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. MethodsIn 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 postcontrast 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•6...

Automated detection and quantification of brain metastases on clinical MRI data using artificial neural networks

“…To mitigate this, previous studies have shown that missing MRI sequences may be synthesized using generative adversarial networks. 34 , 35 Consequently, this may enable the use of HD-BM even with incomplete and heterogeneous sequence protocols.…”

Artificial Intelligence in Neuro-Oncologic Imaging: A Brief Review for Clinical Use Cases and Future Perspectives

“…The GAN utility is an image-to-image translation task, which is useful for generating synthetic data to fill in absent or insufficient data in a multicenter trial. Jayachandran et al [ 41 ] explored the synthesis of post-contrast MRI sequences from pre-contrast MRI sequences alone by filling in absent imaging data without the use of the gadolinium-based contrast agent during MRI. The study incorporated MRI data from three phase 2 and 3 clinical trials with >2,000 patients.…”

Research Highlight: Use of Generative Images Created with Artificial Intelligence for Brain Tumor Imaging

“…Recently, Jayachandran Preetha et al [ 17 ] investigated the synthesis of post-contrast MRI sequences using pre-contrast MRI sequences, filling in the absence of imaging data for imaging evaluation of glioblastoma ( Fig. 1 ).…”

“…From this hypothesis-generating study [ 17 ], we can obtain ideas about how to apply and validate GANs in clinical cases. First, synthetic images can be used as direct substitutes for real images and can make the use contrast media for MRI or CT imaging or an additional radiation exposure for X-ray, CT, or PET imaging optional, thereby reducing the harm or cost associated with the extra imaging procedures.…”

“…The imaging requisites for synthetic vc-T1WI were multi-parametric imaging, including T1WI, T2WI, FLAIR [ 17 ], and additional diffusion-weighted and susceptibility-weighted sequences [ 16 ]. A feasibility study showed that diffusion-weighted imaging and T2WI contributed to demonstrating peritumoral edema, cellularity, and necrosis [ 16 ], while Jayachandran Preetha et al [ 17 ] found that T2WI and FLAIR contributions were larger than diffusion-weighted imaging because the contrast enhancement of brain tumors is based on disruption of the blood-brain barrier, not on cellularity. The different prerequisites for imaging sequences show that the technique is yet to be optimized and further studies are warranted.…”