Hierarchical decision tree for the classification of prostate tissue
Anton L. Huynen, Robert J. B. Giesen, R. Laduc, Frans M.J. Debruyne, Hessel Wijkstra · Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society · 1992
This paper describes an algorithm for the classification of texture in ultrasonographic prostate images. The texture is described by parameters which have to be correlated to the histology of the tissue in the image. An adaptive learn algorithm is used to build a hierarchical decision tree for the partitioning of the parameter space. This tree is then used to predict the probability of malignancy in the tissue.