Deep-learning-based prediction of AMD and its progression with GWAS and fundus image data
Deep-learning-based prediction of AMD and its progression with GWAS and fundus image data
批准号:
10056062
负责人:
Wei Chen
金额:
$18.82万
依托单位国家:
美国
项目类别:
财政年份:
2020
资助国家:
美国
项目状态:
已结题
起止时间:
2020-08-01 至 2022-05-31
关键词:
AchievementAge related macular degenerationApplications GrantsAreaBiologicalBlindnessBlood VesselsCategoriesCharacteristicsClinicalClinical ManagementCohort StudiesCollectionColorCommunitiesComputer softwareDataData SetDevelopmentDiagnosisDiseaseDisease ManagementDisease ProgressionDisease susceptibilityEarly DiagnosisElderlyExposure toEye diseasesGenesGeneticGenotypeGrowthImageIndividualInjectionsInternationalKnowledgeMachine LearningMethodsModelingMonitorNational Eye InstituteNetwork-basedOnline SystemsOphthalmologistPhenotypePositioning AttributeProgressive DiseaseResearchResearch PersonnelRiskSamplingSeveritiesSoftware ToolsStatistical MethodsSubgroupSusceptibility GeneTechniquesTestingTimeTrainingUniversitiesVascular Endothelial Growth FactorsWorkanalytical methodbasebiobankclinical phenotypecohortcomputerized toolsconvolutional neural networkdata warehousedatabase of Genotypes and Phenotypesdeep learningdeep neural networkfundus imaginggenome wide association studygenome-widegenome-wide analysisgraphical user interfaceimprovedindividualized medicineinnovationinterestlearning strategyneural networknovelpersonalized predictionspersonalized risk predictionpredictive modelingpublic repositorysecondary analysissuccesssynergismuser friendly softwareuser-friendlyweb based interfaceweb interface
中文摘要
老年性黄斑变性(AMD)是世界范围内导致不可逆性失明的主要原因。成功
AMD的全基因组关联研究已经确定了许多疾病易感基因。穿过
国际GWAS财团和大型合作项目、海量数据集的巨大努力
包括高质量的GWAS数据和特征良好的临床表型现已公开提供
DBGaP和UK Biobank等存储库。在临床上,彩色眼底图像已被广泛应用于
眼科医生诊断AMD及其严重程度。丰富的地理信息系统数据和眼底的结合
图像数据为研究人员提供了一个前所未有的机会来测试超越
原始项目的目标。其中,基于AMD发展的预测模型及其进展
无论是在GWAS上还是在眼底图像上,都没有探索过数据。大多数现有的预测模型只关注于
经典的统计方法,通常是带有有限数量预测因子的回归模型(例如,SNP)。
此外,大多数预测只给出静态风险,而不是随时间推移的动态风险轨迹,其中
后者对于像AMD这样的进展性疾病更具信息量。机器学习技术的最新进展,
特别是深度学习,已被证明通过结合
当具有明确定义的表型的大规模训练数据集被
可用。尽管深度学习在许多领域取得了成功,但在AMD和其他眼科领域,深度学习还没有得到充分的探索
疾病。受多项关于AMD发展或进展的大规模研究的推动,其中Gwas和/或
已收集到的眼底图像数据,我们提出了新的深度学习方法来预测
AMD的状况及其进展,并确定具有显著不同风险特征的亚组。特别是,在AIM
1,我们将构建一种新的局部卷积神经网络来预测疾病的发生(AMD或非AMD)和
严重程度(例如,轻度AMD、中度AMD、晚期AMD)基于(1a):35,000名患有
GWAS数据和(1b):拥有GWAS和眼底图像数据的4,000人的较小队列。在目标2中,
我们将开发一种新的深度神经网络生存模型来预测个体疾病的进展
轨迹(例如,迟到时间-AMD)。在这两个目标中,我们将使用局部线性逼近技术来识别
有助于个人风险概况预测和识别具有不同风险的子组的重要预测因素
配置文件。在目标3中,我们将使用独立的队列来验证和校准我们的方法,并实施
方法转化为用户友好的软件和易于访问的Web界面。最近FDA批准了
Beovu,一种通过抑制血管内皮生长因子从而抑制湿性AMD(一种晚期AMD)的新型注射疗法
异常血管的生长,使我们的研究更有意义,因为它将提供最前沿的
和AMD的综合预测模型,具有促进早期诊断和治疗的巨大潜力
为疾病量身定做的治疗和临床管理。
英文摘要
Age-related macular degeneration (AMD) is a leading cause of irreversible blindness worldwide. Successful
genome-wide association studies (GWAS) of AMD have identified many disease-susceptibility genes. Through
great efforts from international GWAS consortium and large-scale collaborative projects, massive datasets
including high-quality GWAS data and well-characterized clinical phenotypes are now available in public
repositories such as dbGaP and UK Biobank. Clinically, color fundus images have been extensively used by
ophthalmologists to diagnose AMD and its severity level. The combination of wealthy GWAS data and fundus
image data provides an unprecedented opportunity for researchers to test new hypotheses that are beyond the
objectives of original projects. Among them, predictive models for AMD development and its progression based
on both GWAS and fundus image data have not been explored. Most existing prediction models only focus on
classic statistical approaches, often regression models with a limited number of predictors (e.g., SNPs).
Moreover, most predictions only give static risks rather than dynamic risk trajectories over time, of which the
latter is more informative for a progressive disease like AMD. Recent advances of machine learning techniques,
particularly deep learning, have been proven to significantly improve prediction accuracy by incorporating
multiple layers of hidden non-linear effects when large-scale training datasets with well-defined phenotypes are
available. Despite its success in many areas, deep learning has not been fully explored in AMD and other eye
diseases. Motivated by multiple large-scale studies of AMD development or progression, where GWAS and/or
longitudinal fundus image data have been collected, we propose novel deep learning methods for predicting
AMD status and its progression, and to identify subgroups with significant different risk profiles. Specially, in Aim
1, we will construct a novel local convolutional neural network to predict disease occurrence (AMD or not) and
severity (e.g., mild AMD, intermediate AMD, late AMD) based on (1a): a large cohort of 35,000+ individuals with
GWAS data and (1b): a smaller cohort of 4,000+ individuals with both GWAS and fundus image data. In Aim 2,
we will develop a novel deep neural network survival model for predicting individual disease progression
trajectory (e.g., time to late-AMD). In both aims, we will use the local linear approximation technique to identify
important predictors that contribute to individual risk profile prediction and to identify subgroups with different risk
profiles. In Aim 3, we will validate and calibrate our methods using independent cohorts and implement proposed
methods into user-friendly software and easy-to-access web interface. With the very recent FDA approval for
Beovu, a novel injection treatment for wet AMD (one type of late AMD) by inhibiting VEGF and thus suppressing
the growth of abnormal blood vessels, it makes our study more significant, as it will provide most cutting-edge
and comprehensive prediction models for AMD which have great potential to facilitate early diagnosis and
tailored treatment and clinical management of the disease.
期刊论文(0)
专著(0)
科研奖励(0)
会议论文
An ensemble deep learning model for tumor bud detection and risk stratification in colorectal carcinoma.
-
批准号:10564824
-
项目类别:
-
资助金额:$54.37万
-
财政年份:2023
-
负责人:Wei Chen
-
依托单位:
Establishing translational neuroimaging tools for quantitative assessment of energy metabolism and metabolic reprogramming in healthy and diseased human brain at 7T
-
批准号:10714863
-
项目类别:
-
资助金额:$63.02万
-
财政年份:2023
-
负责人:Wei Chen
-
依托单位:
SCH: New Advanced Machine Learning Framework for Mining Heterogeneous Ocular Data to Accelerate
-
批准号:10601180
-
项目类别:
-
资助金额:$30.0万
-
财政年份:2022
-
负责人:Wei Chen
-
依托单位:
SCH: New Advanced Machine Learning Framework for Mining Heterogeneous Ocular Data to Accelerate
-
批准号:10665804
-
项目类别:
-
资助金额:$30.0万
-
财政年份:2022
-
负责人:Wei Chen
-
依托单位:
Cellular Interactions in Vascular Calcification of Chronic Kidney Disease
-
批准号:10525401
-
项目类别:
-
资助金额:$12.53万
-
财政年份:2022
-
负责人:Wei Chen
-
依托单位:
Console Replacement and Upgrade of 9.4 Tesla Animal Instrument
-
批准号:10414184
-
项目类别:
-
资助金额:$132.8万
-
财政年份:2022
-
负责人:Wei Chen
-
依托单位:
Deep-learning-based prediction of AMD and its progression with GWAS and fundus image data
-
批准号:10226322
-
项目类别:
-
资助金额:$22.03万
-
财政年份:2020
-
负责人:Wei Chen
-
依托单位:
Advancing simultaneous fMRI-multiphoton imaging technique to study brain function and connectivity across different scales at ultrahigh field
-
批准号:10043972
-
项目类别:
-
资助金额:$46.69万
-
财政年份:2020
-
负责人:Wei Chen
-
依托单位:
Advancing simultaneous fMRI-multiphoton imaging technique to study brain function and connectivity across different scales at ultrahigh field
-
批准号:10268184
-
项目类别:
-
资助金额:$54.75万
-
财政年份:2020
-
负责人:Wei Chen
-
依托单位:
Advancing simultaneous fMRI-multiphoton imaging technique to study brain function and connectivity across different scales at ultrahigh field
-
批准号:10463737
-
项目类别:
-
资助金额:$55.69万
-
财政年份:2020
-
负责人:Wei Chen
-
依托单位:
Advancing simultaneous fMRI-multiphoton imaging technique to study brain function and connectivity across different scales at ultrahigh field
-
批准号:10670768
-
项目类别:
-
资助金额:$56.59万
-
财政年份:2020
-
负责人:Wei Chen
-
依托单位:
Cbfβ mediates articular cartilage regeneration and repair in aging
-
批准号:9982158
-
项目类别:
-
资助金额:$40.73万
-
财政年份:2019
-
负责人:Wei Chen
-
依托单位:
Cbf mediates articular cartilage regeneration and repair in aging
-
批准号:10615874
-
项目类别:
-
资助金额:$41.69万
-
财政年份:2019
-
负责人:Wei Chen
-
依托单位:
Cbf mediates articular cartilage regeneration and repair in aging
-
批准号:10405827
-
项目类别:
-
资助金额:$41.69万
-
财政年份:2019
-
负责人:Wei Chen
-
依托单位:
Cbf mediates articular cartilage regeneration and repair in aging
-
批准号:10430288
-
项目类别:
-
资助金额:$41.69万
-
财政年份:2019
-
负责人:Wei Chen
-
依托单位:
Calcification Propensity, using Dynamic Light Scattering, to Study Vascular Calcification in Patients with Advanced Chronic Kidney Disease
-
批准号:10171838
-
项目类别:
-
资助金额:$19.72万
-
财政年份:2018
-
负责人:Wei Chen
-
依托单位:
Breaking Spatiotemporal Barriers of MR Imaging Technologies to Study Human Brain Function and Neuroenergetics
-
批准号:10455036
-
项目类别:
-
资助金额:$131.5万
-
财政年份:2018
-
负责人:Wei Chen
-
依托单位:
Calcification Propensity, using Dynamic Light Scattering, to Study Vascular Calcification in Patients with Advanced Chronic Kidney Disease
-
批准号:10418310
-
项目类别:
-
资助金额:$16.16万
-
财政年份:2018
-
负责人:Wei Chen
-
依托单位:
Breaking Spatiotemporal Barriers of MR Imaging Technologies to Study Human Brain Function and Neuroenergetics
-
批准号:10252903
-
项目类别:
-
资助金额:$122.91万
-
财政年份:2018
-
负责人:Wei Chen
-
依托单位:
Breaking Spatiotemporal Barriers of MR Imaging Technologies to Study Human Brain Function and Neuroenergetics
-
批准号:9789873
-
项目类别:
-
资助金额:$124.81万
-
财政年份:2018
-
负责人:Wei Chen
-
依托单位:
海外基金