Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Residual Dense Swin Transformer for Continuous Depth-Independent Ultrasound Imaging

Jintong Hu, Hui Che, Zishuo Li, Wenming Yang

TL;DR

The RDSTN strategy streamlines balancing image quality and field-of-view, which offers superior textures over traditional methods and shows promising potential for ultrasound image enhancement by overcoming the limitations of conventional interpolation-based methods and achieving depth-independent imaging.

Abstract

Ultrasound imaging is crucial for evaluating organ morphology and function, yet depth adjustment can degrade image quality and field-of-view, presenting a depth-dependent dilemma. Traditional interpolation-based zoom-in techniques often sacrifice detail and introduce artifacts. Motivated by the potential of arbitrary-scale super-resolution to naturally address these inherent challenges, we present the Residual Dense Swin Transformer Network (RDSTN), designed to capture the non-local characteristics and long-range dependencies intrinsic to ultrasound images. It comprises a linear embedding module for feature enhancement, an encoder with shifted-window attention for modeling non-locality, and an MLP decoder for continuous detail reconstruction. This strategy streamlines balancing image quality and field-of-view, which offers superior textures over traditional methods. Experimentally, RDSTN outperforms existing approaches while requiring fewer parameters. In conclusion, RDSTN shows promising potential for ultrasound image enhancement by overcoming the limitations of conventional interpolation-based methods and achieving depth-independent imaging.

Residual Dense Swin Transformer for Continuous Depth-Independent Ultrasound Imaging

TL;DR

The RDSTN strategy streamlines balancing image quality and field-of-view, which offers superior textures over traditional methods and shows promising potential for ultrasound image enhancement by overcoming the limitations of conventional interpolation-based methods and achieving depth-independent imaging.

Abstract

Ultrasound imaging is crucial for evaluating organ morphology and function, yet depth adjustment can degrade image quality and field-of-view, presenting a depth-dependent dilemma. Traditional interpolation-based zoom-in techniques often sacrifice detail and introduce artifacts. Motivated by the potential of arbitrary-scale super-resolution to naturally address these inherent challenges, we present the Residual Dense Swin Transformer Network (RDSTN), designed to capture the non-local characteristics and long-range dependencies intrinsic to ultrasound images. It comprises a linear embedding module for feature enhancement, an encoder with shifted-window attention for modeling non-locality, and an MLP decoder for continuous detail reconstruction. This strategy streamlines balancing image quality and field-of-view, which offers superior textures over traditional methods. Experimentally, RDSTN outperforms existing approaches while requiring fewer parameters. In conclusion, RDSTN shows promising potential for ultrasound image enhancement by overcoming the limitations of conventional interpolation-based methods and achieving depth-independent imaging.
Paper Structure (13 sections, 4 equations, 3 figures, 3 tables)

This paper contains 13 sections, 4 equations, 3 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Methods
  3. Single Image Super-Resolution
  4. Arbitrary-Scale Image Super-Resolution
  5. Model Architecture
  6. Residual Dense Swin Transformer Encoder
  7. Local Enhanced Implicit Representation Upscaling
  8. Experiment Results
  9. Comparison with other methods
  10. Ablation Study
  11. Generalization
  12. Conclusion
  13. Acknowledgments

Figures (3)

  • Figure 1: An example of magnified images of abitrary scales generated by RDSTN.
  • Figure 2: The main pipeline of our RDSTN. RDSTN introduces non-locality and allows for essential feature reuse, improving representation and performance.
  • Figure 3: Visual comparison between methods. RDSTN achieves better continuity in texture and has the fewest white noise points compared to other methods.