Development of an AI/ML-ready knee ultrasound dataset in a population-based cohort

在基于人群的队列中开发支持 AI/ML 的膝盖超声数据集

• 批准号: 10591756
• 负责人: Amanda E Nelson
• 金额: $ 30.45万
• 依托单位: UNIV OF NORTH CAROLINA CHAPEL HILL
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-05-05 至 2025-04-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10591756
• 关键词: Administrative Supplement; Affect; Age; Area; Assessment tool; Atlases; Attention; Award; Benchmarking; Biochemical; Biological Markers; Black race; Chronic; Clinic; Clinical; Clinical Research; Clinical Trials; Collaborations; Communities; County; Data; Data Analyses; Data Set; Degenerative polyarthritis; Development; Disease; Documentation; Enrollment; Ethical Issues; Explosion; FAIR principles; Funding; Future; Goals; Grant; Health; Hispanic; Image; Image Analysis; Implant; Institutes; Joints; Knee; Knee Osteoarthritis; Lead; Magnetic Resonance Imaging; Manuscripts; Mentors; Methodology; Methods; Mission; Modality; Musculoskeletal; National Institute of Arthritis and Musculoskeletal and Skin Diseases; Nature; North Carolina; Pain; Parents; Phase; Phenotype; Population; Population Study; Preparation; Privacy; Protocols documentation; Public Health; Publishing; Radiation; Readiness; Renaissance; Reproducibility; Research; Resource-limited setting; Resources; Risk Factors; Role; Scoring Method; Standardization; Subgroup; Technology; Time; Tissues; Ultrasonography; United States; Universities; Validation; Variant; Visit; Weight; Woman; Work; aged; base; clinical center; clinical practice; cohort; convolutional neural network; cost; cost effective; deep learning; disability; follow-up; graduate student; health equity; imaging genetics; imaging modality; improved; innovation; insight; knee pain; men; metallicity; neural network algorithm; novel; parent project; population based; precision medicine; process optimization; prospective; radiological imaging; repository; response; soft tissue; ultrasound; uptake

SUMMARY Our long-term goal is to demonstrate the utility of ultrasound for OA (OsteoArthritis) assessment, standardize its acquisition and scoring, and promote increased uptake of ultrasound for use in clinical, research, and trial settings. This supplement will allow us to enhance the original proposal by providing additional resources to support AI/ML approaches utilizing the image data in addition to the semiquantitative scoring we initially proposed. Knee osteoarthritis (KOA) is highly prevalent and frequently debilitating. Development of potential treatments has been hampered by the heterogeneous nature of this common chronic condition, which is characterized by several subgroups, or phenotypes, with different underlying pathophysiological mechanisms. Imaging, genetics, biochemical biomarkers, and other features can be used to characterize phenotypes, but variations in data types can make it difficult to harmonize definitions. Ultrasound is a widely accessible, time- efficient, and cost-effective imaging modality that can provide detailed and reliable information for all joint tissues. Application of deep learning methodology to discover ultrasound features associated with pain and radiographic change in KOA is highly innovative and will be a major step forward for the field. We will leverage standardized ultrasound images from the diverse and inclusive population-based Johnston County Health Study (JoCoHS), the new enrollment phase of the 30-year Johnston County OA Project which includes Black, White, and Hispanic men and women aged 35-70. In Aim 1, we will apply deep learning methodology to understand the features in ultrasound images that are most associated with knee pain and with radiographic features of knee OA in this diverse group. Aim 2 will allow the process of optimization for full AI/ML readiness of these images, including annotation, documentation, formatting, and storage of these images according to FAIR principles. This supplement will enhance the parent study by allowing AI/ML analysis of the ultrasound images, beyond just the semi-quantitative scores, and represents a crucial step to determine the ultrasound features of greatest importance to pain and other aspects of OA. By developing and maintaining an AI/ML ready repository of standardized ultrasound images from this generalizable cohort, we can enhance the uptake of this modality and contribute to further study on its use in OA worldwide, including in low-resource settings and across populations.

总结