Deep Learning-based Framework for Segmentation and Motion Tracking of Left Ventricle in 3D Echocardiography

基于深度学习的 3D 超声心动图左心室分割和运动跟踪框架

基本信息

批准号：
10666687
负责人：
Shawn Ahn
金额：
$ 5.04万
依托单位：
YALE 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：
2021-07-01 至 2024-05-31
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/10666687
关键词：
3-Dimensional Acute Acute myocardial infarction Address Algorithms Appearance Area Assessment tool Attention Biocompatible Materials Cardiac Cause of Death Clinical Communities Congestive Heart Failure Coronary Arteriosclerosis Data Data Set Detection Diagnosis Disadvantaged Echocardiography Effectiveness Evaluation Event Exercise Fellowship Functional disorder Goals Heart High Resolution Computed Tomography Image Image Analysis Imaging Techniques Implant Infarction Injury Interobserver Variability Ischemia Label Learning Left Ventricular Remodeling Left ventricular structure Manuals Maps Measurement Mechanics Medical Imaging Methods Modeling Morbidity - disease rate Motion Myocardial Myocardial Infarction Myocardium Nature Neural Network Simulation Noise Organ Patients Pattern Performance Process Public Health Radial Research Rest Shapes Signal Transduction Stress Stress Echocardiography Surface Therapeutic Three-Dimensional Echocardiography Time Training Transplantation Two-Dimensional Echocardiography United States Visual Work X-Ray Computed Tomography canine model clinical practice convolutional neural network cost effective deep learning deep learning algorithm detection method feature extraction heart function heart imaging imaging modality improved mortality myocardial injury neural network neural network architecture novel outcome prediction pharmacologic radio frequency screening segmentation algorithm spatiotemporal tool two-dimensional vector

项目摘要

PROJECT SUMMARY/ABSTRACT Coronary artery disease remains the leading cause of death around the world. Acute myocardial infarction (MI) causes regional dysfunction which places remote areas of the heart at a mechanical disadvantage resulting in long term adverse left ventricular (LV) remodeling and complicated congestive heart failure (CHF). Stress echocardiography is currently the clinically established, cost-effective 2D imaging technique for detecting and characterizing myocardial injury by imaging the left ventricle at rest and after either exercise or pharmacologically-induced stress to reveal ischemia and/or infarct. However, the inherent limitations of a 2D echocardiography make it difficult to characterize the whole 3D volume of ischemic/infarct zone, and the qualitative assessment of wall-motion abnormality to characterize myocardial deformation leads to variability among experts. Although 3D echocardiography has potential to address the limitations of 2D imaging, it is not widely accepted in standard clinical use due to the low signal-to-noise ratio (SNR). With the recent advancements in deep learning algorithms, many segmentation and registration tasks have achieved near expert level accuracy. Also, previous works have shown the utility of strain analysis as a way to quantify the degree of wall-motion abnormality in cardiac imaging modalities. Still, many of the current deep learning frameworks focus largely on intensity-based features which are still difficult to train on 3D echocardiography datasets, which in turn leads to poor strain analysis. Thus, in this fellowship, I propose to develop novel data-driven neural network models specifically tailored to 3D echocardiography to improve segmentation and motion tracking of left ventricle in order to achieve full 3D cardiac strain analysis. My first aim is to develop a multi-frame attention-based neural network to exploit the spatiotemporal features of the echocardiography dataset to improve 3D segmentation of left ventricle. This method will take advantage of the inter-frame spatiotemporal features to augment the relevant feature extractions for segmentation. My second aim is to develop a registration neural network in 3D echocardiography by combining intensity-based features and surface-curvature bending energy to improve the motion tracking of left ventricle. This neural network will build upon the accurate segmentations from the first aim to include unique curvature energy features at the boundaries to enhance tracking accuracy at all areas of the myocardium. The improved motion tracking will be used to calculate strain for detection of full 3D ischemic/infarct zones. In summary, this research will provide an objective, quantitative tools for characterizing wall-motion abnormality with strain analysis in 3D echocardiography.

项目概要/摘要冠状动脉疾病仍然是世界各地死亡的主要原因。急性心肌梗塞（MI）导致区域功能障碍，使心脏的偏远区域处于机械劣势，从而导致长期不良左心室（LV）重构和复杂的充血性心力衰竭（CHF）。压力超声心动图是目前临床上建立的、具有成本效益的二维成像技术，用于检测和通过对静息时和运动后或运动后的左心室进行成像来表征心肌损伤药理学诱导的应激以揭示缺血和/或梗塞。然而，2D 的固有局限性超声心动图很难表征缺血/梗塞区的整个 3D 体积，并且对室壁运动异常进行定性评估以表征心肌变形会导致变异专家之中。尽管 3D 超声心动图有潜力解决 2D 成像的局限性，但它并不能由于信噪比（SNR）低，在标准临床应用中被广泛接受。随着最近的进展在深度学习算法中，许多分割和配准任务已经达到了接近专家级的精度。此外，之前的工作已经展示了应变分析作为量化壁运动程度的方法的实用性心脏影像学异常。尽管如此，当前的许多深度学习框架主要集中在基于强度的特征仍然难以在 3D 超声心动图数据集上进行训练，这反过来又导致应变分析不佳。因此，在本次研究金中，我建议开发新颖的数据驱动神经网络模型专为 3D 超声心动图量身定制，以改善左心室的分割和运动跟踪，以便实现完整的 3D 心脏应变分析。我的第一个目标是开发一种基于多帧注意力的神经网络网络利用超声心动图数据集的时空特征来改进 3D 左心室的分割。该方法将利用帧间时空特征增强分割的相关特征提取。我的第二个目标是开发一个配准神经网络通过结合基于强度的特征和表面曲率弯曲来构建 3D 超声心动图网络能量以改善左心室的运动跟踪。该神经网络将建立在准确的分割的第一个目标是在边界处包含独特的曲率能量特征，以增强追踪心肌所有区域的准确性。改进的运动跟踪将用于计算应变用于检测完整的 3D 缺血/梗塞区域。总而言之，本研究将提供一个客观的、定量的通过 3D 超声心动图应变分析来表征室壁运动异常的工具。