Radiogenomics framework for non-invasive personalized medicine

非侵入性个性化医疗的放射基因组学框架

• 批准号: 10005534
• 负责人: Olivier Gevaert
• 金额: $ 44.4万
• 依托单位: STANFORD UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2015
• 资助国家: 美国
• 起止时间: 2015-02-15 至 2021-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10005534
• 关键词: 3-Dimensional; Algorithms; Area; Biological Assay; Biological Markers; Brain Neoplasms; Cancer Patient; Clinical; Computer Simulation; Computer Vision Systems; Data; Data Sources; Development; Diagnostic; Diagnostic Imaging; Diffusion; Drug Targeting; Drug usage; Epidermal Growth Factor Receptor; Eye; Gene Expression; Gene Expression Profile; Genes; Genome; Genomics; Glioblastoma; Goals; Head and Neck Cancer; High-Throughput Nucleotide Sequencing; Human; Image; Image Analysis; Individual; Informatics; Investigation; Lesion; Letters; Link; Magnetic Resonance Imaging; Malignant Neoplasms; Malignant neoplasm of lung; Manuals; Maps; Medical Imaging; Medical center; Methods; Modeling; Molecular; Molecular Profiling; Monitor; Outcome; Pathway interactions; Patients; Pattern; Perfusion; Pharmaceutical Preparations; Positron-Emission Tomography; Prediction of Response to Therapy; Primary carcinoma of the liver cells; Process; Prognostic Marker; Property; Radiogenomics; Rectal Cancer; Research; Resistance; Retrospective cohort; Shapes; Site; Somatic Mutation; Squamous cell carcinoma; Technology; Texture; Therapeutic; Time; Translating; Translations; Treatment outcome; Tumor Tissue; Work; X-Ray Computed Tomography; actionable mutation; base; cancer site; clinical application; clinical care; cohort; follow-up; genome analysis; genome sequencing; human data; imaging biomarker; imaging modality; imaging study; improved outcome; in vivo; interest; malignant breast neoplasm; molecular imaging; multimodality; multiple omics; mutational status; novel therapeutics; outcome forecast; outcome prediction; personalized medicine; precision medicine; precision oncology; predict clinical outcome; predictive signature; quantitative imaging; radiologist; radiomics; response; supervised learning; synergism; tool; transcriptome sequencing; treatment choice; treatment response; tumor

Project summary Radiogenomics, is a burgeoning area of research that aims to link medical imaging with multi-omics molecular profiles of the same patients. Radiogenoimcs has shown its potential through its ability to predict clinical outcomes e.g. prognosis, and through predicting actionable molecular properties of tumors, e.g. the activity of EGFR, a major drug target in many cancers. The typical imaging genomics workflow consists of the following steps: (1) Identify the tumor through segmentation. This is often also defined as identifying Regions Of Interests or ROIs through a manual process with a radiologist or using computer vision algorithms. (2) Feature extraction, often also known as radiomics, whereby 100s of features are identified that capture the shape, the texture and the intensity distributions of lesions in 2D or 3D. (3) Supervised machine learning to predict clinical outcomes such as prognosis, overall survival or response to treatment, or predicting molecular profiles such as gene expression patterns or metagenes, or individual molecular properties such as the mutation status of a gene (e.g. EGFR). This workflow has been demonstrated in several cancers including lung cancer, brain tumors, hepatocellular carcinoma, breast cancer etc. Current radiogenomics applications are limited to study associations between imaging and molecular data, and predicting long term outcomes. However, no actionable information is gained from radiogenomics maps. In this renewal, we propose to develop a radiogenomics framework to support treatment response, treatment allocation and treatment monitoring: (1) we will develop informatics algorithms that integrate radiogenomic data for treatment response, (2) algorithms that allow combining radiogenomic data during treatment follow-up, and (3) algorithms that use the radiogenomic map to suggest novel drugs and predict drug target activities. Combining these complementary data sources in a radiogenomics framework for data fusion can have profound contributions toward predicting treatment outcomes by uncovering unknown synergies and relationships. More specifically, developing computational models integrating quantitative image features and molecular data to develop radiogenomics signatures, holds the potential to translate in benefit to tumor patients by investigating biomarkers that accurately predict therapy response of tumors. Readily, because medical imaging is part of the routine diagnostic work-up of cancer patients and molecular data of human tumors is increasingly being used in clinical workflows, therefore if reliable radiogenomic signatures can be found reflecting treatment response, translation to the clinical applications is feasible.

项目摘要 放射基因组学是一个新兴的研究领域，旨在将医学成像与多组学分子生物学联系起来。 相同患者的特征。放射基因组学通过其预测临床 结果，例如预后，并通过预测肿瘤的可操作的分子特性，例如肿瘤的活性， EGFR是许多癌症的主要药物靶点。 典型的成像基因组学工作流程由以下步骤组成：（1）通过以下步骤识别肿瘤： 细分这通常也被定义为通过手动过程识别感兴趣区域或ROI 或者使用计算机视觉算法。(2)特征提取，通常也被称为放射组学， 从而识别出数百个特征，这些特征捕获了物体的形状、纹理和强度分布， 2D或3D病变。(3)监督机器学习来预测临床结果，如预后，总体 生存或对治疗的反应，或预测分子谱，如基因表达模式， 多基因或个体分子特性，如基因（例如EGFR）的突变状态。这 工作流程已经在几种癌症中得到证实，包括肺癌、脑肿瘤、肝细胞癌、 癌、乳腺癌等。 目前的放射基因组学应用仅限于研究成像和分子数据之间的关联， 预测长期结果。然而，从放射基因组学图谱中没有获得可操作的信息。在这 更新，我们建议制定一个放射基因组学框架，以支持治疗反应，治疗 分配和治疗监测：（1）我们将开发整合放射基因组学数据的信息学算法 对于治疗反应，（2）允许在治疗随访期间组合放射基因组学数据的算法，以及 (3)使用放射基因组图谱来建议新药和预测药物靶点活性的算法。 在放射基因组学框架中组合这些互补数据源以进行数据融合可以具有 通过发现未知的协同作用，为预测治疗结果做出了深远的贡献， 关系。更具体地说，开发整合定量图像特征和 开发放射基因组学特征的分子数据，有可能转化为对肿瘤患者有益的信息。 通过研究生物标志物来准确预测肿瘤的治疗反应。很容易，因为医疗 成像是癌症患者常规诊断检查的一部分， 越来越多地用于临床工作流程，因此，如果可以找到可靠的放射基因组签名， 反映治疗反应，转化为临床应用是可行的。

项目成果

A Shallow Convolutional Neural Network Predicts Prognosis of Lung Cancer Patients in Multi-Institutional CT-Image Data.

• DOI: 10.1038/s42256-020-0173-6
• 发表时间: 2020-05
• 期刊: Nature machine intelligence
• 影响因子: 23.8
• 作者: Mukherjee P;Zhou M;Lee E;Schicht A;Balagurunathan Y;Napel S;Gillies R;Wong S;Thieme A;Leung A;Gevaert O
• 通讯作者: Gevaert O

Topological image modification for object detection and topological image processing of skin lesions.

• DOI: 10.1038/s41598-020-77933-y
• 发表时间: 2020-12-03
• 期刊: Scientific reports
• 影响因子: 4.6
• 作者: Vandaele R;Nervo GA;Gevaert O
• 通讯作者: Gevaert O

Structuring clinical text with AI: Old versus new natural language processing techniques evaluated on eight common cardiovascular diseases.

• DOI: 10.1016/j.patter.2021.100289
• 发表时间: 2021-07-09
• 期刊: Patterns (New York, N.Y.)
• 作者: Zhan X;Humbert-Droz M;Mukherjee P;Gevaert O
• 通讯作者: Gevaert O

A meta-learning approach for genomic survival analysis.

• DOI: 10.1038/s41467-020-20167-3
• 发表时间: 2020-12-11
• 期刊: Nature communications
• 影响因子: 16.6
• 作者: Qiu YL;Zheng H;Devos A;Selby H;Gevaert O
• 通讯作者: Gevaert O

AI-based analysis of CT images for rapid triage of COVID-19 patients.

• DOI: 10.1038/s41746-021-00446-z
• 发表时间: 2021-04-22
• 期刊: NPJ digital medicine
• 影响因子: 15.2
• 作者: Xu Q;Zhan X;Zhou Z;Li Y;Xie P;Zhang S;Li X;Yu Y;Zhou C;Zhang L;Gevaert O;Lu G
• 通讯作者: Lu G