Next-Generation Cardiovascular MRI powered by Artificial Intelligence

由人工智能驱动的下一代心血管 MRI

• 批准号: 10226541
• 负责人: Oliver Strides Cossairt
• 金额: $ 18.98万
• 依托单位: NORTHWESTERN UNIVERSITY AT CHICAGO
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-04-15 至 2023-01-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10226541
• 关键词: 3-Dimensional; 4D MRI; Acceleration; Address; Adopted; Adoption; Adult; Agreement; Architecture; Artificial Intelligence; Cardiac; Cardiovascular system; Childhood; Cine Magnetic Resonance Imaging; Classification; Clinical; Community Hospitals; Computer Vision Systems; Computer software; Data; Databases; Digital Imaging and Communications in Medicine; Echocardiography; Gadolinium; Generations; Goals; Hour; Human; Image; Image Analysis; Image Enhancement; Institution; Intervention; Learning; Magnetic Resonance Imaging; Patients; Pattern; Performance; Perfusion; Phase; Physicians; Process; Prognosis; Protocols documentation; Reading; Reporting; Resources; Sampling; Scanning; Series; Speed; Technology; Testing; Time; Training; United States National Institutes of Health; base; cardiovascular imaging; clinical practice; clinical translation; computer science; convolutional neural network; cost; data space; deep learning; empowered; experimental study; heart imaging; high reward; high risk; image processing; image reconstruction; imaging Segmentation; imaging facilities; interest; network architecture; neural network; neural network architecture; next generation; novel; reconstruction; response; risk prediction; routine practice; signal processing; single photon emission computed tomography; success

Project Summary/Abstract: Despite the accuracy and versatility of cardiovascular MRI, its footprint is only 1% among cardiac imaging tests (SPECT, echocardiography, CT, MRI) in the US. While there are several factors such as referral patterns favoring SPECT and echocardiography among cardiologists that account for low utilization, the two addressable obstacles that preclude widespread adoption are lengthy scan time (imaging facility operational cost) and reading (physician cost). These obstacles must be addressed for community hospitals with limited resources to adopt cardiovascular MRI into clinical routine practice. While compressed sensing (CS), since its introduction into the MRI world in 2007, has led to highly-accelerated cardiovascular MRI acquisitions, the subsequent image reconstruction remains too slow (> 5 min for 2D time series, > 1 hour for 3D time series) for clinical translation (unmet need 1). Downstream, image analysis for cardiovascular MRI is notoriously labor intensive (e.g. 30- to 60-min) and limited (“circles” at two cardiac phases for cine MRI, whereas perfusion and late gadolinium-enhanced (LGE) images are evaluated visually), for what is essentially a basic computer vision task (unmet need 2). In direct response, we will address these two unmet needs and unlock the enormous potential of CMR using deep learning (DL). DL applications have exploded since advancements in optimization and GPU hardware. While several recent studies have applied neural networks such as convolutional neural networks (CNNs), U-Nets, and Generative Adversarial Nets (GANs) for reconstruction and segmentation, no study has implemented an inline end-to-end pipeline that receives raw k-space from the MRI scanner and delivers both reconstructed images and fully processed images automatically with high speed (< 1 min). The objectives of this study are: a) developing a network for image reconstruction with maximal acceleration (aim 1), (b) developing a network for image processing tasks (aim 2), and c) developing an integrated, end-to-end network that does both (aim 3). By developing an architecture that can simultaneously learn maximal acceleration, fine tune end-to-end performance, and perform reconstruction/inference using feed-forward networks, we anticipate a disruptive technology that will lead to a paradigm shift in cardiovascular MRI and increase its footprint in community hospitals. This 2-year study is doable because of the requisite database of raw k-space (not derived from DICOM) data (N = 617) and annotated cardiac MR images (N=3,021) from over 3,000 patients existing at our institution. Success of this proposal will deliver a disruptive technology that has potential to cause a paradigm shift in cardiovascular MRI and enable widespread adoption of cardiovascular MRI into clinical routine practice.

项目摘要/摘要：尽管心血管 MRI 具有准确性和多功能性，但其占地面积仅 在美国，心脏影像检查（SPECT、超声心动图、CT、MRI）中的这一比例为 1%。虽然有几个 心脏病专家中倾向于 SPECT 和超声心动图的转诊模式等因素 利用率低，阻碍广泛采用的两个可解决的障碍是扫描时间过长 （成像设施运营成本）和阅读（医生成本）。必须解决这些障碍 资源有限的社区医院无法将心血管 MRI 纳入临床常规实践。 而压缩感知 (CS) 自 2007 年引入 MRI 领域以来，已经带来了高度加速的 心血管 MRI 采集，随后的图像重建仍然太慢（2D 时间 > 5 分钟） 系列，> 1 小时（3D 时间序列）用于临床翻译（未满足的需求 1）。下游，图像分析 心血管 MRI 众所周知是劳动密集型（例如 30 至 60 分钟）且有限（两个心脏的“圆圈”） 电影 MRI 的阶段，而灌注和晚期钆增强 (LGE) 图像则通过视觉评估）， 本质上是一项基本的计算机视觉任务（未满足的需求 2）。作为直接回应，我们将解决这些问题 两个未满足的需求，并利用深度学习 (DL) 释放 CMR 的巨大潜力。 随着优化和 GPU 硬件的进步，深度学习应用程序呈爆炸式增长。虽然最近有几个 研究已经应用了神经网络，例如卷积神经网络（CNN）、U-Net 和生成网络 用于重建和分割的对抗网络（GAN），没有研究实现内联端到端 从 MRI 扫描仪接收原始 k 空间并提供重建图像和完整图像的管道 高速自动处理图像（< 1 分钟）。本研究的目标是：a) 开发 以最大加速度进行图像重建的网络（目标 1），(b) 开发图像网络 处理任务（目标 2），以及 c) 开发一个可同时完成这两项任务的集成端到端网络（目标 3）。经过 开发一种可以同时学习最大加速度、端到端微调的架构 性能，并使用前馈网络执行重建/推理，我们预计会出现破坏性的 技术将导致心血管 MRI 范式转变并增加其在社区中的足迹 医院。这项为期 2 年的研究是可行的，因为需要原始 k 空间数据库（不是源自 DICOM）数据（N = 617）和带注释的心脏 MR 图像（N = 3,021）来自我们医院现有的 3,000 多名患者 机构。该提案的成功将带来一种颠覆性技术，有可能成为一种范例 心血管 MRI 的转变，并使心血管 MRI 广泛应用于临床常规实践。