A modified Mittag–Leffler function framework for contrast enhancement in medical imaging

Medical image contrast enhancement is an essential preprocessing step for improving the visibility of anatomical structures and pathological regions, particularly in low-contrast modalities where clinically relevant details may be obscured. This study proposes a modified Mittag–Leffler function-based contrast enhancement framework founded on nonlinear mathematical modelling. It employs a generalized Mittag–Leffler intensity transformation with tunable parameters that enables nonlinear contrast enhancement while preserving structural information. This transformation provides a flexible intensity mapping, enhancing subtle image details while maintaining anatomical consistency. The effectiveness of the proposed framework is evaluated on different medical imaging datasets, including COVID-19 CT, brain tumor MRI, bone fracture X-ray, and pneumonia chest X-ray images. Comprehensive experimental comparisons are performed against Histogram Equalization (HE), Contrast Limited Adaptive Histogram Equalization (CLAHE), Gamma Correction, Single-Scale Retinex (SSR), and Multi-Scale Retinex (MSR). Performance is assessed using both full-reference and no-reference image quality metrics, including a Peak Signal-to-Noise Ratio (PSNR) of 34.78 dB, a Structural Similarity Index Measure (SSIM) of 99%, an Absolute Mean Brightness Error (AMBE) of 3.50, an entropy of 6.05, an Enhancement Measure Estimation (EME) of 22.52, and a Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) of 23.46 for COVID data, and other dataset results follow this. Experimental results demonstrate that the proposed method achieves contrast preservation and improved information content across all datasets compared with existing enhancement techniques. Statistical significance analysis confirms that the observed improvements are consistent across different medical imaging modalities. These findings demonstrate that the proposed modified Mittag–Leffler framework provides a mathematically and computationally efficient approach to medical image contrast enhancement.