Development of deepometry for the supervised and weakly supervised learning of imaging data

成像流式细胞术提供了在短时间内对数百万个细胞成像的机会，它是一项具有诊断多种疾病潜力的变革性技术。该项目将使用最新的算法和分析技术，从使用该系统生成的大型数据集中提取有用的信息，用于大量临床协作。具体地说，该项目建立在深度测量的基础上，这是一种开源工作流程，旨在将深度学习算法与单细胞分析一起应用于细胞学数据的分析，该工作流程是与GSK、麻省理工学院博德研究所和哈佛大学合作开发的。“深度测量2”的目标是开发我们目前的软件，用于2D和3D图像，并使用该技术对患者样本中的组织进行成像。该项目将涉及软件开发和将这一深度学习工具应用于一些令人兴奋的数据集。

Imaging flow cytometry offers the opportunity to image millions of cells in a short period of time, it is a transformative technology with the potential to diagnose a host of diseases. This project will use the latest algorithms and analytic techniques to extract useful information from large datasets generated using this system for a host of clinical collaborations. Specifically, the project builds on, Deepometry, an open-source workflow developed with the objective of applying deep learning algorithms along with single cell analytics to the analysis of cytometry data which was developed in collaboration with GSK and the Broad Institute of MIT and Harvard. 'Deepometry 2' aims to develop our current software for use on both 2D and 3D images and to use the technology to image tissue from patient samples. This project will involve software development and the application of this deep learning tool to a number of exciting datasets.