The use of hybrid classifier to assist in the diagnosis of lip lesions in thermal images: a preliminary study

This research presents a methodology for the classification of actinic chelitis and lip cancer in thermal images. A hybrid classifier that uses two methods of supervised learning (SVM and KNN) to classify patient images into three groups: healthy, squamous cell carcinoma and actinic cheilitis (malig...

Full description

Saved in:
Bibliographic Details
Published in2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) pp. 1585 - 1588
Main Authors Paulino, Jose Alberto Souza, da Silva Alves, Alanne Vandreia, de Sousa, Robson Pequeno, Galdino, Katia Elizabete, Alves, Pollianna Muniz, Oliveira, Eduardo Jorge Valadares
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.11.2019
Subjects
actinic cheilitis
lip cancer
supervised learning
thermal images
Online AccessGet full text

Cover

More Information
Summary:This research presents a methodology for the classification of actinic chelitis and lip cancer in thermal images. A hybrid classifier that uses two methods of supervised learning (SVM and KNN) to classify patient images into three groups: healthy, squamous cell carcinoma and actinic cheilitis (malignant potentially disorder) was developed. The classifier obtained results that were equivalent to the results of the biopsies of the patients, which proves the efficiency of the developed method and guarantees its use in a CAD system to assist in the diagnosis of actinic cheilitis and lip cancer.
DOI:10.1109/BIBM47256.2019.8983008