Learning-based 3D modeling of AMD to assess disease progression and response to treatment

基于学习的 AMD 3D 建模，用于评估疾病进展和治疗反应

• 批准号: 10592517
• 负责人: Majda Hadziahmetovic
• 金额: $ 43.38万
• 依托单位: DUKE UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-09-30 至 2025-08-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10592517
• 关键词: 3-Dimensional; Affect; Age related macular degeneration; Angiography; Area; Blindness; Classification; Computer Models; Computing Methodologies; Data; Data Set; Developed Countries; Development; Diagnostic; Dimensions; Disease; Disease Progression; Drusen; Dryness; Early treatment; Elderly; Evolution; Fundus; Goals; Human; Image; Individual; Institution; Label; Learning; Maps; Medical Imaging; Methods; Modality; Modeling; Morphology; Multimedia; Natural History; Network-based; Neural Network Simulation; Nonexudative age-related macular degeneration; Optical Coherence Tomography; Outcome; Output; Pathologic; Pathology; Patient-Focused Outcomes; Patients; Recording of previous events; Records; Registries; Research; Retina; Retinal Diseases; Risk; Robotics; Scanning; Schedule; Slice; Specific qualifier value; Techniques; Testing; Thick; Time; Tissues; Training; Visit; Visual; Western World; Work; aging population; automated image analysis; biomarker identification; clinical database; clinical practice; convolutional neural network; deep learning; deep learning model; deep neural network; disease classification; disease natural history; feature extraction; follow-up; high reward; high risk; imaging biomarker; imaging modality; improved; inclusion criteria; innovation; insight; learning strategy; long short term memory; longitudinal dataset; neural network; novel; patient stratification; prediction algorithm; reconstruction; retinal imaging; spatiotemporal; three-dimensional modeling; transfer learning; treatment response

Abstract: Age-related macular degeneration (AMD) is the leading cause of irreversible vision loss in developed countries. With the growing aging population, the burden of AMD will continue to rise. Despite significant research efforts, we still have limited understanding of what drives the disease progression and why some patients advance to final stages, not respond to available treatments, and have profound vision loss. To improve visual outcomes for these patients, it is critical to develop methods that can identify individuals with early, asymptomatic changes who are at the risk of developing advanced forms of disease. Consequently, by employing recent developments in deep learning and automated image and video analysis, the goal of this project is to develop computational methods and models for automated image analysis and biomarker identification to improve our understanding of AMD and help us to predict its course. To achieve this, we will develop Deep Neural Network (DNN)-based models to identify useful image biomarkers for AMD from different imaging modalities commonly used in clinical practice – Optical-Coherence Tomography (OCT), Fundus Autofluorescence (FAF), and Fundus Angiography (FA). We hypothesize that adding FAF and FA images will significantly improve localization and classification of pathology; thus, facilitate a better understanding of the disease's natural history and response to treatment. To execute this innovative, high-risk/high-reward project, we will use the data from The Duke Ophthalmic Registry, the largest single-institution clinical database for ophthalmic records in the world. We have access to a downloaded and expert-annotated large image dataset numbering over 6400 patients that meet our study's inclusion criteria – progression of AMD from early to advanced stages (dry and wet). For each patient, OCT, FAF, and FA images were captured during a single visit or within specified follow-up intervals (up to ten years or more). We will develop learning-based methods and models for one-time-point image fusion and analysis; specifically, DNN models for AMD classification (early vs. intermediate vs. advanced dry AMD vs. wet AMD), segmentation of the diseased tissue, and 3D reconstruction of the affected area. Finally, using the longitudinal datasets, we will develop deep-learning methods and models to analyze disease evolution over time. The critical insight and novelty are to consider longitudinal datasets as sequences of 2D and 3D pathology models, which allows for the use of Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM)-based neural networks, which were recently introduced and employed for time-dependent video frame prediction in the context of autonomous vehicles and human action recognition. The proposed research will result in early AMD patient stratification, which will allow for individually tailored follow-up schedules and lead to timely treatments; this is very important since the early treatment of wet AMD results in better visual outcomes.

抽象的： 与年龄相关的黄斑变性（AMD）是发达国家视力丧失的主要原因。 随着人口衰老的增长，AMD的燃烧将继续上升。尽管进行了重大的研究工作， 我们仍然对驱动疾病进展的原因以及某些患者前进的理解有限 最后阶段，不对可用的治疗做出反应，并具有深远的视力丧失。改善视觉结果 这些患者，开发可以识别早期，不对称变化的个体的方法至关重要 他们有发展高级疾病形式的风险。因此，通过采用最近的发展 在深度学习和自动化图像和视频分析中，该项目的目的是开发计算 自动图像分析和生物标记识别的方法和模型以提高我们的理解 AMD并帮助我们预测其课程。为了实现这一目标，我们将开发基于深的神经网络（DNN） 从临床中常用的不同成像方式中识别有用的AMD的有用图像生物标志物的模型 练习 - 光学固定断层扫描（OCT），眼底自动荧光（FAF）和眼底血管造影 （FA）。我们假设添加FAF和FA图像将显着改善本地化和分类 病理;因此，促进对疾病的自然史和对治疗的反应有更好的了解。 为了执行这个创新的高风险/高奖励项目，我们将使用Duke Ophthalmic的数据 注册表是世界上眼科记录的最大的单机构临床数据库。我们可以访问 下载且专家注册的大图数据集，符合我们研究的6400名患者编号 纳入标准 - AMD从早期到高级阶段（干燥和湿）的发展。对于每个患者，十月， FAF和FA图像在一次访问或指定的随访间隔内被捕获（最多十年或 更多的）。我们将开发基于学习的方法和模型，用于一次时间点图像融合和分析； 具体而言，用于AMD分类的DNN模型（早期与中级与高级干AMD与湿AMD）， 解剖组织的分割，受影响区域的3D重建。最后，使用纵向 数据集，我们将开发深入学习的方法和模型，以分析随着时间的推移疾病进化。关键 洞察力和新颖性是将纵向数据集视为2D和3D病理模型的序列，这些序列 允许使用卷积神经网络（CNN）和基于短期记忆（LSTM）的神经 网络最近是在上下文中引入和工作的。 自动驾驶汽车和人类行动识别。拟议的研究将导致早期AMD患者 分层，这将允许单独量身定制的随访时间表并导致及时治疗；这是 由于早期治疗湿AMD会带来更好的视觉结果，因此非常重要。