edoc-vmtest

Computational TMA analysis and cell nucleus classification of renal cell carcinoma

Peter J. Schüffler, and Thomas J. Fuchs, and Cheng Soon Ong, and Volker Roth, and Joachim M. Buhmann, . (2010) Computational TMA analysis and cell nucleus classification of renal cell carcinoma. In: Pattern Recognition : 32nd DAGM Symposium, Darmstadt, Germany, September 22-24, 2010. Proceedings. Berlin, pp. 202-211.

Full text not available from this repository.

Official URL: http://edoc.unibas.ch/dok/A5840195

Downloads: Statistics Overview

Abstract

We consider an automated processing pipeline for tissue micro array analysis (TMA) of renal cell carcinoma. It consists of several consecutive tasks, which can be mapped to machine learning challenges. We investigate three of these tasks, namely nuclei segmentation, nuclei classification and staining estimation. We argue for a holistic view of the processing pipeline, as it is not obvious whether performance improvements at individual steps improve overall accuracy. The experimental results show that classification accuracy, which is comparable to trained human experts, can be achieved by using support vector machines (SVM) with appropriate kernels. Furthermore, we provide evidence that the shape of cell nuclei increases the classification performance. Most importantly, these improvements in classification accuracy result in corresponding improvements for the medically relevant estimation of immunohistochemical staining.
Faculties and Departments:05 Faculty of Science > Departement Mathematik und Informatik > Informatik > Biomedical Data Analysis (Roth)
UniBasel Contributors:Roth, Volker
Item Type:Conference or Workshop Item, refereed
Conference or workshop item Subtype:Conference Paper
Publisher:Springer
ISBN:978-3-642-15986-2 ; 978-3-642-15985-5
Series Name:Lecture Notes in Computer Science
Issue Number:6376
Note:Publication type according to Uni Basel Research Database: Conference paper
Identification Number:
Last Modified:06 Mar 2014 14:18
Deposited On:26 Apr 2013 06:52

Repository Staff Only: item control page