|Table of Contents|

Deep learning-based 3D reconstruction of CT tomography from a single projection(PDF)

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

Issue:
2021年第10期
Page:
1223-1228
Research Field:
医学影像物理
Publishing date:

Info

Title:
Deep learning-based 3D reconstruction of CT tomography from a single projection
Author(s):
ZHANG Xinyang1;  2;  3;  4;  HE Pengbo1;  2;  3;  4;  LIU Xinguo1;  2;  3;  4;  DAI Zhongying1;  2;  3;  4;  MA Yuanyuan1;  2;  3;  4;  SHEN Guosheng1;  2;  3;  4;  ZHANG Hui1; 2; 3; 4;  CHEN Weiqiang1;  2;  3;  4;  LI Qiang1;  2;  3;  4
1. Institute of Modern Physics, Chinese Academy of Sciences, Lanzhou 730000, China 2. Key Laboratory of Heavy Ion Radiation Biology and Medicine of Chinese Academy of Sciences, Lanzhou 730000, China 3. Key Laboratory of Basic Research on Heavy Ion Radiation Application in Medicine, Lanzhou 730000, China 4. School of Nuclear Science and Technology, University of Chinese Academy of Sciences, Beijing 100049, China
Keywords:
Keywords: deep learning single-view computed tomography three-dimensional reconstruction convolutional neural network sparse projection imaging
PACS:
R318
DOI:
DOI:10.3969/j.issn.1005-202X.2021.10.008
Abstract:
Abstract: Objective To propose a deep learning-based method for the 3D reconstruction of single-view computed tomography (CT) image, thereby realizing the 3D reconstruction of CT image for different patients under the condition of reducing the amount of data collection and decreasing imaging dose. Methods After the CT images of different patients were processed by data enhancement, and the corresponding digitally reconstructed radiograph (DRR) was obtained by simulation, data normalization was carried out. A neural network model universally suitable for different patients was established by training the pre-processed data using deep neural networks, and the trained neural network model was then deployed on the test dataset. Finally, the reconstruction results were evaluated using mean absolute error, root mean square error, structural similarity and peak signal noise ratio. Results The qualitative and quantitative analyses showed that the 3D CT images with high quality could be constructed by the proposed method using a single-view 2D image of different patients, with mean absolute error, root mean square error, structural similarity and peak signal noise ratio of 0.006, 0.079, 0.982 and 38.424 dB, respectively. Additionally, compared with the situation specific to a single patient, the proposed method greatly increased the reconstruction speed and save 70% of model training time. Conclusion The neural network model established in the study can reconstruct the corresponding 3D CT images using single-view 2D image of different patients. The study may play an important role in simplifying clinical imaging devices and image guidance in radiotherapy.

References:

Memo

Memo:
-
Last Update: 2021-10-29