FULLY-AUTOMATED SEGMENTATION OF TUMOR AREAS IN TISSUE CONFOCAL IMAGES - Comparison between a Custom Unsupervised and a Supervised SVM Approach

Santa Di Cataldo, Elisa Ficarra, Enrico Macii

2008

Abstract

In this paper we present a fully-automated method for the detection of tumor areas in immunohistochemical confocal images. The image segmentation provided by the proposed technique allows quantitative protein activity evaluation on the target tumoral tissue disregarding tissue areas that are not affected by the pathology, such as connective tissue. The automated method, that is based on an innovative unsupervised clustering approach, enables more accurate tissue segmentation compared to traditional supervised methods that can be found in literature, such as Support Vector Machine (SVM). Experimental results conducted on a large set of heterogeneous immunohistochemical lung cancer tissue images demonstrate that the proposed approach overcomes the performance of SVM by 8%, achieving on average an accuracy of 90%.

Paper Citation

in Harvard Style

Di Cataldo S., Ficarra E. and Macii E. (2008). FULLY-AUTOMATED SEGMENTATION OF TUMOR AREAS IN TISSUE CONFOCAL IMAGES - Comparison between a Custom Unsupervised and a Supervised SVM Approach . In Proceedings of the First International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2008) ISBN 978-989-8111-18-0, pages 116-123. DOI: 10.5220/0001068501160123

in Bibtex Style

@conference{biosignals08,
author={Santa Di Cataldo and Elisa Ficarra and Enrico Macii},
title={FULLY-AUTOMATED SEGMENTATION OF TUMOR AREAS IN TISSUE CONFOCAL IMAGES - Comparison between a Custom Unsupervised and a Supervised SVM Approach},
booktitle={Proceedings of the First International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2008)},
year={2008},
pages={116-123},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001068501160123},
isbn={978-989-8111-18-0},
}

in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2008)
TI - FULLY-AUTOMATED SEGMENTATION OF TUMOR AREAS IN TISSUE CONFOCAL IMAGES - Comparison between a Custom Unsupervised and a Supervised SVM Approach
SN - 978-989-8111-18-0
AU - Di Cataldo S.
AU - Ficarra E.
AU - Macii E.
PY - 2008
SP - 116
EP - 123
DO - 10.5220/0001068501160123