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
基本信息
- 批准号:10421222
- 负责人:
- 金额:$ 76.45万
- 依托单位:
- 依托单位国家:美国
- 项目类别:
- 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:
- 关键词:AreaAstrocytomaAtlasesBrain NeoplasmsCharacteristicsClinicalClinical TrialsCommunitiesComplexComputer softwareDataData SetDatabasesDecision MakingDiffusionExcisionFoundationsGenomicsGlioblastomaGliomaGoalsGuidelinesHeterogeneityImageImage AnalysisInfiltrationInstitutionInternationalLaboratoriesLifeMGMT geneMachine LearningMagnetic Resonance ImagingMalignant NeoplasmsMalignant neoplasm of brainMeasuresMetabolicMethodsMethylationMolecularOutcomePatientsPatternPerfusionPhasePhenotypePhysiologicalPrognosisProgression-Free SurvivalsProgressive DiseasePropertyProtocols documentationRadiationRadiology SpecialtyRecurrenceReproducibilityResearchResearch PersonnelScanningShapesSignal TransductionSiteStratificationTestingTextureTissuesTrainingUpdatebasebiophysical modelcancer imagingclinical practiceclinical trial enrollmentdata resourcedeep learningdisease heterogeneityheterogenous dataimaging modalityimproved outcomein vivo evaluationlearning strategymachine learning methodmachine learning modelmutantneuro-oncologyopen sourcepersonalized diagnosticspersonalized medicinepersonalized predictionsphase II trialphenomicspredict clinical outcomepredictive modelingprogramspromoterquantitative imagingradiomicstooltreatment effecttreatment planningtreatment strategytreatment stratificationtreatment trialtumortumor growth
项目摘要
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.
摘要
磁共振成像(MRI)方法在神经肿瘤学中的现状提供了很大的
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,是一种复杂且高度异质性的癌症。
尤其是胶质母细胞瘤(GBM)预后很差,中位总存活率(OS)低于
15个月,在过去15年中,Stupp协议的改善相对较小
介绍。许多实验性治疗正在进行中;然而,OS在很大程度上仍然存在
停滞不前。改善这一结果的一些障碍是1)疾病的异质性,
这使得在第一阶段甚至第二阶段试验中很难检测到治疗效果,并且调用
个人化,而不是一刀切的治疗策略;2)用于肿瘤的方法
基于大小、增强、灌注和扩散特性的表征相对
粗糙,没有充分利用成像数据的丰富性或其空间异构性。量子-
过去十年发展起来的定量成像和机器学习(QIML)方法显示
极大的潜力剖析基底膜的空间、时间和患者间的异质性;
发现成像和分子特征之间的关系;提供个性化
对临床结果的预测;以及利用数据中微妙的多参数关系
检测肿瘤周围的浸润或辨别与治疗相关的变化,即假性进展
(PSP),来自真正的肿瘤复发。我们小组一直走在QIML的前列,重点是
A)依靠多参数信号、纹理参数、形状获得丰富的成像表型
属性、从图谱注册获得的空间模式、以及肿瘤生长的生物物理模型,
以及b)使用机器学习将这种成像特征集成到临床预测中
预后、肿瘤周围浸润的早期复发、PSP和GBM的放射学亚型。
尽管QIML方法前景看好,但它有一个臭名昭著的局限性:它们可能会过度匹配特定的
从其派生的数据集,在现实生活中可能表现出较差的重复性
不同扫描仪类型和成像协议的条件。在这项提案中,我们的目标是利用
最近成立的RESPONSE(用于精密诊断的放射组学签名)联盟,以
整合、协调和分析来自全球14个中心的4578个数据集,因此
更合适的是,培训和交叉验证QIML工具以获得更广泛的通用性。这个财团
将产生一个史无前例的数据库,其中包含各种精心协调的MRI和
临床措施,旨在为社区提供健壮和可重现的QIML模型
为这一可怕的脑癌的精确诊断和个性化治疗做出贡献。
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
数据更新时间:{{ journalArticles.updateTime }}
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Christos Davatzikos其他文献
Christos Davatzikos的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('Christos Davatzikos', 18)}}的其他基金
Disentangling the anatomical, functional and clinical heterogeneity of major depression, using machine learning methods
使用机器学习方法解开重度抑郁症的解剖学、功能和临床异质性
- 批准号:
10714834 - 财政年份:2023
- 资助金额:
$ 76.45万 - 项目类别:
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:
10625442 - 财政年份:2022
- 资助金额:
$ 76.45万 - 项目类别:
Ultrascale Machine Learning to Empower Discovery in Alzheimers Disease Biobanks
超大规模机器学习助力阿尔茨海默病生物库的发现
- 批准号:
10696100 - 财政年份:2020
- 资助金额:
$ 76.45万 - 项目类别:
Ultrascale Machine Learning to Empower Discovery in Alzheimers Disease Biobanks
超大规模机器学习助力阿尔茨海默病生物库的发现
- 批准号:
10263220 - 财政年份:2020
- 资助金额:
$ 76.45万 - 项目类别:
Benchmarking and Comparing AD-Related AI Methods Across Sites on a Standardized Dataset
在标准化数据集上跨站点对 AD 相关 AI 方法进行基准测试和比较
- 批准号:
10825403 - 财政年份:2020
- 资助金额:
$ 76.45万 - 项目类别:
Ultrascale Machine Learning to Empower Discovery in Alzheimers Disease Biobanks
超大规模机器学习助力阿尔茨海默病生物库的发现
- 批准号:
10475286 - 财政年份:2020
- 资助金额:
$ 76.45万 - 项目类别:
Ultrascale Machine Learning to Empower Discovery in Alzheimers Disease Biobanks
超大规模机器学习助力阿尔茨海默病生物库的发现
- 批准号:
10028746 - 财政年份:2020
- 资助金额:
$ 76.45万 - 项目类别:
Machine Learning and Large-scale Imaging analytics for dimensional representations of brain trajectories in aging and preclinical Alzheimer's Disease: The brain aging chart and the iSTAGING consortium
机器学习和大规模成像分析,用于衰老和临床前阿尔茨海默氏病大脑轨迹的维度表示:大脑衰老图表和 iSTAGING 联盟
- 批准号:
10839623 - 财政年份:2017
- 资助金额:
$ 76.45万 - 项目类别:
Biomedical Image Computing and Informatics Cluster
生物医学图像计算与信息学集群
- 批准号:
9273767 - 财政年份:2017
- 资助金额:
$ 76.45万 - 项目类别:
相似海外基金
A Phase 2 biomarker driven, Study of DB107, a Retroviral Replicating Vector, Combined With 5-FC in Patients with Recurrent Glioblastoma or Anaplastic Astrocytoma
由生物标志物驱动的 DB107(一种逆转录病毒复制载体)与 5-FC 联合治疗复发性胶质母细胞瘤或间变性星形细胞瘤患者的 2 期研究
- 批准号:
10722246 - 财政年份:2023
- 资助金额:
$ 76.45万 - 项目类别:
Multimodality Neuroimaging Evaluation of Cognitive Functioning in Lower Grade Astrocytoma
低级别星形细胞瘤认知功能的多模态神经影像评估
- 批准号:
10701775 - 财政年份:2022
- 资助金额:
$ 76.45万 - 项目类别:
Targeting metabolic vulnerabilities in Astrocytoma, IDH-mutant, Grade 4
针对星形细胞瘤、IDH 突变、4 级的代谢脆弱性
- 批准号:
10306229 - 财政年份:2021
- 资助金额:
$ 76.45万 - 项目类别:
Targeting metabolic vulnerabilities in Astrocytoma, IDH-mutant, Grade 4
针对星形细胞瘤、IDH 突变、4 级的代谢脆弱性
- 批准号:
10491830 - 财政年份:2021
- 资助金额:
$ 76.45万 - 项目类别:
metabolome analysis focusing on the malignant transformation of astrocytoma
关注星形细胞瘤恶性转化的代谢组分析
- 批准号:
19K09520 - 财政年份:2019
- 资助金额:
$ 76.45万 - 项目类别:
Grant-in-Aid for Scientific Research (C)
Exploring the tumorigenesis of H3F3A mutations in pediatric high-grade astrocytoma (HGA) and Giant cell tumor of the bone (GCTB).
探索儿童高级星形细胞瘤 (HGA) 和骨巨细胞瘤 (GCTB) 中 H3F3A 突变的肿瘤发生。
- 批准号:
377032 - 财政年份:2017
- 资助金额:
$ 76.45万 - 项目类别:
Fellowship Programs
A Phase 1 Study of M032, a Genetically Engineered HSV-1 Expressing IL-12, in Patients with Recurrent/Progressive Glioblastoma Multiforme, Anaplastic Astrocytoma, or Gliosarcoma.
M032(一种表达 IL-12 的基因工程 HSV-1)在复发/进行性多形性胶质母细胞瘤、间变性星形细胞瘤或胶质肉瘤患者中的 1 期研究。
- 批准号:
9455636 - 财政年份:2017
- 资助金额:
$ 76.45万 - 项目类别:
Defining the role of the histone 3 (H3.3G34R) mutation in the pathogenesis of pediatric high grade astrocytoma
定义组蛋白 3 (H3.3G34R) 突变在儿童高级星形细胞瘤发病机制中的作用
- 批准号:
368929 - 财政年份:2017
- 资助金额:
$ 76.45万 - 项目类别:
Operating Grants
Establishment of diffuse astrocytoma cell line utilizing advanced culture system
利用先进的培养系统建立弥漫性星形细胞瘤细胞系
- 批准号:
16K15641 - 财政年份:2016
- 资助金额:
$ 76.45万 - 项目类别:
Grant-in-Aid for Challenging Exploratory Research
Detection and clinical application of pilocytic astrocytoma minimal residual disease
毛细胞型星形细胞瘤微小残留病的检测及临床应用
- 批准号:
16K10011 - 财政年份:2016
- 资助金额:
$ 76.45万 - 项目类别:
Grant-in-Aid for Scientific Research (C)