Machine learning approach to non-invasive MRI-based blood oximetry

基于 MRI 的无创血氧测定的机器学习方法

基本信息

批准号：
10217710
负责人：
Juliet J. Varghese
金额：
$ 58.78万
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：
2021-09-21 至 2024-09-20
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/10217710
关键词：
3-Dimensional Adult Age Anatomy Biomedical Technology Biophysics Blood Blood Circulation Blood Vessels Blood flow Blood specimen Cardiac Catheterization Catheters Cerebrum Clinical Clinical Management Collaborations Complex Congenital Cardiovascular Abnormality Consumption Data Detection Development Diagnosis Diagnostic Disease Early Diagnosis Early Intervention Evaluation Fetus Fingers Frequencies Funding Goals Health Heart Heart Abnormalities Heart failure Hemoglobin Human Image Imaging Device Institution Intervention Kidney Learning Limb structure Location Machine Learning Magnetic Resonance Magnetic Resonance Imaging Maps Measurement Measures Methods Mission Modeling Morphology National Institute of Biomedical Imaging and Bioengineering Nature Network-based Operative Surgical Procedures Organ Outcome Oxygen Oxygen saturation measurement Patients Pediatric Hospitals Peripheral Physiologic pulse Physiology Procedures Process Property Psychological Transfer Public Health Pulmonary Hypertension Pulmonary vessels Radiation Radiation exposure Relaxation Risk Roentgen Rays Salvelinus Scanning Signal Transduction Structure Techniques Technology Testing Time Training Variant Vascular System Venous Work base cerebrovascular clinical application clinical practice cohort congenital heart disorder data acquisition design diagnostic catheterization disease diagnosis feedforward neural network flexibility imaging capabilities improved in vivo individual patient interest limb ischemia machine learning algorithm machine learning method meetings neonate neural network new technology nonlinear regression novel post-transplant prevent supervised learning tool

项目摘要

PROJECT SUMMARY Measurement of blood oxygen (O2) saturation, the fraction of oxygen-saturated hemoglobin in blood, provides information on whole-body and organ-specific O2 delivery and consumption and is used to guide therapy and intervention. Blood sampling and analysis by invasive catheterization performed under X-ray fluoroscopic guidance is the standard method used to measure O2 saturation in multiple anatomical locations in the cardiac chambers and major blood vessels. Non-invasive measurement of O2 saturation using magnetic resonance (MR) imaging was first proposed nearly 30 years ago; however, previous techniques have relied on fitting the Luz- Meiboom model and other model variants using traditional linear and non-linear regression model approaches. Although the model captures the basic underlying biophysical principles, it does not fully characterize the complex relationship between blood O2 saturation and the MR signal. Despite being a non-invasive, non- radiating alternative to invasive catheterization, the low accuracy of MR oximetry, due to inadequacy of the model as well as estimation methods, have prevented the technique from gaining clinical acceptance. We propose to overcome this critical limitation by meeting our overall objective; to deploy a model-free approach based on machine learning (ML) to develop and implement an accurate, clinically feasible, MR oximetry technique. We hypothesize that ML algorithms provide greater flexibility in parameter estimation than traditional methods, and can be trained to learn and map the true in vivo relationship that describes the sensitivity of MR blood signal to O2 saturation. We intend to achieve our objective through the following specific aims. In Aim 1, we will develop a supervised ML algorithm for MR oximetry. Pre-training will occur with training data simulated using the L-M model and then augmented with in vivo data via transfer learning. Simultaneously, in Aim 2, we will design and implement a 3D MR oximetry method for volumetric data acquisition. A volumetric map will facilitate O2 saturation measurement throughout the vascular system, and will support the combination with 4D flow to evaluate O2 delivery and consumption. In Aim 3, we will validate the proposed ML-based 3D MR oximetry technique in a small cohort of patients referred for catheter-based O2 saturation measurement. For the first time, our proposed work will apply machine learning to accurately characterize the in vivo sensitivity of the transverse relaxation time (T2) weighted MR blood signal to O2 saturation, using a unique combination of simulated and in vivo training data. ML-based MR oximetry will provide the accuracy of measurement required for clinical use, and therefore will be able to replace or reduce the frequency and duration of an invasive, radiation-based method with a safe, non-invasive alternative. ML-based MR oximetry as an imaging tool is expected to significantly improve the diagnostic value of an MR exam, and will be especially valuable in the management of patients with congenital heart disease. Our work thus aligns with the mission of NIBIB to have a positive impact on human health with the development of novel technology.

项目概要血氧 (O2) 饱和度（血液中氧饱和血红蛋白的分数）的测量可提供有关全身和器官特异性 O2 输送和消耗的信息，用于指导治疗和干涉。在 X 射线透视下通过侵入性导管进行血液采样和分析指导是用于测量心脏多个解剖位置的 O2 饱和度的标准方法腔室和主要血管。使用磁共振 (MR) 无创测量 O2 饱和度成像技术最早在近 30 年前被提出；然而，以前的技术依赖于拟合 Luz- Meiboom 模型和其他模型变体使用传统的线性和非线性回归模型方法。尽管该模型捕捉了基本的生物物理原理，但它并没有完全表征血氧饱和度和 MR 信号之间的复杂关系。尽管是一种非侵入性、非辐射替代侵入性导管插入术，由于模型的不足，MR 血氧测定法的准确性较低以及估计方法，阻碍了该技术获得临床认可。我们建议通过实现我们的总体目标来克服这一关键限制；部署基于无模型的方法机器学习 (ML)，用于开发和实施准确的、临床上可行的 MR 血氧测定技术。我们假设 ML 算法在参数估计方面比传统方法提供更大的灵活性，并且可以通过训练来学习和绘制真实的体内关系，该关系描述了 MR 血液信号对氧气饱和度。我们打算通过以下具体目标来实现我们的目标。在目标 1 中，我们将开发用于 MR 血氧测定的监督式 ML 算法。预训练将使用 L-M 模拟的训练数据进行模型，然后通过迁移学习用体内数据进行增强。同时，在目标 2 中，我们将设计并实施 3D MR 血氧测定方法来采集体积数据。体积图将有助于 O2 饱和度测量整个血管系统，并将支持与 4D 流相结合来评估 O2 交付和消费。在目标 3 中，我们将验证所提出的基于 ML 的 3D MR 血氧测定技术转诊进行基于导管的 O2 饱和度测量的一小群患者。我们提出的工作将首次应用机器学习来准确表征体内敏感性使用独特的组合，将横向弛豫时间 (T2) 加权 MR 血液信号与 O2 饱和度进行比较模拟和体内训练数据。基于 ML 的 MR 血氧测定法将提供所需的测量精度用于临床，因此将能够取代或减少侵入性、基于辐射的方法，具有安全、非侵入性的替代方法。基于 ML 的 MR 血氧测定法作为一种成像工具预计将显着提高 MR 检查的诊断价值，并且在先天性心脏病患者的管理。因此，我们的工作与 NIBIB 的使命是一致的：随着新技术的发展，对人类健康产生积极影响。