Cargando…

Machine Learning for Histologic Subtype Classification of Non-Small Cell Lung Cancer: A Retrospective Multicenter Radiomics Study

BACKGROUND: Histologic phenotype identification of Non-Small Cell Lung Cancer (NSCLC) is essential for treatment planning and prognostic prediction. The prediction model based on radiomics analysis has the potential to quantify tumor phenotypic characteristics non-invasively. However, most existing...

Descripción completa

Detalles Bibliográficos
Autores principales: Yang, Fengchang, Chen, Wei, Wei, Haifeng, Zhang, Xianru, Yuan, Shuanghu, Qiao, Xu, Chen, Yen-Wei
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7840845/
https://www.ncbi.nlm.nih.gov/pubmed/33520719
http://dx.doi.org/10.3389/fonc.2020.608598
_version_ 1783643665366777856
author Yang, Fengchang
Chen, Wei
Wei, Haifeng
Zhang, Xianru
Yuan, Shuanghu
Qiao, Xu
Chen, Yen-Wei
author_facet Yang, Fengchang
Chen, Wei
Wei, Haifeng
Zhang, Xianru
Yuan, Shuanghu
Qiao, Xu
Chen, Yen-Wei
author_sort Yang, Fengchang
collection PubMed
description BACKGROUND: Histologic phenotype identification of Non-Small Cell Lung Cancer (NSCLC) is essential for treatment planning and prognostic prediction. The prediction model based on radiomics analysis has the potential to quantify tumor phenotypic characteristics non-invasively. However, most existing studies focus on relatively small datasets, which limits the performance and potential clinical applicability of their constructed models. METHODS: To fully explore the impact of different datasets on radiomics studies related to the classification of histological subtypes of NSCLC, we retrospectively collected three datasets from multi-centers and then performed extensive analysis. Each of the three datasets was used as the training dataset separately to build a model and was validated on the remaining two datasets. A model was then developed by merging all the datasets into a large dataset, which was randomly split into a training dataset and a testing dataset. For each model, a total of 788 radiomic features were extracted from the segmented tumor volumes. Then three widely used features selection methods, including minimum Redundancy Maximum Relevance Feature Selection (mRMR), Sequential Forward Selection (SFS), and Least Absolute Shrinkage and Selection Operator (LASSO) were used to select the most important features. Finally, three classification methods, including Logistics Regression (LR), Support Vector Machines (SVM), and Random Forest (RF) were independently evaluated on the selected features to investigate the prediction ability of the radiomics models. RESULTS: When using a single dataset for modeling, the results on the testing set were poor, with AUC values ranging from 0.54 to 0.64. When the merged dataset was used for modeling, the average AUC value in the testing set was 0.78, showing relatively good predictive performance. CONCLUSIONS: Models based on radiomics analysis have the potential to classify NSCLC subtypes, but their generalization capabilities should be carefully considered.
format Online
Article
Text
id pubmed-7840845
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-78408452021-01-29 Machine Learning for Histologic Subtype Classification of Non-Small Cell Lung Cancer: A Retrospective Multicenter Radiomics Study Yang, Fengchang Chen, Wei Wei, Haifeng Zhang, Xianru Yuan, Shuanghu Qiao, Xu Chen, Yen-Wei Front Oncol Oncology BACKGROUND: Histologic phenotype identification of Non-Small Cell Lung Cancer (NSCLC) is essential for treatment planning and prognostic prediction. The prediction model based on radiomics analysis has the potential to quantify tumor phenotypic characteristics non-invasively. However, most existing studies focus on relatively small datasets, which limits the performance and potential clinical applicability of their constructed models. METHODS: To fully explore the impact of different datasets on radiomics studies related to the classification of histological subtypes of NSCLC, we retrospectively collected three datasets from multi-centers and then performed extensive analysis. Each of the three datasets was used as the training dataset separately to build a model and was validated on the remaining two datasets. A model was then developed by merging all the datasets into a large dataset, which was randomly split into a training dataset and a testing dataset. For each model, a total of 788 radiomic features were extracted from the segmented tumor volumes. Then three widely used features selection methods, including minimum Redundancy Maximum Relevance Feature Selection (mRMR), Sequential Forward Selection (SFS), and Least Absolute Shrinkage and Selection Operator (LASSO) were used to select the most important features. Finally, three classification methods, including Logistics Regression (LR), Support Vector Machines (SVM), and Random Forest (RF) were independently evaluated on the selected features to investigate the prediction ability of the radiomics models. RESULTS: When using a single dataset for modeling, the results on the testing set were poor, with AUC values ranging from 0.54 to 0.64. When the merged dataset was used for modeling, the average AUC value in the testing set was 0.78, showing relatively good predictive performance. CONCLUSIONS: Models based on radiomics analysis have the potential to classify NSCLC subtypes, but their generalization capabilities should be carefully considered. Frontiers Media S.A. 2021-01-14 /pmc/articles/PMC7840845/ /pubmed/33520719 http://dx.doi.org/10.3389/fonc.2020.608598 Text en Copyright © 2021 Yang, Chen, Wei, Zhang, Yuan, Qiao and Chen http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Oncology
Yang, Fengchang
Chen, Wei
Wei, Haifeng
Zhang, Xianru
Yuan, Shuanghu
Qiao, Xu
Chen, Yen-Wei
Machine Learning for Histologic Subtype Classification of Non-Small Cell Lung Cancer: A Retrospective Multicenter Radiomics Study
title Machine Learning for Histologic Subtype Classification of Non-Small Cell Lung Cancer: A Retrospective Multicenter Radiomics Study
title_full Machine Learning for Histologic Subtype Classification of Non-Small Cell Lung Cancer: A Retrospective Multicenter Radiomics Study
title_fullStr Machine Learning for Histologic Subtype Classification of Non-Small Cell Lung Cancer: A Retrospective Multicenter Radiomics Study
title_full_unstemmed Machine Learning for Histologic Subtype Classification of Non-Small Cell Lung Cancer: A Retrospective Multicenter Radiomics Study
title_short Machine Learning for Histologic Subtype Classification of Non-Small Cell Lung Cancer: A Retrospective Multicenter Radiomics Study
title_sort machine learning for histologic subtype classification of non-small cell lung cancer: a retrospective multicenter radiomics study
topic Oncology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7840845/
https://www.ncbi.nlm.nih.gov/pubmed/33520719
http://dx.doi.org/10.3389/fonc.2020.608598
work_keys_str_mv AT yangfengchang machinelearningforhistologicsubtypeclassificationofnonsmallcelllungcanceraretrospectivemulticenterradiomicsstudy
AT chenwei machinelearningforhistologicsubtypeclassificationofnonsmallcelllungcanceraretrospectivemulticenterradiomicsstudy
AT weihaifeng machinelearningforhistologicsubtypeclassificationofnonsmallcelllungcanceraretrospectivemulticenterradiomicsstudy
AT zhangxianru machinelearningforhistologicsubtypeclassificationofnonsmallcelllungcanceraretrospectivemulticenterradiomicsstudy
AT yuanshuanghu machinelearningforhistologicsubtypeclassificationofnonsmallcelllungcanceraretrospectivemulticenterradiomicsstudy
AT qiaoxu machinelearningforhistologicsubtypeclassificationofnonsmallcelllungcanceraretrospectivemulticenterradiomicsstudy
AT chenyenwei machinelearningforhistologicsubtypeclassificationofnonsmallcelllungcanceraretrospectivemulticenterradiomicsstudy