Generalizable quantitative imaging and machine learning signatures in glioblastoma, for precision diagnostics and personalized treatment: the ReSPOND consortium

胶质母细胞瘤的通用定量成像和机器学习特征，用于精确诊断和个性化治疗：ReSPOND 联盟

• 批准号: 10421222
• 负责人: Christos Davatzikos
• 金额: $ 76.45万
• 依托单位: UNIVERSITY OF PENNSYLVANIA
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-06-01 至 2027-05-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10421222
• 关键词: Area; Astrocytoma; Atlases; Brain Neoplasms; Characteristics; Clinical; Clinical Trials; Communities; Complex; Computer software; Data; Data Set; Databases; Decision Making; Diffusion; Excision; Foundations; Genomics; Glioblastoma; Glioma; Goals; Guidelines; Heterogeneity; Image; Image Analysis; Infiltration; Institution; International; Laboratories; Life; MGMT gene; Machine Learning; Magnetic Resonance Imaging; Malignant Neoplasms; Malignant neoplasm of brain; Measures; Metabolic; Methods; Methylation; Molecular; Outcome; Patients; Pattern; Perfusion; Phase; Phenotype; Physiological; Prognosis; Progression-Free Survivals; Progressive Disease; Property; Protocols documentation; Radiation; Radiology Specialty; Recurrence; Reproducibility; Research; Research Personnel; Scanning; Shapes; Signal Transduction; Site; Stratification; Testing; Texture; Tissues; Training; Update; base; biophysical model; cancer imaging; clinical practice; clinical trial enrollment; data resource; deep learning; disease heterogeneity; heterogenous data; imaging modality; improved outcome; in vivo evaluation; learning strategy; machine learning method; machine learning model; mutant; neuro-oncology; open source; personalized diagnostics; personalized medicine; personalized predictions; phase II trial; phenomics; predict clinical outcome; predictive modeling; programs; promoter; quantitative imaging; radiomics; tool; treatment effect; treatment planning; treatment strategy; treatment stratification; treatment trial; tumor; tumor growth

Abstract The current state of magnetic resonance imaging (MRI) methods in neurooncology offers great potential for providing rich characterizations of structural, physiological, and metabolic character- istics of brain tumors, especially gliomas, which are complex and highly heterogeneous cancers. Glioblastoma (GBM), in particular, has a grim prognosis, with median overall survival (OS) less than 15 months with relatively little improvement in the past 15 years since the Stupp protocol was introduced. Many experimental treatments are being pursued; however, OS has largely remained stagnant. Some of the obstacles in improving this outcome have been 1) disease heterogeneity, which both renders it difficult to detect treatment effects in Phase 1 or even Phase 2 trials, and calls for personalized, rather than one-size fits-all, treatment strategies; 2) methods used for tumor characterization based on size, enhancement, perfusion and diffusion properties are relatively crude and don't fully leverage the richness of imaging data or their spatial heterogeneity. Quanti- tative imaging and machine learning (QIML) methods developed in the past decade have shown great potential for dissecting the spatial, temporal and inter-patient heterogeneity of GBM; for discoveringrelationships between imaging and molecular characteristics ; foroffering personalized predictions of clinical outcome; and for leveraging subtle multi-parametric relationships in the data to detect peri-tumoral infiltration or distinguish treatment related changes, i.e., pseudo-progression (PsP), from true tumor recurrence. Our group has been at the forefront of QIML, with emphasis on a) obtaining rich imaging phenotypes relying on multi-parametric signals, texture parameters, shape properties, spatial patterns derived from atlas registration, and biophysical models of tumor growth, and b) integrating such imaging signatures using machine learning into predictors of clinical outcome, early recurrence from peri-tumoral infiltration, PsP, and radiologic subtypes of GBM. Despite their promise, QIML methods have a notorious limitation: they might overfit specific datasets from which they are derived, and might display poor reproducibility under real-life conditions of variable scanner types and imaging protocols. In this proposal we aim to leverage the recently formed ReSPOND (Radiomics Signatures for PrecisiON Diagnostics) consortium, to integrate, harmonize, and analyze 4,578 datasets from 14 centers around the world, and hence more appropriately train and cross-validate QIML tools for a wider generalizability. This consortium will generate an unprecedented database of diverse and carefully harmonized sets of MRI and clinical measures, and aims to provide the community with robust and reproducible QIML models contributing to precision diagnostics and personalize treatment for this dreaded brain cancer.

抽象的 神经学中磁共振成像（MRI）方法的当前状态提供了很好的 提供结构，生理和代谢特征的丰富特征的潜力 脑肿瘤，尤其是神经胶质瘤的疾病，它们是复杂且高度异质性癌症的。 尤其是胶质母细胞瘤（GBM）具有严峻的预后，中位总生存率（OS）小于 自Stupp协议的过去15年中，15个月的改善相对较小 引入。正在追求许多实验治疗；但是，操作系统在很大程度上仍然存在 停滞。改善这一结果的一些障碍是1）疾病异质性， 这两者都使在第1阶段甚至第2阶段试验中都难以检测治疗效果，并调用 用于个性化而不是一定程度的治疗策略； 2）用于肿瘤的方法 根据大小，增强，灌注和扩散特性的表征相对 粗糙，不要充分利用成像数据或空间异质性的丰富性。量化 过去十年中开发的表面成像和机器学习（QIML）方法 剖析GBM的空间，时间和患者间异质性的巨大潜力；为了 在成像和分子特征之间发现培养；有助于个性化 临床结果的预测；并利用数据中的微妙多参数关系 检测肿瘤周日浸润或区分相关的变化，即伪造 （PSP），来自真正的肿瘤复发。我们的小组一直处于QIML的最前沿，重点是 a）获得依赖多参数信号，纹理参数，形状的丰富成像表型 特性，源自ATLAS登记的空间模式以及肿瘤生长的生物物理模型， b）使用机器学习到临床预测指标 结果，肿瘤周围浸润，PSP和放射线亚型的早期复发。 尽管他们承诺，QIML方法仍有臭名昭著的限制：它们可能过于特定 它们从中得出的数据集，在现实生活中可能表现出差的可重复性 可变扫描仪类型和成像协议的条件。在此提案中，我们旨在利用 最近形成的响应（精确诊断的放射学特征）联盟， 整合，协调和分析来自全球14个中心的4,578个数据集，因此 更适当地训练和交叉验证的QIML工具，以提供更广泛的概括性。这个财团 将生成一个前所未有的数据库，包括多种多样的MRI集合集和 临床措施，旨在为社区提供强大而可重复的QIML模型 有助于精确诊断并个性化这种可怕的脑癌治疗。