6533b859fe1ef96bd12b7784

RESEARCH PRODUCT

Diffusion equations with negentropy applied to denoise mammographic images.

subject

description

Mammography is a radiographic technique used for the detection of breast lesions. The analysis of the digital image normally requires a previous application of filters as a preprocessing step to reduce the noise level of the image, while preserving important details to carry out a suitable diagnostic. In the literature, there are a large amount of denoising techniques applied to different medical images. In this work we have studied the performance of a diffusive filter with a stopping condition based on the statistical concept of negentropy, applied to denoise mammographic images. The negentropy has been succesfully prove with other denoising methods as independent component analysis by the authors in (1). We have evaluated the final image quality obtained, measuring a root mean squared error between the noise-free initial image and the final restored image and compared the results obtained by this diffusive filter with those obtained by an adaptative non-linear Wiener filter. I. INTRODUCTION The low contrast of the small tumours to the background, which is sometimes close to the noise, makes that small breast cancer lesions can hardly be seen in the mammography (2). So a preprocessing stage for the reduction of the noise present in the original image, is important to carry out the analysis of the medical images. The noise reduction improves the visual evaluation of the image and the detection of important features of the medical image. Different methods have been proposed for image restora- tion from noisy images (1), (3) and, in particular, they have been successfully employed to denoise medical digital images. An important class of image denoising methods is based on nonlinear diffusion equations (4), (5). These methods usually appear associated to a variational problem for minimizing an energy functional. It is solved by means of a gradient like method, ending up with a time dependent non linear diffusion equation. In this work we will evaluate the possibility of using the negentropy of the image to develop an automatic stopping criterion for the diffusive filter for the mammographic image restoration process.