Ultrasound image enhancement using an adaptive anisotropic diffusion filter

Abstract

In this work, an effective technique to perform ultrasound image enhancement is presented. The algorithm proposed is based on the anisotropic diffusion equation of Perona and Malik (PM), and introduces a new implementation to determine the scale space parameter of the diffusion function in an adaptive manner and to ensure the convergence process. The adaptation is done according to the local intensity variance which was computed for each image pixel. The proposed method is evaluated and verified on the basis of Peak Signal to Noise Ratio (PSNR), Edge Preservation Factor (EPF), Structure Similarity Index Map (SSIM), Universal Quality Index (UQI) and Feature Similarity Index (FSIM). The experimental data demonstrate that the proposed method can reduce the speckle noise effectively without blurring the edges.