Development and Validation of an Automated Algorithm for Real-time Detection of Neoplasia in Barrett's Esophagus using a Low-cost, Portable Microendoscope

使用低成本便携式显微内窥镜实时检测巴雷特食管肿瘤的自动算法的开发和验证

• 批准号: 10610492
• 负责人: Mimi Chang Tan
• 金额: $ 19.81万
• 依托单位: BAYLOR COLLEGE OF MEDICINE
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-04-18 至 2027-03-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10610492
• 关键词: Age; Agreement; Algorithmic Software; Algorithms; Architecture; Area; Artificial Intelligence; Barrett Esophagus; Bioinformatics; Biopsy; Blood Vessels; Calibration; Cancer Detection; Categories; Classification; Clinical; Clinical Trials; Communities; Computer Assisted; Computer-Assisted Diagnosis; Data; Detection; Development; Development Plans; Devices; Diagnosis; Diagnostic; Discrimination; Dysplasia; Early Diagnosis; Early treatment; Endoscopes; Endoscopy; Epidemiology; Esophageal Adenocarcinoma; Esophageal Neoplasms; Esophageal mucous membrane; Esophagus; Ethnic Origin; Evaluation; Funding; Future; Goals; High grade dysplasia; Histopathology; Image; Image Analysis; Imaging technology; Incidence; Interview; K-Series Research Career Programs; Learning; Length; Lesion; Life Style; Light; Longitudinal Studies; Machine Learning; Malignant neoplasm of esophagus; Malignant neoplasm of gastrointestinal tract; Measures; Mentors; Methodology; Microscopic; Modeling; Neoplasms; Nuclear; Obesity; Optical Biopsy; Patients; Performance; Positioning Attribute; Public Health; Qualitative Research; Quality-Adjusted Life Years; ROC Curve; Race; Recommendation; Recording of previous events; Research; Research Personnel; Research Training; Resolution; Resource-limited setting; Risk; Risk Assessment; Risk Factors; Screening for cancer; Site; Smoking; Specificity; Structure; Tablet Computer; Techniques; Technology; Time; United States; Validation; Work; artificial intelligence algorithm; automated algorithm; cancer diagnosis; career development; cellular imaging; classification algorithm; clinical risk; clinically relevant; community setting; cost; cost effective; curative treatments; diagnostic accuracy; diagnostic tool; experience; indexing; men; microendoscope; microendoscopy; neoplastic; new technology; novel; portability; prevent; prospective; recruit; research and development; risk prediction model; risk stratification; sex; technology development

Project Summary/Abstract Endoscopic surveillance of Barrett’s esophagus (BE) is recommended for early diagnosis and treatment of neoplasia (i.e., esophageal adenocarcinoma and high-grade dysplasia). However, neoplasia is difficult to detect on regular white-light endoscopy (WLE; sensitivity 64%), and 26% of neoplasia is missed with WLE alone. On the other hand, confocal high-resolution microendoscopy (cHRME) is a low-cost, portable, reusable imaging technology that provides microscopic “optical biopsy” images of the esophageal mucosa at the time of endoscopy and has sensitivity of neoplasia detection upwards of 89% in the hands of experts. Despite these advantages, the dissemination of cHRME is limited by the availability of expert microendoscopists capable of interpreting these histopathology-like images. Artificial intelligence algorithms that automate interpretation of cHRME images could bridge this gap by providing a real-time computer-assisted diagnosis to users in community-based BE surveillance settings and reducing the need for expert review. My objective is to develop and validate an automated software algorithm for real-time BE neoplasia detection using cHRME. Furthermore, I will optimize the software algorithm by incorporating traditional clinical risk factors for comprehensive risk stratification. Thus, I propose the following Specific Aims: Aim 1: Technology Development: To develop a software algorithm that automates interpretation of cHRME images in BE neoplasia detection. Aim 2. Technology Evaluation and Optimization: (a) To validate the cHRME automated software algorithm for real-time neoplasia detection in BE; (b) To optimize the automated software algorithm by integrating demographic, lifestyle, and clinical risk factors for comprehensive BE neoplasia detection. Aim 3. Technology Acceptability: (a) To evaluate the acceptability and experiences of endoscopists using computer-assisted diagnosis; (b) To assess feasibility of the automated software algorithm in clinical BE neoplasia detection. The overarching goal of this proposal is to develop artificial intelligence algorithms that facilitate dissemination of novel, low-cost technologies into community settings for rapid, real-time, accurate neoplasia detection. Future longitudinal studies will focus on validation of comprehensive risk models that use macroscopic and microscopic metrics to predict future neoplasia risk in BE patients undergoing surveillance endoscopy. My long-term goal is to become an independently funded investigator in novel techniques for early gastrointestinal cancer detection. I have assembled an experienced mentoring committee comprised of senior, funded investigators with expertise in technology development, artificial intelligence algorithms, epidemiology, bioinformatics, and qualitative research. My career development plan includes additional formal research training in artificial intelligence methodology, machine learning, and clinical trials. With the support and protected time provided by the K23 Career Development Award, I will be able to complete my proposed research and career development goals and generate preliminary data to be competitive for independent research funding.

项目总结/摘要 建议对Barrett食管（BE）进行内镜监测，以便早期诊断和治疗 瘤形成（即，食管腺癌和高度异型增生）。然而，肿瘤很难检测到 常规白光内窥镜检查（WLE;灵敏度64%），26%的肿瘤被单独WLE遗漏。对 另一方面，共焦高分辨率显微内窥镜（cHRME）是一种低成本、便携式、可重复使用成像技术 在内窥镜检查时提供食管粘膜显微镜“光学活检”图像的技术 并且在专家手中具有89%以上的肿瘤检测灵敏度。尽管有这些优点， cHRME的传播受到能够解释的显微镜专家的可用性的限制 这些类似组织病理学的图像。自动解释cHRME图像的人工智能算法 可以通过为社区BE用户提供实时计算机辅助诊断来弥合这一差距 监督设置和减少对专家审查的需要。 我的目标是开发和验证一个自动化的软件算法，用于实时BE肿瘤检测 使用cHRME。此外，我将通过结合传统的临床风险因素来优化软件算法 进行全面的风险分层。因此，我提出以下具体目标：目标1：技术 开发：开发一种软件算法，用于自动判读BE瘤形成中的cHRME图像 侦测目标2.技术评估和优化：（a）验证cHRME自动化软件 用于BE中的实时瘤形成检测的算法;（B）通过集成 人口统计学、生活方式和临床危险因素对全面BE肿瘤检测的影响。目标3.技术 可接受性：（a）评价内镜医师使用计算机辅助 （B）评估自动软件算法在临床BE瘤形成检测中的可行性。 这项提案的首要目标是开发便于传播的人工智能算法 新的，低成本的技术进入社区设置快速，实时，准确的肿瘤检测。未来 纵向研究将侧重于验证综合风险模型， 用于预测接受监测内镜检查的BE患者未来肿瘤风险的指标。 我的长期目标是成为一名独立资助的研究人员，研究早期的新技术。 胃肠癌检测我召集了一个经验丰富的指导委员会， 资助的研究人员在技术开发，人工智能算法，流行病学， 生物信息学和定性研究。我的职业发展计划包括额外的正式研究培训 人工智能方法学、机器学习和临床试验。有了时间的支持和保护 通过K23职业发展奖，我将能够完成我的研究和职业生涯 发展目标，并生成初步数据，以竞争独立的研究资金。