Gaussian quantum arithmetic optimization-based histogram equalization for medical image enhancement

The quality of medical images is critical for accurate diagnosis. This paper introduces a novel Quantum-behaved Arithmetic Optimization Algorithm (QAOA) for medical images. A mutation operator with Gaussian probability distribution is used in the proposed QAOA as a powerful strategy to enhance QAOA performance in preventing premature convergence to local optima. Gaussian QAOA (GQAOA) is tailored for medical image enhancement and hybridized with Contrast Limited Adaptive Histogram Equalization (CLAHE) to boost the information contents and details of medical images. GQAOA computes the optimal clip limit and other parameters of CLAHE using a new multiobjective fitness function. A combination of five image quality measurements including contrast, information entropy, edge information, Structural Similarity Index Measure (SSIM), and sharpness is suggested as an efficient fitness function to help the proposed framework produce good results. A comparative study is conducted with well-known histogram-based process techniques and state-of-art methods to demonstrate the efficiency of the suggested algorithm. The experimental results prove that the suggested approach performs better than the most current well-established enhancement strategies in the terms of visual interpretation, information entropy, SSIM, Peak Signal to Noise Ratio (PSNR), Naturalness Image Quality Evaluator (NIQE), Absolute Mean Brightness Error (AMBE), and Quality Index (QI) metrics.