Share Email Print
cover

Proceedings Paper

Computational-efficient cascaded neural network for CT image reconstruction
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In computed tomographic (CT) image reconstruction, image prior design and parameter tuning are important to improving the image reconstruction quality from noisy or undersampled projections. In recent years, the development of deep learning in medical image reconstruction made it possible to automatically find both suitable image priors and hyperparameters. By unrolling reconstruction algorithm to finite iterations and parameterizing prior functions and hyperparameters with deep artificial neural networks, all the parameters can be learned end-to-end to reduce the difference between reconstructed images and the training ground truth. Despite of its superior performance, the unrolling scheme suffers from huge memory consumption and computational cost in the training phase, made it hard to apply to 3 dimensional applications in CT, such as cone-beam CT, helical CT, tomosynthesis, etc. In this paper, we proposed a training-time computational-efficient cascaded neural network for CT image reconstruction, which had several sequentially trained cascades of networks for image quality improvement, connected with data fidelity correction steps. Each cascade was trained purely in the image domain, so that image patches could be utilized for training, which would significantly accelerate the training process and reduce memory consumption. The proposed method was fully scalable to 3D data with current hardware. Simulation of sparse-view sampling were done and demonstrated that the proposed method could achieve similar image quality compared to the state-of-the-art unrolled networks.

Paper Details

Date Published: 1 March 2019
PDF: 6 pages
Proc. SPIE 10948, Medical Imaging 2019: Physics of Medical Imaging, 109485Z (1 March 2019); doi: 10.1117/12.2511526
Show Author Affiliations
Dufan Wu, Massachusetts General Hospital (United States)
Harvard Medical School (United States)
Kyungsang Kim, Massachusetts General Hospital (United States)
Harvard Medical School (United States)
Georges El Fakhri, Massachusetts General Hospital (United States)
Harvard Medical School (United States)
Quanzheng Li, Massachusetts General Hospital (United States)
Harvard Medical School (United States)


Published in SPIE Proceedings Vol. 10948:
Medical Imaging 2019: Physics of Medical Imaging
Taly Gilat Schmidt; Guang-Hong Chen; Hilde Bosmans, Editor(s)

© SPIE. Terms of Use
Back to Top