A Hierarchical Feature-Based Methodology to Perform Cervical Cancer Classification
Prevention of cervical cancer could be performed using Pap smear image analysis. This test screens pre-neoplastic changes in the cervical epithelial cells; accurate screening can reduce deaths caused by the disease. Pap smear test analysis is exhaustive and repetitive work performed visually by a cy...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/9/4091 |
| _version_ | 1797535689092366336 |
|---|---|
| author | Débora N. Diniz Mariana T. Rezende Andrea G. C. Bianchi Claudia M. Carneiro Daniela M. Ushizima Fátima N. S. de Medeiros Marcone J. F. Souza |
| author_facet | Débora N. Diniz Mariana T. Rezende Andrea G. C. Bianchi Claudia M. Carneiro Daniela M. Ushizima Fátima N. S. de Medeiros Marcone J. F. Souza |
| author_sort | Débora N. Diniz |
| collection | DOAJ |
| description | Prevention of cervical cancer could be performed using Pap smear image analysis. This test screens pre-neoplastic changes in the cervical epithelial cells; accurate screening can reduce deaths caused by the disease. Pap smear test analysis is exhaustive and repetitive work performed visually by a cytopathologist. This article proposes a workload-reducing algorithm for cervical cancer detection based on analysis of cell nuclei features within Pap smear images. We investigate eight traditional machine learning methods to perform a hierarchical classification. We propose a hierarchical classification methodology for computer-aided screening of cell lesions, which can recommend fields of view from the microscopy image based on the nuclei detection of cervical cells. We evaluate the performance of several algorithms against the Herlev and CRIC databases, using a varying number of classes during image classification. Results indicate that the hierarchical classification performed best when using Random Forest as the key classifier, particularly when compared with decision trees, k-NN, and the Ridge methods. |
| first_indexed | 2024-03-10T11:48:56Z |
| format | Article |
| id | doaj.art-3090ddcbf4c44c1f84696c09f41f5612 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T11:48:56Z |
| publishDate | 2021-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-3090ddcbf4c44c1f84696c09f41f56122023-11-21T17:52:28ZengMDPI AGApplied Sciences2076-34172021-04-01119409110.3390/app11094091A Hierarchical Feature-Based Methodology to Perform Cervical Cancer ClassificationDébora N. Diniz0Mariana T. Rezende1Andrea G. C. Bianchi2Claudia M. Carneiro3Daniela M. Ushizima4Fátima N. S. de Medeiros5Marcone J. F. Souza6Departamento de Computação, Universidade Federal de Ouro Preto (UFOP), Ouro Preto 35400-000, BrazilDepartamento de Análises Clínicas, Universidade Federal de Ouro Preto (UFOP), Ouro Preto 35400-000, BrazilDepartamento de Computação, Universidade Federal de Ouro Preto (UFOP), Ouro Preto 35400-000, BrazilDepartamento de Análises Clínicas, Universidade Federal de Ouro Preto (UFOP), Ouro Preto 35400-000, BrazilComputational Research Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USADepartamento de Engenharia de Teleinformática, Universidade Federal do Ceará (UFC), Fortaleza 60020-181, BrazilDepartamento de Computação, Universidade Federal de Ouro Preto (UFOP), Ouro Preto 35400-000, BrazilPrevention of cervical cancer could be performed using Pap smear image analysis. This test screens pre-neoplastic changes in the cervical epithelial cells; accurate screening can reduce deaths caused by the disease. Pap smear test analysis is exhaustive and repetitive work performed visually by a cytopathologist. This article proposes a workload-reducing algorithm for cervical cancer detection based on analysis of cell nuclei features within Pap smear images. We investigate eight traditional machine learning methods to perform a hierarchical classification. We propose a hierarchical classification methodology for computer-aided screening of cell lesions, which can recommend fields of view from the microscopy image based on the nuclei detection of cervical cells. We evaluate the performance of several algorithms against the Herlev and CRIC databases, using a varying number of classes during image classification. Results indicate that the hierarchical classification performed best when using Random Forest as the key classifier, particularly when compared with decision trees, k-NN, and the Ridge methods.https://www.mdpi.com/2076-3417/11/9/4091image classificationlearning algorithmRandom Forest classifierhierarchical modelcervical lesionscancer classification |
| spellingShingle | Débora N. Diniz Mariana T. Rezende Andrea G. C. Bianchi Claudia M. Carneiro Daniela M. Ushizima Fátima N. S. de Medeiros Marcone J. F. Souza A Hierarchical Feature-Based Methodology to Perform Cervical Cancer Classification Applied Sciences image classification learning algorithm Random Forest classifier hierarchical model cervical lesions cancer classification |
| title | A Hierarchical Feature-Based Methodology to Perform Cervical Cancer Classification |
| title_full | A Hierarchical Feature-Based Methodology to Perform Cervical Cancer Classification |
| title_fullStr | A Hierarchical Feature-Based Methodology to Perform Cervical Cancer Classification |
| title_full_unstemmed | A Hierarchical Feature-Based Methodology to Perform Cervical Cancer Classification |
| title_short | A Hierarchical Feature-Based Methodology to Perform Cervical Cancer Classification |
| title_sort | hierarchical feature based methodology to perform cervical cancer classification |
| topic | image classification learning algorithm Random Forest classifier hierarchical model cervical lesions cancer classification |
| url | https://www.mdpi.com/2076-3417/11/9/4091 |
| work_keys_str_mv | AT deborandiniz ahierarchicalfeaturebasedmethodologytoperformcervicalcancerclassification AT marianatrezende ahierarchicalfeaturebasedmethodologytoperformcervicalcancerclassification AT andreagcbianchi ahierarchicalfeaturebasedmethodologytoperformcervicalcancerclassification AT claudiamcarneiro ahierarchicalfeaturebasedmethodologytoperformcervicalcancerclassification AT danielamushizima ahierarchicalfeaturebasedmethodologytoperformcervicalcancerclassification AT fatimansdemedeiros ahierarchicalfeaturebasedmethodologytoperformcervicalcancerclassification AT marconejfsouza ahierarchicalfeaturebasedmethodologytoperformcervicalcancerclassification AT deborandiniz hierarchicalfeaturebasedmethodologytoperformcervicalcancerclassification AT marianatrezende hierarchicalfeaturebasedmethodologytoperformcervicalcancerclassification AT andreagcbianchi hierarchicalfeaturebasedmethodologytoperformcervicalcancerclassification AT claudiamcarneiro hierarchicalfeaturebasedmethodologytoperformcervicalcancerclassification AT danielamushizima hierarchicalfeaturebasedmethodologytoperformcervicalcancerclassification AT fatimansdemedeiros hierarchicalfeaturebasedmethodologytoperformcervicalcancerclassification AT marconejfsouza hierarchicalfeaturebasedmethodologytoperformcervicalcancerclassification |