Improving AI/ML-Readiness of data generated from NIH-funded research on oral cancer screening

提高 NIH 资助的口腔癌筛查研究生成的数据的 AI/ML 就绪性

• 批准号: 10594120
• 负责人: Rongguang Liang
• 金额: $ 28.23万
• 依托单位: UNIVERSITY OF ARIZONA
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-08-10 至 2024-07-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10594120
• 关键词: Accounting; Administrative Supplement; Algorithms; Arizona; Cancer Detection; Clinical; Data; Data Set; Development; Diagnosis; Early Diagnosis; Equilibrium; FAIR principles; Funding; Image; Label; Lesion; Light; Malignant - descriptor; Malignant Neoplasms; Modeling; Modernization; Morbidity - disease rate; Oncology; Ontology; Optical Coherence Tomography; Oral; Oral Diagnosis; Oropharyngeal Squamous Cell Carcinoma; Parents; Patients; Readiness; Research; Resource-limited setting; Screening for Oral Cancer; Survival Rate; Techniques; Technology; Translating; Translations; Uncertainty; United States National Institutes of Health; Universities; Vision; base; cancer classification; cancer diagnosis; cancer imaging; commercialization; cost; data ecosystem; data interoperability; data repository; deep learning; flexibility; high risk population; image processing; imaging modality; imaging system; improved; low and middle-income countries; machine learning model; malignant mouth neoplasm; mortality; multimodal data; multimodality; open data; optical imaging; oral dysplasia; portability; prototype; tool; trustworthiness

Oral and oropharyngeal squamous cell carcinoma (OSCC) together rank as the sixth most common cancer worldwide, accounting for 400,000 new cancer cases each year. Two-thirds of these cancers occur in low- and middle-income countries (LMICs). While the 5-year survival rate in the U.S. is 62%, the survival rate is only 10- 40% and cure rate around 30% in the developing world. To meet the need for technologies that enable comprehensive oral cancer screening and diagnosis in low resource settings (LRS). In the parent R01DE030682 project titled “Multimodal Intraoral Imaging System for Oral Cancer Detection and Diagnosis in Low Resource Setting”, we have formed an interdisciplinary team with complementary expertise in optical imaging, oncology, deep learning, technology translation, and commercialization to develop, validate, and clinically translate a multimodal intraoral imaging system for oral cancer detection and diagnosis. We will achieve the project objective through three Aims: (1) develop a portable, semi-flexible, and compact multimodal intraoral imaging system; (2) evaluate the clinical feasibility of the prototyped intraoral imaging system and develop deep learning based image processing algorithms for early detection, diagnosis, and mapping of oral dysplastic and malignant lesions; and (3) validate the capability of the prototyped intraoral imaging system for diagnosing oral dysplasia and malignant lesions. In our UH3CA239682 project titled “Low-cost Mobile Oral Cancer Screening for Low Resource Setting”, we have screened ~7,000 high-risk population for oral cancer and obtained at least two pairs of dual-modal images (white light and autofluorescence) from each patient and obtained more than 28,000 de-identified images and related information. It is the largest image dataset on oral cancers. With this Administrative Supplements, we will make the image data AI/ML-ready by improving data compatibility with AI/ML tools, cleaning dataset, balancing data, reducing uncertainty, improving the interoperability of the data with ontology, and improving trustworthiness of AI/ML models using pixel-level annotation. We will also demonstrate the use of the transformed data in AI/ML applications through (1) multi-class oral cancer classification using the transformed multi-modal data and (2) interpretable and trustworthy AI model using image-level labels and pixel-level annotation. The image data and machine learning models will be available through The University of Arizona Research Data Repository (ReDATA). Completion of this project will accelerate development of AI/ML-based techniques for early oral cancer detection in low-resource settings, reducing morbidity and mortality. It will make data FAIR (Findable, Accessible, Interoperable, and Reusable) with high impact for open science, contributing to the NIH vision of a modernized and integrated biomedical data ecosystem. The parent R01 project will directly benefit from this dataset and the developed AI/ML algorithms as deep learning segmentation based on dual-modal images will be used to locate the suspicious regions for optical coherence tomography (OCT) imaging.

口腔和口咽鳞状细胞癌 (OSCC) 一起成为第六大常见癌症 全球每年新增癌症病例 40 万例，其中三分之二发生在低度和中度癌症中。 中等收入国家 (LMIC) 的 5 年生存率为 62%，而美国的生存率仅为 10%。 发展中国家的治愈率约为 40%，治愈率约为 30%，以满足对技术的需求。 资源匮乏环境中的综合口腔癌筛查和诊断 (LRS) 在父 R01DE030682 中。 项目名称为“用于低资源条件下口腔癌检测和诊断的多模态口内成像系统” “环境”，我们组建了一支跨学科团队，在光学成像、肿瘤学、 深度学习、技术转化和商业化，以开发、验证和临床转化 用于口腔癌检测和诊断的多模态口腔内成像系统我们将实现该项目目标。 通过三个目标：（1）开发便携式、半柔性、紧凑的多模态口腔内成像系统；（2） 评估原型口内成像系统的临床可行性并开发基于深度学习的图像 用于口腔发育不良和恶性病变的早期检测、诊断和绘图的处理算法；以及 (3) 验证原型口内成像系统诊断口腔发育不良和恶性病变的能力 病变。 在我们题为“低资源环境下的低成本移动口腔癌筛查”的 UH3CA239682 项目中，我们 筛查了约 7,000 名口腔癌高危人群，并获得了至少两对双模态图像 （白光和自发荧光）从每位患者身上获得了超过 28,000 张去识别图像 相关信息。这是有关口腔癌的最大图像数据集。 通过提高与 AI/ML 工具的数据兼容性、清理数据集、平衡，使图像数据为 AI/ML 做好准备 数据，减少不确定性，提高数据与本体的互操作性，提高可信度 我们还将演示如何在 AI/ML 中使用转换后的数据。 通过 (1) 使用转换后的多模态数据进行多类口腔癌分类和 (2) 使用图像级标签和像素级注释的可解释且值得信赖的人工智能模型。 图像数据和机器学习模型将通过亚利桑那大学研究中心提供 数据存储库（ReDATA）的完成将加速基于人工智能/机器学习的技术的开发。 在资源匮乏的地区进行早期口腔癌检测，降低发病率和死亡率，这将使数据变得公平。 （可查找、可访问、可互操作和可重复使用）对开放科学具有重大影响，为 NIH 做出贡献 现代化、集成的生物医学数据生态系统的愿景将直接受益于母项目 R01。 根据该数据集和开发的 AI/ML 算法作为基于双模态的深度学习分割 图像将用于定位光学相干断层扫描（OCT）成像的可疑区域。