Deep-Learning-Derived Endophenotypes from Retina Images

来自视网膜图像的深度学习衍生的内表型

• 批准号: 10706984
• 负责人: RUI CHEN
• 金额: $ 56.81万
• 依托单位: UNIVERSITY OF TEXAS HLTH SCI CTR HOUSTON
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-09-30 至 2025-06-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10706984
• 关键词: 3-Dimensional; Adopted; Age; Algorithms; Artificial Intelligence; Candidate Disease Gene; Chromosome Mapping; Classification; Clinical; Clinical Data; Clinical Research; Communities; Computer software; Data; Descriptor; Development; Diabetes Mellitus; Diabetic Retinopathy; Diagnostic; Disease; Exclusion; Eye; Eye diseases; Funding; Fundus; Gender; Genes; Genetic; Genetic study; Goals; Health Status; Heritability; Human; Image; Individual; Knowledge; Label; Learning; Liquid substance; Manuals; Maps; Masks; Medical; Medical Imaging; Methods; Microaneurysm; Modality; Modeling; Morphology; Optical Coherence Tomography; Output; Participant; Pathologic; Patient imaging; Patients; Pattern; Persons; Phenotype; Physiology; Process; Reading; Reporting; Research; Retina; Retinal Diseases; Retinal Hemorrhage; Scanning; Self Perception; Standardization; Stimulus; Supervision; Testing; Thick; Training; Validation; Visual System; Visualization; biobank; bioinformatics tool; cardiovascular risk factor; clinical imaging; data resource; deep learning; deep learning algorithm; deep learning model; disorder risk; efficacy testing; endophenotype; fundus imaging; genome wide association study; genomic locus; high dimensionality; insight; learning strategy; macular edema; multimodality; natural language; neovascularization; neural network architecture; novel; novel strategies; reconstruction; response; retinal imaging; success; supervised learning; targeted treatment; tool

Abstract The goal of this proposal is to establish a novel artificial intelligence-based strategy of genome wide association studies (GWAS) to identify new genetic loci associated with common human disorders. Identification of the genetic factors underlying these diseases will provide not only mechanistic insights into the diseases but also form the basis for developing novel preventative, diagnostic, and targeted therapeutic methods. While GWAS has achieved great successes in the past 1.5 decades, only a small portion of common diseases' heritability can be currently explained by loci identified from traditional GWAS. Leveraging on the public genetics and clinical imaging data, we propose a novel approach, termed image based GWAS (iGWAS), where GWAS will be performed on endophenotypes derived from images using cutting edge deep learning (DL) algorithms. By creating a more objective and quantitative output from the images, with less information loss, many new disease-associated genetic loci are expected to be identified. To test the efficacy of this novel approach, the human visual system will be used as an example. A DL-phenotyper, Multi-modal multi-view Self-Supervised deep Learning Encoder for Retinal images (MuSSLER), will be developed to extract quantitative output from optical coherence tomography scans and fundus images from both normal eyes and patients with diabetic retinopathy (DR). GWAS will be performed on normal eye endophenotypes to elucidate genes relevant to retina development and physiology. Also, GWAS will be performed on DR-specific endophenotypes to identify DR associated genetic loci and candidate genes. If successful, our approach represents a general framework that can be readily extended to the study of other retinal diseases and other common diseases with imaging data. Furthermore, the phenotyping neural network architecture established in this project can be readily adopted to develop an automated grading tool for heterogeneous clinical data and applied to many other common diseases.

摘要 该方案的目标是建立一种新的基于人工智能的基因组策略 广泛关联研究（GWAS），以确定与普通人类相关的新的遗传位点， 紊乱对这些疾病的遗传因素的鉴定不仅可以提供 对疾病的机械见解，而且还形成了开发新的预防性， 诊断和靶向治疗方法。虽然GWAS已经取得了巨大的成功， 在过去的1.5年里，只有一小部分常见疾病的遗传性目前可以 从传统的GWAS中识别的基因座解释。利用公共遗传学和 临床成像数据，我们提出了一种新的方法，称为基于图像的GWAS（iGWAS）， 其中GWAS将对使用最新技术从图像中获得的内表型进行 深度学习（DL）算法。通过创建一个更客观和量化的输出， 图像，信息丢失较少，许多新的疾病相关的遗传位点预计将 被识别。为了测试这种新方法的有效性，将使用人类视觉系统 作为一个例子。DL-表型，多模态多视图自监督深度学习 将开发视网膜图像编码器（MuSSLER），以从 正常眼和患者的光学相干断层扫描和眼底图像 糖尿病视网膜病变（DR）将对正常眼内表型进行GWAS， 阐明与视网膜发育和生理相关的基因。此外，将执行GWAS DR特异性内表型，以确定DR相关的遗传基因座和候选基因。如果 成功的，我们的方法代表了一个通用的框架，可以很容易地扩展到 研究其他视网膜疾病和其他常见疾病的影像学资料。而且 在本项目中建立的表型神经网络架构可以很容易地被采用， 开发一个自动分级工具，用于异质性临床数据，并应用于许多其他 常见疾病。