Abstract
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.
| Original language | English |
|---|---|
| Journal | IEEE Transactions on Cybernetics |
| DOIs | |
| Publication status | Accepted/In press - 2018 Jan 8 |
Fingerprint
Keywords
- Brain
- Guided bilateral filtering (GBF)
- image interpolation
- Image reconstruction
- image super-resolution (SR)
- magnetic resonance imaging (MRI)
- Pediatrics
- Spatial resolution
- total variation (TV)
ASJC Scopus subject areas
- Software
- Control and Systems Engineering
- Information Systems
- Human-Computer Interaction
- Computer Science Applications
- Electrical and Electronic Engineering
Cite this
Longitudinally Guided Super-Resolution of Neonatal Brain Magnetic Resonance Images. / Zhang, Yongqin; Shi, Feng; Cheng, Jian; Wang, Li; Yap, Pew Thian; Shen, Dinggang.
In: IEEE Transactions on Cybernetics, 08.01.2018.Research output: Contribution to journal › Article
}
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
PY - 2018/1/8
Y1 - 2018/1/8
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 - Brain
KW - Guided bilateral filtering (GBF)
KW - image interpolation
KW - Image reconstruction
KW - image super-resolution (SR)
KW - magnetic resonance imaging (MRI)
KW - Pediatrics
KW - Spatial resolution
KW - total variation (TV)
UR - http://www.scopus.com/inward/record.url?scp=85041178714&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85041178714&partnerID=8YFLogxK
U2 - 10.1109/TCYB.2017.2786161
DO - 10.1109/TCYB.2017.2786161
M3 - Article
C2 - 29994176
AN - SCOPUS:85041178714
JO - IEEE Transactions on Cybernetics
JF - IEEE Transactions on Cybernetics
SN - 2168-2267
ER -