TY - JOUR
T1 - Super-resolution reconstruction of neonatal brain magnetic resonance images via residual structured sparse representation
AU - Zhang, Yongqin
AU - Yap, Pew Thian
AU - Chen, Geng
AU - Lin, Weili
AU - Wang, Li
AU - Shen, Dinggang
N1 - Funding Information:
This work was supported in part by NIH grants (MH100217, MH108914), as well as an NIH grant (1U01MH110274) and the efforts of the UNC/UMN Baby Connectome Project Consortium. The authors declare no conflict of interest.
Funding Information:
This work was supported in part by NIH grants ( MH100217 , MH108914 ), as well as an NIH grant ( 1U01MH110274 ) and the efforts of the UNC/UMN Baby Connectome Project Consortium.
Publisher Copyright:
© 2019 Elsevier B.V.
PY - 2019/7
Y1 - 2019/7
N2 - Magnetic resonance images of neonates, compared with toddlers, exhibit lower signal-to-noise ratio and spatial resolution. In this paper, we propose a novel method for super-resolution reconstruction of neonate images with the help of toddler images, using residual-structured sparse representation with convex regularization. Specifically, we introduce a two-layer image representation, consisting of a base layer and a detail layer, to cater to signal variation across scanners and sites. The base layer consists of the smoothed version of the image obtained via Gaussian filtering. The detail layer is the difference between the original image and the base layer. High-frequency details in the detail layer are borrowed across subjects for super-resolution reconstruction. Experimental results on T1 and T2 images demonstrate that the proposed algorithm can recover fine anatomical structures, and generally outperform the state-of-the-art methods both qualitatively and quantitatively.
AB - Magnetic resonance images of neonates, compared with toddlers, exhibit lower signal-to-noise ratio and spatial resolution. In this paper, we propose a novel method for super-resolution reconstruction of neonate images with the help of toddler images, using residual-structured sparse representation with convex regularization. Specifically, we introduce a two-layer image representation, consisting of a base layer and a detail layer, to cater to signal variation across scanners and sites. The base layer consists of the smoothed version of the image obtained via Gaussian filtering. The detail layer is the difference between the original image and the base layer. High-frequency details in the detail layer are borrowed across subjects for super-resolution reconstruction. Experimental results on T1 and T2 images demonstrate that the proposed algorithm can recover fine anatomical structures, and generally outperform the state-of-the-art methods both qualitatively and quantitatively.
KW - Convex optimization
KW - Dictionary learning
KW - Magnetic resonance imaging
KW - Sparse representation
UR - http://www.scopus.com/inward/record.url?scp=85066918559&partnerID=8YFLogxK
U2 - 10.1016/j.media.2019.04.010
DO - 10.1016/j.media.2019.04.010
M3 - Article
C2 - 31029865
AN - SCOPUS:85066918559
VL - 55
SP - 76
EP - 87
JO - Medical Image Analysis
JF - Medical Image Analysis
SN - 1361-8415
ER -