Machine learning-based segmentation and risk modeling for real-time prediction of major arterial bleeding after pelvic fractures

基于机器学习的分割和风险建模，用于实时预测骨盆骨折后大动脉出血

基本信息

批准号：
10471193
负责人：
David Dreizin
金额：
$ 18.62万
依托单位：
UNIVERSITY OF MARYLAND BALTIMORE
依托单位国家：
美国
项目类别：
财政年份：
2019
资助国家：
美国
起止时间：
2019-07-01 至 2023-06-30
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/10471193
关键词：
Admission activity Adoption Algorithms Angiography Architecture Area Arterial Injury Award Blunt Trauma Caliber Catheters Cause of Death Clinical Communities Comparative Effectiveness Research Computer Models Computer Vision Systems Computer software Crush Injury Data Data Science Data Set Derivation procedure Detection Development Diagnosis Early Intervention Engineering Environment Extravasation Funding Goals Hematoma Hemorrhage Hospitalization Human Image Industry Intervention Intuition K-Series Research Career Programs Knowledge Label Lead Learning Life Logistic Regressions Machine Learning Manuals Maryland Measurement Measures Medical Imaging Mentors Methods Modeling Modernization Nature Obesity Outcome Patients Pelvis Predictive Value Probability Theory Process Programming Languages Pythons Radiology Specialty Research Research Activity Research Personnel Resources Risk Scanning Sensitivity and Specificity Shorthand Speed Supervision Techniques Terminology Testing Therapeutic Embolization Thinness Time Training Transfusion Translations Trauma Treatment outcome Triage Universities Vehicle crash Work X-Ray Computed Tomography adverse outcome algorithm development artificial neural network automated segmentation base clinical decision-making computer infrastructure convolutional neural network cost deep learning deep learning algorithm experience fall injury hemodynamics heuristics image processing imaging Segmentation improved improved outcome learning strategy machine learning model medical schools mortality multidisciplinary muscle form neural network architecture outcome prediction pelvis fracture personalized predictions predictive modeling prevent primary outcome radiologist random forest real time model risk prediction secondary outcome segmentation algorithm skills standard of care support vector machine temporal measurement tool

项目摘要

PROJECT SUMMARY/ABSTRACT: Arterial hemorrhage after pelvic fractures is a leading reversible cause of death after blunt trauma. Prediction of arterial bleeding risk is difficult, and currently determined using subjective criteria, often based on qualitative results of admission computed tomography (CT). Segmented hematoma and contrast extravasation (CE) volumes predict need for angioembolization, major transfusion, and mortality but cannot be applied in real-time. The ill-defined multi-focal nature of pelvic hematomas and CE prevents reliable estimation using diameter-based measurements. Dr. Dreizin is a trauma radiologist at the University of Maryland School of Medicine. His early work has focused on improving the speed and reliability of volumetric analysis of pelvic hematomas using semi-automated techniques, and derivation of a logistic regression-based prediction tool for major arterial injury after pelvic fractures. Dr. Dreizin’s goal for this four- year K08 mentored career development award proposal is to gain the skills needed to 1) implement deep learning architectures for automated hematoma volume segmentation and 2) develop computational models for outcome prediction after pelvic trauma. These tools could greatly improve the speed and accuracy of clinical decision making in the setting of life-threatening traumatic pelvic bleeding. Fully convolutional neural networks (FCNs) have emerged as the most robust and scalable method for automated medical image segmentation. Intuitive software platforms for training FCN implementations and generating multivariable machine learning models have been developed in the Python programming environment. The training objectives and research activities of this proposal are necessary to provide Dr. Dreizin with new skills and practical experience in Python programming, deep learning software, and computational modeling software. By understanding the principles and computational infrastructure behind modern machine learning, Dr. Dreizin will be able to train and validate state-of-the-art algorithms independently and effectively lead a team of researchers in this area. To achieve his goals, Dr. Dreizin has assembled a multidisciplinary team of mentors, advisors, and collaborators with world-leading expertise in computer vision in medical imaging, probability theory, data science, and comparative effectiveness research. Dr. Dreizin will focus on two specific aims. In Aim 1, he will train and validate deep learning architectures for segmentation of traumatic pelvic hematomas and CE by computing the Dice metric, time effort, and correlation with clinical outcomes. In Aim 2, he will generate and test quantitative models for predicting major arterial bleeding after pelvic trauma based on a rich multi-label dataset of segmented features. The training and pilot data will be necessary for Dr. Dreizin’s long- term goal of research independence and R01 support to develop automated segmentation algorithms for the spectrum of clinically important imaging features after pelvic trauma, as well as fully automated multivariable clinical prediction tools with potential for translation to industry and as an FDA-cleared product.

项目摘要/摘要：骨盆骨折后动脉出血是导致骨盆骨折的主要可逆性原因预测动脉出血风险很困难，目前使用以下方法确定。标准，通常基于入院分段计算机断层扫描 (CT) 的定性主观结果。血肿和造影剂外渗 (CE) 量预测需要血管栓塞、大输血和盆腔血肿和 CE 的多灶性性质不明确，但无法实时应用。 Dreizin 博士是一名创伤放射科医生，无法使用基于直径的测量进行可靠的估计。他早期的工作重点是提高马里兰大学医学院的速度和可靠性。使用半自动技术对盆腔血肿进行体积分析，并推导逻辑回归 Dreizin 博士的目标是基于回归的骨盆骨折后主要动脉损伤预测工具。 K08 年指导职业发展奖提案旨在获得 1) 深入实施所需的技能自动血肿体积分割的学习架构和 2) 开发计算模型这些工具可以大大提高骨盆创伤后的结果预测的速度和准确性。在危及生命的创伤性盆腔出血的情况下进行临床决策全卷积神经。网络（FCN）已成为自动化医学图像最强大且可扩展的方法用于训练 FCN 实现和生成多变量的直观软件平台。机器学习模型是在Python编程环境中开发的。该提案的目标和研究活动对于为 Dreizin 博士提供新技能和 Python 编程、深度学习软件和计算建模软件的实践经验。了解现代机器学习背后的原理和计算基础设施，Dreizin 博士将能够独立地训练和验证最先进的算法，并有效地领导一个团队为了实现他的目标，Dreizin 博士组建了一个多学科的导师团队，在医学成像、概率等计算机视觉领域拥有世界领先专业知识的顾问和合作者 Dreizin 博士将重点关注两个具体目标。目标 1，他将训练和验证用于分割创伤性盆腔血肿的深度学习架构在目标 2 中，他将通过计算 Dice 指标、时间投入以及与临床结果的相关性来进行 CE。基于丰富的数据生成并测试预测骨盆创伤后主要动脉出血的定量模型分段特征的多标签数据集对于 Dreizin 博士的长期研究来说是必要的。研究独立性和 R01 支持的长期目标是开发自动分割算法盆腔创伤后临床重要的影像学特征谱，以及全自动多变量临床预测工具有可能转化为行业并作为 FDA 批准的产品。

项目成果

期刊论文数量（24）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

External Attention Assisted Multi-Phase Splenic Vascular Injury Segmentation With Limited Data.

DOI：
10.1109/tmi.2021.3139637
发表时间：
2022-06
期刊：
IEEE transactions on medical imaging
影响因子：
10.6
作者：
通讯作者：

CT of Sacral Fractures: Classification Systems and Management.

DOI：
10.1148/rg.220075
发表时间：
2022-11
期刊：
Radiographics : a review publication of the Radiological Society of North America, Inc
影响因子：
0
作者：
通讯作者：

Accelerating voxelwise annotation of cross-sectional imaging through AI collaborative labeling with quality assurance and bias mitigation.

通过 AI 协作标记加速横截面成像的体素注释，并提供质量保证和偏差缓解。

DOI：
10.3389/fradi.2023.1202412
发表时间：
2023
期刊：
Frontiers in radiology
影响因子：
0
作者：
Dreizin,David;Zhang,Lei;Sarkar,Nathan;Bodanapally,UttamK;Li,Guang;Hu,Jiazhen;Chen,Haomin;Khedr,Mustafa;Khetan,Udit;Campbell,Peter;Unberath,Mathias
通讯作者：
Unberath,Mathias

Pulmonary contusion: automated deep learning-based quantitative visualization.

DOI：
10.1007/s10140-023-02149-2
发表时间：
2023-08
期刊：
EMERGENCY RADIOLOGY
影响因子：
2.2
作者：
Sarkar, Nathan;Zhang, Lei;Campbell, Peter;Liang, Yuanyuan;Li, Guang;Khedr, Mustafa;Khetan, Udit;Dreizin, David
通讯作者：
Dreizin, David

Deep learning-based quantitative visualization and measurement of extraperitoneal hematoma volumes in patients with pelvic fractures: Potential role in personalized forecasting and decision support.