Departmental Papers (CIS)

Graph Embedding to Improve Supervised Classification and Novel Class Detection: Application to Prostate Cancer

Jianbo Shi, University of Pennsylvania
Anant Madabhushi, Rutgers University - New Brunswick/Piscataway
Mark Rosen, University of Pennsylvania
John Tomaszeweski, University of Pennsylvania
Michael D. Feldman, University of Pennsylvania

Document Type Conference Paper

J. Duncan and G. Gerig (Eds.): MICCAI 2005, LNCS 3749, pp. 729–737, 2005. Copyright Springer-Verlag Berlin Heidelberg 2005

Abstract

Recently there has been a great deal of interest in algorithms for constructing low-dimensional feature-space embeddings of high dimensional data sets in order to visualize inter- and intra-class relationships. In this paper we present a novel application of graph embedding in improving the accuracy of supervised classification schemes, especially in cases where object class labels cannot be reliably ascertained. By refining the initial training set of class labels we seek to improve the prior class distributions and thus classification accuracy. We also present a novel way of visualizing the class embeddings which makes it easy to appreciate inter-class relationships and to infer the presence of new classes which were not part of the original classification. We demonstrate the utility of the method in detecting prostatic adenocarcinoma from highresolution MRI.

 

Date Posted: 16 July 2012