Enhancing Radiological Imaging for Better Healthcare Outcomes Through High Performance Hybrid Approach

Radiological image enhancement algorithms provide a range of techniques to modify images, aiming for optimal visual quality. The selection of these techniques depends on the specific task, image content, observer characteristics, and viewing conditions. However, most enhancement methods for radiological images are tailored to specific applications, creating challenges in standardizing medical imaging practices and increasing costs due to varied enhancement protocols required by different imaging systems. To address this, a hybrid technique integrating unsharp masking, logarithm transformation, and adaptive histogram equalization has been developed. This hybrid method was evaluated against CLAHE and Wavelet Transform-based methods using radiological images. The results showed that the proposed hybrid method consistently achieved the lowest mean squared error (MSE), highest peak signal-to-noise ratio (PSNR), and highest average mean brightness error (AMBE), demonstrating its superior performance in enhancing radiological images. This innovative approach not only enhances diagnostic accuracy but also supports the sustainability of medical imaging infrastructure by streamlining enhancement protocols across diverse imaging systems. Keywords: Medical, enhancement, un-sharp masking, log transformation, adaptive equalization