Assuring AI/ML-readiness of digital pathology in diverse existing and emerging multi-omic datasets through quality control workflows

通过质量控制工作流程，确保现有和新兴的多组学数据集中数字病理学的 AI/ML 就绪性

• 批准号: 10841333
• 负责人: Julie Ann Bletz
• 金额: $ 27万
• 依托单位: SAGE BIONETWORKS
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-09-14 至 2024-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10841333
• 关键词: Adoption; Area; Artificial Intelligence; Basic Science; Biomedical Research; Biopsy; Classification; Clinical; Clinical Research; Collaborations; Data; Data Commons; Data Set; Deposition; Development; Diagnosis; Division of Cancer Biology; Drops; Ensure; Evaluation; Exclusion; FAIR principles; Failure; Funding; Future; Genotype; Genotype-Tissue Expression Project; Grant; Health Resources; Histology; Image; Inferior; Infrastructure; Learning; Link; Machine Learning; Manuals; Masks; Modeling; Morphologic artifacts; Morphology; Multiomic Data; National Cancer Institute; Nephrotic Syndrome; Output; Performance; Play; Process; Prognosis; Quality Control; Reader; Readiness; Reporting; Reproducibility; Research; Research Personnel; Role; Sampling; Science; Slide; Synapses; Techniques; The Cancer Genome Atlas; Time; Tissues; Training; Translational Research; Trust; United States National Institutes of Health; Universities; Validation; Work; anticancer research; biomarker discovery; cohort; comparative; cost; data management; data mining; data quality; data sharing; deep learning; digital pathology; generalist repository; histological image; imaging biomarker; imaging detection; improved; interest; machine learning method; machine learning model; multiple omics; open data; open source; parent grant; programs; prospective; prototype; public repository; repository; success; tool; treatment response; whole slide imaging

Abstract In an era of multi-omics, histology remains an essential approach for basic, translational, and clinical research providing valuable, low-cost, and non-destructive information about tissue morphology. The adoption of whole slide imaging (WSI) and digital pathology (DP) has led to large clinical and research repositories being instantiated for computational data mining of image-based biomarkers associated with genotype, diagnosis, prognosis, and therapy response. Importantly, data quality plays a critical role in the usage of these WSI, especially when employing artificial intelligence (AI) and machine learning (ML) methods. Artifacts and batch effects may arise at many points in the process from biopsy to digitization, and while several tools to detect them have been developed, consistent application and reporting are lacking, with none being routinely applied in public repositories. This leaves a unique opportunity to immediately provide added value to existing and future NIH- supported datasets. This proposal sees a collaboration between Sage Bionetworks, experts in FAIR data sharing and Team Science, and Dr. Andrew Janowczyk, a leader in automated quality control (QC) of WSI who has spearheaded the development of an open-source DP QC tool, HistoQC. We propose to enhance the AI/ML readiness of existing and future DP data by providing transparent, reproducible, reporting of detected imaging artifacts and batch effects within NIH-sponsored datasets in an automated fashion via the extension of our existing QC workflows. Implementing transparent reporting of DP data quality will enable researchers to exclude artifacts from their training sets in a consistent cross-investigator manner. Our work will provide greater trust in dataset reuse and experimental reproducibility while also easing AI/ML model creation and enhancing their performance. We will build on strong preliminary data and prototypes, demonstrating both significantly improved cross-reader QC reproducibility and technical feasibility, with three specific aims. Aim 1 sees this enrichment process will be applied to WSI from NIH-supported public datasets, including TCGA and GTEx, and for NIH/NCI Division of Cancer Biology research programs supported by the Multi-Consortia Coordinating (MC2) Center parent grant. Aim 2 employs the lessons learned from the enhancement of raw DP data to be AI/ML ready in Aim 1 to deploy a scalable workflow for QC of all incoming DP data from MC2-supported programs, providing continual prospective data enrichment to assure AI/ML readiness. Lastly, Aim 3 demonstrates enhanced AI/ML readiness of DP data subjected to our automated QC processes using a prototypical self-supervised tissue classification task. Our deliverables include (a) 5000 WSI annotated by our QC workflow and enhanced into AI/ML ready datasets; (b) workflows to enable processing of incoming datasets for AI-readiness, (c) a failure rate of identifying poor quality slides is <1%; and (d) our QC comparative AI/ML demonstration yields an improvement of >10% performance in terms of tissue classification performance as a result of our data enhancements.

抽象的 在多组学时代，组织学仍然是基础、转化和临床研究的重要方法 提供有关组织形态的有价值的、低成本的、非破坏性的信息。整体采用 幻灯片成像 (WSI) 和数字病理学 (DP) 已导致大型临床和研究存储库 实例化用于与基因型、诊断相关的基于图像的生物标志物的计算数据挖掘， 预后和治疗反应。重要的是，数据质量在这些 WSI 的使用中起着至关重要的作用， 尤其是在采用人工智能（AI）和机器学习（ML）方法时。工件和批次 从活检到数字化的过程中，许多点可能会出现影响，而检测这些影响的工具有多种 已开发出来，但缺乏一致的应用和报告，没有一个在公共场合常规应用 存储库。这留下了一个独特的机会，可以立即为现有和未来的 NIH 提供附加值 支持的数据集。该提案见证了 FAIR 数据共享专家 Sage Bionetworks 之间的合作 和 Team Science，以及 WSI 自动化质量控制 (QC) 领域的领导者 Andrew Janowczyk 博士，他 率先开发了开源 DP QC 工具 HistoQC。我们建议加强人工智能/机器学习 通过提供透明、可重复的检测成像报告，为现有和未来的 DP 数据做好准备 通过我们的扩展，以自动化的方式在 NIH 赞助的数据集中生成工件和批次效应 现有的 QC 工作流程。实施透明的 DP 数据质量报告将使研究人员能够排除 以一致的跨研究者方式从他们的训练集中提取工件。我们的工作将给大家带来更大的信任 数据集重用和实验再现性，同时还简化了 AI/ML 模型的创建并增强了它们的性能 表现。我们将建立在强大的初步数据和原型的基础上，展示两者的显着改进 跨阅读器质量控制重现性和技术可行性，具有三个具体目标。目标 1 看到了这种丰富 流程将应用于来自 NIH 支持的公共数据集（包括 TCGA 和 GTEx）的 WSI，以及 NIH/NCI 多联盟协调 (MC2) 中心支持的癌症生物学研究项目 家长补助金。目标 2 利用从增强原始 DP 数据中汲取的经验教训，为 AI/ML 做好准备 目标 1 部署一个可扩展的工作流程，用于对来自 MC2 支持的程序的所有传入 DP 数据进行质量控制，提供 持续的前瞻性数据丰富，以确保 AI/ML 做好准备。最后，Aim 3 展示了增强的 AI/ML 使用原型自监督组织，DP 数据已准备好接受我们的自动化 QC 流程 分类任务。我们的可交付成果包括 (a) 5000 WSI，由我们的 QC 工作流程注释并增强为 AI/ML 就绪数据集； (b) 能够处理传入数据集以做好 AI 准备的工作流程，(c) 故障率 识别劣质载玻片的比例 <1%； (d) 我们的 QC 比较 AI/ML 演示取得了进步 由于我们的数据增强，在组织分类性能方面的性能超过 10%。