Is a pattern-based artificial neural network that belongs to the supervised networks family. A winner-take-all learning approach is applied.
Published in Chapter:
Artificial Intelligence and Image Analysis for the Identification of Endometrial Malignancies: A Comparative Study
Abraham Pouliakis (Second Department of Pathology, National and Kapodistrian University of Athens, Greece), Vasileia Damaskou (School of Medicine, Attikon University Hospital, Greece), Niki Margari (Independent Researcher, Greece), Efrossyni Karakitsou (Department of Biology, University of Barcelona, Spain), Vasilios Pergialiotis (Third Department of Obstetrics and Gynaecology, National and Kapodistrian University of Athens, Greece), George Valasoulis (Department of Obstetrics and Gynaecology, IASO Thessaly Hospital, Larissa, Greece), George Michail (Department of Obstetrics and Gynaecology, Patras University Medical School, Greece), Charalampos Chrelias (Third Department of Obstetrics and Gynaecology, National and Kapodistrian University of Athens, Greece), George Chrelias (Third Department of Obstetrics and Gynaecology, National and Kapodistrian University of Athens, Greece), Vasileios Sioulas (Third Department of Obstetrics and Gynaecology, National and Kapodistrian University of Athens, Greece), Alina-Roxani Gouloumi (Second Department of Pathology, National and Kapodistrian University of Athens, Greece), Nektarios Koufopoulos (Second Department of Pathology, National and Kapodistrian University of Athens, Greece), Martha Nifora (Second Department of Pathology, National and Kapodistrian University of Athens, Greece), Andriani Zacharatou (Second Department of Pathology, National and Kapodistrian University of Athens, Greece), Sophia Kalantaridou (Third Department of Obstetrics and Gynaecology, National and Kapodistrian University of Athens, Greece), and Ioannis G. Panayiotides (Second Department of Pathology, National and Kapodistrian University of Athens, Greece)
Copyright: © 2020
|Pages: 37
DOI: 10.4018/978-1-7998-2390-2.ch005
Abstract
The aim of this study is to compare machine learning algorithms (MLAs) in the discrimination between benign and malignant endometrial nuclei and lesions. Nuclei characteristics are obtained via image analysis and were measured from liquid-based cytology slides. Four hundred sixteen histologically confirmed patients were involved, 168 healthy, and the remaining with pathological endometrium. Fifty percent of the cases were used to three MLAs: a feedforward artificial neural network (ANN) trained by the backpropagation algorithm, a learning vector quantization (LVQ), and a competitive learning ANN. The outcome of this process was the classification of cell nuclei as benign or malignant. Based on the nuclei classification, an algorithm to classify individual patients was constructed. The sensitivity of the MLAs in training set for nuclei classification was in the range of 77%-84%. Patients' classification had sensitivity in the range of 90%-98%. These findings indicate that MLAs have good performance for the classification of endometrial nuclei and lesions.