Signal Enhancement of Low Magnetic Field Magnetic Resonance Image Using a Conventional- and Cyclic-Generative Adversarial Network Models With Unpaired Image Sets

In this study, the signal enhancement ratio of low-field magnetic resonance (MR) images was investigated using a deep learning-based algorithm. Unpaired image sets (0.06 Tesla and 1.5 Tesla MR images for different patients) were used in this study following three steps workflow. In the first step, t...

Full description

Bibliographic Details
Main Authors: Denis Yoo, Yuni Annette Choi, C. J. Rah, Eric Lee, Jing Cai, Byung Jun Min, Eun Ho Kim
Format: Article
Language:English
Published: Frontiers Media S.A. 2021-05-01
Series:Frontiers in Oncology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fonc.2021.660284/full
id doaj-67437f8daab6457381a6512acd252d2c
record_format Article
spelling doaj-67437f8daab6457381a6512acd252d2c2021-05-11T06:42:15ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2021-05-011110.3389/fonc.2021.660284660284Signal Enhancement of Low Magnetic Field Magnetic Resonance Image Using a Conventional- and Cyclic-Generative Adversarial Network Models With Unpaired Image SetsDenis Yoo0Yuni Annette Choi1C. J. Rah2Eric Lee3Jing Cai4Byung Jun Min5Eun Ho Kim6Artificial Intelligence Research Lab, Talos, Sheung Wan, Hong KongArtificial Intelligence Research Lab, Talos, Sheung Wan, Hong KongArtificial Intelligence Research Lab, Talos, Sheung Wan, Hong KongArtificial Intelligence Research Lab, Talos, Sheung Wan, Hong KongDepartment of Health Technology & Informatics, Hong Kong Polytechnic University, Hung Hom, Hong KongDepartment of Radiation Oncology, Chungbuk National University Hospital, Cheongju, South KoreaDepartment of Biochemistry, School of Medicine, Daegu Catholic University, Daegu, South KoreaIn this study, the signal enhancement ratio of low-field magnetic resonance (MR) images was investigated using a deep learning-based algorithm. Unpaired image sets (0.06 Tesla and 1.5 Tesla MR images for different patients) were used in this study following three steps workflow. In the first step, the deformable registration of a 1.5 Tesla MR image into a 0.06 Tesla MR image was performed to ensure that the shapes of the unpaired set matched. In the second step, a cyclic-generative adversarial network (GAN) was used to generate a synthetic MR image of the original 0.06 Tesla MR image based on the deformed or original 1.5 Tesla MR image. Finally, an enhanced 0.06 Tesla MR image could be generated using the conventional-GAN with the deformed or synthetic MR image. The results from the optimized flow and enhanced MR images showed significant signal enhancement of the anatomical view, especially in the nasal septum, inferior nasal choncha, nasopharyngeal fossa, and eye lens. The signal enhancement ratio, signal-to-noise ratio (SNR) and correlation factor between the original and enhanced MR images were analyzed for the evaluation of the image quality. A combined method using conventional- and cyclic-GANs is a promising approach for generating enhanced MR images from low-magnetic-field MR.https://www.frontiersin.org/articles/10.3389/fonc.2021.660284/fullconventional-GANcyclic-GANenhancement of MR imagelow magnetic fieldMagnetic Resonance Image (MRI)
collection DOAJ
language English
format Article
sources DOAJ
author Denis Yoo
Yuni Annette Choi
C. J. Rah
Eric Lee
Jing Cai
Byung Jun Min
Eun Ho Kim
spellingShingle Denis Yoo
Yuni Annette Choi
C. J. Rah
Eric Lee
Jing Cai
Byung Jun Min
Eun Ho Kim
Signal Enhancement of Low Magnetic Field Magnetic Resonance Image Using a Conventional- and Cyclic-Generative Adversarial Network Models With Unpaired Image Sets
Frontiers in Oncology
conventional-GAN
cyclic-GAN
enhancement of MR image
low magnetic field
Magnetic Resonance Image (MRI)
author_facet Denis Yoo
Yuni Annette Choi
C. J. Rah
Eric Lee
Jing Cai
Byung Jun Min
Eun Ho Kim
author_sort Denis Yoo
title Signal Enhancement of Low Magnetic Field Magnetic Resonance Image Using a Conventional- and Cyclic-Generative Adversarial Network Models With Unpaired Image Sets
title_short Signal Enhancement of Low Magnetic Field Magnetic Resonance Image Using a Conventional- and Cyclic-Generative Adversarial Network Models With Unpaired Image Sets
title_full Signal Enhancement of Low Magnetic Field Magnetic Resonance Image Using a Conventional- and Cyclic-Generative Adversarial Network Models With Unpaired Image Sets
title_fullStr Signal Enhancement of Low Magnetic Field Magnetic Resonance Image Using a Conventional- and Cyclic-Generative Adversarial Network Models With Unpaired Image Sets
title_full_unstemmed Signal Enhancement of Low Magnetic Field Magnetic Resonance Image Using a Conventional- and Cyclic-Generative Adversarial Network Models With Unpaired Image Sets
title_sort signal enhancement of low magnetic field magnetic resonance image using a conventional- and cyclic-generative adversarial network models with unpaired image sets
publisher Frontiers Media S.A.
series Frontiers in Oncology
issn 2234-943X
publishDate 2021-05-01
description In this study, the signal enhancement ratio of low-field magnetic resonance (MR) images was investigated using a deep learning-based algorithm. Unpaired image sets (0.06 Tesla and 1.5 Tesla MR images for different patients) were used in this study following three steps workflow. In the first step, the deformable registration of a 1.5 Tesla MR image into a 0.06 Tesla MR image was performed to ensure that the shapes of the unpaired set matched. In the second step, a cyclic-generative adversarial network (GAN) was used to generate a synthetic MR image of the original 0.06 Tesla MR image based on the deformed or original 1.5 Tesla MR image. Finally, an enhanced 0.06 Tesla MR image could be generated using the conventional-GAN with the deformed or synthetic MR image. The results from the optimized flow and enhanced MR images showed significant signal enhancement of the anatomical view, especially in the nasal septum, inferior nasal choncha, nasopharyngeal fossa, and eye lens. The signal enhancement ratio, signal-to-noise ratio (SNR) and correlation factor between the original and enhanced MR images were analyzed for the evaluation of the image quality. A combined method using conventional- and cyclic-GANs is a promising approach for generating enhanced MR images from low-magnetic-field MR.
topic conventional-GAN
cyclic-GAN
enhancement of MR image
low magnetic field
Magnetic Resonance Image (MRI)
url https://www.frontiersin.org/articles/10.3389/fonc.2021.660284/full
work_keys_str_mv AT denisyoo signalenhancementoflowmagneticfieldmagneticresonanceimageusingaconventionalandcyclicgenerativeadversarialnetworkmodelswithunpairedimagesets
AT yuniannettechoi signalenhancementoflowmagneticfieldmagneticresonanceimageusingaconventionalandcyclicgenerativeadversarialnetworkmodelswithunpairedimagesets
AT cjrah signalenhancementoflowmagneticfieldmagneticresonanceimageusingaconventionalandcyclicgenerativeadversarialnetworkmodelswithunpairedimagesets
AT ericlee signalenhancementoflowmagneticfieldmagneticresonanceimageusingaconventionalandcyclicgenerativeadversarialnetworkmodelswithunpairedimagesets
AT jingcai signalenhancementoflowmagneticfieldmagneticresonanceimageusingaconventionalandcyclicgenerativeadversarialnetworkmodelswithunpairedimagesets
AT byungjunmin signalenhancementoflowmagneticfieldmagneticresonanceimageusingaconventionalandcyclicgenerativeadversarialnetworkmodelswithunpairedimagesets
AT eunhokim signalenhancementoflowmagneticfieldmagneticresonanceimageusingaconventionalandcyclicgenerativeadversarialnetworkmodelswithunpairedimagesets
_version_ 1721452914435686400