Predicting the Presence of Clinically Significant Thyroid Cancer using Ultrasound Imaging

使用超声成像预测临床上显着的甲状腺癌的存在

基本信息

批准号：
10418612
负责人：
William F Speier
金额：
$ 18.56万
依托单位：
UNIVERSITY OF CALIFORNIA LOS ANGELES
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：
2021-06-04 至 2024-03-31
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/10418612
关键词：
3-Dimensional Address Age Aggressive behavior Algorithms Architecture Attention Biological Markers Biopsy Cancer Detection Cancer Patient Classification Clinical Clinical Data Complex Computer Vision Systems Data Data Set Detection Diagnosis Diagnostic Procedure Diagnostic tests Disease Electronic Health Record Evaluation Fluoroscopy Functional disorder Future Goals Graph Image Image Analysis Incidence Individual Indolent Location Machine Learning Malignant Neoplasms Malignant neoplasm of thyroid Manuals Maps Medical Medical Imaging Methods Modeling Morbidity - disease rate Nature Nodule Nomograms Pathology Patient risk Patients Pattern Physiological Play Probability Procedures Protocols documentation Reading Research Risk Risk Factors Role Savings Series Signal Transduction Structure Techniques Thyroid Gland Thyroid Nodule Training Tweens Ultrasonography United States Work base body system cancer imaging cancer risk clinical imaging clinically significant computer aided detection convolutional neural network cost estimate deep learning detection platform functional outcomes graph neural network image registration imaging biomarker imaging modality imaging study innovation mortality multimodality network models noninvasive diagnosis novel patient stratification predictive modeling prevent quantitative imaging radiologist risk stratification tool treatment planning ultrasound unnecessary treatment ward

项目摘要

PROJECT SUMMARY/ABSTRACT There has been significant work in creating tools that leverage computer vision algorithms to automate medical image analysis. Most of these algorithms have been developed for natural images, which are usually single static images that can be treated individually. However, medical images are usually part of a study that may include various views and orientations that are considered together with other clinical data when making a diagnosis. Three dimensional convolution neural networks (CNN) can address this issue in part when images are evenly spaced, but many medical imaging modalities such as ultrasound (US), fluoroscopy, and biopsy imaging have variable orientations and irregular spacing. Graph convolutional networks (GCN) have the potential to address this issue as they generalize the assumptions of CNNs to work on arbitrarily structured graphs. Automatic thyroid nodule detection in ultrasound (US) is one application that such a graph-based approach could have a large impact. The thyroid cancer incidence rate has tripled in the past thirty years, with an estimated cost of $18-21 billon in 2019. US is the imaging modality of choice, which consists of multiple 2D images of different locations and orientations. US readings are often vague and subjective in nature, which has resulted in a steady increase in the number of biopsies performed over the past 20 years. It is estimated that about one-third of all thyroid biopsy procedures performed in the United States are medically unnecessary, leading to the unmet need for noninvasive diagnostic tests that can reliably identify which nodules require a biopsy. The research objective of this R21 is to develop a new graph-based approach to leverage spatial information contained within imaging studies that will be combined with biomarkers and other known risk factors. Our graph model will enable more complete detection of thyroid cancer, as well as the prediction of future cancer aggression, both with spatially localized explanations. GCN features will be used to predict voxel-level cancer suspicion, thereby enabling a novel method for performing “imaging biopsy.” Finally, voxel-level suspicion maps will be aggregated into patient-level quantitative imaging biomarkers and combined with clinical data to create a multimodal nomogram for performing risk stratification.

项目概要/摘要在创建利用计算机视觉算法实现医疗自动化的工具方面已经开展了大量工作这些算法大多数是针对自然图像而开发的，这些图像通常是单一静态的。然而，医学图像通常是可能包括的研究的一部分。做出诊断时与其他临床数据一起考虑的各种观点和方向。当图像均匀时，三维卷积神经网络（CNN）可以部分解决这个问题间隔，但许多医学成像方式，例如超声（美国）、透视和活检成像图卷积网络（GCN）有潜力解决可变方向和不规则间距问题。这个问题是因为他们将 CNN 的假设推广到了任意结构的图上。超声中自动甲状腺结节检测（美国）是这种基于图形的方法可以实现的应用之一甲状腺癌的发病率在过去三十年中增加了两倍，估计费用增加了三倍。 2019 年将达到 18-21 亿美元。US 是首选的成像模式，它由不同类型的多个 2D 图像组成美国的读数通常是模糊和主观的，这导致了稳定的结果。据估计，过去 20 年来进行的活检数量增加了约三分之一。在美国进行的甲状腺活检手术在医学上是不必要的，导致需求未得到满足用于无创诊断测试，可以可靠地识别哪些结节需要活检。 R21 的研究目标是开发一种新的基于图的方法来利用空间信息包含在影像学研究中，将与生物标志物和其他已知的风险因素相结合。该模型将能够更全面地检测甲状腺癌，并预测未来的癌症攻击性，两者都具有空间局部解释，将用于预测体素水平的癌症。怀疑，从而实现了一种执行“成像活检”的新方法。最后，体素级怀疑图。将被聚合成患者水平的成像生物标志物，并与定量临床数据相结合，创建一个用于进行风险分层的多模态列线图。