SEGMENTATION AND CLASSIFICATION OF CUTANEOUS ULCERS IN DIGITAL IMAGES THROUGH ARTIFICIAL NEURAL NETWORKS

André de Souza Tarallo, Adilson Gonzaga, Marco Andrey Cipriano Frade

2008

Abstract

Treatments of leg ulcers are generally expensive and those conducted through the direct manipulation for analysis of its evolution. The treatment efficiency is observed through the reduction of the size of ulcers in relation to the amount of tissues found in their beds, which are classified as granulated/slough. These results are obtained through analyses performed after consultation due to the time these analyses take. This work proposes a new non-invasive technique for the follow-up of treatments aimed at cutaneous ulcers. In this methodology, it was proposed that digital photos of cutaneous ulcers would be submitted to an artificial neural network (ANN), so that all surrounding the wound except for the wound itself could be extracted (skin/background), thus obtaining the ulcerated area. Computer vision techniques have been applied in order to classify the different types of tissues found in the ulcer bed, thus obtaining the corresponding granulation and slough percentages as well as its area. The results obtained have been compared with the results obtained by Image J software. Finally, this methodology will be a useful tool for health professionals in relation to the quickness and precision that it will provide results along the consultation.

Download


Paper Citation


in Harvard Style

de Souza Tarallo A., Gonzaga A. and Andrey Cipriano Frade M. (2008). SEGMENTATION AND CLASSIFICATION OF CUTANEOUS ULCERS IN DIGITAL IMAGES THROUGH ARTIFICIAL NEURAL NETWORKS . In Proceedings of the First International Conference on Health Informatics - Volume 2: HEALTHINF, (BIOSTEC 2008) ISBN 978-989-8111-16-6, pages 59-65. DOI: 10.5220/0001037000590065


in Bibtex Style

@conference{healthinf08,
author={André de Souza Tarallo and Adilson Gonzaga and Marco Andrey Cipriano Frade},
title={SEGMENTATION AND CLASSIFICATION OF CUTANEOUS ULCERS IN DIGITAL IMAGES THROUGH ARTIFICIAL NEURAL NETWORKS},
booktitle={Proceedings of the First International Conference on Health Informatics - Volume 2: HEALTHINF, (BIOSTEC 2008)},
year={2008},
pages={59-65},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001037000590065},
isbn={978-989-8111-16-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Health Informatics - Volume 2: HEALTHINF, (BIOSTEC 2008)
TI - SEGMENTATION AND CLASSIFICATION OF CUTANEOUS ULCERS IN DIGITAL IMAGES THROUGH ARTIFICIAL NEURAL NETWORKS
SN - 978-989-8111-16-6
AU - de Souza Tarallo A.
AU - Gonzaga A.
AU - Andrey Cipriano Frade M.
PY - 2008
SP - 59
EP - 65
DO - 10.5220/0001037000590065