IMAT-ITCR Collaboration: Develop deep learning-based methods to identify subtypes of circulating tumor cells from optical microscope images

IMAT-ITCR 合作：开发基于深度学习的方法，从光学显微镜图像中识别循环肿瘤细胞的亚型

• 批准号: 10675886
• 负责人: Wei Li
• 金额: $ 7.19万
• 依托单位: TEXAS TECH UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-09-01 至 2023-07-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10675886
• 关键词: Administrative Supplement; Advanced Malignant Neoplasm; Algorithmic Software; Algorithms; Architecture; Artificial Intelligence; Cell model; Cells; Classification; Code; Collaborations; Communities; Computer Assisted; Computing Methodologies; Consumption; Data; Data Analyses; Data Analytics; Data Set; Development; Educational Curriculum; Enhancers; Environment; Equilibrium; Fractionation; Funding; Goals; Head; Hematoxylin; Hybrids; Image; Image Analysis; Image Enhancement; Individual; Informatics; Knowledge; Libraries; Location; Machine Learning; Manuals; Maps; Masks; Methodology; Methods; Modeling; Morphologic artifacts; Neoplasm Circulating Cells; Network-based; Occupations; Optics; Parents; Pattern; Positioning Attribute; Process; Protocols documentation; Research; Research Personnel; Residual state; Resolution; Resources; Running; Security; Services; Signal Transduction; Software Design; Speed; Stains; Structure; System; Technology; TensorFlow; Testing; Time; Tissue imaging; Training; Tumor Tissue; Update; Variant; Vertebral column; Visualization; Work; adaptation algorithm; anticancer research; application programming interface; base; cell type; cellular imaging; computer infrastructure; computerized data processing; deep learning; deep learning algorithm; experience; experimental study; fluid flow; fluorescence microscope; generative adversarial network; handheld mobile device; improved; informatics tool; innovation; learning strategy; loss of function; microchip; microscopic imaging; novel; operation; preservation; restoration; simulation; tool; user-friendly; web services

IMAT-ITCR Collaboration: Develop deep learning-based methods to identify subtypes of circulating tumor cells from optical microscope images Project Summary/Abstract The goal of the parent IMAT project (R21CA240185) is to develop a new platform for fractionation and profiling of CTC subpopulations and elucidate the metastatic potential of CTCs. Currently, this work requires researchers to record hundreds of individual microscope images of the cells captured on the microchip, integrate all images with flow fluid simulations, and analyze three features of the capture cells (including angular position, normalized velocity and shear) for identification of CTC subtypes. This process is very labor-intensive and time-consuming, as most of the steps rely on manual operations. The goal of the ITCR project (1U01CA249245) is to develop an informatics platform, iSEE-Cell (image-based Spatial pattern ExplorEr for Cells), which features a suite of informatics tools for tissue image analysis, visualization, exploration and spatial modeling at the single-cell level. This proposed Administrative Supplement application in support of collaboration between IMAT and ITCR-funded projects aims to develop deep learning-based methods to identify subtypes of CTCs from optical microscope images. The rationale underlying this proposal is that the development of deep learning methods will provide automatic characterization and classification of CTC captured on HU structured microchips. This proposed collaborative project will leverage the technologies developed by both projects, which will bring together and enhance the capabilities of complementary technology platforms and methodologies to advance cancer research. Innovation of the proposed methods include the following: 1) Identification of multiple subtypes of CTCs using their location information on an HU microchip without destructive immunostaining analysis; 2) Novel Restore-GAN model to improve quality of microscope image obtained in CTC capture experiments and enhance predication accuracy for CTC subtypes; 3) The proposed informatics tools will provide computer-assisted automated tools to empower CTC research with artificial intelligence. Specific aims include: Aim 1: Using the microscope images and analysis/prediction results (from the IMAT project) as data input to test whether algorithms to classify different types of cell from tumor tissue images (iSEE-Cell, developed in the ICTR project) can be applied for microscope images; Aim 2: Apply novel computational methods (Restore- GAN, developed in the ICTR project) to improve image quality of the images obtained from the IMAT project, and test whether they can improve prediction accuracy for CTC subtypes; Aim 3: Develop a user-friendly interface to incorporate the iSEE-Cell platform for analyzing optical/fluorescent microscope images remotely. The ability to automatically extract/analyze information from captured cells in the microscope images is urgently needed and will dramatically enhance the throughput and work efficiency of the IMAT project.

IMAT-ITCR 合作：开发基于深度学习的方法来识别循环肿瘤的亚型 光学显微镜图像中的细胞 项目概要/摘要 父 IMAT 项目 (R21CA240185) 的目标是开发一个用于 CTC 分级和分析的新平台 亚群并阐明 CTC 的转移潜力。目前，这项工作需要研究人员记录数百个 微芯片上捕获的细胞的单个显微镜图像，将所有图像与流动流体模拟集成， 并分析捕获细胞的三个特征（包括角位置、归一化速度和剪切力）以进行识别 CTC 亚型。这个过程非常费力且耗时，因为大部分步骤都依赖于手动操作。 ITCR 项目 (1U01CA249245) 的目标是开发一个信息学平台 iSEE-Cell（基于图像的空间 pattern ExplorEr for Cells），它具有一套用于组织图像分析、可视化、探索的信息学工具 以及单细胞水平的空间建模。本拟议的行政补充申请旨在支持 IMAT 和 ITCR 资助的项目之间的合作旨在开发基于深度学习的方法来识别亚型 来自光学显微镜图像的 CTC。该提议的基本原理是深度学习的发展 这些方法将提供 HU 结构微芯片上捕获的 CTC 的自动表征和分类。这 拟议的合作项目将利用两个项目开发的技术，将汇集和 增强互补技术平台和方法的能力，以推进癌症研究。创新 所提出的方法包括以下内容： 1) 利用位置识别 CTC 的多个亚型 HU 微芯片上的信息，无需破坏性免疫染色分析； 2）新颖的Restore-GAN模型改进 提高 CTC 捕获实验中获得的显微镜图像的质量，并提高 CTC 亚型的预测准确性； 3） 拟议的信息学工具将提供计算机辅助自动化工具，使 CTC 研究能够通过人工 智力。具体目标包括： 目标 1：使用显微镜图像和分析/预测结果（来自 IMAT 项目）作为数据输入来测试算法是否可以从肿瘤组织图像中分类不同类型的细胞（iSEE-Cell， 在卢旺达问题国际法庭项目中开发）可应用于显微镜图像；目标 2：应用新颖的计算方法（恢复） GAN，在 ICTR 项目中开发）用于提高从 IMAT 项目获得的图像的图像质量，并测试 是否可以提高 CTC 亚型的预测准确性；目标3：开发一个用户友好的界面来整合 iSEE-Cell 平台用于远程分析光学/荧光显微镜图像。自动的能力 迫切需要从显微镜图像中捕获的细胞中提取/分析信息，这将极大地增强 IMAT 项目的吞吐量和工作效率。

项目成果

Deep learning detector for high precision monitoring of cell encapsulation statistics in microfluidic droplets.

深度学习检测器，用于高精度监测微流体液滴中的细胞封装统计数据。

• 发表时间: 2022-10-25
• 影响因子: 6.1
• 作者: Gardner, Karl;Uddin, Md Mezbah;Linh Tran;Thanh Pham;Vanapalli, Siva;Li, Wei
• 通讯作者: Li, Wei