Neural Operator Learning to Predict Aneurysmal Growth and Outcomes

神经算子学习预测动脉瘤的生长和结果

• 批准号: 10636358
• 负责人: Roland Assi
• 金额: $ 70.5万
• 依托单位: YALE UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-04-01 至 2027-03-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10636358
• 关键词: Acute; Adherence; Affect; Aging; Algorithms; Aneurysm; Aorta; Aortic Diseases; Arteries; Attention; Basic Science; Biomechanics; Biomedical Engineering; Blood Vessels; Body Surface Area; Caring; Cessation of life; Clinical; Clinical Data; Clinical Management; Clinical Research; Collagen; Collection; Computer Models; DNA Sequence Alteration; Data; Data Analyses; Data Set; Databases; Diameter; Disease; Dissection; Distal; Elastic Fiber; Emergency Situation; Event; Female; Foundations; Frequencies; Generations; Genetic; Genetic Predisposition to Disease; Goals; Grant; Growth; Guidelines; Human; Hypertension; Image; Incidence; Individual; Intervention; Knowledge; Learning; Lesion; Life; Machine Learning; Medical Genetics; Medical Imaging; Medical Surveillance; Medicine; Methods; Modeling; Morbidity - disease rate; Mus; Natural History; Neural Network Simulation; Operative Surgical Procedures; Outcome; Paper; Pathology; Patient Care; Patients; Persons; Pharmacotherapy; Phenocopy; Physicians; Physics; Postdoctoral Fellow; Predisposition; Prevalence; Prognosis; Prosthesis; Regulation; Research; Resolution; Risk; Risk Factors; Rupture; Sampling; Scientist; Shapes; Students; Surgeon; Syndrome; Techniques; Testing; Thoracic Aortic Aneurysm; Thoracic aorta; Time; Tissues; Training; Uncertainty; United States; Work; biomechanical model; biophysical model; clinical care; clinical imaging; design; disability; drug efficacy; experience; falls; generative adversarial network; human data; improved; in silico; in vivo; innovation; machine learning algorithm; machine learning prediction algorithm; male; mechanotransduction; mortality; mouse model; neural; neural network; next generation; novel; predictive modeling; premature; prophylactic; prospective; repaired; risk prediction; sex; sobriety; tool

PROJECT SUMMARY Despite continuing advances in medical genetics, medical imaging, and surgical interventions, thoracic aortic aneurysms (TAAs) are increasingly responsible for significant morbidity and mortality. Large clinical studies reveal the complexity of the disease, which typically presents sporadically in older individuals, with uncontrolled hypertension amongst the key risk factors, while also presenting in younger individuals having genetic or congenital predispositions. Standard methods (including multivariate regressions) have failed to improve prediction of life-threatening acute aortic syndromes (dissection and rupture) and current AHA/ACC guidelines based on maximum aortic diameter fail to predict risk. Further complicating the situation, recent data show that, although life-saving, surgical repair of the proximal aorta with a prosthetic graft increases incidence of distal aortic disease and acute events, thus emphasizing the need to time surgery appropriately – that is, either unnecessary delays due to adherence to current guidelines or pre-mature intervention may increase risk to patients. There is a dire need for a better approach for predicting thoracic aortic growth and potential outcomes. This proposal is significant for it is designed to resolve this unmet clinical need; it is innovative for we propose a novel mechanobiological and biomechanical data-driven approach to develop a next-generation (neural operator based) machine learning tool that can better predict TAA growth and certain outcomes, including drug efficacy. We will combine a novel repurposing of extant murine and human data, generation of ~25000 new synthetic data sets, and collection of unique new murine data (12 models of TAAs) to identify the best machine learning approach, then combine extant and prospective clinical imaging data (~300 patients) to train and test the final neural network (a deep operator neural network, or DeepONet). Our proposed unique meta-learning framework is simply not possible with standard neural networks. We will exploit multi-fidelity training so that both low resolution data and relatively inaccurate models can be used in training when combined with high-fidelity real or synthetic data and uncertainty quantification via functional priors (the most informative Bayesian priors) that are learned by combining historical data, biophysical models, and GANs (generative adversarial networks). This unique combination allows us to learn posteriors with few samples (e.g., 2 or 3 new medical images), hence predictions can be made for new cases with minimal (clinical) information. This project is possible given our highly collaborative team of physician-scientists, bioengineers, and applied mathematicians having a strong track record of successful research (grants, papers) and training of diverse students, post-docs, and residents.

项目摘要 尽管在医学遗传学、医学影像学和外科干预方面不断取得进展， 动脉瘤（TAA）越来越多地导致显著的发病率和死亡率。大型临床研究 揭示了疾病的复杂性，通常在老年人中零星出现， 高血压是关键的危险因素之一，同时也出现在年轻的个体中， 先天性倾向标准方法（包括多元回归）未能改善 危及生命的急性主动脉综合征（夹层和破裂）的预测和当前AHA/ACC指南 基于最大主动脉直径不能预测风险。使情况进一步复杂化的是，最近的数据显示， 虽然可以挽救生命，但用人工移植物对近端主动脉进行手术修复会增加远端 主动脉疾病和急性事件，因此强调需要适当的手术时间-也就是说， 由于遵守当前指南或过早干预而导致的不必要延迟可能会增加以下风险： 患者迫切需要一种更好的方法来预测胸主动脉生长和潜在的结果。 这一建议具有重要意义，因为它旨在解决这一未满足的临床需求;它具有创新性，因为我们提出了一种 一种新的机械生物学和生物力学数据驱动的方法来开发下一代（神经操作 机器学习工具，可以更好地预测TAA的增长和某些结果，包括药物疗效。 我们将结合联合收割机，对现有的鼠和人类数据进行新的再利用，产生约25000个新的合成数据。 集，并收集独特的新小鼠数据（12种TAA模型），以确定最佳机器学习 方法，然后结合联合收割机现有的和前瞻性的临床成像数据（约300例患者）来训练和测试最终的 深度算子神经网络（Deep Operator Neural Network，DeepONet）我们提出的独特的元学习框架 是标准神经网络无法做到的。我们将利用多保真度训练， 分辨率数据和相对不准确的模型在与高保真真实的或 通过功能先验（信息量最大的贝叶斯先验）的合成数据和不确定性量化， 通过结合历史数据，生物物理模型和GAN（生成对抗网络）来学习。这 独特的组合允许我们用很少的样本学习后验（例如，2或3个新的医学图像），因此 可以用最少的（临床）信息对新病例进行预测。这个项目是可能的，因为我们的 一个高度合作的团队，由物理学家、科学家、生物工程师和应用数学家组成，有着强大的跟踪能力。 成功的研究记录（赠款，论文）和不同的学生，博士后和居民的培训。