Cargando…

MRI-Based Deep Learning Tools for MGMT Promoter Methylation Detection: A Thorough Evaluation

SIMPLE SUMMARY: A major prognosis factor for glioblastoma patients is the methylation status of the DNA repair enzyme MGMT. Obtaining this information using deep learning models trained on non-invasive MRI data is a major challenge with no scientific consensus to date. In this study, we provide a mo...

Descripción completa

Detalles Bibliográficos
Autores principales: Robinet, Lucas, Siegfried, Aurore, Roques, Margaux, Berjaoui, Ahmad, Cohen-Jonathan Moyal, Elizabeth
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10137327/
https://www.ncbi.nlm.nih.gov/pubmed/37190181
http://dx.doi.org/10.3390/cancers15082253
_version_ 1785032436187398144
author Robinet, Lucas
Siegfried, Aurore
Roques, Margaux
Berjaoui, Ahmad
Cohen-Jonathan Moyal, Elizabeth
author_facet Robinet, Lucas
Siegfried, Aurore
Roques, Margaux
Berjaoui, Ahmad
Cohen-Jonathan Moyal, Elizabeth
author_sort Robinet, Lucas
collection PubMed
description SIMPLE SUMMARY: A major prognosis factor for glioblastoma patients is the methylation status of the DNA repair enzyme MGMT. Obtaining this information using deep learning models trained on non-invasive MRI data is a major challenge with no scientific consensus to date. In this study, we provide a more rigorous and comprehensive answer to this question by using confidence metrics and relating them to the exact percentage of methylation obtained at biopsy. This systematic approach confirms that the deep learning algorithms developed until now are not suitable for clinical application. We also provide, to the best of our knowledge, the first fully reproducible source code and experiments on this issue. ABSTRACT: Glioblastoma is the most aggressive primary brain tumor, which almost systematically relapses despite surgery (when possible) followed by radio-chemotherapy temozolomide-based treatment. Upon relapse, one option for treatment is another chemotherapy, lomustine. The efficacy of these chemotherapy regimens depends on the methylation of a specific gene promoter known as MGMT, which is the main prognosis factor for glioblastoma. Knowing this biomarker is a key issue for the clinician to personalize and adapt treatment to the patient at primary diagnosis for elderly patients, in particular, and also upon relapse. The association between MRI-derived information and the prediction of MGMT promoter status has been discussed in many studies, and some, more recently, have proposed the use of deep learning algorithms on multimodal scans to extract this information, but they have failed to reach a consensus. Therefore, in this work, beyond the classical performance figures usually displayed, we seek to compute confidence scores to see if a clinical application of such methods can be seriously considered. The systematic approach carried out, using different input configurations and algorithms as well as the exact methylation percentage, led to the following conclusion: current deep learning methods are unable to determine MGMT promoter methylation from MRI data.
format Online
Article
Text
id pubmed-10137327
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-101373272023-04-28 MRI-Based Deep Learning Tools for MGMT Promoter Methylation Detection: A Thorough Evaluation Robinet, Lucas Siegfried, Aurore Roques, Margaux Berjaoui, Ahmad Cohen-Jonathan Moyal, Elizabeth Cancers (Basel) Article SIMPLE SUMMARY: A major prognosis factor for glioblastoma patients is the methylation status of the DNA repair enzyme MGMT. Obtaining this information using deep learning models trained on non-invasive MRI data is a major challenge with no scientific consensus to date. In this study, we provide a more rigorous and comprehensive answer to this question by using confidence metrics and relating them to the exact percentage of methylation obtained at biopsy. This systematic approach confirms that the deep learning algorithms developed until now are not suitable for clinical application. We also provide, to the best of our knowledge, the first fully reproducible source code and experiments on this issue. ABSTRACT: Glioblastoma is the most aggressive primary brain tumor, which almost systematically relapses despite surgery (when possible) followed by radio-chemotherapy temozolomide-based treatment. Upon relapse, one option for treatment is another chemotherapy, lomustine. The efficacy of these chemotherapy regimens depends on the methylation of a specific gene promoter known as MGMT, which is the main prognosis factor for glioblastoma. Knowing this biomarker is a key issue for the clinician to personalize and adapt treatment to the patient at primary diagnosis for elderly patients, in particular, and also upon relapse. The association between MRI-derived information and the prediction of MGMT promoter status has been discussed in many studies, and some, more recently, have proposed the use of deep learning algorithms on multimodal scans to extract this information, but they have failed to reach a consensus. Therefore, in this work, beyond the classical performance figures usually displayed, we seek to compute confidence scores to see if a clinical application of such methods can be seriously considered. The systematic approach carried out, using different input configurations and algorithms as well as the exact methylation percentage, led to the following conclusion: current deep learning methods are unable to determine MGMT promoter methylation from MRI data. MDPI 2023-04-12 /pmc/articles/PMC10137327/ /pubmed/37190181 http://dx.doi.org/10.3390/cancers15082253 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Robinet, Lucas
Siegfried, Aurore
Roques, Margaux
Berjaoui, Ahmad
Cohen-Jonathan Moyal, Elizabeth
MRI-Based Deep Learning Tools for MGMT Promoter Methylation Detection: A Thorough Evaluation
title MRI-Based Deep Learning Tools for MGMT Promoter Methylation Detection: A Thorough Evaluation
title_full MRI-Based Deep Learning Tools for MGMT Promoter Methylation Detection: A Thorough Evaluation
title_fullStr MRI-Based Deep Learning Tools for MGMT Promoter Methylation Detection: A Thorough Evaluation
title_full_unstemmed MRI-Based Deep Learning Tools for MGMT Promoter Methylation Detection: A Thorough Evaluation
title_short MRI-Based Deep Learning Tools for MGMT Promoter Methylation Detection: A Thorough Evaluation
title_sort mri-based deep learning tools for mgmt promoter methylation detection: a thorough evaluation
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10137327/
https://www.ncbi.nlm.nih.gov/pubmed/37190181
http://dx.doi.org/10.3390/cancers15082253
work_keys_str_mv AT robinetlucas mribaseddeeplearningtoolsformgmtpromotermethylationdetectionathoroughevaluation
AT siegfriedaurore mribaseddeeplearningtoolsformgmtpromotermethylationdetectionathoroughevaluation
AT roquesmargaux mribaseddeeplearningtoolsformgmtpromotermethylationdetectionathoroughevaluation
AT berjaouiahmad mribaseddeeplearningtoolsformgmtpromotermethylationdetectionathoroughevaluation
AT cohenjonathanmoyalelizabeth mribaseddeeplearningtoolsformgmtpromotermethylationdetectionathoroughevaluation