Distortion Correction in Functional MRI with Deep Learning

利用深度学习进行功能 MRI 畸变校正

• 批准号: 10647991
• 负责人: Qingfei Luo
• 金额: $ 8万
• 依托单位: UNIVERSITY OF ILLINOIS AT CHICAGO
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-05-01 至 2025-04-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10647991
• 关键词: Acute; Adopted; Algorithms; Anatomy; Architecture; Area; Brain; Brain Mapping; Brain region; Chicago; Compensation; Complex; Data; Data Collection; Databases; Exhibits; Functional Magnetic Resonance Imaging; Funding; Goals; Illinois; Image; Individual; Lead; Learning; Magnetic Resonance; Magnetic Resonance Imaging; Measures; Methods; Modeling; Morphologic artifacts; Neurosciences; Patient Care; Performance; Phase; Physics; Random Allocation; Research; Residual state; Resolution; Scanning; Signal Transduction; Site; Techniques; Testing; Time; Tissues; Training; United States National Institutes of Health; Universities; analytical method; anatomic imaging; chronic pain; clinical application; cognitive neuroscience; convolutional neural network; data space; deep learning; deep learning algorithm; detection sensitivity; executive function; frontal lobe; functional MRI scan; image reconstruction; image registration; learning network; loss of function; magnetic field; mind control; novel; novel strategies; physical model; reconstruction; tool

Project Abstract Functional magnetic resonance imaging (fMRI), a non-invasive technique for mapping brain activity, has been widely used in cognitive neuroscience and patient care. Magnetic field inhomogeneities (B) around tissue interfaces can induce severe geometric distortions in specific brain regions in fMRI images. The image distortions lead to errors in the registration between fMRI and high-resolution anatomical MRI images, and thus decrease spatial accuracy and sensitivity of detecting brain activity with fMRI. In present fMRI studies, B-induced distortions are typically corrected in the reconstructed magnitude images using methods based on image registration, which assume a smoothly varying B. However, the registration-based correction (Reg-Corr) can cause image artifacts and blurring because its assumption breaks down in brain regions where B changes rapidly and omission of phase information in the magnitude images can exacerbate calculation errors. The overarching goal of this project is to develop a novel approach based on deep learning (DL) to accurately correct for geometric distortions through image reconstruction. By integrating the physical model of B effects into an unrolling DL network, distortion-free fMRI images will be directly reconstructed from the complex MR signal in k- space, without the assumption about the smoothness of B. The proposed reconstruction-based correction (Recon-Corr) algorithm will be trained and tested with raw k-space data from 4050 fMRI scans, in the Acute to Chronic Pain Signatures (A2CPS) consortium, in which the University of Illinois at Chicago is a primary performing site. The project has two specific aims: (1) To develop a physics-guided DL algorithm for simultaneous fMRI image reconstruction and distortion correction; (2) To systematically compare the performance of Recon-Corr and traditional Reg-Corr methods. By developing the Recon-Corr method and leveraging the large A2CPS fMRI k-space database, this project will demonstrate an accurate method for fMRI distortion correction that can offer better registration accuracy of functional and anatomical MRI images. Successful completion of the project will resolve a long-standing and important problem in fMRI (i.e., image distortion), contributing to fMRI applications in neuroscience, patient care, and other research areas.

项目摘要 功能性磁共振成像（fMRI）是一种绘制大脑活动图的非侵入性技术， 广泛应用于认知神经科学和患者护理中组织周围的磁场不均匀性 (B)。 界面会在功能磁共振成像图像中的特定大脑区域引起严重的几何扭曲。 导致功能磁共振成像和高分辨率解剖磁共振图像之间的配准错误，从而降低 使用 fMRI 检测大脑活动的空间准确性和灵敏度 在目前的 fMRI 研究中，B 诱导。 通常使用基于图像的方法来校正重建幅度图像中的畸变 配准，假设 B 平滑变化，但是，基于配准的校正（Reg-Corr）可以。 导致图像伪影和模糊，因为它的假设在 B 发生变化的大脑区域中不成立 快速计算并且幅度图像中相位信息的遗漏会加剧计算误差。 该项目的总体目标是开发一种基于深度学习（DL）的新颖方法来准确纠正 通过将 B 效应的物理模型集成到 展开 DL 网络，无失真的 fMRI 图像将直接从 k- 中的复杂 MR 信号重建 空间，没有关于 B 平滑度的假设。所提出的基于重建的校正。 (Recon-Corr) 算法将使用来自 4050 个 fMRI 扫描的原始 k 空间数据进行训练和测试，从急性到 慢性疼痛特征 (A2CPS) 联盟，其中伊利诺伊大学芝加哥分校是主要成员 该项目有两个具体目标：（1）开发物理引导的深度学习算法。 同时进行fMRI图像重建和畸变校正；（2）系统地比较 Recon-Corr 和传统 Reg-Corr 方法的性能 通过开发 Recon-Corr 方法和 利用大型 A2CPS fMRI k 空间数据库，该项目将演示一种准确的 fMRI 方法 畸变校正，可以提供更好的功能和解剖 MRI 图像配准精度。 该项目的成功完成将解决功能磁共振成像领域长期存在的重要问题（即图像 失真），有助于功能磁共振成像在神经科学、患者护理和其他研究领域的应用。