Department of Computer Engineering
S E M I N A R
A Resampling-Based Markovian Model for Automated Cancer Diagnosis
Computer Engineering Department
In recent years, there has been a great effort in the research of implementing automated diagnostic systems for tissue images. One major challenge in this implementation is to design systems that are robust to image perturbations since tissue images may contain a considerable amount of variance arising from their nature as well as tissue preparation and image acquisition steps. In order to meet this challenge, it is important to learn the systems on a large number of labeled images from a different range of variation. However, acquiring labeled images is quite difficult in this domain, and hence, the labeled training data are typically very limited. Although the issue of having limited labeled data is acknowledged by many researchers, it has rarely been considered in the system design.
This paper successfully addresses this issue, introducing a new resampling framework to simulate perturbations in tissue images. This framework generates multiple sequences from an image to represent its perturbed samples and models these sequences using a Markov process. Working with colon tissue images, our experiments show that this framework increases the generalization capacity of a learner by increasing the size and variation of the training data and improves the classification performance of a given image by combining the decisions obtained on its perturbed samples.
DATE: 18 April, 2011, Monday @ 15:40