Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

On the application of rough sets to skeletal maturation classification

On the application of rough sets to skeletal maturation classification Assessment of skeletal maturation is important for the accurate diagnosis and medical treatment of many disorders and syndromes. However, determining skeletal maturation is not a trivial task, and requires professional medical training. The aim of this paper is to review the application of classification techniques to the problem of identifying the skeletal maturation stage of individuals, in order to provide the specialists a second opinion to backup or reject their assessments. A methodology based on Rough Sets is developed, which formulates skeletal maturation as a multicriteria classification problem, and generates classification rules employing data from lateral radiographs. Our methodology introduces the concept of transition maturity stages to obtain a finer classification on the data. Our empirical evaluation shows that the rules generated match the terms used by experts to determine maturation stage. Furthermore, our rough sets methodology produces the best results in our case of study, both in terms of coverage on the data and accuracy of the classification process, with respect to alternative classification approaches. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Artificial Intelligence Review Springer Journals

On the application of rough sets to skeletal maturation classification

Loading next page...
 
/lp/springer-journals/on-the-application-of-rough-sets-to-skeletal-maturation-classification-AZ0OpfX27b

References (40)

Publisher
Springer Journals
Copyright
Copyright © 2015 by Springer Science+Business Media Dordrecht
Subject
Computer Science; Artificial Intelligence (incl. Robotics); Computer Science, general
ISSN
0269-2821
eISSN
1573-7462
DOI
10.1007/s10462-015-9450-x
Publisher site
See Article on Publisher Site

Abstract

Assessment of skeletal maturation is important for the accurate diagnosis and medical treatment of many disorders and syndromes. However, determining skeletal maturation is not a trivial task, and requires professional medical training. The aim of this paper is to review the application of classification techniques to the problem of identifying the skeletal maturation stage of individuals, in order to provide the specialists a second opinion to backup or reject their assessments. A methodology based on Rough Sets is developed, which formulates skeletal maturation as a multicriteria classification problem, and generates classification rules employing data from lateral radiographs. Our methodology introduces the concept of transition maturity stages to obtain a finer classification on the data. Our empirical evaluation shows that the rules generated match the terms used by experts to determine maturation stage. Furthermore, our rough sets methodology produces the best results in our case of study, both in terms of coverage on the data and accuracy of the classification process, with respect to alternative classification approaches.

Journal

Artificial Intelligence ReviewSpringer Journals

Published: Dec 18, 2015

There are no references for this article.