Accurate, reliable, and interpretable machine learning for assessment of neonatal and pediatric brain micro-structure

准确、可靠且可解释的机器学习，用于评估新生儿和儿童大脑微结构

• 批准号: 10566299
• 负责人: Davood Karimi
• 金额: $ 38.06万
• 依托单位: BOSTON CHILDREN'S HOSPITAL
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-04-06 至 2028-01-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10566299
• 关键词: Address; Adoption; Anatomy; Architecture; Assessment tool; Atlases; Attention; Biological Markers; Birth; Brain; Calibration; Childhood; Complex; Computer Vision Systems; Data; Data Set; Development; Diffusion; Diffusion Magnetic Resonance Imaging; Failure; Goals; Human; Image; Integration Host Factors; Knowledge; Learning; Machine Learning; Maps; Mathematics; Measurement; Methods; Modeling; Neonatal; Noise; Population; Reliability of Results; Reproducibility; Research; Sampling; Scanning; Signal Transduction; Software Tools; Structural Models; Structure; Techniques; Testing; Trust; Uncertainty; Work; biophysical model; brain abnormalities; connectome; deep learning; deep neural network; detection method; imaging study; improved; interest; machine learning method; machine learning model; machine learning prediction; magnetic resonance imaging biomarker; neonatal magnetic resonance imaging; neonate; nervous system disorder; neural network; neural network architecture; novel; pediatric patients; spatiotemporal; tool

Project Summary The goal of this project is to enhance the capabilities of diffusion-weighted magnetic resonance imaging (dMRI)for neonatal and pediatric subjects. Currently, dMRI is the only viable non-invasive method for probing brain microstructure. The past two decades have witnessed development of more powerful and more complex modelsof brain microstructure based on dMRI signal. Unfortunately, accurate and reliable estimation of these models require large numbers of high-quality measurements, which may be difficult or impossible to obtain in neonatal and pediatric subjects. Therefore, there is an urgent need for methods that can accurately and robustly estimatethe micro-structural biomarkers from reduced and low-quality measurements. To address this need, this researchwill develop and validate data-driven and machine learning (ML) techniques methods for estimating dMRI biomarkers for neonatal and pediatric subjects. The potential of these methods has greatly increased by the availability of large high-quality dMRI datasets such as the Human Connectome Project (HCP) data. Recent works, including our own studies, have demonstrated that ML techniques have a great potential to overcome limitations of the existing analysis tools and to achieve superior estimation accuracy. This research will substantially extend our preliminary work and generate important new capabilities that currently do not exist. Specifically, we will develop and validate novel methods for estimating important micro- structural models and biomarkers, ranging from diffusion tensor to advanced multi-compartment models, with far fewer measurements.In this regard, the two main novel aspects of our work will include 1) the use of spatio- temporal atlases to improvethe accuracy of subject-level analysis and 2) development of new deep neural network architectures based on self-attention. Furthermore, we will develop new techniques for enhancing the reliability, robustness, and explainability of ML methods for dMRI analysis. This will include techniques for computing well-calibrated uncertainty estimations, techniques that can detect corrupt, noisy, and out-of- distribution measurements, and techniques that enable interpretation and explanation of the predictions of these ML methods. We will evaluate the new methods using test-retest and bootstrapping methods and via assessment by experts in brain anatomyand micro-structure. The methods developed in this research will enable quantitative assessment of neonatal and pediatric brain micro-structure and the impact of developmental factors and neurological disorders at thesecritical stages in brain development with accuracy, detail, and reproducibility that is currently beyond reach.

项目概要 该项目的目标是增强扩散加权磁共振成像的能力 (dMRI) 适用于新生儿和儿科受试者。目前，dMRI 是唯一可行的非侵入性探测方法 脑微观结构。过去二十年见证了更强大、更复杂的发展 基于 dMRI 信号的脑微结构模型。不幸的是，对这些的准确和可靠的估计 模型需要大量高质量的测量，这可能很难或不可能在 新生儿和儿科科目。因此，迫切需要能够准确、准确的方法 从减少和低质量的测量中稳健地估计微观结构生物标志物。为了解决这个问题 根据需要，本研究将开发和验证数据驱动和机器学习 (ML) 技术方法 估计新生儿和儿科受试者的 dMRI 生物标志物。这些方法的潜力极大 通过大型高质量 dMRI 数据集（例如人类连接组计划）的可用性而增加 （HCP）数据。最近的工作，包括我们自己的研究，已经证明机器学习技术有很大的作用 克服现有分析工具的局限性并实现卓越的估计精度的潜力。 这项研究将大大扩展我们的前期工作并产生重要的新功能 目前不存在。具体来说，我们将开发和验证用于估计重要微观因素的新方法 结构模型和生物标志物，范围从扩散张量到高级多室模型， 测量要少得多。在这方面，我们工作的两个主要新颖方面将包括 1）使用空间 时间图谱以提高主题级分析的准确性，2）开发新的深度神经网络 基于自注意力的网络架构。此外，我们将开发新技术来增强 用于 dMRI 分析的 ML 方法的可靠性、稳健性和可解释性。这将包括以下技术： 计算经过良好校准的不确定性估计，以及可以检测损坏、噪声和异常的技术 分布测量以及能够解释和解释预测的技术 这些机器学习方法。我们将使用测试再测试和引导方法来评估新方法，并通过 由大脑解剖学和微观结构专家评估。本研究中开发的方法将 能够定量评估新生儿和儿童的大脑微结构及其影响 准确地了解大脑发育这些关键阶段的发育因素和神经系统疾病， 细节和再现性是目前无法达到的。