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...

Objectives To assess the interreader and test-retest reliability of magnetization transfer imaging (MTI) and T2 relaxometry in sciatic nerve MR neurography (MRN). Materials and methods In this prospective study, 21 healthy volunteers were examined three times on separate days by a standardized MRN protocol at 3 Tesla, consisting of an MTI sequence, a multi-echo T2 relaxometry sequence, and a high-resolution T2-weighted sequence. Magnetization transfer ratio (MTR), T2 relaxation time, and proton spin density (PSD) of the sciatic nerve were assessed by two independent observers, and both interreader and test-retest reliability for all readout parameters were reported by intraclass correlation coefficients (ICCs) and standard error of measurement (SEM). Results For the sciatic nerve, overall mean ± standard deviation MTR was 26.75 ± 3.5%, T2 was 64.54 ± 8.2 ms, and PSD was 340.93 ± 78.8. ICCs ranged between 0.81 (MTR) and 0.94 (PSD) for interreader reliability and between 0.75 (MTR) and 0.94 (PSD) for test-retest reliability. SEM for interreader reliability was 1.7% for MTR, 2.67 ms for T2, and 21.3 for PSD. SEM for test-retest reliability was 1.7% for MTR, 2.66 ms for T2, and 20.1 for PSD. Conclusions MTI and T2 relaxometry of the sciatic nerve are reliable and reproducible. The values of measurement imprecision reported here may serve as a guide for correct interpretation of quantitative MRN biomarkers in future studies. Key Points • Magnetization transfer imaging (MTI) and T2 relaxometry of the sciatic nerve are reliable and reproducible. • The imprecision that is unavoidably associated with different scans or different readers can be estimated by the here presented SEM values for the biomarkers T2, PSD, and MTR. • These values may serve as a guide for correct interpretation of quantitative MRN biomarkers in future studies and possible clinical applications.

Background To assess whether AI-based decision support allows more reproducible and standardized assessment of treatment response on MRI in neuro-oncology as compared to manual 2-dimensional measurements of tumor burden using the RANO criteria. Methods A series of 30 patients (15 lower-grade gliomas, 15 glioblastoma) with availability of consecutive MRI scans was selected. The time to progression (TTP) on MRI was separately evaluated for each patient by 15 investigators over two rounds. In the 1 st round the TTP was evaluated based on the RANO-criteria, whereas in the 2 nd round the TTP was evaluated by incorporating additional information from AI-enhanced MRI-sequences depicting the longitudinal changes in tumor volumes. The agreement of the TTP-measurements between investigators was evaluated using concordance correlation coefficients (CCC) with confidence intervals (CI) and p-values obtained using bootstrap resampling. Results The CCC of TTP-measurements between investigators was 0.77 (95%CI=0.69,0.88) with RANO alone and increased to 0.91 (95%CI=0.82,0.95) with AI-based decision support (p=0.005). This effect was significantly greater (p=0.008) for patients with lower-grade gliomas (CCC=0.70 [95%CI=0.56,0.85] without vs. 0.90 [95%CI=0.76,0.95] with AI-based decision support) as compared to glioblastoma (CCC=0.83 [95%CI=0.75,0.92] without vs. 0.86 [95%CI=0.78,0.93] with AI-based decision support). Investigators with less years of experience judged the AI-based decision as more helpful (p=0.02). Conclusions AI-based decision support has the potential to yield more reproducible and standardized assessment of treatment response in neuro-oncology as compared to manual 2-dimensional measurements of tumor burden, particularly in patients with lower-grade gliomas. A fully-functional version of this AI-based processing pipeline is provided as open-source (https://github.com/NeuroAI-HD/HD-GLIO-XNAT).