Data-Driven Learning Framework for Fast Quantitative Knee Joint Mapping

用于快速定量膝关节绘图的数据驱动学习框架

• 批准号: 10430275
• 负责人: Ravinder Regatte
• 金额: $ 53.44万
• 依托单位: NEW YORK UNIVERSITY SCHOOL OF MEDICINE
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-07-01 至 2027-05-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10430275
• 关键词: 3-Dimensional; Acceleration; Affect; Algorithms; Biochemical; Biological Models; Cartilage; Chronic; Clinical; Clinical Protocols; Collagen; Collagen Fiber; Contrast Media; Data; Data Set; Degenerative polyarthritis; Detection; Diagnostic; Discrimination; Early Diagnosis; Elderly; Evaluation; Extracellular Matrix; Extracellular Matrix Degradation; Future; Goals; Heterogeneity; Human; Hydration status; Image; Imaging Techniques; Knee; Knee Osteoarthritis; Knee joint; Learning; Life; Machine Learning; Magnetic Resonance Imaging; Maps; Meniscus structure of joint; Meta-Analysis; Methods; Modeling; Modification; Morphology; Musculoskeletal; Pathologic Processes; Patients; Pattern; Performance; Persons; Population; Process; Proteoglycan; Protocols documentation; Relaxation; Research Personnel; Resolution; Sampling; Scanning; Screening procedure; Slice; Structure; T2 weighted imaging; Techniques; Therapeutic Agents; Thick; Thinness; Time; Tissue Engineering; Tissues; Translating; Validation; Water; articular cartilage; base; cartilage degradation; curative treatments; design; disability; early screening; efficacy evaluation; healing; human data; improved; in vivo; learning algorithm; macromolecule; prevent; reconstruction; repaired; tool; water environment

PROJECT SUMMARY Osteoarthritis (OA), a leading cause of chronic disability in the elderly population, occurs with the degradation of the extracellular matrix of articular cartilage, mainly composed of proteoglycan, collagen fibers, and water. Early diagnosis of cartilage degeneration requires the detection of changes in proteoglycan concentration and collagen integrity, preferably non-invasively and before any morphological changes occur. Spin-spin relaxation time (T2) and spin-lattice relaxation time in the rotating frame (T1ρ) can provide quantitative information about the structure and biochemical composition of the cartilage before morphological changes occur. Mono-exponential (ME) models can characterize the T2 and T1ρ relaxation processes and map it for articular cartilage in the knee joint. A recent meta-analysis showed that T1ρ provides more discrimination than T2 for OA. However, the ME model alone cannot provide distinct information from different compartments of the cartilage. Recent studies have shown that T1ρ relaxation might have bi-exponential (BE) components, following the hypothesis of the multi- compartmental structure of the cartilage. BE T2 relaxation has shown better diagnostic performance than ME for OA and can show the dispersion of the relaxation times, reflecting the heterogeneity in the macromolecular environment of water in the cartilage. BE analysis of cartilage typically requires a larger number of acquisitions with different spin-lock times (TSLs) or echo times (TEs), resulting in long scan time. High spatial resolution is also needed to visualize the thin and curved cartilage and fine structures in the knee joint. As a result, in vivo application of BE three-dimensional (3D) T1ρ and T2 mapping techniques is still very limited. Compressed sensing (CS) combined with parallel imaging (PI) can accelerate acquisition and reduce the scan time required for ME 3D T1ρ and T2 mappings. T1ρ scans can be reduced from 30 min to ~3 min with an error smaller than 6.5%. However, the error is two to three times larger for BE mapping. This problem can be potentially solved by optimizing the sampling times (TSLs for T1ρ and TEs for T2) and the free parameters of the CS approach (k- space sampling pattern, regularization function, regularization parameter, and minimization algorithm parameters) using fully sampled 3D knee joint datasets, supported by machine learning tools. The overarching goal of this proposal is to develop, optimize, and translate a high-spatial-resolution, rapid 3D magnetic resonance imaging sequence using data-driven learning-based CS for assessment of the human knee joint and using ME and BE 3D T1ρ (T2) mapping for improved biochemical characterization of cartilage and menisci on a standard clinical 3T scanner.

项目概要 骨关节炎（OA）是老年人慢性残疾的主要原因，随着骨关节炎的退化而发生 关节软骨的细胞外基质，主要由蛋白聚糖、胶原纤维和水组成。早期的 诊断软骨退变需要检测蛋白聚糖浓度和胶原蛋白的变化 完整性，优选地非侵入性地并且在任何形态变化发生之前。自旋-自旋弛豫时间（T2） 旋转坐标系中的自旋晶格弛豫时间（T1ρ）可以提供有关结构的定量信息 以及发生形态变化之前软骨的生化成分。单指数 (ME) 模型可以表征 T2 和 T1ρ 松弛过程，并将其映射到膝关节的关节软骨。 最近的一项荟萃​​分析表明，对于 OA，T1ρ 比 T2 提供更多的区分度。然而，ME 模型 单独的方法不能提供软骨不同区室的不同信息。最近的研究有 显示 T1ρ 弛豫可能具有双指数 (BE) 分量，遵循多重假设 软骨的区室结构。 BE T2 松弛显示出比 ME 更好的诊断性能 OA可以显示弛豫时间的分散性，反映大分子的异质性 软骨中的水环境。软骨的 BE 分析通常需要大量采集 具有不同的自旋锁定时间（TSL）或回波时间（TE），导致扫描时间较长。高空间分辨率是 还需要可视化膝关节中薄而弯曲的软骨和精细结构。结果，体内 BE 三维 (3D) T1ρ 和 T2 映射技术的应用仍然非常有限。压缩感知 (CS) 与并行成像 (PI) 结合可加速采集并减少 ME 所需的扫描时间 3D T1ρ 和 T2 映射。 T1ρ 扫描时间可从 30 分钟缩短至约 3 分钟，误差小于 6.5%。 然而，BE 映射的误差要大两到三倍。这个问题可以通过以下方式解决 优化采样时间（T1ρ 的 TSL 和 T2 的 TE）和 CS 方法的自由参数（k- 空间采样模式、正则化函数、正则化参数和最小化算法 参数）使用完全采样的 3D 膝关节数据集，并由机器学习工具支持。首要的 该提案的目标是开发、优化和转化高空间分辨率、快速的 3D 磁共振 使用数据驱动的基于学习的 CS 来评估人体膝关节并使用 ME 进行成像序列 和 BE 3D T1ρ (T2) 绘图，以改善标准软骨和半月板的生化特征 临床 3T 扫描仪。