Comparison of Supervised and Unsupervised Deep Learning Methods for Medical Image Synthesis between Computed Tomography and Magnetic Resonance Images
Joint Authors
Xiong, Jing
Li, Wen
Li, Yafen
Xie, Yaoqin
Xia, Jun
Source
Issue
Vol. 2020, Issue 2020 (31 Dec. 2020), pp.1-9, 9 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2020-11-05
Country of Publication
Egypt
No. of Pages
9
Main Subjects
Abstract EN
Cross-modality medical image synthesis between magnetic resonance (MR) images and computed tomography (CT) images has attracted increasing attention in many medical imaging area.
Many deep learning methods have been used to generate pseudo-MR/CT images from counterpart modality images.
In this study, we used U-Net and Cycle-Consistent Adversarial Networks (CycleGAN), which were typical networks of supervised and unsupervised deep learning methods, respectively, to transform MR/CT images to their counterpart modality.
Experimental results show that synthetic images predicted by the proposed U-Net method got lower mean absolute error (MAE), higher structural similarity index (SSIM), and peak signal-to-noise ratio (PSNR) in both directions of CT/MR synthesis, especially in synthetic CT image generation.
Though synthetic images by the U-Net method has less contrast information than those by the CycleGAN method, the pixel value profile tendency of the synthetic images by the U-Net method is closer to the ground truth images.
This work demonstrated that supervised deep learning method outperforms unsupervised deep learning method in accuracy for medical tasks of MR/CT synthesis.
American Psychological Association (APA)
Li, Yafen& Li, Wen& Xiong, Jing& Xia, Jun& Xie, Yaoqin. 2020. Comparison of Supervised and Unsupervised Deep Learning Methods for Medical Image Synthesis between Computed Tomography and Magnetic Resonance Images. BioMed Research International،Vol. 2020, no. 2020, pp.1-9.
https://search.emarefa.net/detail/BIM-1134563
Modern Language Association (MLA)
Li, Yafen…[et al.]. Comparison of Supervised and Unsupervised Deep Learning Methods for Medical Image Synthesis between Computed Tomography and Magnetic Resonance Images. BioMed Research International No. 2020 (2020), pp.1-9.
https://search.emarefa.net/detail/BIM-1134563
American Medical Association (AMA)
Li, Yafen& Li, Wen& Xiong, Jing& Xia, Jun& Xie, Yaoqin. Comparison of Supervised and Unsupervised Deep Learning Methods for Medical Image Synthesis between Computed Tomography and Magnetic Resonance Images. BioMed Research International. 2020. Vol. 2020, no. 2020, pp.1-9.
https://search.emarefa.net/detail/BIM-1134563
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1134563