TY - JOUR
T1 - Longitudinally Guided Super-Resolution of Neonatal Brain Magnetic Resonance Images
AU - Zhang, Yongqin
AU - Shi, Feng
AU - Cheng, Jian
AU - Wang, Li
AU - Yap, Pew Thian
AU - Shen, Dinggang
N1 - Funding Information:
Manuscript received October 10, 2017; accepted December 18, 2017. Date of publication January 9, 2018; date of current version January 15, 2019. This work was supported in part by NIH under Grant EB006733, Grant EB008374, Grant MH100217, Grant MH108914, Grant AG041721, Grant AG049371, Grant AG042599, Grant DE022676, Grant CA206100, Grant AG053867, Grant EB022880, and Grant NS093842, in part by the National Natural Science Foundation of China under Grant 61375112, in part by the Natural Science Basic Research Plan in Shaanxi Province of China under Program 2016JQ6068, and in part by the Scientific Research Program Funded by Shaanxi Provincial Education Department under Program 16JK1762. This paper was recommended by Associate Editor Y. Yuan. (Yongqin Zhang and Feng Shi contributed equally to this work.) (Corresponding author: Dinggang Shen.) Y. Zhang, L. Wang, and P.-T. Yap are with the Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599 USA.
Publisher Copyright:
© 2013 IEEE.
PY - 2019/2
Y1 - 2019/2
N2 - Neonatal magnetic resonance (MR) images typically have low spatial resolution and insufficient tissue contrast. Interpolation methods are commonly used to upsample the images for the subsequent analysis. However, the resulting images are often blurry and susceptible to partial volume effects. In this paper, we propose a novel longitudinally guided super-resolution (SR) algorithm for neonatal images. This is motivated by the fact that anatomical structures evolve slowly and smoothly as the brain develops after birth. We propose a strategy involving longitudinal regularization, similar to bilateral filtering, in combination with low-rank and total variation constraints to solve the ill-posed inverse problem associated with image SR. Experimental results on neonatal MR images demonstrate that the proposed algorithm recovers clear structural details and outperforms state-of-the-art methods both qualitatively and quantitatively.
AB - Neonatal magnetic resonance (MR) images typically have low spatial resolution and insufficient tissue contrast. Interpolation methods are commonly used to upsample the images for the subsequent analysis. However, the resulting images are often blurry and susceptible to partial volume effects. In this paper, we propose a novel longitudinally guided super-resolution (SR) algorithm for neonatal images. This is motivated by the fact that anatomical structures evolve slowly and smoothly as the brain develops after birth. We propose a strategy involving longitudinal regularization, similar to bilateral filtering, in combination with low-rank and total variation constraints to solve the ill-posed inverse problem associated with image SR. Experimental results on neonatal MR images demonstrate that the proposed algorithm recovers clear structural details and outperforms state-of-the-art methods both qualitatively and quantitatively.
KW - Guided bilateral filtering (GBF)
KW - image interpolation
KW - image super-resolution (SR)
KW - magnetic resonance imaging (MRI)
KW - total variation (TV)
UR - http://www.scopus.com/inward/record.url?scp=85041178714&partnerID=8YFLogxK
U2 - 10.1109/TCYB.2017.2786161Y
DO - 10.1109/TCYB.2017.2786161Y
M3 - Article
C2 - 29994176
AN - SCOPUS:85041178714
VL - 49
SP - 662
EP - 674
JO - IEEE Transactions on Cybernetics
JF - IEEE Transactions on Cybernetics
SN - 2168-2267
IS - 2
M1 - 8252756
ER -