CT-Based Radiomics to Predict KRAS Mutation in CRC Patients Using a Machine Learning Algorithm: A Retrospective Study

Colorectal cancer (CRC) is one of the most common types of cancer worldwide. The KRAS mutation is present in 30-50% of CRC patients. This mutation confers resistance to treatment with anti-EGFR therapy. This article aims at proving that computer tomography (CT)-based radiomics can predict the KRAS m...

Full description

Bibliographic Details
Authors: Porto-Álvarez, J., Cernadas, E., Aldaz Martínez, R., Fernández-Delgado, M., Huelga Zapico, E., González-Castro, V., Baleato Gonzalez, Sandra, García Figueiras, Roberto, Antúnez López, José Ramón, Souto-Bayarri, M.
Format: article
Publication Date:2023
Country:España
Institution:Servizo Galego de Saúde (SERGAS)
Repository:RUNA. Repositorio da Consellería de Sanidade e Sergas
OAI Identifier:oai:runa.sergas.gal:20.500.11940/21297
Online Access:https://portalcientifico.sergas.gal//documentos/64f6356966ccc641d10d6d19
http://hdl.handle.net/20.500.11940/21297
Access Level:Open access
Keyword:AS Santiago
CHUS
id ES_a3bedbb1dda365a7a59f7c5e24e893c8
oai_identifier_str oai:runa.sergas.gal:20.500.11940/21297
network_acronym_str ES
network_name_str España
repository_id_str
spelling CT-Based Radiomics to Predict KRAS Mutation in CRC Patients Using a Machine Learning Algorithm: A Retrospective StudyPorto-Álvarez, J.Cernadas, E.Aldaz Martínez, R.Fernández-Delgado, M.Huelga Zapico, E.González-Castro, V.Baleato Gonzalez, SandraGarcía Figueiras, RobertoAntúnez López, José RamónSouto-Bayarri, M.AS SantiagoCHUSAS SantiagoCHUSAS SantiagoCHUSColorectal cancer (CRC) is one of the most common types of cancer worldwide. The KRAS mutation is present in 30-50% of CRC patients. This mutation confers resistance to treatment with anti-EGFR therapy. This article aims at proving that computer tomography (CT)-based radiomics can predict the KRAS mutation in CRC patients. The piece is a retrospective study with 56 CRC patients from the Hospital of Santiago de Compostela, Spain. All patients had a confirmatory pathological analysis of the KRAS status. Radiomics features were obtained using an abdominal contrast enhancement CT (CECT) before applying any treatments. We used several classifiers, including AdaBoost, neural network, decision tree, support vector machine, and random forest, to predict the presence or absence of KRAS mutation. The most reliable prediction was achieved using the AdaBoost ensemble on clinical patient data, with a kappa and accuracy of 53.7% and 76.8%, respectively. The sensitivity and specificity were 73.3% and 80.8%. Using texture descriptors, the best accuracy and kappa were 73.2% and 46%, respectively, with sensitivity and specificity of 76.7% and 69.2%, also showing a correlation between texture patterns on CT images and KRAS mutation. Radiomics could help manage CRC patients, and in the future, it could have a crucial role in diagnosing CRC patients ahead of invasive methods.This work received financial support from Xunta de Galicia (ED431G-2019/04) and the European Regional Development Fund (ERDF), which acknowledges the CiTIUS-Centro Singular de Investigacion en Tecnoloxias Intelixentes da Universidade de Santiago de Compostela as a Research Center of the Galician University System.2023info:eu-repo/semantics/articlehttps://portalcientifico.sergas.gal//documentos/64f6356966ccc641d10d6d19http://hdl.handle.net/20.500.11940/21297reponame:RUNA. Repositorio da Consellería de Sanidade e Sergasinstname:Servizo Galego de Saúde (SERGAS)Ingléshttp://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:runa.sergas.gal:20.500.11940/212972026-06-12T08:40:47Z
dc.title.none.fl_str_mv CT-Based Radiomics to Predict KRAS Mutation in CRC Patients Using a Machine Learning Algorithm: A Retrospective Study
title CT-Based Radiomics to Predict KRAS Mutation in CRC Patients Using a Machine Learning Algorithm: A Retrospective Study
spellingShingle CT-Based Radiomics to Predict KRAS Mutation in CRC Patients Using a Machine Learning Algorithm: A Retrospective Study
Porto-Álvarez, J.
AS Santiago
CHUS
AS Santiago
CHUS
AS Santiago
CHUS
title_short CT-Based Radiomics to Predict KRAS Mutation in CRC Patients Using a Machine Learning Algorithm: A Retrospective Study
title_full CT-Based Radiomics to Predict KRAS Mutation in CRC Patients Using a Machine Learning Algorithm: A Retrospective Study
title_fullStr CT-Based Radiomics to Predict KRAS Mutation in CRC Patients Using a Machine Learning Algorithm: A Retrospective Study
title_full_unstemmed CT-Based Radiomics to Predict KRAS Mutation in CRC Patients Using a Machine Learning Algorithm: A Retrospective Study
title_sort CT-Based Radiomics to Predict KRAS Mutation in CRC Patients Using a Machine Learning Algorithm: A Retrospective Study
dc.creator.none.fl_str_mv Porto-Álvarez, J.
Cernadas, E.
Aldaz Martínez, R.
Fernández-Delgado, M.
Huelga Zapico, E.
González-Castro, V.
Baleato Gonzalez, Sandra
García Figueiras, Roberto
Antúnez López, José Ramón
Souto-Bayarri, M.
author Porto-Álvarez, J.
author_facet Porto-Álvarez, J.
Cernadas, E.
Aldaz Martínez, R.
Fernández-Delgado, M.
Huelga Zapico, E.
González-Castro, V.
Baleato Gonzalez, Sandra
García Figueiras, Roberto
Antúnez López, José Ramón
Souto-Bayarri, M.
author_role author
author2 Cernadas, E.
Aldaz Martínez, R.
Fernández-Delgado, M.
Huelga Zapico, E.
González-Castro, V.
Baleato Gonzalez, Sandra
García Figueiras, Roberto
Antúnez López, José Ramón
Souto-Bayarri, M.
author2_role author
author
author
author
author
author
author
author
author
dc.subject.none.fl_str_mv AS Santiago
CHUS
AS Santiago
CHUS
AS Santiago
CHUS
topic AS Santiago
CHUS
AS Santiago
CHUS
AS Santiago
CHUS
description Colorectal cancer (CRC) is one of the most common types of cancer worldwide. The KRAS mutation is present in 30-50% of CRC patients. This mutation confers resistance to treatment with anti-EGFR therapy. This article aims at proving that computer tomography (CT)-based radiomics can predict the KRAS mutation in CRC patients. The piece is a retrospective study with 56 CRC patients from the Hospital of Santiago de Compostela, Spain. All patients had a confirmatory pathological analysis of the KRAS status. Radiomics features were obtained using an abdominal contrast enhancement CT (CECT) before applying any treatments. We used several classifiers, including AdaBoost, neural network, decision tree, support vector machine, and random forest, to predict the presence or absence of KRAS mutation. The most reliable prediction was achieved using the AdaBoost ensemble on clinical patient data, with a kappa and accuracy of 53.7% and 76.8%, respectively. The sensitivity and specificity were 73.3% and 80.8%. Using texture descriptors, the best accuracy and kappa were 73.2% and 46%, respectively, with sensitivity and specificity of 76.7% and 69.2%, also showing a correlation between texture patterns on CT images and KRAS mutation. Radiomics could help manage CRC patients, and in the future, it could have a crucial role in diagnosing CRC patients ahead of invasive methods.
publishDate 2023
dc.date.none.fl_str_mv 2023
dc.type.none.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://portalcientifico.sergas.gal//documentos/64f6356966ccc641d10d6d19
http://hdl.handle.net/20.500.11940/21297
url https://portalcientifico.sergas.gal//documentos/64f6356966ccc641d10d6d19
http://hdl.handle.net/20.500.11940/21297
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.rights.none.fl_str_mv http://creativecommons.org/licenses/by/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.source.none.fl_str_mv reponame:RUNA. Repositorio da Consellería de Sanidade e Sergas
instname:Servizo Galego de Saúde (SERGAS)
instname_str Servizo Galego de Saúde (SERGAS)
reponame_str RUNA. Repositorio da Consellería de Sanidade e Sergas
collection RUNA. Repositorio da Consellería de Sanidade e Sergas
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869415422479040512
score 15,812429

Similar Items