{"id":"doi:10.1088/1361-6560/ad209c","kind":"article","title":"High-resolution MRI synthesis using a data-driven framework with denoising diffusion probabilistic modeling","authors":["Chih‐Wei Chang","Junbo Peng","Mojtaba Safari","Elahheh Salari","Shaoyan Pan","Justin R. Roper","Richard L. J. Qiu","Yuan Gao","Hui‐Kuo G. Shu","Hui Z. Mao","Xiaofeng Yang"],"author_count":11,"year":2024,"published":"2024-01-19","venue":"Physics in Medicine and Biology","cited_by":39,"doi":"10.1088/1361-6560/ad209c","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1088/1361-6560/ad209c","archive_url":"https://space-kitty.com/papers/doi:10.1088/1361-6560/ad209c","updated":null,"pmid":"38241726","pmcid":null,"openalex_id":"W4391014509","pdf_url":null,"abstract":"Abstract Objective . 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 uncertainty of denoising diffusion probabilistic models (DDPM). Approach . 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). Main results . 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 peak signal-to-noise ratio 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. Significance . 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.","abstract_license":"CC-BY (publisher license, via OpenAlex)","license":"cc-by","is_open_access":true,"retracted":false,"peer_reviewed":null,"categories":["Advanced Image Processing Techniques"],"details":null,"provenance":"openalex","attribution":"Abstract of \"High-resolution MRI synthesis using a data-driven framework with denoising diffusion probabilistic modeling\" by Chih‐Wei Chang, Junbo Peng, Mojtaba Safari et al., https://doi.org/10.1088/1361-6560/ad209c, used under its Creative Commons Attribution license (CC-BY); markup removed, otherwise unmodified.","topics":[{"slug":"generative-multimodal","name":"Generative & Multimodal Models","domain_slug":"ai"}],"cited_in_dossiers":[]}