Leveraging artificial intelligence/machine learning-based technology to overcome specialized training and technology barriers for the diagnosis and prognostication of colorectal cancer in Africa

利用基于人工智能/机器学习的技术克服非洲结直肠癌诊断和预测的专业培训和技术障碍

• 批准号: 10712793
• 负责人: Ulysses Gregory John Balis
• 金额: $ 25万
• 依托单位: AGA KHAN UNIVERSITY (KENYA)
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-09-15 至 2026-08-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10712793
• 关键词: Address; Adjuvant; Africa; African; Algorithmic Analysis; Algorithms; Architecture; Area; Artificial Intelligence; Biological; Breast; Cancer Detection; Cancer Etiology; Cancer Prognosis; Cells; Cellular Morphology; Cervical; Cessation of life; Classification; Clinical; Collaborations; Colorectal Cancer; Communities; Computer Vision Systems; Computer software; Computers; Country; Data; Data Science; Diagnosis; Diagnostic; Disease; E-learning; Early Diagnosis; Education; Eye; Funding; Future; Goals; Hematoxylin and Eosin Staining Method; Histologic; Histology; Histopathology; Hospitals; Human; Image; Image Analysis; Incidence; Income; Individual; Infrastructure; Intervention; Kenya; Machine Learning; Malignant Neoplasms; Measurement; Methods; Michigan; Oncologist; Online Systems; Outcome; Pathologist; Pathology; Pattern; Performance; Physical shape; Population; Prognosis; Prostate; Public Hospitals; Radiation Oncologist; Reagent; Recommendation; Reproducibility; Research; Research Project Grants; Resources; Retrospective cohort; Risk Assessment; Rural; Services; Site; Slide; Stains; Surgeon; System; Techniques; Technology; Texture; Therapeutic; Tissue Sample; Training; Treatment Effectiveness; Universities; University Hospitals; Work; accurate diagnosis; cancer care; cancer diagnosis; clinical care; clinically relevant; cohort; computational pipelines; cost; deep learning; diagnostic algorithm; digital; digital imaging; imaging Segmentation; innovation; machine learning method; machine vision; mortality; open source; prognostic; prognostication; programs; risk stratification; routine imaging; screening; supervised learning; support tools; survivorship; tertiary care; tool; treatment planning; tumor; unsupervised learning; vector

SUMMARY/ABSTRACT Colorectal cancer (CRC) is the third most commonly diagnosed cancer and the second leading cause of cancer related deaths worldwide. Rates in Africa are on the rise, but essential histopathology services critical for cancer care are scarce. To address this barrier, we developed an artificial intelligence (AI)/machine learning (ML)-based computational pipeline (SIVQ/VIPR) that performs automated pixel-level image segmentation and classification from digital images of routinely collected hematoxylin and eosin (H&E)-stained slides. SIVQ/VIPR is highly precise, reproducible, and outperforms subject matter experts. Once histologically distinct regions are identified, image analysis algorithms can then identify individual regions and aggregate them to predict diagnostic and prognostic features in conjunction with clinical outcomes to guide treatment. Our overall approach is to leverage our validated SIVQ/VIPR computational pipeline to develop and validate an AI-based diagnostic decision support (AI-DDS) tool for CRC diagnosis and prognosis in an existing Kenyan cohort. To carry out this work, the Aga Khan University (AKU)- East Africa and the University of Michigan have partnered with Tenwek Hospital, a non-academic community-based public hospital in rural Bomet, Kenya, to develop a unique collaboration of oncologists, pathologists, surgeons, statisticians, and informaticians, making us uniquely suited to develop population-relevant, affordable, and scalable data science solutions in Kenya – all priorities of the DS-I Africa Program. We will: Aim 1. Adapt and validate an existing ML-based diagnostic algorithm for CRC using digital fields of view from H&E-stained slides in a retrospective cohort of n=675 CRC cases from the AKU and Tenwek Hospitals. We will apply the CRC-trained SIVQ/VIPR computational pipeline for segmentation and classification for CRC features, followed by a confirmatory classifier step to achieve a case level, binary result of a cancer/no-cancer (i.e., diagnosis). Aim 2. Develop and refine an unsupervised ML method to identify histopathology image-derived measurements associated with CRC prognosis. We will use computer/machine vision approaches to identify image features (e.g., cellular morphology) discriminative of CRC prognosis and biological potential for disease aggressiveness. Combined use of AI-based morphological signatures of aggressive disease (e.g., high-grade tumor architecture) will be compiled with other clinically relevant features towards the goal of generating a multi-axial multiplexed AI-DDS tool that can maximally inform of the biological and metastatic potential of each CRC case. This project will lay the groundwork for an AI-DDS tool for clinicians (e.g., pathologists, oncologists) that facilitates prompt and accurate diagnosis, prognosis, and risk stratification for CRC care in Africa. Because this approach leverages open-source software and can be deployed as a turn-key system intended for web-based cloud deployment, it is well-suited for capacity building, integrating into educational programs, and expanding to other emergent or prevalent cancers (i.e., breast, cervical, prostate) as part of the DS-I Africa Consortium.

总结/摘要 结直肠癌（CRC）是第三大最常诊断的癌症，也是第二大导致结肠癌的原因。 全世界癌症相关的死亡非洲的发病率正在上升，但基本的组织病理学服务至关重要 癌症治疗是稀缺的。为了解决这一障碍，我们开发了一种人工智能（AI）/机器学习 基于ML的计算流水线（SIVQ/VIPR），执行自动像素级图像分割， 根据常规收集的苏木精和伊红（H&E）染色的载玻片的数字图像进行分类。SIVQ/VIPR 是高度精确的，可重复的，并优于主题专家。一旦组织学上不同的区域 识别后，图像分析算法可以识别各个区域并将其聚合以预测 诊断和预后特征结合临床结果来指导治疗。我们的整体 方法是利用我们经过验证的SIVQ/VIPR计算管道来开发和验证基于AI的 诊断决策支持（AI-DDS）工具，用于现有肯尼亚队列的CRC诊断和预后。到 开展这项工作，阿加汗大学（AKU）-东非和密歇根大学合作， Tenwek医院是肯尼亚Bomet农村的一家非学术性社区公立医院， 肿瘤学家、病理学家、外科医生、统计学家和信息学家的独特合作，使我们 唯一适合在肯尼亚开发与人口相关、负担得起且可扩展的数据科学解决方案-所有 DS-I非洲计划的优先事项。我们将：目标1。调整和验证现有的基于ML的诊断 在n=675例CRC的回顾性队列中使用H& E染色切片的数字视野的CRC算法 AKU和Tenwek医院的病例。我们将应用CRC训练的SIVQ/VIPR计算管道 用于CRC特征的分割和分类，然后是验证性分类器步骤，以实现 病例水平，癌症/非癌症的二元结果（即，诊断）。目标2.开发和优化无监督ML 识别与CRC相关的组织病理学图像衍生测量的方法 预后 我们将使用 用于识别图像特征的计算机/机器视觉方法（例如，细胞形态学）区分 CRC预后和疾病侵袭性的生物学潜力。结合使用基于AI的形态学 侵袭性疾病的特征（例如，高级别肿瘤结构）将与其他临床 相关功能，以实现生成多轴多路复用AI-DDS工具的目标， 告知每个CRC病例的生物学和转移潜力。该项目将为一个 用于临床医生的AI-DDS工具（例如，病理学家，肿瘤学家），其有助于迅速和准确的诊断， 预后和非洲CRC护理的风险分层。因为这种方法利用了开源 软件，并且可以部署为用于基于Web的云部署的交钥匙系统，它非常适合 能力建设，融入教育计划，并扩展到其他新兴或流行的 癌症（即，乳腺、宫颈、前列腺）作为DS-I非洲联盟的一部分。