3D Super Resolution for Non-Isotropic Medical Image Through Multi-Input 3D ResUnet

Fluid-attenuated inversion recovery imaging (FLAIR) is a magnetic resonance (MR) method that is frequently utilized to diagnose brain lesions. However, it usually provides transverse section imaging in high resolution but with very low resolution in the other axis. This non-isotropy huddles its wide...

Full description

Saved in:
Bibliographic Details
Published in2023 International Joint Conference on Neural Networks (IJCNN) pp. 1 - 6
Main Authors Seo, Youjin, Jeong, ByeongChang, Yoon, Yeji, Kim, Daegyeom, Min, JuHong, Han, Cheol E.
Format Conference Proceeding
LanguageEnglish
Published IEEE 18.06.2023
Subjects
Fluid-attenuated inversion recovery (FLAIR) imaging
Lesions
Machine learning
Magnetic resonance
Medical diagnostic imaging
multi-input 3D ResUnet
non-isotropy
Solid modeling
Super Resolution
Superresolution
Three-dimensional displays
Online AccessGet full text

Cover

More Information
Summary:Fluid-attenuated inversion recovery imaging (FLAIR) is a magnetic resonance (MR) method that is frequently utilized to diagnose brain lesions. However, it usually provides transverse section imaging in high resolution but with very low resolution in the other axis. This non-isotropy huddles its wide utilization in research including machine learning. In this study, we applied a deep-learning based super resolution (SR) technique to convert non-isotropic FLAIR images into isotropic one. We proposed a multi-input 3D ResUnet that uses both FLAIR and T1-weighted MR images as its inputs. As a result, our proposed model successfully reconstructed isotropic FLAIR images (SSIM: 0.9947 \pm 0.0009) , and out-performed the FLAIR only single-input 3D ResUnet.
ISSN:2161-4407
DOI:10.1109/IJCNN54540.2023.10191100