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

Abstract

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.

Conflict of interest statement

Declaration of interests SH reports grants from the German Research Council and Dietmar-Hopp Foundation, outside of the submitted work. JD reports grants from ViewRay, the Clinical Research Institute, Accuray, RaySearch Laboratories, Vision RT, Merck, Astellas Pharma, AstraZeneca, Siemens Healthcare, Solution Akademie, Egomed, Quintiles, Pharmaceutical Research Association, Boehringer Ingelheim, PTW-Freiburg, and Nanobiotix, outside of the submitted work. MP reports non-financial support from Pfizer, and grants and personal fees from Bayer, outside of the submitted work. MP also has a licensed patent for IDH1 vaccines, a patent H3 vaccine pending, and a patent AHR inhibitor with royalties paid to Bayer. AI reports grants and travel funding from Carthera; research grants from Transgene, Sanofi, Air Liquide, and Nutritheragene; travel funding from Leo Pharma; and is on the advisory board for Novocure and Leo Pharma, outside the submitted work. MjvdB reports personal fees from Roche, Cellgene, Bristol Myers Squibb, Agios, Merck Sharpe & Dohme, and Boehringer Ingelheim; and grants and personal fees from AbbVie, outside of the submitted work. BN is on the scientific advisory board for Karyopharm and BTG Pharmaceuticals and is on the data safety and monitoring board for the University of Pennsylvania (Philadelphia, PA, USA), outside of the submitted work. J-CT reports personal fees from BrainLab and carThera, outside of the submitted work. WW reports grants from Apogenix, Boehringer Ingelheim, and Pfizer; grants and personal fees from Merck Sharp and Dohme and Roche; and personal fees from Bristol Myers Squibb and Celldex, outside of the submitted work. MB reports personal fees from Boehringer Ingelheim, Merck, Bayer, Teva, B Braun, Springer, and Vascular Dynamics; grants and personal fees from Novartis, Codman, and Guerbet; and grants from Siemens, Hopp Foundation, the German Research Council, the EU, Stryker, and Medtronic, outside of the submitted work. All other authors declare no competing interests.

Copyright © 2021 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license. Published by Elsevier Ltd.. All rights reserved.