Mathematical model based on fractional trace operator for COVID-19 image enhancement.

Area of Science:

• Medical Imaging
• Image Processing
• Fractional Calculus

Background:

• Enhancing medical image quality is crucial for accurate diagnosis.
• Low contrast in medical images, particularly for COVID-19, presents a significant challenge.
• Existing enhancement techniques may not sufficiently address contrast issues in specific medical imaging contexts.

Purpose of the Study:

• To propose a novel image enhancement algorithm for low-contrast COVID-19 medical images.
• To leverage fractional calculus and fractional Rényi entropy for improved image quality.
• To provide a method that aids in more reliable medical diagnosis.

Main Methods:

• A novel image enhancement model utilizing a trace operator in fractional calculus.
• Integration of the derivative of fractional Rényi entropy to guide enhancement.
• Calculation of pixel probability values and covariance matrix for image manipulation.
• Application of convolution with the covariance matrix for the final enhancement.

Main Results:

• The proposed algorithm was tested on three diverse medical image datasets.
• Quantitative quality assessments using BRISQUE and PIQE metrics demonstrated superior performance.
• The enhancement method significantly improved image quality compared to existing approaches.
• Visual inspection confirmed enhanced clarity and detail in the processed medical images.

Conclusions:

• The developed fractional calculus-based algorithm effectively enhances low-contrast COVID-19 medical images.
• The method shows significant potential for improving diagnostic accuracy in medical imaging.
• This approach offers a valuable tool for medical image processing and analysis.