Ultra-Fast Knee MRI with Deep Learning

具有深度学习功能的超快速膝关节 MRI

• 批准号: 10177641
• 负责人: Valentina Pedoia
• 金额: $ 57.43万
• 依托单位: UNIVERSITY OF CALIFORNIA, SAN FRANCISCO
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-04-01 至 2026-03-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10177641
• 关键词: 3-Dimensional; Acceleration; Area; Automation; Bayesian Modeling; Benchmarking; Cartilage; Characteristics; Clinical; Collection; Complement; Data; Data Set; Degenerative polyarthritis; Detection; Development; Ensure; Evaluation; Human; Image; Image Analysis; Injury; Intelligence; Knee; Knee joint; Label; Lead; Learning; Licensing; MRI Scans; Magnetic Resonance Imaging; Manuals; Measurement; Methodology; Methods; Modeling; Morphology; Patient Triage; Patients; Performance; Probability; Process; Protocols documentation; Protons; Radiology Specialty; Reader; Reading; Reproducibility; Research; Resolution; Resource Sharing; Sampling; Scanning; Severities; Signal Transduction; Staging; Standardization; Statistical Distributions; System; Techniques; Testing; Thick; Time; Tissues; Training; Translating; Translations; Uncertainty; Vendor; base; clinical application; clinical practice; clinical translation; clinically relevant; cohort; computerized data processing; convolutional neural network; data space; data to knowledge; deep learning; density; design; domain mapping; experimental study; feature extraction; heterogenous data; image processing; image reconstruction; imaging system; joint destruction; learning ability; musculoskeletal imaging; neural network; new technology; novel; open source; preservation; prospective; radiologist; reconstruction; recruit; research study; sensor; supervised learning; tool; validation studies

ABSTRACT Fast, robust and reliable quantitative knee joint MR imaging would be a significant step forward in studying joint degeneration, injury and osteoarthritis (OA). Automation of compositional and morphological feature extraction of the tissues in the knee it is an essential step for translation to clinical practice of promising quantitative techniques. It would enable the analysis of large patient cohorts and assist the radiologist/clinician in augmenting the value of MRI. Automation of several human tasks has been achieved in the last few years by the usage of Deep Learning techniques. With the availability of large amounts of annotated data and processing power, using the concepts of transforming data to knowledge by the observation of examples, supervised learning can today accomplish challenges never demonstrated before. In addition to image analysis and interpretation, Deep Learning is revolutionizing the acquisition and reconstruction aspects of the pipeline. Models can learn a direct mapping between under sampled k-space and image domain. While Deep Learning application to musculoskeletal imaging showed promising results when applied in a controlled setting, it is well understood that generalization beyond the statistical distribution of the training set is still an unmet challenge. In MRI this translates into poor performances when trained models are tested on different imaging protocols or images acquired on different MRI systems. With this proposal, we aim to leverage on this recent advancement and filling the existing gaps. We aim to study novel integrated models able to simultaneously accelerate MRI acquisition and automate the image processing that can overcome the limitation of single domain application. Fast image acquisition and accurate image post processing are typically considered to be separate problems. However, the neural networks optimization design gives us an opportunity to integrate the two to maximize both acceleration and machine-based image processing and interpretation. We will use both publicly available benchmark dataset (FastMRI) and internally collected dataset to build deep learning models able to accurately reconstruct under sampled MRI acquisitions. We will use a dataset prospectively acquired during the course of this study to validate the clinical applicability of the developed methods. Specifically, we will test the hypothesis that the proposed integrated pipeline can be applied in clinical setting for a fast and intelligent knee scan obtaining image quality comparable to standard acquisition and automated processing accuracy comparable with human reproducibility. Additionally, we propose to make our annotated image datasets and trained models a shared resource, a centralized, open evaluation platform for MRI reconstruction and image post processing techniques.

抽象的 快速，健壮和可靠的定量膝关节MR成像将是研究关节的重要一步 变性，损伤和骨关节炎（OA）。组成和形态特征提取的自动化 膝盖中的组织是转化为有希望定量的临床实践的重要步骤 技术。它将能够分析大型患者队列，并协助放射线医生/临床医生增强 MRI的价值。 在过去的几年中，通过深度学习实现了几项人类任务的自动化 技术。使用大量注释的数据和处理能力，使用概念 通过观察示例将数据转换为知识的知识，今天有监督的学习可以完成 挑战从未表现出来。除了图像分析和解释外，深度学习是 彻底改变了管道的获取和重建方面。模型可以学习直接映射 在采样的K空间和图像域之间。 当将深度学习应用于肌肉骨骼成像时显示出令人鼓舞的结果 受控设置，众所周知，超出培训集的统计分布的概括是 仍然是一个未满足的挑战。在MRI中，这转化为在测试训练模型时的表现不佳 在不同的MRI系统上获取的不同成像协议或图像。 通过此提案，我们旨在利用这一最近的进步并填补现有空白。我们的目标是学习 可同时加速MRI获取并自动化图像处理的新型集成模型 这可以克服单个域应用的限制。快速图像获取和准确的图像帖子 处理通常被认为是单独的问题。但是，神经网络优化设计 使我们有机会整合两者以最大化加速度和基于机器的图像处理 和解释。我们将使用公开可用的基准数据集（FastMRI）并在内部收集 数据集以建立能够在采样的MRI采集下准确重建的深度学习模型。我们将 在本研究过程中使用前瞻性获取的数据集来验证 开发的方法。具体而言，我们将测试可以应用所提出的集成管道的假设 在临床环境中，快速且智能的膝盖扫描获得与标准收购相当的图像质量 和自动处理精度与人类可重复性相当。 此外，我们建议将带注释的图像数据集和训练的模型作为共享资源，一个 MRI重建和图像后处理技术的集中式开放评估平台。