Integrating cancer genomics and spatial architecture of tumor infiltrating lymphocytes

整合癌症基因组学和肿瘤浸润淋巴细胞的空间结构

基本信息

批准号：
10637960
负责人：
Hanlee P Ji
金额：
$ 44.52万
依托单位：
STANFORD UNIVERSITY
依托单位国家：
美国
项目类别：
财政年份：
2023
资助国家：
美国
起止时间：
2023-04-11 至 2027-03-31
项目状态：
未结题

来源：
https://reporter.nih.gov/project-details/10637960
关键词：
Address Architecture Area Biopsy Brain Cancer Patient Cells Characteristics Classification Clinical Computing Methodologies Consumption Data Data Set Disease Endothelial Cells Epithelium Evaluation Fibroblasts Gene Expression Genomics Guidelines Head and Neck Cancer Hematoxylin and Eosin Staining Method Histopathology Image Image Analysis Immune Immune response Immunohistochemistry Immunologic Markers Immunotherapy Joints Label Learning Lung Lymphocyte Macrophage Malignant Neoplasms Manuals Maps Measures Methods Modeling Molecular Mutation Observer Variation Outcome Pathologic Pathologist Pathology Patients Performance Phenotype Population Predictive Value Procedures Proxy Regional Cancer Reproducibility Research Resolution Sampling Spatial Distribution Stains Standardization Structure Testing The Cancer Genome Atlas Time Tissue Fixation Training Tumor-Infiltrating Lymphocytes Validation automated analysis cancer genomics cancer imaging cancer immunotherapy cancer type cell type cohort computer framework convolutional neural network data exchange deep learning deep learning model digital genomic data geometric structure imaging modality imaging system immune checkpoint immune checkpoint blockade innovation insertion/deletion mutation microscopic imaging molecular marker multiplexed imaging neoantigens nonsynonymous mutation pathology imaging patient prognosis prognostic value response spatial relationship tumor tumor heterogeneity tumor microenvironment

项目摘要

ABSTRACT Tumor infiltrating lymphocytes (TILs) are an important component of the immune cells that reside in the tumor microenvironment (TME). The type and number of TILs in the TME have an impact on overall survival and are an indicator of response to immunotherapy. Despite their importance as an indicator of a patient’s immune response to cancer, there are multiple challenges for analyzing TILS from large population data sets involving thousands of samples. There is a lack of methods that can automate an analysis of histopathologic images for different features such as the spatial distribution of TILs, their topological interactions with their neighboring cells in the TME and their association with specific clinical outcomes. Even more challenging is integrating TIL metrics with cancer genomic data. Most other methods provide qualitive metrics of TILs and frequently rely on manual inspection from pathologists – this approach lacks scalability and is subject to observer bias. To address these challenges, we developed a computational framework that uses a deep learning model to identify multiple cell types from histopathology images. The major innovation of our approach is molecular label transferring that annotates tens of thousands of small areas extracted from histopathology images without manual inspections. This approach is highly accurate, efficient, scalable and readily automated for the analysis of millions of images. The objective of this project is to address a key challenge in the application of deep learning to histopathological image: large number of labeled images as training data set. We have three specific aims to 1) identify spatial quantification of TILs from over 10,000 histopathological images from the Cancer Genome Atlas Project; 2) correlate TIL metrics with clonal tumor mutation burden (TMB); 3) determine association of TILs with immune checkpoint blockade responses. This research is significant because our approach enables for a comprehensive characterization of TILs from histopathological images at cellular level, using data that is commonly accessible in clinical settings and can be readily integrated with cancer genomic data.

抽象的肿瘤浸润淋巴细胞 (TIL) 是肿瘤中免疫细胞的重要组成部分微环境 (TME) TME 中 TIL 的类型和数量对总体生存有影响。尽管它们作为患者免疫的指标很重要，但它是免疫治疗反应的指标。对于癌症的反应，从大量人口数据集中分析 TILS 面临着多重挑战，其中包括缺乏可以自动分析数千个样本的方法。不同的特征，例如 TIL 的空间分布、它们与相邻细胞的拓扑相互作用 TME 及其与特定临床结果的关联更具挑战性的是整合 TIL 指标。大多数其他方法提供 TIL 的定性指标，并且经常依赖于手动。病理学家的检查——这种方法缺乏可扩展性，并且容易受到观察者偏差的影响。挑战，我们开发了一个计算框架，使用深度学习模型来识别多个细胞我们方法的主要创新是分子标签转移。注释从组织病理学图像中提取的数万个小区域，无需手动检查。这种方法非常准确、高效、可扩展，并且很容易实现自动化，可用于分析数百万张图像。该项目的目标是解决深度学习应用中的一个关键挑战组织病理学图像：大量标记图像作为训练数据集，我们有三个具体目标：1）。从癌症基因组图谱的 10,000 多张组织病理学图像中识别 TIL 的空间量化项目；2) 将 TIL 指标与克隆肿瘤突变负荷 (TMB) 相关联；3) 确定 TIL 与克隆肿瘤突变负荷的关联；这项研究意义重大，因为我们的方法能够实现免疫检查点阻断反应。使用以下数据从细胞水平的组织病理学图像中全面表征 TIL 在临床环境中普遍可用，并且可以轻松地与癌症基因组数据集成。