Dual-Filter X-Ray Image Enhancement Using Cream and Bosso Algorithms: Contrast and Entropy Optimization Across...

Area of Science:

• Medical Imaging
• Image Processing
• Radiography

Background:

• Radiographic imaging quality is crucial for accurate clinical diagnosis.
• Existing enhancement techniques may have limitations in contrast, definition, or computational efficiency.
• Resource-limited settings often require robust and accessible image enhancement solutions.

Purpose of the Study:

• To introduce and evaluate a novel dual-filter X-ray image enhancement technique.
• To improve the quality of radiographic images for knee, breast, and wrist.
• To assess the technique's performance against established methods and deep learning models.

Main Methods:

• Implementation of the Cream and Bosso algorithms for dual-filter X-ray enhancement.
• Derivation of processing parameters based on entropy metrics and the filtering parameter 'd'.
• Quantitative analysis of improvements in bone, edge definition, and contrast.

Main Results:

• Significant improvements observed in bone, edge definition, and contrast (p < 0.001).
• Demonstrated contrast enhancement for knee and wrist radiographs with acceptable noise levels.
• The dual-filter method showed comparable or superior results to CLAHE, unsharp masking, and deep learning models.

Conclusions:

• The dual-filter X-ray enhancement technique reliably improves image quality for specific anatomical regions.
• The method is computationally efficient and suitable for resource-limited environments.
• Enhanced radiographic images improve diagnostic accuracy and interpretability.