2.5D dictionary learning based computed tomography reconstruction

Jiajia Luo; Haneda Eri; Ali Can; Sathish Ramani; Lin Fu; Bruno De Man

doi:10.1117/12.2223786

12 May 2016 2.5D dictionary learning based computed tomography reconstruction

Jiajia Luo, Haneda Eri, Ali Can, Sathish Ramani, Lin Fu, Bruno De Man

Proceedings Volume 9847, Anomaly Detection and Imaging with X-Rays (ADIX); 98470L (2016) https://doi.org/10.1117/12.2223786
Event: SPIE Defense + Security, 2016, Baltimore, MD, United States

Abstract

A computationally efficient 2.5D dictionary learning (DL) algorithm is proposed and implemented in the model- based iterative reconstruction (MBIR) framework for low-dose CT reconstruction. MBIR is based on the minimization of a cost function containing data-fitting and regularization terms to control the trade-off between data-fidelity and image noise. Due to the strong denoising performance of DL, it has previously been considered as a regularizer in MBIR, and both 2D and 3D DL implementations are possible. Compared to the 2D case, 3D DL keeps more spatial information and generates images with better quality although it requires more computation. We propose a novel 2.5D DL scheme, which leverages the computational advantage of 2D-DL, while attempting to maintain reconstruction quality similar to 3D-DL. We demonstrate the effectiveness of this new 2.5D DL scheme for MBIR in low-dose CT.

By applying the 2D DL method in three different orthogonal planes and calculating the sparse coefficients accordingly, much of the 3D spatial information can be preserved without incurring the computational penalty of the 3D DL method. For performance evaluation, we use baggage phantoms with different number of projection views. In order to quantitatively compare the performance of different algorithms, we use PSNR, SSIM and region based standard deviation to measure the noise level, and use the edge response to calculate the resolution. Experimental results with full view datasets show that the different DL based algorithms have similar performance and 2.5D DL has the best resolution. Results with sparse view datasets show that 2.5D DL outperforms both 2D and 3D DL in terms of noise reduction. We also compare the computational costs, and 2.5D DL shows strong advantage over 3D DL in both full-view and sparse-view cases.

Citation Download Citation

Jiajia Luo, Haneda Eri, Ali Can, Sathish Ramani, Lin Fu, and Bruno De Man "2.5D dictionary learning based computed tomography reconstruction", Proc. SPIE 9847, Anomaly Detection and Imaging with X-Rays (ADIX), 98470L (12 May 2016); https://doi.org/10.1117/12.2223786

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available