ADAPTIVE-NET: deep computed tomography reconstruction network with analytical domain transformation knowledge

Recently, the paradigm of computed tomography (CT) reconstruction has shifted as the deep learning technique evolves. In this study, we proposed a new convolutional neural network (called ADAPTIVE-NET) to perform CT image reconstruction directly from a sinogram by integrating the analytical domain t...

Full description

Saved in:
Bibliographic Details
Published in:Quantitative imaging in medicine and surgery Vol. 10; no. 2; p. 415
Main Authors: Ge, Yongshuai, Su, Ting, Zhu, Jiongtao, Deng, Xiaolei, Zhang, Qiyang, Chen, Jianwei, Hu, Zhanli, Zheng, Hairong, Liang, Dong
Format: Journal Article
Language:English
Published: China 01.02.2020
Subjects:
Computed tomography (CT)
convolutional neural network (CNN)
domain transformation
low dose CT reconstruction
CT reconstruction
ISSN:2223-4292
Online Access:Get more information
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recently, the paradigm of computed tomography (CT) reconstruction has shifted as the deep learning technique evolves. In this study, we proposed a new convolutional neural network (called ADAPTIVE-NET) to perform CT image reconstruction directly from a sinogram by integrating the analytical domain transformation knowledge. In the proposed ADAPTIVE-NET, a specific network layer with constant weights was customized to transform the sinogram onto the CT image domain via analytical back-projection. With this new framework, feature extractions were performed simultaneously on both the sinogram domain and the CT image domain. The Mayo low dose CT (LDCT) data was used to validate the new network. In particular, the new network was compared with the previously proposed residual encoder-decoder (RED)-CNN network. For each network, the mean square error (MSE) loss with and without VGG-based perceptual loss was compared. Furthermore, to evaluate the image quality with certain metrics, the noise correlation was quantified via the noise power spectrum (NPS) on the reconstructed LDCT for each method. CT images that have clinically relevant dimensions of 512×512 can be easily reconstructed from a sinogram on a single graphics processing unit (GPU) with moderate memory size (e.g., 11 GB) by ADAPTIVE-NET. With the same MSE loss function, the new network is able to generate better results than the RED-CNN. Moreover, the new network is able to reconstruct natural looking CT images with enhanced image quality if jointly using the VGG loss. The newly proposed end-to-end supervised ADAPTIVE-NET is able to reconstruct high-quality LDCT images directly from a sinogram.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:2223-4292
DOI:10.21037/qims.2019.12.12