Anisotropic diffusion filtering of infrared medical images

Thyroid diseases, in general, and in particular thyroid cancer can be detected by infrared built-in image processing. A good spatial resolution is needed to assess the specific patterns, but small signal-to-noise ratio and low contrast makes much difficult to achieve infrared image denoising and edge enhancement. This paper proposes an improved method of anisotropic diffusion filtering which reduces noise in infrared images while enhancing and preserving edges. It uses the heat diffusion equation proposed by Weickert, but it is completed by a linear term showing the mechanism of heat transport as a result of the blood perfusion, boundaries conditions and distinct values for the four diffusion coefficients. Experimental results demonstrate that the new proposed method can effectively realize infrared image denoising and edge enhancement and it can be used for the early diagnose of cancer.