Arbitrary Reduction of MRI Inter-slice Spacing Using Hierarchical Feature Conditional Diffusion

by   Xin Wang, et al.
ShanghaiTech University

Magnetic resonance (MR) images collected in 2D scanning protocols typically have large inter-slice spacing, resulting in high in-plane resolution but reduced through-plane resolution. Super-resolution techniques can reduce the inter-slice spacing of 2D scanned MR images, facilitating the downstream visual experience and computer-aided diagnosis. However, most existing super-resolution methods are trained at a fixed scaling ratio, which is inconvenient in clinical settings where MR scanning may have varying inter-slice spacings. To solve this issue, we propose Hierarchical Feature Conditional Diffusion (HiFi-Diff) for arbitrary reduction of MR inter-slice spacing. Given two adjacent MR slices and the relative positional offset, HiFi-Diff can iteratively convert a Gaussian noise map into any desired in-between MR slice. Furthermore, to enable fine-grained conditioning, the Hierarchical Feature Extraction (HiFE) module is proposed to hierarchically extract conditional features and conduct element-wise modulation. Our experimental results on the publicly available HCP-1200 dataset demonstrate the high-fidelity super-resolution capability of HiFi-Diff and its efficacy in enhancing downstream segmentation performance.


page 2

page 7

page 8


Arbitrary Reduction of MRI Slice Spacing Based on Local-Aware Implicit Representation

Magnetic resonance (MR) images are often acquired in 2D settings for rea...

FA-GAN: Fused Attentive Generative Adversarial Networks for MRI Image Super-Resolution

High-resolution magnetic resonance images can provide fine-grained anato...

Semi-Supervised Hybrid Spine Network for Segmentation of Spine MR Images

Automatic segmentation of vertebral bodies (VBs) and intervertebral disc...

MR Slice Profile Estimation by Learning to Match Internal Patch Distributions

To super-resolve the through-plane direction of a multi-slice 2D magneti...

Deep filter bank regression for super-resolution of anisotropic MR brain images

In 2D multi-slice magnetic resonance (MR) acquisition, the through-plane...

Fine Perceptive GANs for Brain MR Image Super-Resolution in Wavelet Domain

Magnetic resonance imaging plays an important role in computer-aided dia...

Medical Image Imputation from Image Collections

We present an algorithm for creating high resolution anatomically plausi...

Please sign up or login with your details

Forgot password? Click here to reset