Artificial Intelligence for Improved Breast Cancer Screening Accuracy: External Validation, Refinement, and Clinical Translation

人工智能提高乳腺癌筛查准确性：外部验证、细化和临床转化

• 批准号: 9912472
• 负责人: CHRISTOPH I LEE
• 金额: $ 54.73万
• 依托单位: UNIVERSITY OF WASHINGTON
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-01-01 至 2024-12-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9912472
• 关键词: 3-Dimensional; Address; Algorithms; Artificial Intelligence; Benign; Big Data; Biometry; Biopsy; Breast; Breast Cancer Detection; California; Characteristics; Clinical; Code; Collaborations; Community Practice; Computer software; Computers; DNA Sequence Alteration; Data; Data Science; Data Set; Data Storage and Retrieval; Databases; Diagnostic; Digital Breast Tomosynthesis; Digital Mammography; Engineering; Equilibrium; Goals; Grant; Health; Human; Image; Imaging Device; Imaging technology; Institution; International; Lead; Link; Machine Learning; Malignant Neoplasms; Mammographic screening; Mammography; Medicine; Metadata; Methods; Modality; Modeling; Molecular; Nature; Oncology; Outcome; Output; Participant; Pathology; Performance; Population; Population Heterogeneity; Positioning Attribute; Publications; Randomized Controlled Trials; Registries; Risk; Seminal; Series; Supervision; Techniques; Technology Assessment; Testing; Time; Training; Translating; Universities; Validation; Washington; Woman; algorithm development; algorithmic methodologies; base; breast imaging; clinical implementation; clinical risk; clinical translation; clinically relevant; clinically significant; cloud based; computer aided detection; crowdsourcing; deep learning; digital; experience; genetic risk factor; improved; industry partner; innovation; intelligent algorithm; long short term memory; malignant breast neoplasm; molecular subtypes; mortality; multidisciplinary; novel; novel strategies; patient population; population based; prospective; radiological imaging; radiologist; routine screening; screening; tool; tumor

PROJECT SUMMARY Screening mammography saves lives but human interpretation alone is imperfect and is associated with significant harms including ~30,000 missed breast cancers and ~3.8 million false-positives exams each year in the U.S. alone. Traditional computer-aided detection failed to improve screening accuracy, in part due to the static nature of software trained and tested on small datasets decades ago. Recent advances in improved computer processing power, cloud-based data storage capabilities, and availability of large imaging datasets have led to renewed excitement for applying artificial intelligence (AI) to mammography interpretation. We propose a unique academic-industry partnership to validate, refine, scale, and clinically translate our proven 2D mammography AI algorithm to 3D mammography interpretation. Our team helped organize and lead the Dialogue for Reverse Engineering Assessments and Methods (DREAM) Digital Mammography Challenge, an open crowdsourced AI algorithmic challenge that provided >640,000 digital 2D mammogram images and associated clinical metadata to >1,200 coding teams worldwide. Our industry partner for this grant, DeepHealth, Inc., was the top performing team in the DREAM Challenge. With >50% of U.S. facilities now offering 3D mammography for screening, the 50-to-100-fold increase in imaging data represents a new critical barrier for both radiologists and AI algorithm developers. To date, there have been few publications addressing AI-enhanced interpretation of 3D mammography, the emerging screening exam of choice. We will validate our post-DREAM algorithm for 2D mammography (which currently rivals human interpretation alone) using UCLA's Athena Breast Health Network, one of the largest population-based breast imaging registries. We will enhance our 2D AI algorithm with expert radiologist supervision and examine the impact of adding novel non-imaging data parameters, including genetic mutation and tumor molecular subtype data, to help train the AI model to identify more clinically significant cancers. We will use several novel technical algorithmic approaches to scale from 2D to 3D mammography which, in our preliminary studies, have shown improved accuracy beyond radiologist interpretation alone. Finally, we will perform a series of interpretive studies to identify the optimal interface between “black box” outputs and radiologist interpreters, which remains an understudied topic. With >40 million U.S. women undergoing screening each year, seemingly small improvements in overall accuracy would still imply significantly improved population-based outcomes. In summary, we have assembled an unparalleled multidisciplinary team with expertise in machine/deep learning, breast cancer screening accuracy, medicine, oncology, radiology, imaging technology assessment, and biostatistics. We have a proven track record of strong collaboration and are well positioned to validate, enhance, scale, and translate our proven 2D AI algorithm for improved 3D mammography accuracy. Our new end user tool will help tip the balance of routine screening towards greater benefits than harms.

项目概要 筛查乳房X光检查可以挽救生命，但仅靠人类的解释是不完美的，并且与 重大危害，包括每年约 30,000 例漏检乳腺癌和约 380 万例假阳性检查 仅在美国。传统的计算机辅助检测未能提高筛查准确性，部分原因是 几十年前在小数据集上训练和测试的软件的静态性质。改进的最新进展 计算机处理能力、基于云的数据存储能力以及大型成像数据集的可用性 人们对将人工智能 (AI) 应用于乳房 X 线摄影解读重新燃起热情。 我们提出了一种独特的学术-工业合作伙伴关系，以验证、完善、扩展和临床转化我们的 经过验证的 2D 乳房 X 线摄影 AI 算法到 3D 乳房 X 线摄影解释。我们的团队帮助组织和 领导逆向工程评估和方法 (DREAM) 数字乳房 X 线摄影对话 Challenge，一项开放式众包 AI 算法挑战赛，提供了超过 640,000 张数字 2D 乳房 X 光照片 向全球超过 1,200 个编码团队提供图像和相关临床元数据。我们的行业合作伙伴 DeepHealth, Inc. 是 DREAM Challenge 中表现最好的团队。拥有超过 50% 的美国设施 现在提供用于筛查的 3D 乳房 X 光检查，成像数据增加 50 至 100 倍代表着新的 对于放射科医生和人工智能算法开发人员来说，这是一个关键障碍。迄今为止，发表的文章还很少 解决 3D 乳房 X 光检查（新兴的筛查检查）的人工智能增强解读问题。 我们将验证用于 2D 乳房 X 线摄影的 post-DREAM 算法（目前该算法可与人类解释相媲美） 单独）使用加州大学洛杉矶分校的 Athena 乳腺健康网络，这是最大的基于人群的乳腺成像之一 注册表。我们将在专家放射科医生的监督下增强我们的 2D AI 算法，并检查 添加新的非影像数据参数，包括基因突变和肿瘤分子亚型数据，以 帮助训练人工智能模型来识别更多具有临床意义的癌症。我们将使用多项新颖的技术 从 2D 到 3D 乳房 X 线摄影的算法方法，在我们的初步研究中已经表明 提高的准确性超出了放射科医生单独解释的范围。最后我们将进行一系列的解读 研究确定“黑匣子”输出和放射科医生口译员之间的最佳接口， 仍然是一个未被充分研究的话题。每年有超过 4000 万美国女性接受筛查，似乎 总体准确性的小幅提高仍然意味着基于人群的结果显着改善。 总之，我们组建了一支无与伦比的多学科团队，拥有机器/深度学习方面的专业知识 学习、乳腺癌筛查准确性、医学、肿瘤学、放射学、影像技术评估、 和生物统计学。我们拥有良好的合作记录，并且有能力验证、 增强、扩展和转换我们经过验证的 2D AI 算法，以提高 3D 乳房 X 光检查的准确性。我们的新 最终用户工具将有助于平衡常规筛查，使其利大于弊。