Dual-Enhanced Registration for Field of View Ultrasound Sonography

Zijia Fan, Zhongyang Wang, Junchang Xin, Zhiqiong Wang, Lu Liu, Xia Zhang, Jiren LiuIEEE Access 2020 · DOI · OpenReview

Introduction

Standard ultrasound probes have a limited field of view (FOV), which can be restrictive when clinicians need to visualize large organs or long lesions. Extended Field of View Ultrasound (EFOV-US) addresses this by stitching multiple frames into a single panoramic image. However, ultrasound images are often characterized by speckle noise, low contrast, and low resolution, making it difficult for computer vision algorithms to identify the "feature points" necessary for accurate alignment. Sparse or inaccurate feature points lead to stitching artifacts, blurring, and geometric distortions.

Proposed Methodology

To overcome these challenges, researchers developed a Dual-enhanced EFOV-US pipeline. This approach enhances the image in two distinct stages before the final registration process.

The Dual-enhanced EFOV-US pipeline, showing the parallel enhancement stages followed by feature extraction and matching.

1. Gray-scale Enhancement

The first stage targets speckle noise and low contrast. The process involves inverting the image, fitting a quadratic curve to the grayscale histogram to identify a noise threshold, and then normalizing the histogram. This "cleans" the image and highlights structural details that were previously obscured.

The gray-scale enhancement process, illustrating the transformation from the original image to a denoised, processed version.

2. GAN-based Super-Resolution

Following denoising, the image undergoes super-resolution using a Generative Adversarial Network (GAN), specifically a variation of SRResNet. Unlike standard interpolation, the GAN generates high-frequency details, increasing the resolution and creating a sharper image with more detectable landmarks.

3. Registration and Fusion

For the stitching phase, the system uses SIFT (Scale-Invariant Feature Transform) for point extraction and GLOH (Gradient Location and Orientation Histogram) for description. GLOH was selected for its robustness to the specific types of blur and noise found in medical imaging. Finally, RANSAC filters out outlier matches, and a weighted average method fuses the images into a seamless panorama.

Experimental Results

The method was evaluated on a clinical dataset of 84 ultrasound images of the Common Carotid Artery (CCA). The "Dual-Enhanced" approach significantly outperformed traditional methods:

  • Feature Extraction: The number of successfully matched feature points increased from 108 in the original images to 496 in the dual-enhanced versions.
  • Image Sharpness: The proposed method achieved an Average Gradient of 5.6258, more than double the 2.2001 of standard EFOV-US.
  • Information Content: The Standard Deviation (measuring detail and contrast) reached 92, compared to 37 in the baseline model.
  • Efficiency: The total calculation time was reduced to approximately 3 seconds, bringing the technology closer to real-time clinical application.

Conclusion

The Dual-Enhanced registration method demonstrates that significant "hidden" information can be recovered from noisy ultrasound frames through effective preprocessing. By combining denoising with GAN-based super-resolution, the system generates a much larger pool of reliable feature points, leading to more stable and accurate panoramic images. Future work will focus on optimizing the GAN for diverse clinical environments and achieving true real-time stitching.

Summary updated

Abstract

Extended Field of View Ultrasound Sonography (EFOV-US) uses the existing ultrasound images for image stitching, so as to display the shape and scope of organ occupation and the relationship with surrounding tissues comprehensively. However, there are still some problems in Extended Field of View Ultrasound Sonography, such as matching error and unstable quality of image stitching. In view of these problems, we propose Dual-enhanced EFOV-US method that overcomes the limitation and produces higher quality results. Firstly, the gray enhancement method is used to improve the image contrast and reduce the noise interference. Then the super-resolution method based on the generative adversarial network is used to improve the resolution of the ultrasonic image further and increase the number of feature point matching between stitching images. The high quality ultrasound wide-range image is gotten by stitching and fusing the double enhanced image. The experimental results show that the proposed method is effective and practical.
BibTeX
@article{fan2020dual,
  author = {Zijia Fan and Zhongyang Wang and Junchang Xin and Zhiqiong Wang and Lu Liu and Xia Zhang and Jiren Liu},
  title = {{Dual-Enhanced Registration for Field of View Ultrasound Sonography}},
  journal = {IEEE Access},
  year = {2020},
  doi = {10.1109/access.2020.3008525},
}
Figure