Paper Info
Title
Design of a multi-classifier system for discriminating benign from malignant thyroid nodules using routinely H&E-stained cytological images
Abstract
A multi-classifier diagnostic system was designed for distinguishing between benign and malignant thyroid nodules from routinely taken (FNA, H&E-stained) cytological images. To construct the multi-classifier system, several combination rules and different mixtures of ensemble classifier members, employing morphological and textural nuclear features, were comparatively evaluated. Experimental results illustrated that the classifier combination k-NN/PNN/Bayesian and the majority vote rule enhanced significantly classification accuracy (95.7%) as compared to best single classifier (PNN: 89.6%). The proposed system was designed with purpose to be utilized in daily clinical practice as a second opinion tool to support cytopathologists' decisions, when a definite diagnosis is difficult to be obtained.
Year
DOI
Venue
2008
10.1016/j.compbiomed.2007.09.005
Computers in biology and medicine
Keywords
DocType
Volume
multi-classifier systems,cytological image,computer-assisted microscopy,classification accuracy,hematoxylin & eosin,thyroid nodules,E-stained cytological image,daily clinical practice,combination rule,best single classifier,classifier combination k-NN,quantitative analysis of cell nuclei,cytological images,multi-classifier system,proposed system,malignant thyroid,ensemble classifier member,multi-classifier diagnostic system
Journal
38
Issue
ISSN
Citations 
2
Computers in Biology and Medicine
8
PageRank 
References 
Authors
0.54
13
9
Name
Order
Citations
PageRank
Antonis Daskalakis1708.26
Spiros Kostopoulos2558.73
Panagiota Spyridonos322217.43
Dimitris Glotsos413912.43
Panagiota Ravazoula515212.25
Maria Kardari680.54
Ioannis Kalatzis712414.74
Dionisis Cavouras822422.08
George Nikiforidis922521.70