Publication
ISBI 2016
Conference paper

A computational framework for disease grading using protein signatures

View publication

Abstract

In this paper, we propose a novel framework for computational disease stratification based on protein expression tissue images. We extract cellular staining response using color information and create a graph based on morphological features and their spatial distance. This graph is collapsed using a learned dictionary. We then compute the commute time matrix and use it as unique signature per protein and disease grade. We combine protein-based signatures using SVM with an Multiple Kernel Learning approach. We test the proposed framework on a prostate cancer tissue dataset and demonstrate the efficacy of the derived protein signatures for both disease stratification and quantification of the relative importance of each protein.

Date

Publication

ISBI 2016

Authors

Share