Deep-learning-based synthesis of post-contrast T1-weighted MRI for tumour response assessment in neuro-oncology: a multicentre, retrospective cohort study

Summary: Background: Gadolinium-based contrast agents (GBCAs) are widely used to enhance tissue contrast during MRI scans and play a crucial role in the management of patients with cancer. However, studies have shown gadolinium deposition in the brain after repeated GBCA administration with yet unk...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Chandrakanth Jayachandran Preetha, MSc, Hagen Meredig, MD, Gianluca Brugnara, MD, Mustafa A Mahmutoglu, MD, Martha Foltyn, MD, Fabian Isensee, PhD, Tobias Kessler, MD, Irada Pflüger, MD, Marianne Schell, MD, Ulf Neuberger, MD, Jens Petersen, PhD, Antje Wick, MD, Sabine Heiland, ProfPhD, Jürgen Debus, ProfMD, Michael Platten, ProfMD, Ahmed Idbaih, MD, Alba A Brandes, ProfMD, Frank Winkler, ProfMD, Martin J van den Bent, ProfMD, Burt Nabors, ProfMD, Roger Stupp, ProfMD, Klaus H Maier-Hein, ProfPhD, Thierry Gorlia, PhD, Jörg-Christian Tonn, ProfMD, Michael Weller, ProfMD, Wolfgang Wick, ProfMD, Martin Bendszus, ProfMD, Philipp Vollmuth, MD
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Computer applications to medicine. Medical informatics R858-859.7
Acceso en línea:	https://doaj.org/article/1d0604c10cd74d3aaeb41f01be7c60b0
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:1d0604c10cd74d3aaeb41f01be7c60b0
record_format	dspace
institution	DOAJ
collection	DOAJ
language	EN
topic	Computer applications to medicine. Medical informatics R858-859.7
spellingShingle	Computer applications to medicine. Medical informatics R858-859.7 Chandrakanth Jayachandran Preetha, MSc Hagen Meredig, MD Gianluca Brugnara, MD Mustafa A Mahmutoglu, MD Martha Foltyn, MD Fabian Isensee, PhD Tobias Kessler, MD Irada Pflüger, MD Marianne Schell, MD Ulf Neuberger, MD Jens Petersen, PhD Antje Wick, MD Sabine Heiland, ProfPhD Jürgen Debus, ProfMD Michael Platten, ProfMD Ahmed Idbaih, MD Alba A Brandes, ProfMD Frank Winkler, ProfMD Martin J van den Bent, ProfMD Burt Nabors, ProfMD Roger Stupp, ProfMD Klaus H Maier-Hein, ProfPhD Thierry Gorlia, PhD Jörg-Christian Tonn, ProfMD Michael Weller, ProfMD Wolfgang Wick, ProfMD Martin Bendszus, ProfMD Philipp Vollmuth, MD Deep-learning-based synthesis of post-contrast T1-weighted MRI for tumour response assessment in neuro-oncology: a multicentre, retrospective cohort study
description	Summary: Background: Gadolinium-based contrast agents (GBCAs) are widely used to enhance tissue contrast during MRI scans and play a crucial role in the management of patients with cancer. However, studies have shown gadolinium deposition in the brain after repeated GBCA administration with yet unknown clinical significance. We aimed to assess the feasibility and diagnostic value of synthetic post-contrast T1-weighted MRI generated from pre-contrast MRI sequences through deep convolutional neural networks (dCNN) for tumour response assessment in neuro-oncology. Methods: In this multicentre, retrospective cohort study, we used MRI examinations to train and validate a dCNN for synthesising post-contrast T1-weighted sequences from pre-contrast T1-weighted, T2-weighted, and fluid-attenuated inversion recovery sequences. We used MRI scans with availability of these sequences from 775 patients with glioblastoma treated at Heidelberg University Hospital, Heidelberg, Germany (775 MRI examinations); 260 patients who participated in the phase 2 CORE trial (1083 MRI examinations, 59 institutions); and 505 patients who participated in the phase 3 CENTRIC trial (3147 MRI examinations, 149 institutions). Separate training runs to rank the importance of individual sequences and (for a subset) diffusion-weighted imaging were conducted. Independent testing was performed on MRI data from the phase 2 and phase 3 EORTC-26101 trial (521 patients, 1924 MRI examinations, 32 institutions). The similarity between synthetic and true contrast enhancement on post-contrast T1-weighted MRI was quantified using the structural similarity index measure (SSIM). Automated tumour segmentation and volumetric tumour response assessment based on synthetic versus true post-contrast T1-weighted sequences was performed in the EORTC-26101 trial and agreement was assessed with Kaplan-Meier plots. Findings: The median SSIM score for predicting contrast enhancement on synthetic post-contrast T1-weighted sequences in the EORTC-26101 test set was 0·818 (95% CI 0·817–0·820). Segmentation of the contrast-enhancing tumour from synthetic post-contrast T1-weighted sequences yielded a median tumour volume of 6·31 cm3 (5·60 to 7·14), thereby underestimating the true tumour volume by a median of −0·48 cm3 (−0·37 to −0·76) with the concordance correlation coefficient suggesting a strong linear association between tumour volumes derived from synthetic versus true post-contrast T1-weighted sequences (0·782, 0·751–0·807, p<0·0001). Volumetric tumour response assessment in the EORTC-26101 trial showed a median time to progression of 4·2 months (95% CI 4·1–5·2) with synthetic post-contrast T1-weighted and 4·3 months (4·1–5·5) with true post-contrast T1-weighted sequences (p=0·33). The strength of the association between the time to progression as a surrogate endpoint for predicting the patients' overall survival in the EORTC-26101 cohort was similar when derived from synthetic post-contrast T1-weighted sequences (hazard ratio of 1·749, 95% CI 1·282–2·387, p=0·0004) and model C-index (0·667, 0·622–0·708) versus true post-contrast T1-weighted MRI (1·799, 95% CI 1·314–2·464, p=0·0003) and model C-index (0·673, 95% CI 0·626–0·711). Interpretation: Generating synthetic post-contrast T1-weighted MRI from pre-contrast MRI using dCNN is feasible and quantification of the contrast-enhancing tumour burden from synthetic post-contrast T1-weighted MRI allows assessment of the patient's response to treatment with no significant difference by comparison with true post-contrast T1-weighted sequences with administration of GBCAs. This finding could guide the application of dCNN in radiology to potentially reduce the necessity of GBCA administration. Funding: Deutsche Forschungsgemeinschaft.
format	article
author	Chandrakanth Jayachandran Preetha, MSc Hagen Meredig, MD Gianluca Brugnara, MD Mustafa A Mahmutoglu, MD Martha Foltyn, MD Fabian Isensee, PhD Tobias Kessler, MD Irada Pflüger, MD Marianne Schell, MD Ulf Neuberger, MD Jens Petersen, PhD Antje Wick, MD Sabine Heiland, ProfPhD Jürgen Debus, ProfMD Michael Platten, ProfMD Ahmed Idbaih, MD Alba A Brandes, ProfMD Frank Winkler, ProfMD Martin J van den Bent, ProfMD Burt Nabors, ProfMD Roger Stupp, ProfMD Klaus H Maier-Hein, ProfPhD Thierry Gorlia, PhD Jörg-Christian Tonn, ProfMD Michael Weller, ProfMD Wolfgang Wick, ProfMD Martin Bendszus, ProfMD Philipp Vollmuth, MD
author_facet	Chandrakanth Jayachandran Preetha, MSc Hagen Meredig, MD Gianluca Brugnara, MD Mustafa A Mahmutoglu, MD Martha Foltyn, MD Fabian Isensee, PhD Tobias Kessler, MD Irada Pflüger, MD Marianne Schell, MD Ulf Neuberger, MD Jens Petersen, PhD Antje Wick, MD Sabine Heiland, ProfPhD Jürgen Debus, ProfMD Michael Platten, ProfMD Ahmed Idbaih, MD Alba A Brandes, ProfMD Frank Winkler, ProfMD Martin J van den Bent, ProfMD Burt Nabors, ProfMD Roger Stupp, ProfMD Klaus H Maier-Hein, ProfPhD Thierry Gorlia, PhD Jörg-Christian Tonn, ProfMD Michael Weller, ProfMD Wolfgang Wick, ProfMD Martin Bendszus, ProfMD Philipp Vollmuth, MD
author_sort	Chandrakanth Jayachandran Preetha, MSc
title	Deep-learning-based synthesis of post-contrast T1-weighted MRI for tumour response assessment in neuro-oncology: a multicentre, retrospective cohort study
title_short	Deep-learning-based synthesis of post-contrast T1-weighted MRI for tumour response assessment in neuro-oncology: a multicentre, retrospective cohort study
title_full	Deep-learning-based synthesis of post-contrast T1-weighted MRI for tumour response assessment in neuro-oncology: a multicentre, retrospective cohort study
title_fullStr	Deep-learning-based synthesis of post-contrast T1-weighted MRI for tumour response assessment in neuro-oncology: a multicentre, retrospective cohort study
title_full_unstemmed	Deep-learning-based synthesis of post-contrast T1-weighted MRI for tumour response assessment in neuro-oncology: a multicentre, retrospective cohort study
title_sort	deep-learning-based synthesis of post-contrast t1-weighted mri for tumour response assessment in neuro-oncology: a multicentre, retrospective cohort study
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/1d0604c10cd74d3aaeb41f01be7c60b0
work_keys_str_mv	AT chandrakanthjayachandranpreethamsc deeplearningbasedsynthesisofpostcontrastt1weightedmrifortumourresponseassessmentinneurooncologyamulticentreretrospectivecohortstudy AT hagenmeredigmd deeplearningbasedsynthesisofpostcontrastt1weightedmrifortumourresponseassessmentinneurooncologyamulticentreretrospectivecohortstudy AT gianlucabrugnaramd deeplearningbasedsynthesisofpostcontrastt1weightedmrifortumourresponseassessmentinneurooncologyamulticentreretrospectivecohortstudy AT mustafaamahmutoglumd deeplearningbasedsynthesisofpostcontrastt1weightedmrifortumourresponseassessmentinneurooncologyamulticentreretrospectivecohortstudy AT marthafoltynmd deeplearningbasedsynthesisofpostcontrastt1weightedmrifortumourresponseassessmentinneurooncologyamulticentreretrospectivecohortstudy AT fabianisenseephd deeplearningbasedsynthesisofpostcontrastt1weightedmrifortumourresponseassessmentinneurooncologyamulticentreretrospectivecohortstudy AT tobiaskesslermd deeplearningbasedsynthesisofpostcontrastt1weightedmrifortumourresponseassessmentinneurooncologyamulticentreretrospectivecohortstudy AT iradapflugermd deeplearningbasedsynthesisofpostcontrastt1weightedmrifortumourresponseassessmentinneurooncologyamulticentreretrospectivecohortstudy AT marianneschellmd deeplearningbasedsynthesisofpostcontrastt1weightedmrifortumourresponseassessmentinneurooncologyamulticentreretrospectivecohortstudy AT ulfneubergermd deeplearningbasedsynthesisofpostcontrastt1weightedmrifortumourresponseassessmentinneurooncologyamulticentreretrospectivecohortstudy AT jenspetersenphd deeplearningbasedsynthesisofpostcontrastt1weightedmrifortumourresponseassessmentinneurooncologyamulticentreretrospectivecohortstudy AT antjewickmd deeplearningbasedsynthesisofpostcontrastt1weightedmrifortumourresponseassessmentinneurooncologyamulticentreretrospectivecohortstudy AT sabineheilandprofphd deeplearningbasedsynthesisofpostcontrastt1weightedmrifortumourresponseassessmentinneurooncologyamulticentreretrospectivecohortstudy AT jurgendebusprofmd deeplearningbasedsynthesisofpostcontrastt1weightedmrifortumourresponseassessmentinneurooncologyamulticentreretrospectivecohortstudy AT michaelplattenprofmd deeplearningbasedsynthesisofpostcontrastt1weightedmrifortumourresponseassessmentinneurooncologyamulticentreretrospectivecohortstudy AT ahmedidbaihmd deeplearningbasedsynthesisofpostcontrastt1weightedmrifortumourresponseassessmentinneurooncologyamulticentreretrospectivecohortstudy AT albaabrandesprofmd deeplearningbasedsynthesisofpostcontrastt1weightedmrifortumourresponseassessmentinneurooncologyamulticentreretrospectivecohortstudy AT frankwinklerprofmd deeplearningbasedsynthesisofpostcontrastt1weightedmrifortumourresponseassessmentinneurooncologyamulticentreretrospectivecohortstudy AT martinjvandenbentprofmd deeplearningbasedsynthesisofpostcontrastt1weightedmrifortumourresponseassessmentinneurooncologyamulticentreretrospectivecohortstudy AT burtnaborsprofmd deeplearningbasedsynthesisofpostcontrastt1weightedmrifortumourresponseassessmentinneurooncologyamulticentreretrospectivecohortstudy AT rogerstuppprofmd deeplearningbasedsynthesisofpostcontrastt1weightedmrifortumourresponseassessmentinneurooncologyamulticentreretrospectivecohortstudy AT klaushmaierheinprofphd deeplearningbasedsynthesisofpostcontrastt1weightedmrifortumourresponseassessmentinneurooncologyamulticentreretrospectivecohortstudy AT thierrygorliaphd deeplearningbasedsynthesisofpostcontrastt1weightedmrifortumourresponseassessmentinneurooncologyamulticentreretrospectivecohortstudy AT jorgchristiantonnprofmd deeplearningbasedsynthesisofpostcontrastt1weightedmrifortumourresponseassessmentinneurooncologyamulticentreretrospectivecohortstudy AT michaelwellerprofmd deeplearningbasedsynthesisofpostcontrastt1weightedmrifortumourresponseassessmentinneurooncologyamulticentreretrospectivecohortstudy AT wolfgangwickprofmd deeplearningbasedsynthesisofpostcontrastt1weightedmrifortumourresponseassessmentinneurooncologyamulticentreretrospectivecohortstudy AT martinbendszusprofmd deeplearningbasedsynthesisofpostcontrastt1weightedmrifortumourresponseassessmentinneurooncologyamulticentreretrospectivecohortstudy AT philippvollmuthmd deeplearningbasedsynthesisofpostcontrastt1weightedmrifortumourresponseassessmentinneurooncologyamulticentreretrospectivecohortstudy
_version_	1718415962304151552
spelling	oai:doaj.org-article:1d0604c10cd74d3aaeb41f01be7c60b02021-11-24T04:33:28ZDeep-learning-based synthesis of post-contrast T1-weighted MRI for tumour response assessment in neuro-oncology: a multicentre, retrospective cohort study2589-750010.1016/S2589-7500(21)00205-3https://doaj.org/article/1d0604c10cd74d3aaeb41f01be7c60b02021-12-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2589750021002053https://doaj.org/toc/2589-7500Summary: Background: Gadolinium-based contrast agents (GBCAs) are widely used to enhance tissue contrast during MRI scans and play a crucial role in the management of patients with cancer. However, studies have shown gadolinium deposition in the brain after repeated GBCA administration with yet unknown clinical significance. We aimed to assess the feasibility and diagnostic value of synthetic post-contrast T1-weighted MRI generated from pre-contrast MRI sequences through deep convolutional neural networks (dCNN) for tumour response assessment in neuro-oncology. Methods: In this multicentre, retrospective cohort study, we used MRI examinations to train and validate a dCNN for synthesising post-contrast T1-weighted sequences from pre-contrast T1-weighted, T2-weighted, and fluid-attenuated inversion recovery sequences. We used MRI scans with availability of these sequences from 775 patients with glioblastoma treated at Heidelberg University Hospital, Heidelberg, Germany (775 MRI examinations); 260 patients who participated in the phase 2 CORE trial (1083 MRI examinations, 59 institutions); and 505 patients who participated in the phase 3 CENTRIC trial (3147 MRI examinations, 149 institutions). Separate training runs to rank the importance of individual sequences and (for a subset) diffusion-weighted imaging were conducted. Independent testing was performed on MRI data from the phase 2 and phase 3 EORTC-26101 trial (521 patients, 1924 MRI examinations, 32 institutions). The similarity between synthetic and true contrast enhancement on post-contrast T1-weighted MRI was quantified using the structural similarity index measure (SSIM). Automated tumour segmentation and volumetric tumour response assessment based on synthetic versus true post-contrast T1-weighted sequences was performed in the EORTC-26101 trial and agreement was assessed with Kaplan-Meier plots. Findings: The median SSIM score for predicting contrast enhancement on synthetic post-contrast T1-weighted sequences in the EORTC-26101 test set was 0·818 (95% CI 0·817–0·820). Segmentation of the contrast-enhancing tumour from synthetic post-contrast T1-weighted sequences yielded a median tumour volume of 6·31 cm3 (5·60 to 7·14), thereby underestimating the true tumour volume by a median of −0·48 cm3 (−0·37 to −0·76) with the concordance correlation coefficient suggesting a strong linear association between tumour volumes derived from synthetic versus true post-contrast T1-weighted sequences (0·782, 0·751–0·807, p<0·0001). Volumetric tumour response assessment in the EORTC-26101 trial showed a median time to progression of 4·2 months (95% CI 4·1–5·2) with synthetic post-contrast T1-weighted and 4·3 months (4·1–5·5) with true post-contrast T1-weighted sequences (p=0·33). The strength of the association between the time to progression as a surrogate endpoint for predicting the patients' overall survival in the EORTC-26101 cohort was similar when derived from synthetic post-contrast T1-weighted sequences (hazard ratio of 1·749, 95% CI 1·282–2·387, p=0·0004) and model C-index (0·667, 0·622–0·708) versus true post-contrast T1-weighted MRI (1·799, 95% CI 1·314–2·464, p=0·0003) and model C-index (0·673, 95% CI 0·626–0·711). Interpretation: Generating synthetic post-contrast T1-weighted MRI from pre-contrast MRI using dCNN is feasible and quantification of the contrast-enhancing tumour burden from synthetic post-contrast T1-weighted MRI allows assessment of the patient's response to treatment with no significant difference by comparison with true post-contrast T1-weighted sequences with administration of GBCAs. This finding could guide the application of dCNN in radiology to potentially reduce the necessity of GBCA administration. Funding: Deutsche Forschungsgemeinschaft.Chandrakanth Jayachandran Preetha, MScHagen Meredig, MDGianluca Brugnara, MDMustafa A Mahmutoglu, MDMartha Foltyn, MDFabian Isensee, PhDTobias Kessler, MDIrada Pflüger, MDMarianne Schell, MDUlf Neuberger, MDJens Petersen, PhDAntje Wick, MDSabine Heiland, ProfPhDJürgen Debus, ProfMDMichael Platten, ProfMDAhmed Idbaih, MDAlba A Brandes, ProfMDFrank Winkler, ProfMDMartin J van den Bent, ProfMDBurt Nabors, ProfMDRoger Stupp, ProfMDKlaus H Maier-Hein, ProfPhDThierry Gorlia, PhDJörg-Christian Tonn, ProfMDMichael Weller, ProfMDWolfgang Wick, ProfMDMartin Bendszus, ProfMDPhilipp Vollmuth, MDElsevierarticleComputer applications to medicine. Medical informaticsR858-859.7ENThe Lancet: Digital Health, Vol 3, Iss 12, Pp e784-e794 (2021)

Deep-learning-based synthesis of post-contrast T1-weighted MRI for tumour response assessment in neuro-oncology: a multicentre, retrospective cohort study

Ejemplares similares