Design of a multi-classifier system for discriminating benign from malignant thyroid nodules using routinely H&E-stained cytological images

Authors:
Antonis Daskalakis;Spiros Kostopoulos;Panagiota Spyridonos;Dimitris Glotsos;Panagiota Ravazoula;Maria Kardari;Ioannis Kalatzis;Dionisis Cavouras;George Nikiforidis
Affiliations:
Medical Image Processing and Analysis Group, Lab of Medical Physics, School of Medicine, University of Patras, Rio, Patras 265 04, Greece;Medical Image Processing and Analysis Group, Lab of Medical Physics, School of Medicine, University of Patras, Rio, Patras 265 04, Greece;Medical Image Processing and Analysis Group, Lab of Medical Physics, School of Medicine, University of Patras, Rio, Patras 265 04, Greece;Medical Image Processing and Analysis Group, Lab of Medical Physics, School of Medicine, University of Patras, Rio, Patras 265 04, Greece;Department of Pathology, University Hospital, Rio, Patras 265 04, Greece;Department of Pathology, University Hospital, Rio, Patras 265 04, Greece;Medical Signal and Image Processing Lab, Department of Medical Instruments Technology, Technological Educational Institute of Athens, Ag. Spyridonos Street, Aigaleo, 122 10 Athens, Greece;Medical Signal and Image Processing Lab, Department of Medical Instruments Technology, Technological Educational Institute of Athens, Ag. Spyridonos Street, Aigaleo, 122 10 Athens, Greece;Medical Image Processing and Analysis Group, Lab of Medical Physics, School of Medicine, University of Patras, Rio, Patras 265 04, Greece
Venue:
Computers in Biology and Medicine
Year:
2008

Citing 8
Cited 1

Probabilistic neural networks

Neural Networks
Combination of Multiple Classifiers Using Local Accuracy Estimates

IEEE Transactions on Pattern Analysis and Machine Intelligence
On Combining Classifiers

IEEE Transactions on Pattern Analysis and Machine Intelligence
On combining classifiers using sum and product rules

Pattern Recognition Letters
A Tutorial on Support Vector Machines for Pattern Recognition

Data Mining and Knowledge Discovery
A novel ensemble machine learning for robust microarray data classification

Computers in Biology and Medicine
Score normalization in multimodal biometric systems

Pattern Recognition
A multiple classifier system for early melanoma diagnosis

Artificial Intelligence in Medicine

Specializing for predicting obesity and its co-morbidities

Journal of Biomedical Informatics

Quantified Score

Hi-index	0.00

Visualization

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.