Cargando…

Classification of retinoblastoma-1 gene mutation with machine learning-based models in bladder cancer

PURPOSE: This study aims to evaluate the potential of machine learning algorithms built with radiomics features from computed tomography urography (CTU) images that classify RB1 gene mutation status in bladder cancer. METHOD: The study enrolled CTU images of 18 patients with and 54 without RB1 mutat...

Descripción completa

Detalles Bibliográficos
Autores principales: İnce, Okan, Yıldız, Hülya, Kisbet, Tanju, Ertürk, Şükrü Mehmet, Önder, Hakan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9061624/
https://www.ncbi.nlm.nih.gov/pubmed/35520623
http://dx.doi.org/10.1016/j.heliyon.2022.e09311
_version_ 1784698766192803840
author İnce, Okan
Yıldız, Hülya
Kisbet, Tanju
Ertürk, Şükrü Mehmet
Önder, Hakan
author_facet İnce, Okan
Yıldız, Hülya
Kisbet, Tanju
Ertürk, Şükrü Mehmet
Önder, Hakan
author_sort İnce, Okan
collection PubMed
description PURPOSE: This study aims to evaluate the potential of machine learning algorithms built with radiomics features from computed tomography urography (CTU) images that classify RB1 gene mutation status in bladder cancer. METHOD: The study enrolled CTU images of 18 patients with and 54 without RB1 mutation from a public database. Image and data preprocessing were performed after data augmentation. Feature selection steps were consisted of filter and wrapper methods. Pearson’s correlation analysis was the filter, and a wrapper-based sequential feature selection algorithm was the wrapper. Models with XGBoost, Random Forest (RF), and k-Nearest Neighbors (kNN) algorithms were developed. Performance metrics of the models were calculated. Models’ performances were compared by using Friedman’s test. RESULTS: 8 features were selected from 851 total extracted features. Accuracy, sensitivity, specificity, precision, recall, F1 measure and AUC were 84%, 80%, 88%, 86%, 80%, 0.83 and 0.84, for XGBoost; 72%, 80%, 65%, 67%, 80%, 0.73 and 0.72 for RF; 66%, 53%, 76%, 67%, 53%, 0.60 and 0.65 for kNN, respectively. XGBoost model had outperformed kNN model in Friedman’s test (p = 0.006). CONCLUSIONS: Machine learning algorithms with radiomics features from CTU images show promising results in classifying bladder cancer by RB1 mutation status non-invasively.
format Online
Article
Text
id pubmed-9061624
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-90616242022-05-04 Classification of retinoblastoma-1 gene mutation with machine learning-based models in bladder cancer İnce, Okan Yıldız, Hülya Kisbet, Tanju Ertürk, Şükrü Mehmet Önder, Hakan Heliyon Research Article PURPOSE: This study aims to evaluate the potential of machine learning algorithms built with radiomics features from computed tomography urography (CTU) images that classify RB1 gene mutation status in bladder cancer. METHOD: The study enrolled CTU images of 18 patients with and 54 without RB1 mutation from a public database. Image and data preprocessing were performed after data augmentation. Feature selection steps were consisted of filter and wrapper methods. Pearson’s correlation analysis was the filter, and a wrapper-based sequential feature selection algorithm was the wrapper. Models with XGBoost, Random Forest (RF), and k-Nearest Neighbors (kNN) algorithms were developed. Performance metrics of the models were calculated. Models’ performances were compared by using Friedman’s test. RESULTS: 8 features were selected from 851 total extracted features. Accuracy, sensitivity, specificity, precision, recall, F1 measure and AUC were 84%, 80%, 88%, 86%, 80%, 0.83 and 0.84, for XGBoost; 72%, 80%, 65%, 67%, 80%, 0.73 and 0.72 for RF; 66%, 53%, 76%, 67%, 53%, 0.60 and 0.65 for kNN, respectively. XGBoost model had outperformed kNN model in Friedman’s test (p = 0.006). CONCLUSIONS: Machine learning algorithms with radiomics features from CTU images show promising results in classifying bladder cancer by RB1 mutation status non-invasively. Elsevier 2022-04-21 /pmc/articles/PMC9061624/ /pubmed/35520623 http://dx.doi.org/10.1016/j.heliyon.2022.e09311 Text en © 2022 The Authors. Published by Elsevier Ltd. https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Research Article
İnce, Okan
Yıldız, Hülya
Kisbet, Tanju
Ertürk, Şükrü Mehmet
Önder, Hakan
Classification of retinoblastoma-1 gene mutation with machine learning-based models in bladder cancer
title Classification of retinoblastoma-1 gene mutation with machine learning-based models in bladder cancer
title_full Classification of retinoblastoma-1 gene mutation with machine learning-based models in bladder cancer
title_fullStr Classification of retinoblastoma-1 gene mutation with machine learning-based models in bladder cancer
title_full_unstemmed Classification of retinoblastoma-1 gene mutation with machine learning-based models in bladder cancer
title_short Classification of retinoblastoma-1 gene mutation with machine learning-based models in bladder cancer
title_sort classification of retinoblastoma-1 gene mutation with machine learning-based models in bladder cancer
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9061624/
https://www.ncbi.nlm.nih.gov/pubmed/35520623
http://dx.doi.org/10.1016/j.heliyon.2022.e09311
work_keys_str_mv AT inceokan classificationofretinoblastoma1genemutationwithmachinelearningbasedmodelsinbladdercancer
AT yıldızhulya classificationofretinoblastoma1genemutationwithmachinelearningbasedmodelsinbladdercancer
AT kisbettanju classificationofretinoblastoma1genemutationwithmachinelearningbasedmodelsinbladdercancer
AT erturksukrumehmet classificationofretinoblastoma1genemutationwithmachinelearningbasedmodelsinbladdercancer
AT onderhakan classificationofretinoblastoma1genemutationwithmachinelearningbasedmodelsinbladdercancer