Histotools: scaling digital pathology curation tools for quality control, annotation, labeling, and dataset identification

Histotools：用于质量控制、注释、标记和数据集识别的扩展数字病理学管理工具

• 批准号: 10708011
• 负责人: Andrew Robert Janowczyk
• 金额: $ 35.31万
• 依托单位: EMORY UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-09-21 至 2026-07-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10708011
• 关键词: Active Learning; Address; Adoption; Affect; Antarctica; Automobile Driving; Big Data; Biological; Biopsy; Breast; Cardiac; Categories; Cell Nucleus; Cells; Characteristics; Clinical; Communities; Compensation; Computer Assisted; Data; Data Set; Development; Diagnosis; Disease; Employment; Ensure; European Union; FDA approved; Feedback; Friends; Generations; Genes; Glass; Head and neck structure; Heart; Histologic; Histological Labelings; Histopathology; Human; Image; Infrastructure; Kidney; Kidney Diseases; Label; Letters; Lung; Lymphocyte; Lymphocytic Infiltrate; Machine Learning; Malignant Neoplasms; Malignant neoplasm of lung; Modeling; Morphologic artifacts; Morphology; Neck Cancer; Oncology; Ontology; Organ; Pathologist; Pathway interactions; Pattern; Performance; Privatization; Process; Prognosis; Quality Control; Recording of previous events; Reproducibility; Research; Research Personnel; Resources; Site; Slide; Stains; Testing; Texture; The Cancer Genome Atlas; The Cancer Imaging Archive; Tissues; Validation; Work; allograft rejection; cell type; clinical practice; cluster computing; cohort; companion diagnostics; computer monitor; cost; data curation; data lake; design; diagnostic assay; digital; digital pathology; experience; heart allograft; improved; innovation; interest; malignant breast neoplasm; novel; open source; organ transplant rejection; pathology imaging; patient response; precision medicine; predictive test; prognostic; prototype; quantitative imaging; repository; tool; tool development; treatment response; usability; web site; whole slide imaging

ABSTRACT: With recent approval of whole slide scanners for primary diagnosis, wherein routine glass histopathology slides are digitized and presented to clinical pathologists for diagnosis on computer monitors, a wealth of new untapped data is being created in routine clinical practice and placed in growing data lakes. In digital format, these whole slide images (WSIs) can be subjected to digital pathomics, i.e., the process of extracting quantitative image features associated with morphology, attributes, and relationships of histologic objects in WSIs. These features can subsequently be employed for discovery in many domains such as histogenomics, which sees associating phenotypical presentations with biological pathways and gene ontologies. Additionally, low-cost non-tissue destructive image-based companion diagnostic assays (CDx) can be developed for predicting prognosis and treatment response of patients. Unfortunately, unprocessed large data lakes (e.g., TCGA) are not alone sufficient for pathomics, and often require an intractable amount of human curation effort in (i) performing meticulous quality control of WSI (i.e., avoid “garbage-in, garbage-out”) and subsequently (ii) precisely annotating (e.g., cell boundary) and labeling (e.g., cell type) histologic objects. To address these major limiting factors in curating data lakes, we propose developing our small-scale HistoTools prototypes to employ computing clusters and thus enable their function at the scale of large digital slide repositories (DSR): (i) HistoQC for robust, reproducible quality control of WSI by identifying artifacts (blurriness) and outliers (poorly stained slides) for avoidance in downstream analyses, (ii) CohortFinder for identification and compensation of batch affects, (iii) Quick Annotator for rapid computer aided annotation generation via a combination of active and machine learning, (iv) PatchSorter for improving sub-typing of histologic objects with machine learning. We will evaluate HistoTools for improvement of quality control and the efficiency of both segmenting and labeling histologic objects of interest via (a) onsite curation and release of the 14k WSI used during our internal validation and (b) supported external curation of at least 100k WSI via 24-clinical affiliates from every continent, except Antarctica, whom together have access to over 20 million WSI during this proposal. Our validation use cases are designed to expedite existing onsite projects in the CDx space, consisting of 4 organs (breast, lung, heart, kidney), 3 diseases (cancer, kidney disease, and organ rejection) and WSIs collected from >70 sites. These cohort characteristics will help ensure the generalizability of our tools for curated data lake creation, with open-source and usability study approaches employed to obtain feedback from collaborators and the larger research community. Dissemination through consortia (ITCR, NEPTUNE) and websites (Github, TCIA) will improve visibility and adoption. The tools and well-curated data sets we release are anticipated to bootstrap researcher-initiated CDx discovery projects, along with the creation of their own onsite manicured data lakes. Together, this proposal will engender digital pathology based precision medicine research.

摘要：随着最近批准用于初级诊断的全玻片扫描仪，然而常规玻璃扫描仪 组织病理学幻灯片被数字化并呈现给临床病理学家在计算机显示器上进行诊断， 日常临床实践中正在创建大量新的未开发数据，并将其放入不断增长的数据湖中。 数字格式，这些整个幻灯片图像（WSI）可以进行数字病理组学，即 提取与形态、属性和组织学相关的定量图像特征 WSI 中的对象随后可用于许多领域的发现，例如 组织基因组学，将表型表现与生物途径和基因联系起来 此外，低成本的非组织破坏性基于图像的伴随诊断测定（CDx） 不幸的是，可用于预测患者的预后和治疗反应。 数据湖（例如 TCGA）本身不足以用于病理组学，并且通常需要大量的人力 (i) 对 WSI 进行细致的质量控制（即避免“垃圾进、垃圾出”）以及 随后 (ii) 精确注释（例如，细胞边界）和标记（例如，细胞类型）组织学对象。 为了解决管理数据湖的这些主要限制因素，我们建议开发小型 HistoTools 采用计算集群的原型，从而在大型数字幻灯片的规模上实现其功能 存储库 (DSR)：(i) HistoQC 通过识别伪影（模糊性）对 WSI 进行稳健、可重复的质量控制 和异常值（染色不良的载玻片）以避免下游分析，(ii) CohortFinder 用于识别 和批次影响补偿，(iii) 快速注释器，通过 主动学习和机器学习的结合，(iv) PatchSorter 用于改进组织学对象的子类型 我们将评估 HistoTools 的质量控制和效率的改进。 通过 (a) 现场管理和发布所用的 14k WSI 来分割和标记感兴趣的组织学对象 在我们的内部验证期间，以及 (b) 通过 24 家临床附属机构支持至少 10 万个 WSI 的外部管理 来自除南极洲之外的各大洲的用户在本提案期间总共可以获得超过 2000 万个 WSI。 我们的验证用例旨在加快 CDx 领域现有的现场项目，包括 4 收集器官（乳腺、肺、心脏、肾脏）、3 种疾病（癌症、肾脏疾病和器官排斥）和 WSI 来自超过 70 个站点。这些队列特征将有助于确保我们的策划数据湖工具的通用性。 创建，采用开源和可用性研究方法来获取合作者的反馈和 通过联盟（ITCR、NEPTUNE）和网站（Github、TCIA）进行传播。 我们发布的工具和精心策划的数据集预计将提高可见性和采用率。 研究人员发起的 CDx 发现项目，以及创建自己的现场精心设计的数据湖。 总之，该提案将产生基于数字病理学的精准医学研究。