Cervix Type Classification Using Convolutional Neural Networks

Daniel A. Cruz, Carmen Villar-Patiño, Elizabeth Guevara, Marisol Martinez-Alanis

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

Cervical cancer is still a significant cause of death, especially in developing countries. The detection and correct treatment of the disease is vital in its early stages. One of the key factors in selecting appropriate treatment is the identification of the cervix type. The objective of this work is to propose a Convolutional Neural Network (CNN) architecture to perform a classification of the cervix from a set of images published by Intel and MobileODT. The proposed architecture is combined with a preprocessing algorithm based on an assembly of color models to select the region of interest in the image. The obtained model provides better results than other models in which transfer learning is used or there is no preprocessing stage.

Original languageEnglish
Title of host publication8th Latin American Conference on Biomedical Engineering and 42nd National Conference on Biomedical Engineering - Proceedings of CLAIB-CNIB 2019
EditorsCésar A. González Díaz, Christian Chapa González, Eric Laciar Leber, Hugo A. Vélez, Norma P. Puente, Dora-Luz Flores, Adriano O. Andrade, Héctor A. Galván, Fabiola Martínez, Renato García, Citlalli J. Trujillo, Aldo R. Mejía
PublisherSpringer
Pages377-384
Number of pages8
ISBN (Print)9783030306472
DOIs
StatePublished - 1 Jan 2020
Event8th Latin American Conference on Biomedical Engineering and the 42nd National Conference on Biomedical Engineering, CLAIB-CNIB 2019 - Cancún, Mexico
Duration: 2 Oct 20195 Oct 2019

Publication series

NameIFMBE Proceedings
Volume75
ISSN (Print)1680-0737
ISSN (Electronic)1433-9277

Conference

Conference8th Latin American Conference on Biomedical Engineering and the 42nd National Conference on Biomedical Engineering, CLAIB-CNIB 2019
Country/TerritoryMexico
CityCancún
Period2/10/195/10/19

Keywords

  • Adamax
  • Cervical cancer
  • Color models
  • Convolutional Neural Network

Fingerprint

Dive into the research topics of 'Cervix Type Classification Using Convolutional Neural Networks'. Together they form a unique fingerprint.

Cite this