A comprehensive deep learning framework for MRI reconstruction

用于 MRI 重建的综合深度学习框架

基本信息

批准号：
10608060
负责人：
Rizwan Ahmad
金额：
$ 56.92万
依托单位：
OHIO STATE UNIVERSITY
依托单位国家：
美国
项目类别：
财政年份：
2021
资助国家：
美国
起止时间：
2021-07-01 至 2025-03-31
项目状态：
未结题

来源：
https://reporter.nih.gov/project-details/10608060
关键词：
3-Dimensional 4D MRI Acceleration Address Adoption Adult Algorithms Anesthesia procedures Architecture Awareness Brain Brain Neoplasms Brain imaging Breathing Cardiac Child Childhood Clinical Data Development Diagnosis Disease Evaluation Exhibits Formulation Goals Headache Heart Heart Diseases Image Imaging Device Immune Investigation Learning Magnetic Resonance Imaging Maps Methods Modeling Motion Network-based Patients Pattern Performance Phase Physics Play Predisposition Process Pythons Recovery Rest Sampling Scanning Sedation procedure Speed Structure Techniques Technology Testing Time Training Variant Work cardiovascular imaging computer framework convolutional neural network cost data acquisition data space deep learning denoising design diagnostic value heart imaging high dimensionality image reconstruction imaging modality improved learning strategy musculoskeletal imaging neural network architecture novel pediatric patients prospective real-time images reconstruction repository

项目摘要

PROJECT SUMMARY/ABSTRACT The primary goal of this investigation is to develop and validate a comprehensive, robust deep learning (DL) framework that improves MRI reconstruction beyond the limits of existing technology. The proposed framework uses “plug-and-play” algorithms to combine physics-driven MR acquisition models with state-of-the-art learned image models, which are instantiated by image denoising subroutines. To fully exploit the rich structure of MR images, we propose to use DL-based denoisers that are trained in an application-speciﬁc manner. The proposed framework, termed PnP-DL, offers advantages over other existing DL methods, as well as compressed sensing (CS). Compared to existing DL methods for MRI reconstruction, PnP-DL is more immune to inevitable variations in the forward model, such as changes in the coil sensitivities or undersampling pattern, allowing it to generalize across applications and acquisition settings. Compared to CS, PnP-DL recovers images faster, with higher quality, and with potentially superior diagnostic value. Our preliminary results highlight the potential of PnP-DL to advance MRI technology. In this work, we will fur- ther develop PnP-DL and validate it in these major applications: cardiac cine, 2D brain, and 3D brain imaging. In Aim 1, we will train and optimize convolutional neural network-based application-speciﬁc denoisers for the above-mentioned applications. The denoiser with the best denoising performance will be selected for further investigation. In Aim 2, we will develop and compare different PnP algorithms. The algorithm yielding the best combination of reconstruction accuracy and computational speed will be implemented in Gadgetron for inline processing. In Aim 3, we will compare the performance of PnP-DL to other state-of-the-art methods using retro- spectively undersampled data. This study will demonstrate that, in terms of image quality, PnP-DL is superior to CS and existing DL methods and, despite higher acceleration, is non-inferior to parallel MRI with rate-2 acceler- ation. In Aim 4, we will evaluate the performance of PnP-DL using prospectively undersampled data from adult and pediatric patients. Successful completion of this project will demonstrate that PnP-DL outperforms state- of-the-art methods in terms of image quality while exhibiting a level of robustness and broad applicability that has eluded other DL-based MRI reconstruction methods. The acceleration and image quality improvement afforded by these developments will beneﬁt almost all MRI applications, including pediatric imaging, where reducing sedation is a pressing need, and high-dimensional imaging applications (e.g., whole-heart 4D ﬂow imaging), which are too slow for routine clinical use.

项目概要/摘要这项调查的主要目标是开发和验证全面、强大的深度学习 (DL) 改进 MRI 重建的框架超越了现有技术的限制。使用“即插即用”算法将物理驱动的 MR 采集模型与最先进的学习相结合图像模型，由图像去噪子程序实例化，以充分利用 MR 的丰富结构。对于图像，我们建议使用基于深度学习的降噪器，并以特定于应用的方式进行训练。称为 PnP-DL 的框架比其他现有的 DL 方法以及压缩感知具有优势 (CS) 与现有的 MRI 重建 DL 方法相比，PnP-DL 更容易受到不可避免的变化的影响。在前向模型中，例如线圈灵敏度或欠采样模式的变化，使其能够泛化与 CS 相比，PnP-DL 可以更快地恢复图像，并且质量更高。并具有潜在的优越诊断价值。我们的初步结果凸显了 PnP-DL 推进 MRI 技术的潜力。在这项工作中，我们将进一步研究。他们开发了 PnP-DL 并在以下主要应用中对其进行验证：心脏电影、2D 大脑和 3D 大脑成像。在目标 1 中，我们将训练和优化基于卷积神经网络的特定应用降噪器将选择具有最佳降噪性能的降噪器进行进一步的应用。在目标 2 中，我们将开发并比较产生最佳结果的不同 PnP 算法。重建精度和计算速度的结合将在 Gadgetron 中实现内联在目标 3 中，我们将使用逆向技术将 PnP-DL 的性能与其他最先进的方法进行比较。这项研究将证明，在图像质量方面，PnP-DL 优于。 CS 和现有的 DL 方法，尽管加速度更高，但并不劣于具有速率 2 加速器的并行 MRI 在目标 4 中，我们将使用成人的前瞻性欠采样数据来评估 PnP-DL 的性能。该项目的成功完成将证明 PnP-DL 的性能优于州级患者。在图像质量方面采用最先进的方法，同时表现出一定程度的稳健性和广泛的适用性已经超越了其他基于深度学习的 MRI 重建方法的加速和图像质量改进。这些发展带来的好处将惠及几乎所有 MRI 应用，包括儿科成像，其中减少镇静是迫切需要，高维成像应用（例如全心 4D 血流）成像），这对于常规临床使用来说太慢了。