Longitudinal Prediction of Infant Diffusion MRI Data Via Graph Convolutional Adversarial Networks

Overview

Journal IEEE Trans Med Imaging

Date 2019 Apr 17

PMID 30990424

Citations 10

Authors

Yoonmi Hong

Jaeil Kim

Geng Chen

Weili Lin

Pew-Thian Yap

Dinggang Shen

Affiliations

Soon will be listed here.

Abstract

Missing data is a common problem in longitudinal studies due to subject dropouts and failed scans. We present a graph-based convolutional neural network to predict missing diffusion MRI data. In particular, we consider the relationships between sampling points in the spatial domain and the diffusion wave-vector domain to construct a graph. We then use a graph convolutional network to learn the non-linear mapping from available data to missing data. Our method harnesses a multi-scale residual architecture with adversarial learning for prediction with greater accuracy and perceptual quality. Experimental results show that our method is accurate and robust in the longitudinal prediction of infant brain diffusion MRI data.

Citing Articles

Individualised prediction of longitudinal change in multimodal brain imaging.

Gong W, Beckmann C, Smith S Imaging Neurosci (Camb). 2025; 2:1-19.

PMID: 40046980 PMC: 11877422. DOI: 10.1162/imag_a_00215.

Acceleration of High-Resolution 3D MR Fingerprinting via a Graph Convolutional Network.

Cheng F, Chen Y, Zong X, Lin W, Shen D, Yap P Med Image Comput Comput Assist Interv. 2024; 12262:158-166.

PMID: 38504822 PMC: 10950303. DOI: 10.1007/978-3-030-59713-9_16.

Deep learning prediction of diffusion MRI data with microstructure-sensitive loss functions.

Chen G, Hong Y, Huynh K, Yap P Med Image Anal. 2023; 85:102742.

PMID: 36682154 PMC: 9974781. DOI: 10.1016/j.media.2023.102742.

Health Information Prediction System of Infant Sports Based on Deep Learning Network.

Qi J, Zhang J Biomed Res Int. 2022; 2022:4438251.

PMID: 35958812 PMC: 9357799. DOI: 10.1155/2022/4438251.

DLLNet: An Attention-Based Deep Learning Method for Dental Landmark Localization on High-Resolution 3D Digital Dental Models.

Lang Y, Deng H, Xiao D, Lian C, Kuang T, Gateno J Med Image Comput Comput Assist Interv. 2021; 12904:478-487.

PMID: 34927177 PMC: 8675275. DOI: 10.1007/978-3-030-87202-1_46.

References

Meng Y, Li G, Rekik I, Zhang H, Gao Y, Lin W . Can we predict subject-specific dynamic cortical thickness maps during infancy from birth?. Hum Brain Mapp. 2017; 38(6):2865-2874. PMC: 5426957. DOI: 10.1002/hbm.23555. View

Wolterink J, Leiner T, Viergever M, Isgum I . Generative Adversarial Networks for Noise Reduction in Low-Dose CT. IEEE Trans Med Imaging. 2017; 36(12):2536-2545. DOI: 10.1109/TMI.2017.2708987. View

Nie D, Wang L, Adeli E, Lao C, Lin W, Shen D . 3-D Fully Convolutional Networks for Multimodal Isointense Infant Brain Image Segmentation. IEEE Trans Cybern. 2018; 49(3):1123-1136. PMC: 6230311. DOI: 10.1109/TCYB.2018.2797905. View

Kim J, Chen G, Lin W, Yap P, Shen D . Graph-Constrained Sparse Construction of Longitudinal Diffusion-Weighted Infant Atlases. Med Image Comput Comput Assist Interv. 2018; 10433:49-56. PMC: 5858903. DOI: 10.1007/978-3-319-66182-7_6. View

Fan J, Cao X, Yap P, Shen D . BIRNet: Brain image registration using dual-supervised fully convolutional networks. Med Image Anal. 2019; 54:193-206. PMC: 6764428. DOI: 10.1016/j.media.2019.03.006. View

Rekik I, Li G, Wu G, Lin W, Shen D . Prediction of Infant MRI Appearance and Anatomical Structure Evolution using Sparse Patch-based Metamorphosis Learning Framework. Patch Based Tech Med Imaging (2015). 2017; 9467:197-204. PMC: 5382995. DOI: 10.1007/978-3-319-28194-0_24. View

Chen G, Dong B, Zhang Y, Shen D, Yap P . Neighborhood Matching for Curved Domains with Application to Denoising in Diffusion MRI. Med Image Comput Comput Assist Interv. 2018; 10433:629-637. PMC: 5860684. DOI: 10.1007/978-3-319-66182-7_72. View

Chen G, Zhang P, Li K, Wee C, Wu Y, Shen D . Improving Estimation of Fiber Orientations in Diffusion MRI Using Inter-Subject Information Sharing. Sci Rep. 2016; 6:37847. PMC: 5124958. DOI: 10.1038/srep37847. View

Gilmore J, Kang C, Evans D, Wolfe H, Smith J, Lieberman J . Prenatal and neonatal brain structure and white matter maturation in children at high risk for schizophrenia. Am J Psychiatry. 2010; 167(9):1083-91. PMC: 3105376. DOI: 10.1176/appi.ajp.2010.09101492. View

10.

Li G, Nie J, Wang L, Shi F, Lin W, Gilmore J . Mapping region-specific longitudinal cortical surface expansion from birth to 2 years of age. Cereb Cortex. 2012; 23(11):2724-33. PMC: 3792744. DOI: 10.1093/cercor/bhs265. View

11.

Shelhamer E, Long J, Darrell T . Fully Convolutional Networks for Semantic Segmentation. IEEE Trans Pattern Anal Mach Intell. 2016; 39(4):640-651. DOI: 10.1109/TPAMI.2016.2572683. View

12.

Michailovich O, Rathi Y, Dolui S . Spatially regularized compressed sensing for high angular resolution diffusion imaging. IEEE Trans Med Imaging. 2011; 30(5):1100-15. PMC: 3708319. DOI: 10.1109/TMI.2011.2142189. View

13.

Jones R, Palasis S, Grattan-Smith J . MRI of the neonatal brain: optimization of spin-echo parameters. AJR Am J Roentgenol. 2004; 182(2):367-72. DOI: 10.2214/ajr.182.2.1820367. View

14.

Nie D, Trullo R, Lian J, Wang L, Petitjean C, Ruan S . Medical Image Synthesis with Deep Convolutional Adversarial Networks. IEEE Trans Biomed Eng. 2018; 65(12):2720-2730. PMC: 6398343. DOI: 10.1109/TBME.2018.2814538. View

15.

Dhillon I, Guan Y, Kulis B . Weighted graph cuts without eigenvectors a multilevel approach. IEEE Trans Pattern Anal Mach Intell. 2007; 29(11):1944-57. DOI: 10.1109/TPAMI.2007.1115. View

16.

Li G, Wang L, Yap P, Wang F, Wu Z, Meng Y . Computational neuroanatomy of baby brains: A review. Neuroimage. 2018; 185:906-925. PMC: 6150852. DOI: 10.1016/j.neuroimage.2018.03.042. View

17.

Niethammer M, Huang Y, Vialard F . Geodesic regression for image time-series. Med Image Comput Comput Assist Interv. 2011; 14(Pt 2):655-62. PMC: 4339064. DOI: 10.1007/978-3-642-23629-7_80. View