Machine Learning-Based Adaptation of Data Sampling and Reconstruction for Efficient Dynamic MRI

基于机器学习的数据采样和重建适应高效动态 MRI

• 批准号: 10453232
• 负责人: Saiprasad Ravishankar
• 金额: $ 23.88万
• 依托单位: MICHIGAN STATE UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-09-30 至 2024-07-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10453232
• 关键词: Acceleration; Algorithms; Anatomy; Behavior; Benchmarking; Characteristics; Clinical; Clinical Treatment; Data; Data Collection; Data Set; Detection; Development; Diagnostic; Dictionary; EFRAC; Formulation; Goals; Heart; Hospitals; Image; Imaging Techniques; Imaging technology; Joints; Lead; Learning; Left; MRI Scans; Machine Learning; Magnetic Resonance Imaging; Mathematics; Methods; Modeling; Motion; Neural Network Simulation; Organ; Patients; Pattern; Performance; Physicians; Physiological; Plant Roots; Protocols documentation; Resolution; Sampling; Scanning; Scheme; Slice; Speed; Structure; System; Task Performances; Techniques; Testing; Time; Tissues; Ventricular End-Systolic Volumes; Work; base; cardiac magnetic resonance imaging; clinical diagnosis; clinical practice; convolutional neural network; cost; data acquisition; design; disease diagnosis; effectiveness study; flexibility; future implementation; heart imaging; image reconstruction; imaging system; improved; learning strategy; machine learning algorithm; machine learning method; machine learning pipeline; non-invasive imaging; prospective; public health relevance; reconstruction; soft tissue; spatiotemporal; temporal measurement; tool; transfer learning

ABSTRACT Magnetic resonance imaging (MRI) is essential for the detection and diagnosis of diseases. Clinical MRI scanners use fixed sequential data sampling patterns with long acquisition times, and employ nonadaptive reconstruction algorithms to generate images. The acquisitions are not usually tailored for the specific clinical task and patient characteristics, leading to sub-optimal images; they are often low-resolution, blurry, or contain errors that can reduce their diagnostic efficacy. Dynamic imaging applications, in which many images must be captured quickly to depict the motion of organs such as the heart, tend to suffer the most from these ill-effects. We propose to replace the conventional dynamic MRI acquisitions with a machine learning-based acquisition system, where the data sampling is efficiently optimized together with the reconstruction approach and task prediction, for optimized image quality and clinical task performance. First, we will explore and compare different ways of learning fast sampling of MRI frames to optimize image reconstruction quality metrics using large public data sets and current sophisticated (iterative) reconstruction algorithms. We will as- certain the sampling learning strategies that achieve the best image reconstruction quality at high data undersampling factors. Second, we will further extend machine learning throughout the MRI pipeline and develop approaches for joint adaptation of the data acquisition and image reconstruction and finally the task (e.g., quantification task) predictor as well. A key approach will use highly undersampled initial acquisitions (of current frame) and/or past (frame) data as input to the learned acquisition model to rapidly predict a patient- and frame-adaptive optimized sampling pattern. Then the samples from the scanner will be used to rapidly produce machine-learned reconstructions followed by task predictions. Particularly, for dynamic MRI, the temporal information from preceding images (frames) will be effectively incorporated and exploited in the proposed machine-learned models to drive efficient on-the-fly adaptive acquisitions and reconstruc- tions. We propose the mathematical formulations and algorithmic framework to accomplish these goals. The developed learning-based methods will be comprehensively evaluated and cross-compared in terms of image quality metrics (e.g., root mean squared error) and dynamic cardiac MRI task performance (ejection fraction estimation) at several undersam- pling or acceleration rates, and benchmarked using existing data sets as well as using newly collected cardiac MRI data. The development of smart imaging technologies that infuse learning across the imaging pipeline could enable rapid and effective task-driven adaptive imaging for dynamic cardiac MRI and related applications. Such a machine-learning MRI system could potentially improve clinical diagnosis and treatment, by helping enable the imaging system and acquisition to adapt in real-time to optimally detect and image various features at high resolution. Our goal in this project is to conduct the initial comprehensive studies to determine and analyze the potential, robustness, and algorithm behavior of the proposed machine learning dynamic MRI framework and techniques.

抽象的 磁共振成像 (MRI) 对于临床 MRI 扫描仪的检测和诊断至关重要。 修复具有长采集时间的顺序数据采样模式，并采用非自适应重建算法 生成图像通常不适合特定的临床任务和患者特征， 导致图像质量不佳；它们通常分辨率低、模糊或包含可能降低诊断效果的错误 动态成像应用，其中必须快速捕获许多图像以描绘器官的运动。 例如心脏，往往受到这些不良影响的影响最大，我们建议更换传统的动态 MRI。 使用基于机器学习的采集系统进行采集，其中数据采样同时得到有效优化 通过重建方法和任务预测，优化图像质量和临床任务性能。 我们将探索和比较学习 MRI 帧快速采样以优化图像重建的不同方法 使用大型公共数据集和当前复杂的（迭代）重建算法的质量指标我们将作为- 确定在高数据欠采样下实现最佳图像重建质量的采样学习策略 其次，我们将进一步将机器学习扩展到整个 MRI 流程中，并开发联合方法。 数据采集​​和图像重建的适应，最后任务（例如量化任务）预测器为 一个关键方法将使用高度欠采样的初始采集（当前帧）和/或过去（帧）数据作为输入。 学习到的采集模型可以快速预测患者和框架自适应的优化采样模式。 来自扫描仪的样本将用于快速生成机器学习的重建，然后进行任务预测。 特别是，对于动态 MRI，来自先前图像（帧）的时间信息将被有效地合并 并在所提出的机器学习模型中利用来驱动高效的动态自适应采集和重建 我们提出了实现这些目标的数学公式和算法框架。 基于学习的方法将在图像质量指标方面进行全面评估和交叉比较（例如， 均方根误差）和动态心脏 MRI 任务表现（射血分数估计）在几个欠采样 速度或加速度，并使用现有数据集以及新收集的心脏 MRI 数据进行基准测试。 智能成像技术的发展将学习融入到整个成像流程中，可以实现快速、准确的成像。 用于动态心脏 MRI 和相关应用的有效任务驱动自适应成像。 系统可以通过帮助启用成像系统和采集来改善临床诊断和治疗 实时适应以高分辨率检测和成像各种特征。 进行初步全面研究，以确定和分析潜力、鲁棒性和算法行为 提出的机器学习动态 MRI 框架和技术。