High-resolution MRI synthesis using a data-driven framework with denoising diffusion probabilistic modeling

Abstract

High-resolution magnetic resonance imaging (MRI) can enhance lesion diagnosis, prognosis, and delineation. However, gradient power and hardware limitations prohibit recording thin slices or sub-1 mm resolution. Furthermore, long scan time is not clinically acceptable. Conventional high-resolution images generated using statistical or analytical methods include the limitation of capturing complex, high-dimensional image data with intricate patterns and structures. This study aims to harness cutting-edge diffusion probabilistic deep learning techniques to create a framework for generating high-resolution MRI from low-resolution counterparts, improving the denoising diffusion probabilistic model (DDPM) by minimizing its unpredictability and uncertainty. DDPM includes two processes. The forward process employs a Markov chain to systematically introduce Gaussian noise to low-resolution MRI images. In the reverse process, a U-Net model is trained to denoise the forward process images and produce high-resolution images conditioned on the features of their low-resolution counterparts. The proposed framework was demonstrated using T2-weighted MRI images from institutional prostate patients and brain patients collected in the Brain Tumor Segmentation Challenge 2020 (BraTS2020). For the prostate dataset, the bicubic interpolation model (Bicubic), conditional generative-adversarial network (CGAN), and our proposed DDPM framework improved the noise quality measure from low-resolution images by 4.4%, 5.7%, and 12.8%, respectively. Our method enhanced the signal-to-noise ratios by 11.7%, surpassing Bicubic (9.8%) and CGAN (8.1%). In the BraTS2020 dataset, the proposed framework and Bicubic enhanced PSNR from resolution-degraded images by 9.1% and 5.8%. The multi-scale structural similarity indexes were 0.970±0.019, 0.968±0.022, and 0.967±0.023 for the proposed method, CGAN, and Bicubic, respectively. This study explores a deep learning-based diffusion probabilistic framework for improving MR image resolution. Such a framework can be used to improve clinical workflow by obtaining high-resolution images without penalty of the long scan time. Future investigation will likely focus on prospectively testing the efficacy of this framework with different clinical indications.

CT-based synthetic contrast-enhanced dual-energy CT generation using conditional denoising diffusion probabilistic model

“…Another limitation is the variability inherent in the outputs generated by the proposed method. Our previous study addressed this issue by averaging several outputs, which helped to reduce the likelihood of illusions produced by DDPM-based models (Chang et al 2024 ). Furthermore, it is important to discuss potential biases in the data and limitations in the model’s applicability to different types of CT scans or patient demographics.…”