Curating musculoskeletal CT data to enable the development of AI/ML approaches for analysis of clinical CT in patients with metastatic spinal disease

整理肌肉骨骼 CT 数据，以开发用于分析转移性脊柱疾病患者临床 CT 的 AI/ML 方法

• 批准号: 10593799
• 负责人: RON N ALKALAY
• 金额: $ 35.23万
• 依托单位: BETH ISRAEL DEACONESS MEDICAL CENTER
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-04-01 至 2025-03-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10593799
• 关键词: Administrative Supplement; Advanced Development; Affect; Age; Anatomy; Appearance; Architecture; Area; Artificial Intelligence; Biological; Biological Markers; Cachexia; Cancer Patient; Classification; Clinical; Clinical Data; Communities; Complex; Computer Vision Systems; Data; Data Analyses; Data Collection; Data Set; Databases; Development; Diagnostic; Digital Imaging and Communications in Medicine; Disease; Disease Progression; Ensure; Event; Evolution; Face; Fracture; Guidelines; Human; Image; Individual; Label; Lesion; Machine Learning; Malignant Neoplasms; Malnutrition; Manuals; Mechanics; Mediating; Metabolic; Metadata; Metastatic Neoplasm to the Bone; Metastatic to; Methods; Modeling; Morbidity - disease rate; Muscle; Muscular Atrophy; Musculoskeletal; Neoplasm Metastasis; Neurologic Deficit; Pain; Pathologic; Patient Care; Patients; Physical Function; Property; Quality Control; Radiation; Radiation therapy; Radiology Specialty; Readiness; Research; Research Personnel; Resolution; Risk; Scanning; Sensitivity and Specificity; Skeletal Muscle; Speed; Spinal; Spinal Diseases; Spinal Fractures; Standardization; System; The Cancer Imaging Archive; Tissues; Training; Unnecessary Procedures; Vertebral Bone; Vertebral column; X-Ray Computed Tomography; base; bone; clinical care; clinical risk; clinically significant; cost; deep learning; follow-up; fracture risk; high risk; improved; insight; large datasets; learning strategy; machine learning model; muscle form; novel; palliative; parent grant; predictive marker; prevent; radiological imaging; sarcopenia; sex; skeletal tissue; spine bone structure; treatment optimization

Project Summary/Abstract Vertebral bone metastases, widespread in patients with cancer, destroy vertebral anatomy, bone architecture, and mechanical strength, exposing patients to a high risk of pathologic vertebral fracture (PVF). PVFs cause neurological deficits in up to 50% of patients with further complications that may be fatal. Our parent grant (AR075964) develops and validates a novel computational musculoskeletal approach for patient-specific, precise prediction of PVF risk from clinical CT. Segmentation of vertebral anatomy, bone properties, and individual spinal musculature cross-sectional area from clinical CT imaging, a fundamental step for assembling the computational musculoskeletal models, faces unique challenges due to the cancer-mediated alteration in skeletal tissues radiological appearance. Application of deep learning (DL) methods will speed and standardize the critical segmentation step, permitting analysis of larger datasets promoting new DL analysis for improved insight into the drivers of PVF risk in patients with metastatic spine disease. This development is hindered by the lack of publicly available, clinically annotated image data specific to metastatic human spines. This proposal aims to establish a curated, publicly accessible, 4D CT imaging dataset of human metastatic spines and associated radiological delineations of lesions and vertebral features, to enable the advancement of DL methods to analyze PVF risk. We thus propose three specific aims: 1) prepare the CT dataset for the application of deep learning: Our data is based on our parent grant (AR075964) de-identified spinal column and thoracoabdominal muscles CT image datasets obtained from 140 patients at radiation planning and additional CT diagnostic data at 3, 6, 9, and 12 months follow up (1400 image data sets overall). We will assemble and curate the data for public distribution by a) preprocessing the CT images for machine learning applications, b) delineating the vertebrae, lesions, and muscles in the images, c) assembling metadata, including limited subject demographic and disease status into JSON files, and d) extract SIFT features for computer-vision style analyses. 2) Testbed Deep Learning (DL) Segmentation: To ensure that the curated data set is suitable for training artificial intelligence and machine learning (AI/ML) systems, we will develop and train testbed DL segmentation networks to segment bones, lesions, and muscles in baseline and follow-up clinical CT. We will use the networks to control the quality the curated CT images and delineations, 3) Disseminate 4D dataset following best practices: Upon completion of tasks 1 and 2, we will make the data available to the research community via the Cancer Image Archive (TCIA) following their established methods for de-identifying DICOM scans and annotating and encoding clinical data and analysis results. Integrating DL systems within our approach will change the patient management paradigm from reactive to data-driven proactive management to prevent PVF events and critically reduce bias in patient management.

项目概要/摘要 椎骨骨转移广泛存在于癌症患者中，破坏椎骨解剖结构、骨结构， 和机械强度，使患者面临病理性椎体骨折（PVF）的高风险。 PVF 导致 高达 50% 的患者出现神经功能缺损，并出现可能致命的进一步并发症。我们的家长资助 (AR075964) 开发并验证了一种针对特定患者的新型计算肌肉骨骼方法， 通过临床 CT 精确预测 PVF 风险。椎体解剖结构、骨骼特性的分割，以及 来自临床 CT 成像的个体脊柱肌肉横截面积，这是组装的基本步骤 由于癌症介导的改变，计算肌肉骨骼模型面临着独特的挑战 骨骼组织的放射学外观。深度学习（DL）方法的应用将加速并标准化 关键的分割步骤，允许分析更大的数据集，促进新的深度学习分析，以改进 深入了解转移性脊柱疾病患者 PVF 风险的驱动因素。这种发展受到阻碍 缺乏针对转移性人类脊柱的公开可用的、临床注释的图像数据。 该提案旨在建立一个精心策划的、可公开访问的人类转移性 4D CT 成像数据集 脊柱以及相关病变和椎骨特征的放射学轮廓，以促进 分析 PVF 风险的 DL 方法。因此，我们提出了三个具体目标：1）为 深度学习的应用：我们的数据基于我们的家长资助（AR075964）去识别的脊柱和 从 140 名患者在放射计划和其他方面获得的胸腹肌 CT 图像数据集 随访 3、6、9 和 12 个月时的 CT 诊断数据（总共 1400 个图像数据集）。我们将集合并 通过 a) 为机器学习应用程序预处理 CT 图像，b) 整理数据以供公共分发 描绘图像中的椎骨、病变和肌肉，c) 组装元数据，包括有限的主题 将人口统计和疾病状态写入 JSON 文件，以及 d) 提取 SIFT 特征以进行计算机视觉风格分析。 2）测试床深度学习（DL）分割：确保整理的数据集适合训练人工 智能和机器学习 (AI/ML) 系统，我们将开发和训练测试平台 DL 分割网络 在基线和后续临床 CT 中分割骨骼、病变和肌肉。我们将使用网络来控制 策划的 CT 图像和轮廓的质量，3) 按照最佳实践传播 4D 数据集： 完成任务 1 和 2 后，我们将通过癌症图像向研究界提供数据 Archive (TCIA) 遵循其既定的 DICOM 扫描去识别以及注释和编码方法 临床数据和分析结果。将深度学习系统集成到我们的方法中将改变患者 管理范式从被动管理转变为数据驱动的主动管理，以防止 PVF 事件并关键 减少患者管理中的偏差。