Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Complex Swin Transformer for Accelerating Enhanced SMWI Reconstruction

Muhammad Usman, Sung-Min Gho

TL;DR

This research enables high-quality SMWI generation from reduced k-space data, accelerating scan times while preserving diagnostic detail, and could significantly enhance SMWI's clinical application for Parkinson's Disease and support faster, more efficient neuroimaging workflows.

Abstract

Susceptibility Map Weighted Imaging (SMWI) is an advanced magnetic resonance imaging technique used to detect nigral hyperintensity in Parkinsons disease. However, full resolution SMWI acquisition is limited by long scan times. Efficient reconstruction methods are therefore required to generate high quality SMWI from reduced k space data while preserving diagnostic relevance. In this work, we propose a complex valued Swin Transformer based network for super resolution reconstruction of multi echo MRI data. The proposed method reconstructs high quality SMWI images from low resolution k space inputs. Experimental results demonstrate that the method achieves a structural similarity index of 0.9116 and a mean squared error of 0.076 when reconstructing SMWI from 256 by 256 k space data, while maintaining critical diagnostic features. This approach enables high quality SMWI reconstruction from reduced k space sampling, leading to shorter scan times without compromising diagnostic detail. The proposed method has the potential to improve the clinical applicability of SMWI for Parkinsons disease and support faster and more efficient neuroimaging workflows.

Complex Swin Transformer for Accelerating Enhanced SMWI Reconstruction

TL;DR

This research enables high-quality SMWI generation from reduced k-space data, accelerating scan times while preserving diagnostic detail, and could significantly enhance SMWI's clinical application for Parkinson's Disease and support faster, more efficient neuroimaging workflows.

Abstract

Susceptibility Map Weighted Imaging (SMWI) is an advanced magnetic resonance imaging technique used to detect nigral hyperintensity in Parkinsons disease. However, full resolution SMWI acquisition is limited by long scan times. Efficient reconstruction methods are therefore required to generate high quality SMWI from reduced k space data while preserving diagnostic relevance. In this work, we propose a complex valued Swin Transformer based network for super resolution reconstruction of multi echo MRI data. The proposed method reconstructs high quality SMWI images from low resolution k space inputs. Experimental results demonstrate that the method achieves a structural similarity index of 0.9116 and a mean squared error of 0.076 when reconstructing SMWI from 256 by 256 k space data, while maintaining critical diagnostic features. This approach enables high quality SMWI reconstruction from reduced k space sampling, leading to shorter scan times without compromising diagnostic detail. The proposed method has the potential to improve the clinical applicability of SMWI for Parkinsons disease and support faster and more efficient neuroimaging workflows.
Paper Structure (6 sections, 4 figures)

This paper contains 6 sections, 4 figures.

Table of Contents

  1. Introduction
  2. Proposed Method
  3. Dataset
  4. Results
  5. Discussion and Conclusion
  6. Acknowledgements

Figures (4)

  • Figure 1: Illustration of our proposed pipeline to generate high resolution SMWI scan from low resolution multi-echo data.
  • Figure 2: Illustration of our proposed Complex Swin Transformer Architecture which is designed to enhance the resolution of complex images of multi-echo scans for high resolution SMWI generation.
  • Figure 3: Demonstration of visual results obtained from low resolution data (i.e., 192$\times$192) by employing proposed complex Swin Transformer Network.
  • Figure 4: Demonstration of visual results obtained from low resolution data (i.e., 256$\times$256) by employing proposed complex Swin Transformer Network.