Abstract

The detailed anatomical information of the brain provided by 3D magnetic resonance imaging (MRI) enables various neuroscience research. However, due to the long scan time for 3D MR images, 2D images are mainly obtained in clinical environments. The purpose of this study is to generate 3D images from a sparsely sampled 2D images using an inpainting deep neural network that has a U-net-like structure and DenseNet sub-blocks. To train the network, not only fidelity loss but also perceptual loss based on the VGG network were considered. Various methods were used to assess the overall similarity between the inpainted and original 3D data. In addition, morphological analyzes were performed to investigate whether the inpainted data produced local features similar to the original 3D data. The diagnostic ability using the inpainted data was also evaluated by investigating the pattern of morphological changes in disease groups. Brain anatomy details were efficiently recovered by the proposed neural network. In voxel-based analysis to assess gray matter volume and cortical thickness, differences between the inpainted data and the original 3D data were observed only in small clusters. The proposed method will be useful for utilizing advanced neuroimaging techniques with 2D MRI data.

Details

Title
Deep learning-Based 3D inpainting of brain MR images
Author
Kang, Seung Kwan 1 ; Shin, Seong A 1 ; Seo Seongho 2 ; Byun, Min Soo 3 ; Lee Dong Young 4 ; Kim, Yu Kyeong 5 ; Lee, Dong Soo 6 ; Lee Jae Sung 7 

 Seoul National University College of Medicine, Department of Biomedical Sciences, Seoul, Korea (GRID:grid.31501.36) (ISNI:0000 0004 0470 5905) 
 Pai Chai University, Department of Electronic Engineering, Daejeon, Korea (GRID:grid.412439.9) (ISNI:0000 0004 0533 1423) 
 Seoul National University, Institute of Human Behavioral Medicine, Medical Research Center, Seoul, Korea (GRID:grid.31501.36) (ISNI:0000 0004 0470 5905) 
 Seoul National University College of Medicine, Department of Psychiatry, Seoul, Korea (GRID:grid.31501.36) (ISNI:0000 0004 0470 5905) 
 SMG-SNU Boramae Medical Center, Department of Nuclear Medicine, Seoul, Korea (GRID:grid.412479.d) 
 Seoul National University College of Medicine, Department of Nuclear Medicine, Seoul, Republic of Korea (GRID:grid.31501.36) (ISNI:0000 0004 0470 5905) 
 Seoul National University College of Medicine, Department of Biomedical Sciences, Seoul, Korea (GRID:grid.31501.36) (ISNI:0000 0004 0470 5905); Seoul National University College of Medicine, Department of Nuclear Medicine, Seoul, Republic of Korea (GRID:grid.31501.36) (ISNI:0000 0004 0470 5905) 
Publication year
2021
Publication date
2021
Publisher
Nature Publishing Group
e-ISSN
20452322
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
2478662100
Copyright
© The Author(s) 2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.