Development and Validation of an Artificial-Intelligence-enabled Portable Colposcopy Device for Optimizing Triage Alternatives for HPV-based Cervical Cancer Screening

开发和验证人工智能便携式阴道镜设备，用于优化基于 HPV 的宫颈癌筛查的分诊方案

• 批准号: 10625379
• 负责人: Megan J. Huchko
• 金额: $ 57.13万
• 依托单位: DUKE UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-05-20 至 2027-04-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10625379
• 关键词: Acetic Acids; Address; Adopted; Affect; Algorithms; Ambulatory Care; Artificial Intelligence; Biopsy; Caring; Cause of Death; Cellular Phone; Cervical; Cervical Cancer Screening; Cervix Uteri; Cessation of life; Characteristics; Classification; Clinical; Clinical Research; Colposcopes; Colposcopy; Computer software; Country; Coupled; Cytology; Data; Databases; Decision Aid; Development; Devices; Diagnosis; Diagnostic; Disease; Educational Status; Effectiveness; Ensure; Evaluation; Generations; Goals; Guidelines; HPV-High Risk; Health; Health care facility; Healthcare; Hemorrhage; Human Papillomavirus; Human Resources; Image; Incidence; Income; Infertility; Infrastructure; Intervention; Kenya; Knowledge; Letters; Light; Location; Malignant neoplasm of cervix uteri; Medical Research; Methods; Modeling; National Cancer Institute; Pathology; Performance; Physicians; Pilot Projects; Population; Predictive Value; Prevention strategy; Process; Provider; Public Health; ROC Curve; Recommendation; Research; Research Institute; Resolution; Resources; Retrieval; Risk; Sensitivity and Specificity; Series; Site; Specificity; Technology; Testing; Training; Triage; Validation; Visit; Visual; Woman; Work; World Health Organization; burden of illness; cervical cancer prevention; clinic ready; clinical research site; comparative effectiveness; contrast imaging; convolutional neural network; cost; deep learning; deep learning algorithm; diagnostic accuracy; diagnostic strategy; experience; follow-up; global health; impression; improved; innovation; low and middle-income countries; mHealth; machine learning algorithm; mortality; overtreatment; portability; premalignant; prospective; prospective test; prototype; real world application; risk prediction model; risk stratification; screening; standard care; success; technology development; tool; virtual

Abstract Cervical cancer is the second leading cause of death for women worldwide. Alarmingly, 85% of deaths occur in low and middle-income countries (LMICs), as they lack the health care infrastructure required for cytology-based screening, referral colposcopy diagnosis, and expert physicians, which have dramatically reduced the disease burden in high income countries (HICs). Highly sensitive human papillomavirus (HPV) testing has been effective at reducing the incidence and mortality from cervical cancer when directly coupled with treatment; however, a majority of women with HPV do not have cervical precancer, making HPV testing a poor triage test as overtreatment carries risks like hemorrhage and infertility. Colposcopy followed by biopsy, the preferred triage method in HICs, is untenable in most LMIC settings due to the cost of colposcopes and pathology facilities to process and interpret biopsy results. To make matters worse, women are lost to follow up in LMIC settings when a multi-visit model for cervical cancer screening is used. Visual Inspection with Acetic Acid (VIA), the World Health Organization recommended triage test following HPV testing, has widely varied sensitivity and specificity depending on the training level of the provider. In this proposal we are proposing a single visit model for precision diagnosis and treatment in LMICs for cervical cancer prevention. Two major technological tools are needed to implement this model: a low-cost method to perform imaging of the cervix and a machine learning algorithm to automate diagnosis in the absence of a provider. We have previously developed the Pocket Colposcope, which has shown high concordance with standard colposcopy at a fraction of the cost and validated it on thousands of women across nearly every continent. We are now in the process of developing a state-of-the-art convolutional neural network (CNN), called Colposcopy Automated Risk Evaluation (CARE), trained with Pocket colposcopy images to automate the diagnostic process. Our current prototype algorithm has been highly successful at classifying cervical pre-cancers from Pocket Colposcope images retrospectively. Our goals for this proposal are fourfold: 1) improve and generalize the performance of Pocket CARE using >10,000 National Cancer Institute (NCI) standard colposcopy images; 2) generate synthetic images to address domain shifts due to environmental and personnel changes between different clinical sites; 3) embed the CARE algorithm into our existing software to enable high quality image capture with the Pocket Colposcope for automated diagnosis 4) validate the performance of Pocket CARE prospectively with a clinical study in Kisumu, Kenya, a site where Pocket CARE would ultimately be adopted\. The deliverables for this proposal will be a fully validated Pocket CARE software ready for scale to different clinical scenarios based on location-specific cultural contexts and infrastructure and a comparative effectiveness of Pocket CARE to other publicly available algorithms and standard RI care.

抽象的 宫颈癌是全球女性第二大死亡原因。令人震惊的是，85%的死亡发生在 低收入和中等收入国家 (LMIC)，因为它们缺乏基于细胞学的医疗保健基础设施 筛查、转诊阴道镜诊断和专家医师，大大减少了这种疾病的发生 高收入国家（HIC）的负担。高灵敏人乳头瘤病毒（HPV）检测已取得成效 直接结合治疗可降低宫颈癌的发病率和死亡率；然而，一个 大多数感染 HPV 的女性并没有宫颈癌前病变，因此 HPV 检测是一项较差的分类检测，因为 过度治疗会带来风险，例如 出血和不孕。 阴道镜检查后进行活检，这是首选分类 由于阴道镜和病理设施的成本，这种方法在高收入国家中是站不住脚的。 处理和解释活检结果。更糟糕的是，在中低收入国家环境中，女性在以下情况下无法进行随访： 使用多次访问模型进行宫颈癌筛查。乙酸目视检查 (VIA)，世界 卫生组织推荐的 HPV 检测后的分类检测，其敏感性和特异性差异很大 取决于提供者的培训水平。在本提案中，我们提出了单次访问模型以提高精度 中低收入国家宫颈癌预防的诊断和治疗。需要两个主要的技术工具 实现这个模型：一种低成本的子宫颈成像方法和一种机器学习算法 在没有提供者的情况下自动诊断。我们之前开发了袖珍阴道镜， 已显示出与标准阴道镜检查的高度一致性，且成本仅为标准阴道镜检查的一小部分，并在数千个案例中进行了验证 几乎每个大陆的女性。我们现在正在开发一种最先进的卷积 神经网络 (CNN)，称为阴道镜自动风险评估 (CARE)，通过袖珍阴道镜进行训练 图像以自动化诊断过程。我们当前的原型算法在以下领域取得了巨大成功 从袖珍阴道镜图像中回顾性地对宫颈癌前病变进行分类。我们此提案的目标是 四重：1) 使用超过 10,000 个国家癌症研究所改进和推广 Pocket CARE 的性能 (NCI) 标准阴道镜图像； 2）生成合成图像以解决由于环境导致的域变化 以及不同临床地点之间的人员变动； 3）将CARE算法嵌入到我们现有的软件中 使用袖珍阴道镜捕获高质量图像以进行自动诊断 4) 验证 Pocket CARE 的性能在肯尼亚基苏木进行了一项临床研究，Pocket CARE 在此进行了前瞻性研究 最终会被采纳\.该提案的交付成果将是经过充分验证的 Pocket CARE 软件 准备好根据特定地点的文化背景和基础设施扩展到不同的临床场景 Pocket CARE 与其他公开可用的算法和标准 RI 护理的有效性比较。