Adaptive Contrast Enhancement With Lesion Focusing (ACELF)

Medical image enhancement plays a vital role in improving the visibility of critical regions for accurate diagnosis and lesion detection. This paper presents an Adaptive Contrast Enhancement with Lesion Focusing (ACELF) algorithm designed to enhance brain MRI images while preserving structural and perceptual quality. The proposed method adaptively enhances image contrast and highlights lesion regions more effectively than traditional techniques. The performance of ACELF is evaluated against existing algorithms such as Recursive Mean-Separate Histogram Equalization (RMSHE), Brightness Preserving Bi-Histogram Equalization with Plateau Limit (BHEPL), and Fusion-based Histogram Specification with Adaptive Brightness Preservation (FHSABP). Experimental results demonstrate that ACELF achieves superior results in multiple objective metrics, including Entropy, Contrast Improvement Index (CII), Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity Index (SSIM). Although the processing time is slightly higher, ACELF consistently produces visually balanced and diagnostically significant images. The enhanced performance confirms the effectiveness of ACELF in improving lesion visibility and overall image quality, making it a reliable approach for medical image enhancement and pre-processing in clinical applications.

Keywords: Adaptive Contrast Enhancement, Lesion Focusing, Medical Image Enhancement, Brain MRI, Histogram Equalization, Deep Learning, RMSHE, BHEPL, FHSABP, PSNR, SSIM, Entropy, CII, Visual Quality Assessment.