Cloud strategies for improving cost, scalability, and accessibility of a machine learning system for pathology images

用于提高病理图像机器学习系统的成本、可扩展性和可访问性的云策略

基本信息

批准号：
10824959
负责人：
Lee Cooper
金额：
$ 34.71万
依托单位：
NORTHWESTERN UNIVERSITY AT CHICAGO
依托单位国家：
美国
项目类别：
财政年份：
2021
资助国家：
美国
起止时间：
2021-09-01 至 2025-05-31
项目状态：
未结题

来源：
https://reporter.nih.gov/project-details/10824959
关键词：
Acceleration Active Learning Address Adoption Attention Benchmarking Biomedical Research Classification Client Clinical Research Cloud Computing Cloud Service Communities Complex Computer software Cost Savings Costs and Benefits Data Data Scientist Data Set Data Storage and Retrieval Development Equilibrium Face Familiarity Funding Goals Growth Human Image Institution Label Machine Learning Maps Memory Methodology Methods Modeling Movement Pathology Pattern Performance Price Publishing Pythons Recipe Recommendation Research Institute Research Personnel Sampling Savings Services Specific qualifier value Structure System Techniques Technology TensorFlow Testing Training Triton Visualization Work algorithm training classification algorithm cloud platform computing resources cost cost effective design digital pathology heuristics improved large datasets locust machine learning algorithm machine learning framework machine learning model migration open source operation pathology imaging service providers software development tool web services whole slide imaging

项目摘要

PROJECT SUMMARY Machine learning (ML) has seen tremendous advances in the past decade, fueled by growth in computing power and the availability of large labeled datasets. While the impact of these advances on clinical and biomedical research is potentially significant, these domains face unique challenges due to the difficulty in acquiring labels from experts. This proposal will develop new methodology and open-source software that biomedical data scientists can use with their applications to 1. Improve data labeling by identifying the best samples for labeling that provide the most benefit for training ML algorithms; 2. Improve generalization of ML models across institutes; and 3. Perform this work on Amazon Web Services. These methods and software will be developed in digital pathology applications using multi-institutional datasets. This supplemental funding will enhance cloud support beyond the original proposal, leveraging recent advances in inference server technology that can accelerate our software by orders of magnitude, providing significant savings to users. The supplemental funding will support the additional implementation that is required to incorporate this technology into our software and will help us benchmark the cost-to-benefit ratio of different compute and storage asset classes on Amazon Web Services, Microsoft Azure, and Google Cloud Platform. The deliverables from this work include enhanced software that can support inference serving on multiple cloud service providers and best practices and recommendations for our users.

项目概要在计算技术增长的推动下，机器学习 (ML) 在过去十年中取得了巨大进步大型标记数据集的能力和可用性。虽然这些进步对临床和生物医学研究具有潜在的重要意义，但由于难以进行研究，这些领域面临着独特的挑战从专家那里获取标签。该提案将开发新的方法和开源软件生物医学数据科学家可以将其应用程序用于 1. 通过识别最佳数据来改进数据标签为训练 ML 算法提供最大益处的标记样本； 2. 提高机器学习的泛化能力跨机构的模型； 3. 在 Amazon Web Services 上执行此工作。这些方法和软件将使用多机构数据集在数字病理学应用中开发。这笔补充资金将利用推理服务器的最新进展，增强原始提案之外的云支持技术可以将我们的软件加速几个数量级，为用户节省大量成本。这补充资金将支持纳入该技术所需的额外实施到我们的软件中，将帮助我们对不同计算和存储资产的成本效益比进行基准测试 Amazon Web Services、Microsoft Azure 和 Google Cloud Platform 上的课程。由此产生的成果工作包括可以支持多个云服务提供商的推理服务的增强软件，以及为我们的用户提供最佳实践和建议。