Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Feb;47(2):422-430.
doi: 10.1002/mp.13918. Epub 2019 Dec 29.

Synthesizing images from multiple kernels using a deep convolutional neural network

Andrew D Missert  1 , Lifeng Yu  1 , Shuai Leng  1 , Joel G Fletcher  1 , Cynthia H McCollough  1
Affiliations

Synthesizing images from multiple kernels using a deep convolutional neural network

Andrew D Missert et al. Med Phys. 2020 Feb.

Abstract

Purpose: Filtering measured projections with a particular convolutional kernel is an essential step in analytic reconstruction of computed tomography (CT) images. A tradeoff between noise and spatial resolution exists for different choices of reconstruction kernel. In a clinical setting, this often requires producing multiple images reconstructed with different kernels for a single CT exam, which increases the burden of computation, networking, archival, and reading. We address this problem by training a deep convolutional neural network (CNN) to synthesize multiple input images into a single output image which exhibits low noise while also preserving features in images reconstructed with the sharpest kernels.

Methods: A CNN architecture consisting of repeated blocks of residual units containing a total of 20 convolutional layers was used to combine features. The CNN inputs consisted of two images produced with different reconstruction kernels, one smooth and one sharp, which were stacked in the channel dimension. The network was trained using supervised learning with both full-dose and simulated quarter-dose abdominal CT images. After training, the performance was evaluated using a reserved set of full-dose scans that were not used for network optimization. Noise reduction performance was measured by comparing root mean square (RMS) measurements in uniform regions. Spatial resolution was compared using line profiles of anatomic features.

Results: For the regions tested, the synthetic images feature noise levels slightly below those of the smooth input images, while maintaining the resolution of anatomic details found in the sharp input images.

Conclusions: A deep CNN can be used combine features from CT images reconstructed with different kernels to produce a single synthesized image series that exhibits both low noise and high spatial resolution. This approach has implications for improving image quality, reducing radiation dose, and simplifying the clinical workflow for CT imaging.

Keywords: convolutional neural networks; deep learning; image processing; noise reduction.

PubMed Disclaimer

References

    1. Weiss KL, Cornelius RS, Greeley AL, et al. Hybrid convolution kernel: optimized CT of the head, neck, and spine. AJR Am J Roentgenol. 2011;196:403-406.
    1. Hofmann C, Sawall S, Knaup M, Kachelriess M. Alpha image reconstruction (AIR): a new iterative CT image reconstruction approach using voxel-wise alpha blending. Med Phys. 2014;41:061914.
    1. Chen H, Zhang Y, Kalra MK, et al. Low-dose CT with a residual encoder-eecoder convolutional neural network. IEEE Trans Med Imaging. 2017;36:2524-2535.
    1. Shan H, Padole A, Homayounieh F, et al. Comptetitive performance of a modularized deep neural network compared to commercial algorithms for low-dose CT image reconstructoin. Nat Mach Intell. 2019;1:269.
    1. Missert AD, Lifeng Y, Leng S, Fletcher JG, McCollough CH. Noise subtraction for CT images acquired at multiple dose levels using a deep convolutional neural network. AAPM Annual Meeting; Jul 29 - Aug 02, 2018; Nashville, TN, USA.

MeSH terms

Grants and funding

LinkOut - more resources