Fast Adaptive Anisotropic Filtering for Medical Image Enhancement

Abstract

In this paper, local structure tensor (LST) based adaptive anisotropic filtering (AAF) methodology is used for medical image enhancement over different modalities. This filtering framework enhances and preserves anisotropic image structures while suppressing high-frequency noise. The goal of this work is to reduce the overall computational cost with minimum risk on accuracy by introducing optimized filternets for local structure analysis and reconstruction filtering. This filtering technique facilitates user interaction and direct control over high frequency contents of the signal. The efficacy of the filtering framework is evaluated by testing the system with medical images of different modalities. The results are compared using three different quality measures. Experimental results show that a good level of noise reduction along with structure enhancement can be achieved in the adaptively filtered images.