.png){kind=icon}
返回
High-resolution MRI synthesis using a data-driven framework with denoising diffusion probabilistic modeling
.png){kind=icon}
OA
AI
DOI：10.1088/1361-6560/ad209c.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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.
Keyword:
MRI
diffusion model
high-resolution imaging
image synthesis
deep learning
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.4
论文数:
1.4W
被引数:
3.1W
机构
引用论文
分享收藏SRDiff: Single image super-resolution with diffusion probabilistic modelsSRDiff: 具有扩散概率模型的单幅图像超分辨率.png)
NEUROCOMPUTINGOAAI
NEUROCOMPUTINGIF6.5
OAAI分享收藏Atrophied Brain T2 Lesion Volume at MRI Is Associated with Disability Progression and Conversion to Secondary Progressive Multiple SclerosisRADIOLOGYOAAI
RADIOLOGYIF15.2
OAAI分享收藏A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications生成对抗网络研究综述: 算法、理论与应用
OAAI
OAAI分享收藏分享收藏Unsupervised arterial spin labeling image superresolution via multiscale generative adversarial networkMEDICAL PHYSICS
MEDICAL PHYSICSIF3.2
PREAI
分享收藏
查看更多内容