Edge Enhancement and Noise Smoothening of CT Images with Anisotropic Diffusion Filter and Unsharp Masking

The paper summarizes the implementation of a modified nonlinear anisotropic diffusion filter, in which local noise estimate is calculated based on mean square error value. Moreover, unsharp masking is used for edge enhancement. This filter is implemented based on finite difference method. Experimental results on CT lungs images shows that, noise due to the artifacts is reduced and edges are well preserved. Conventional diffusion filter works better only when brightness gradient generated by the noise is less than the edges. Edges are not preserved at course scales in scale-space filtering. The application of the new filter in CT images of lungs can help radiologists to better detect the presence of tumours and abnormal growths. The enhancement of images by the proposed method is superior to that with unsharp masking scheme employing conventional filters in terms of the visual quality, the noise performance and the computational complexity, making it an ideal candidate for latent CT images. As this algorithm contains basic operations, repeated over the image, hardware implementation can be easily done.