37 (6), 1454-1463
- https://doi.org/10.1109/tmi.2018.2833499
Abstract
In this paper, we present a new deep learning framework for 3-D tomographic reconstruction. To this end, we map filtered back-projection-type algorithms to neural networks. However, the back-projection cannot be implemented as a fully connected layer due to its memory requirements. To overcome this problem, we propose a new type of cone-beam backprojection layer, efficiently calculating the forward pass. We derive this layer’s backward pass as a projection operation. Unlike most deep learning approaches for reconstruction, our new layer permits joint optimization of correction steps in volume and projection domain. Evaluation is performed numerically on a public dataset in a limited angle setting showing a consistent improvement over analytical algorithms while keeping the same computational test-time complexity by design. In the region of interest, the peak signal-to-noise ratio has increased by 23%. In addition, we show that the learned algorithm can be interpreted using known concepts from cone beam reconstruction: the network is able to automatically learn strategies such as compensation weights and apodization windows.Keywords
Funding Information
- National Institute of Biomedical Imaging and Bioengineering (EB017095, EB017185)
This publication has 20 references indexed in Scilit:
- The structure of optimal parameters for image restoration problemsJournal of Mathematical Analysis and Applications, 2016
- Improving Filtered Backprojection Reconstruction by Data-Dependent FilteringIEEE Transactions on Image Processing, 2014
- Fast Tomographic Reconstruction From Limited Data Using Artificial Neural NetworksIEEE Transactions on Image Processing, 2013
- Image Quality Assessment: From Error Visibility to Structural SimilarityIEEE Transactions on Image Processing, 2004
- Image reconstruction from fan-beam projections on less than a short scanPhysics in Medicine & Biology, 2002
- Theoretically Exact Filtered Backprojection-Type Inversion Algorithm for Spiral CTSIAM Journal on Applied Mathematics, 2002
- Unmatched projector/backprojector pairs in an iterative reconstruction algorithmIEEE Transactions on Medical Imaging, 2000
- A cone-beam reconstruction algorithm using shift-variant filtering and cone-beam backprojectionIEEE Transactions on Medical Imaging, 1994
- An artificial neural network for SPECT image reconstructionIEEE Transactions on Medical Imaging, 1991
- Optimal short scan convolution reconstruction for fan beam CTMedical Physics, 1982