Texture analysis of microscopic liver images by a level set approach

In this paper the analysis of liver tissue images is addressed to identify abnormal zones due to the presence of tissue with necrosis, or to malignant lymphoma; the study is performed by texture analysis. A discrete level set approach has been used, applying the well know algorithm of segmentation to a new data constituted by a linear combination of the matrices of Uniformity, Contrast and Entropy. The method proposed in this paper makes use of the classification capability of the discrete level set analysis applied to a suitable transformation of the original data. The algorithm is applied to a significant set of liver tissue, showing encouraging results.