Share Email Print
cover

Proceedings Paper

Combined low-dose simulation and deep learning for CT denoising: application in ultra-low-dose chest CT
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In this study, we present a deep learning approach for denoising of ultra-low-dose chest CT by combining a low-dose simulation and convolutional neural network (CNN). A total of 18,456 anonymized regular-dose chest CT images were used for training of the CNN. The training CT images were fed into the low-dose simulation tool to generate a paired set of simulated low-dose CT and synthetic low-dose noise. A modified U-net model with 4×4 kernel size and five layers was trained with these paired datasets to predict the low-dose noise from the given low-dose CT image. Independent 10 ultra-low-dose chest CT scans at 120 kVp and 5 mAs were used for testing the denoising performance of the trained Unet. Denoised CT images were obtained by subtracting the predicted noise image from ultra-low-dose chest CT images. We evaluated the image quality by measuring noise standard deviation of soft tissue and with visual assessment of bronchial wall, lung fissure, and soft tissue. For comparison, the image quality was assessed on FBP, VEO, and deep learning-denoised FBP images. The visual assessment made with 4 points scale were 1.0, 3.4 and 4.0 in FBP, VEO, and deep learning-denoised FBP images. Image noise of soft tissue was 101±28HU, 20±5HU, 28±10HU in FBP, VEO, deep learning-denoised images.

Paper Details

Date Published: 27 March 2019
PDF: 5 pages
Proc. SPIE 11050, International Forum on Medical Imaging in Asia 2019, 110500E (27 March 2019); doi: 10.1117/12.2521539
Show Author Affiliations
Chulkyun Ahn, Seoul National Univ. (Korea, Republic of)
Changyong Heo, Seoul National Univ. (Korea, Republic of)
Jong Hyo Kim, Seoul National Univ. (Korea, Republic of)
Seoul National Univ. Hospital (Korea, Republic of)


Published in SPIE Proceedings Vol. 11050:
International Forum on Medical Imaging in Asia 2019
Feng Lin; Hiroshi Fujita; Jong Hyo Kim, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray