Can diffusion-based generated magnetic resonance images predict glioma methylation accurately?

Background: Reconstructing accelerated magnetic resonance images across various modalities, particularly those involving pathological features such as brain tumors, represents a challenging yet crucial task for medical diagnostics. While deep learning approaches have improved reconstruction quality, existing methods often struggle with preserving diagnostic features across different contrasts. The development of methods that maintain pathological details while substantially reducing scan time remains a clinical need. The purpose of this study is to develop a generative model capable of reconstructing high-quality sequences from accelerated T1-weighted scans, while preserving pathological features critical for glioma diagnosis and MGMT prediction. Methods: In this retrospective study using the BraTS 2021 dataset (n=1,480), we present a diffusion-based generative model capable of producing enhanced magnetic resonance images from T1-weighted scans for T1 contrast-enhanced (T1CE), T2, and fluid attenuated inversion recovery (FLAIR) sequences. Our model was trained on 785 scans and validated on 695 scans with MGMT using 5-fold cross-validation. Simulating K-space degradation, our model recreates the effects of quicker scans at 4-fold and 32-fold acceleration. Results: For 4-fold acceleration, quantitative assessment showed high fidelity reconstruction across sequences [T1CE: structural similarity (SSIM) =0.972, peak signal-to-noise ratio (PSNR) =37.43; T2: SSIM =0.963, PSNR =33.44; FLAIR: SSIM =0.963, PSNR =34.16]. Two radiologists' visual assessments showed no significant differences between reconstructed and original images (P>0.05). The synthesized images also demonstrated consistent methylation classification, showing strong agreement for T1CE: concordance correlation coefficient (CCC) =0.966, R2=0.938; T2: CCC =0.945, R2=0.893; FLAIR: CCC =0.963, R2=0.928. Area under curve values for MGMT prediction remained stable across original and reconstructed images (FLAIR: 0.606, 0.603, 0.601 for original, 4-fold, and 32-fold acceleration, respectively). Conclusions: Our diffusion-based model demonstrates promise in accelerating magnetic resonance image acquisition while preserving vital pathological detail, suggesting enhanced diagnostic capabilities. Future research will evaluate its clinical application, aiming to enhance procedural efficiency and patient comfort.