Toward ultrasound brain imaging via machine-learning-extracted skull profile and speed of sound

通过机器学习提取的头骨轮廓和声速进行超声脑成像

• 批准号: 10819920
• 负责人: Aiguo Han
• 金额: $ 20.82万
• 依托单位: VIRGINIA POLYTECHNIC INST AND ST UNIV
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-02-01 至 2024-12-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10819920
• 关键词: 3-Dimensional; Acoustics; Address; Adult; Algorithms; Architecture; Blood flow; Brain; Brain imaging; Cephalic; Cerebral hemisphere hemorrhage; Cerebrovascular Disorders; Data; Detection; Diagnosis; Environment; Evaluation; Functional Imaging; Future; Goals; Hospitals; Human; Image; Image Enhancement; Imaging Techniques; Intensive Care Units; Ionizing radiation; Knowledge; Location; Machine Learning; Magnetic Resonance Imaging; Maps; Measures; Methods; Modality; Modeling; Monitor; Organ; Performance; Perfusion; Phase; Physiologic pulse; Physiology; Play; Property; Rest; Role; Scanning; Signal Transduction; Spatial Distribution; Speed; Stroke; Techniques; Testing; Thick; Time; Training; Transportation of Patients; Traumatic Brain Injury; Ultrasonography; X-Ray Computed Tomography; brain based; contrast enhanced; cranium; deep learning; deep learning algorithm; design; disease diagnosis; experimental study; imaging modality; imaging probe; imaging study; in silico; in vivo; learning strategy; machine learning method; microCT; nervous system disorder; neuroregulation; optoacoustic tomography; physical model; portability; radio frequency; skull base; sound; stroke patient; superresolution imaging; transmission process; trauma care; treatment planning; ultrasound

Project Summary Transcranial ultrasound could facilitate a broad variety of applications in brain imaging, e.g., functional imaging, intracerebral hemorrhage detection, brain perfusion evaluation, and stroke diagnosis. Ultrasound has the intrinsic advantages of being real-time, portable, widely available, noninvasive, and free from ionizing radiation. Thus, transcranial ultrasound imaging could potentially play a unique role in a time-sensitive and dynamic environment where X-ray computed tomography (CT) and magnetic resonance imaging (MRI) are unavailable. For instance, transcranial ultrasound has significant potentials in the initial assessment of traumatic brain injury during the transportation of patients to the hospital, and in bedside monitoring of brain physiology for stroke patients in an intensive care unit. Despite its promising potentials, the use of transcranial ultrasound imaging has been limited, largely because adult human skulls cause severe phase aberration, leading to highly degraded ultrasound images. Phase aberration from the skull can be accurately corrected if the speed of sound (SOS) and profile (i.e., thickness distribution) of the skull are known a priori. The skull profile and SOS can be estimated by CT, currently the gold standard approach for treatment planning. The CT-based approach is far less appealing, however, for ultrasound imaging purposes because of the additional CT scans that involve ionizing radiation and image co-registration. We propose a real-time pulse-echo ultrasound approach to estimate the skull profile and SOS using deep learning (DL) methods with ultrasound radiofrequency (RF) signals backscattered from the skull. The proposed approach rests on the scientific premise that these RF signals contain extremely rich information of the interaction between ultrasound and skulls, and the information of skull profile and SOS is encoded in the backscattered signals in a convoluted way that cannot be fully described by simple physical models. We hypothesize that DL, a subclass of machine learning (ML), is capable of automatically and rapidly extracting skull profile and SOS from RF signals with sufficient training. The objective of this Trailblazer R21 application is to develop and validate DL methods for extracting the human skull profile and SOS, with the following aims. Aim 1. In silico study: Develop and evaluate DL-based skull profile and SOS extraction algorithms using synthetic data. Aim 2. Experimental study: Evaluate DL algorithms’ performance in skull profile and SOS extraction using experimental data. Aim 3. Pilot imaging study: Evaluate DL algorithms’ performance in transcranial imaging. Successful completion of this study will facilitate the transcranial application of both conventional (e.g., B-mode imaging, blood flow imaging, and contrast-enhanced ultrasound) and emerging ultrasound imaging methods (e.g, super-resolution imaging and photoacoustic tomography). Although the current application focuses on brain imaging, our method can be extended to phase aberration correction for ultrasound-based brain treatment, neuromodulation, and ultrasound imaging of other organs where phase aberration exists.

项目概要 经颅超声可以促进脑成像的广泛应用，例如功能成像、 脑出血检测、脑灌注评估和中风诊断。超声波具有固有的 具有实时、便携、广泛使用、无创、无电离辐射等优点。因此， 经颅超声成像可能在时间敏感和动态环境中发挥独特的作用 其中 X 射线计算机断层扫描 (CT) 和磁共振成像 (MRI) 不可用。例如， 经颅超声在创伤性脑损伤的初步评估中具有巨大潜力 将患者运送到医院，以及在床边监测中风患者的脑生理机能 重症监护室。尽管其潜力巨大，但经颅超声成像的使用仍受到限制， 主要是因为成年人的头骨造成严重的相位畸变，导致超声波高度退化 图像。如果声速 (SOS) 和轮廓一致，则可以准确校正头骨的相位差 头骨的厚度（即厚度分布）是先验已知的。颅骨轮廓和SOS可以通过CT估计， 目前是治疗计划的黄金标准方法。基于 CT 的方法远没有那么吸引人， 然而，出于超声成像的目的，因为额外的 CT 扫描涉及电离辐射和 图像共同配准。我们提出了一种实时脉冲回波超声方法来估计颅骨轮廓和 SOS 使用深度学习 (DL) 方法以及从头骨反向散射的超声射频 (RF) 信号。 所提出的方法基于这样的科学前提：这些射频信号包含极其丰富的信息 超声波与颅骨之间的相互作用，颅骨轮廓和 SOS 的信息被编码在 以复杂的方式反向散射信号，无法通过简单的物理模型完全描述。我们 假设 DL（机器学习 (ML) 的一个子类）能够自动快速提取头骨 经过充分训练的射频信号的轮廓和求救信号。 Trailblazer R21 应用程序的目标是 开发和验证用于提取人类头骨轮廓和 SOS 的深度学习方法，其目标如下。目标1。 计算机模拟研究：使用合成数据开发和评估基于深度学习的头骨轮廓和 SOS 提取算法。 目标 2. 实验研究：评估 DL 算法在头骨轮廓和 SOS 提取方面的性能 实验数据。目标 3. 初步成像研究：评估 DL 算法在经颅成像中的性能。 这项研究的成功完成将促进传统（例如 B 模式）的经颅应用 成像、血流成像和对比增强超声）和新兴的超声成像方法（例如， 超分辨率成像和光声断层扫描）。虽然目前的应用主要集中在大脑 成像，我们的方法可以扩展到基于超声的脑部治疗的相位像差校正， 神经调节以及存在相位差的其他器官的超声成像。