Cargando…

Radiomics for glioblastoma survival analysis in pre-operative MRI: exploring feature robustness, class boundaries, and machine learning techniques

BACKGROUND: This study aims to identify robust radiomic features for Magnetic Resonance Imaging (MRI), assess feature selection and machine learning methods for overall survival classification of Glioblastoma multiforme patients, and to robustify models trained on single-center data when applied to...

Descripción completa

Detalles Bibliográficos
Autores principales: Suter, Yannick, Knecht, Urspeter, Alão, Mariana, Valenzuela, Waldo, Hewer, Ekkehard, Schucht, Philippe, Wiest, Roland, Reyes, Mauricio
Formato: Online Artículo Texto
Lenguaje:English
Publicado: BioMed Central 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7405445/
https://www.ncbi.nlm.nih.gov/pubmed/32758279
http://dx.doi.org/10.1186/s40644-020-00329-8
_version_ 1783567251387973632
author Suter, Yannick
Knecht, Urspeter
Alão, Mariana
Valenzuela, Waldo
Hewer, Ekkehard
Schucht, Philippe
Wiest, Roland
Reyes, Mauricio
author_facet Suter, Yannick
Knecht, Urspeter
Alão, Mariana
Valenzuela, Waldo
Hewer, Ekkehard
Schucht, Philippe
Wiest, Roland
Reyes, Mauricio
author_sort Suter, Yannick
collection PubMed
description BACKGROUND: This study aims to identify robust radiomic features for Magnetic Resonance Imaging (MRI), assess feature selection and machine learning methods for overall survival classification of Glioblastoma multiforme patients, and to robustify models trained on single-center data when applied to multi-center data. METHODS: Tumor regions were automatically segmented on MRI data, and 8327 radiomic features extracted from these regions. Single-center data was perturbed to assess radiomic feature robustness, with over 16 million tests of typical perturbations. Robust features were selected based on the Intraclass Correlation Coefficient to measure agreement across perturbations. Feature selectors and machine learning methods were compared to classify overall survival. Models trained on single-center data (63 patients) were tested on multi-center data (76 patients). Priors using feature robustness and clinical knowledge were evaluated. RESULTS: We observed a very large performance drop when applying models trained on single-center on unseen multi-center data, e.g. a decrease of the area under the receiver operating curve (AUC) of 0.56 for the overall survival classification boundary at 1 year. By using robust features alongside priors for two overall survival classes, the AUC drop could be reduced by 21.2%. In contrast, sensitivity was 12.19% lower when applying a prior. CONCLUSIONS: Our experiments show that it is possible to attain improved levels of robustness and accuracy when models need to be applied to unseen multi-center data. The performance on multi-center data of models trained on single-center data can be increased by using robust features and introducing prior knowledge. For successful model robustification, tailoring perturbations for robustness testing to the target dataset is key.
format Online
Article
Text
id pubmed-7405445
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher BioMed Central
record_format MEDLINE/PubMed
spelling pubmed-74054452020-08-07 Radiomics for glioblastoma survival analysis in pre-operative MRI: exploring feature robustness, class boundaries, and machine learning techniques Suter, Yannick Knecht, Urspeter Alão, Mariana Valenzuela, Waldo Hewer, Ekkehard Schucht, Philippe Wiest, Roland Reyes, Mauricio Cancer Imaging Research Article BACKGROUND: This study aims to identify robust radiomic features for Magnetic Resonance Imaging (MRI), assess feature selection and machine learning methods for overall survival classification of Glioblastoma multiforme patients, and to robustify models trained on single-center data when applied to multi-center data. METHODS: Tumor regions were automatically segmented on MRI data, and 8327 radiomic features extracted from these regions. Single-center data was perturbed to assess radiomic feature robustness, with over 16 million tests of typical perturbations. Robust features were selected based on the Intraclass Correlation Coefficient to measure agreement across perturbations. Feature selectors and machine learning methods were compared to classify overall survival. Models trained on single-center data (63 patients) were tested on multi-center data (76 patients). Priors using feature robustness and clinical knowledge were evaluated. RESULTS: We observed a very large performance drop when applying models trained on single-center on unseen multi-center data, e.g. a decrease of the area under the receiver operating curve (AUC) of 0.56 for the overall survival classification boundary at 1 year. By using robust features alongside priors for two overall survival classes, the AUC drop could be reduced by 21.2%. In contrast, sensitivity was 12.19% lower when applying a prior. CONCLUSIONS: Our experiments show that it is possible to attain improved levels of robustness and accuracy when models need to be applied to unseen multi-center data. The performance on multi-center data of models trained on single-center data can be increased by using robust features and introducing prior knowledge. For successful model robustification, tailoring perturbations for robustness testing to the target dataset is key. BioMed Central 2020-08-05 /pmc/articles/PMC7405445/ /pubmed/32758279 http://dx.doi.org/10.1186/s40644-020-00329-8 Text en © The Author(s) 2020 Open AccessThis article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated in a credit line to the data.
spellingShingle Research Article
Suter, Yannick
Knecht, Urspeter
Alão, Mariana
Valenzuela, Waldo
Hewer, Ekkehard
Schucht, Philippe
Wiest, Roland
Reyes, Mauricio
Radiomics for glioblastoma survival analysis in pre-operative MRI: exploring feature robustness, class boundaries, and machine learning techniques
title Radiomics for glioblastoma survival analysis in pre-operative MRI: exploring feature robustness, class boundaries, and machine learning techniques
title_full Radiomics for glioblastoma survival analysis in pre-operative MRI: exploring feature robustness, class boundaries, and machine learning techniques
title_fullStr Radiomics for glioblastoma survival analysis in pre-operative MRI: exploring feature robustness, class boundaries, and machine learning techniques
title_full_unstemmed Radiomics for glioblastoma survival analysis in pre-operative MRI: exploring feature robustness, class boundaries, and machine learning techniques
title_short Radiomics for glioblastoma survival analysis in pre-operative MRI: exploring feature robustness, class boundaries, and machine learning techniques
title_sort radiomics for glioblastoma survival analysis in pre-operative mri: exploring feature robustness, class boundaries, and machine learning techniques
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7405445/
https://www.ncbi.nlm.nih.gov/pubmed/32758279
http://dx.doi.org/10.1186/s40644-020-00329-8
work_keys_str_mv AT suteryannick radiomicsforglioblastomasurvivalanalysisinpreoperativemriexploringfeaturerobustnessclassboundariesandmachinelearningtechniques
AT knechturspeter radiomicsforglioblastomasurvivalanalysisinpreoperativemriexploringfeaturerobustnessclassboundariesandmachinelearningtechniques
AT alaomariana radiomicsforglioblastomasurvivalanalysisinpreoperativemriexploringfeaturerobustnessclassboundariesandmachinelearningtechniques
AT valenzuelawaldo radiomicsforglioblastomasurvivalanalysisinpreoperativemriexploringfeaturerobustnessclassboundariesandmachinelearningtechniques
AT hewerekkehard radiomicsforglioblastomasurvivalanalysisinpreoperativemriexploringfeaturerobustnessclassboundariesandmachinelearningtechniques
AT schuchtphilippe radiomicsforglioblastomasurvivalanalysisinpreoperativemriexploringfeaturerobustnessclassboundariesandmachinelearningtechniques
AT wiestroland radiomicsforglioblastomasurvivalanalysisinpreoperativemriexploringfeaturerobustnessclassboundariesandmachinelearningtechniques
AT reyesmauricio radiomicsforglioblastomasurvivalanalysisinpreoperativemriexploringfeaturerobustnessclassboundariesandmachinelearningtechniques