Abstract
The spatial resolution of magnetic resonance imaging (MRI) is often limited due to several reasons, including a short data acquisition time. Several advanced interpolation-based image upsampling algorithms have been developed to increase the resolution of MR images. These methods estimate the voxel intensity in a high-resolution (HR) image by a weighted combination of voxels in the original low-resolution (LR) MR image. As these methods fall into the zero-order point estimation framework, they only include a local constant approximation of the image voxel and hence cannot fully represent the underlying image structure(s). To this end, we extend the existing zero-order point estimation to higher orders of regression, allowing us to approximate a mapping function between local LR-HR image patches by a polynomial function. Extensive experiments on open-access MR image datasets and actual clinical MR images demonstrate that our algorithm can maintain sharp edges and preserve fine details, while the current state-of-the-art algorithms remain prone to some visual artifacts such as blurring and staircasing artifacts.
Highlights
Magnetic resonance (MR) imaging is widely used to assess brain diseases, spinal disorders, cardiac function, and musculoskeletal injuries
A new high-order regression-based framework was proposed in this paper for a high quality MR image upsampling process
Prompted by several recently popular interpolationbased image upsampling methods in MR imaging [2, 5,6,7,8,9,10,11], the proposed method first concludes that these methods all belonged to a zeroth-order regression framework, which would jeopardize the recovery of image’s fine details such as the laminar shape of brain structures
Summary
Magnetic resonance (MR) imaging is widely used to assess brain diseases, spinal disorders, cardiac function, and musculoskeletal injuries. Traditional interpolation methods adopted in natural image processing field such as spline interpolation can be directly employed These methods use fixed interpolation coefficients and only select spatially nearby sampling voxels, thereby producing images with blurred edges and staircasing artifacts. To reduce these unwanted artifacts, some sophisticated interpolation methods [2, 5,6,7,8,9,10,11] have been recently proposed in biomedical image processing. To further strengthen local consistency in the proposed method, a patch-based image reconstruction scheme is utilized rather than voxelby-voxel scheme as other interpolation methods do With these two salient features, the proposed method successfully enhances high-frequency details in final results.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
