X-ray Image Enhancement Based on Nonsubsampled Shearlet Transform and Gradient Domain Guided Filtering

Area of Science:

• Medical Imaging
• Image Processing
• Computational Science

Background:

• X-ray imaging is crucial for medical diagnosis but often suffers from low resolution, noise, and loss of fine details.
• Existing enhancement techniques struggle to balance noise suppression with the preservation of essential image features like edges and textures.

Purpose of the Study:

• To develop an advanced image enhancement algorithm for X-ray images.
• To overcome limitations such as low resolution, noise amplification, and poor edge retention.
• To improve the overall quality and diagnostic value of X-ray images.

Main Methods:

• The proposed algorithm combines non-subsampled shearlet transform (NSST) with gradient-domain guided filtering (GDGF).
• The image is decomposed into low-frequency and high-frequency sub-bands using NSST.
• Adaptive gamma correction is applied to the low-frequency sub-band, while GDGF processes the high-frequency sub-bands for noise reduction and detail enhancement.

Main Results:

• The algorithm successfully enhances X-ray image resolution and contrast.
• It effectively suppresses noise while preserving and highlighting critical details and edge information.
• Experimental results demonstrate superior performance compared to classical enhancement algorithms based on objective metrics.

Conclusions:

• The combined NSST and GDGF approach offers a robust solution for X-ray image enhancement.
• This method significantly improves image quality, aiding in more accurate medical diagnoses.
• The algorithm presents a notable advancement in digital medical imaging processing.