Development of Artificial Intelligence-Based Approaches for Computer-Aided Management of Colorectal Polyps

基于人工智能的结直肠息肉计算机辅助管理方法的开发

• 批准号: 10479308
• 负责人: Eladio Rodriguez-Diaz
• 金额: --
• 依托单位: VA BOSTON HEALTH CARE SYSTEM
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-10-01 至 2026-09-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10479308
• 关键词: Adoption; Age; American; Artificial Intelligence; Aspirin; Augmented Reality; Benign; Biological Markers; Biopsy; Body mass index; Cancer Etiology; Cessation of life; Classification; Clinical; Clinical Data; Colon; Colonic Neoplasms; Colonoscopy; Colorectal Cancer; Colorectal Neoplasms; Colorectal Polyp; Computer Assisted; Computer-Assisted Diagnosis; Computers; Cost Savings; Data; Data Set; Databases; Detection; Development; Diagnosis; Disease Outcome; Diverticulum; Documentation; Educational process of instructing; Electronic Health Record; Endoscopes; Endoscopy; Excision; Explosion; Family history of; Friends; Gastrointestinal Endoscopy; Gender; Generations; Goals; Guidelines; Healthcare; Image; Image Analysis; Individual; Interobserver Variability; Intervention; Intestines; Intuition; Label; Laboratory Study; Light; Measures; Methods; Modeling; Morbidity - disease rate; Mucous Membrane; Neoplastic Polyp; Optics; Output; Pathology; Patients; Performance; Polypectomy; Polyps; Precancerous Polyp; Preparation; Procedures; Records; Rectum; Reporting; Research; Resected; Rest; Risk; Risk Factors; Screening for cancer; Semantics; Serrated Adenoma; Societies; Tattooing; Technology; Testing; Time; Tissues; United States; Visualization; cancer risk; care burden; clinical practice; clinical risk; clinically relevant; colon cancer prevention; colorectal cancer risk; colorectal cancer screening; cost; cost effectiveness; deep field survey; deep learning; deep learning model; design; experience; improved; innovation; model design; mortality; network architecture; patient screening; polyposis; predictive modeling; preservation; quantitative imaging; rectal; skills; visual feedback

Background and Objectives: Colorectal cancer (CRC) is the second leading cause of cancer death in the United States, with nearly 150,000 new cases and 50,000 deaths annually. Colonoscopy with polypectomy remains the gold standard for CRC screening and surveillance since removal of neoplastic polyps during colonoscopy modifies disease outcomes and informs subsequent management. Standard practice continues to favor removal of all visualized polyps for histopathological assessment, despite estimates that nearly half of the polyps are non-neoplastic. Studies have shown that the capability to reliably predict polyp pathology endoscopically in real time could result in substantial improvement in the cost-effectiveness of colonoscopy for CRC. The number of colonoscopies performed is increasing, and in the VA more than doubled in a five-year span. This demand does not include subsequent procedures required in ~30% of screened patients. Thus, colonoscopy can benefit greatly from efficiency improvements at every level. In light of this, the past decade has seen an explosion in advances in endoscopic technologies toward diagnosing and treating colorectal neoplasia more precisely. Recent advances in artificial intelligence (AI), specifically in the field of deep learning, and their application to endoscopic imaging, have shown promise for automating endoscopic polyp pathology predictions, overcoming operator-based polyp pathology assessment factors such as interobserver variability, skill, and experience. Such capability would finally open the door to widespread adoption of cost-saving resect-and-discard and leave-behind paradigms for diminutive polyps, as proposed by the American Society for Gastrointestinal Endoscopy Preservation and Incorporation of Valuable Endoscopic Innovations guidelines. More importantly, the incorporation of AI- based quantitative image interpretation into clinical practice, including in the VA, has the potential to increase early cancer detection thus reducing patient morbidity and mortality. To this end, the main goal of the proposed study is to leverage AI, specifically deep learning models, to develop an accurate and robust computer aided diagnosis (CADx) platform to enable the purely endoscopic, optical assessment of mucosal pathologies, specifically colorectal polyps. In parallel, the use of AI models to assess colonic mucosal and luminal features known to inform colonoscopy quality will be investigated. Methods: The study will be guided by three aims. In Aim 1 robust classification models for predicting polyp pathology will be developed. Labeled images and clinical data, from existing datasets and clinical records, will be used to design and validate deep learning models. The design will consist of two steps: outlining regions in an image containing a polyp, and subsequent analysis of the polyp region to provide a pathology prediction. Borrowing from aspects of augmented reality, the pathology prediction along with the estimated polyp boundary, will be presented to endoscopists in an intuitive and clinically friendly manner as a pseudo- color overlay, enhancing the transparency and interpretability of the models output predictions. This immediate visual feedback can thus inform clinical decisions during colonoscopy. Aim 2 will focus on using clinical risk factors associated with colorectal neoplasia in combination with endoscopic imaging data to enhance predictions of polyp pathology. The goal is to investigate incorporation of recognized CRC clinical risk factors and biomarkers, obtained from patients’ electronic health records, in our polyp pathology prediction deep learning models. Finally, in Aim 3 the deep learning-based detection, segmentation, and classification frameworks developed in Aim 1 will be adapted for scoring bowel preparation, recognizing cecal landmarks and rectal retroflexion, identifying colonic diverticula, and delineating endoscopic tattoo markings. These features are associated with performing of high-quality colonoscopy, for which automated identification could improve and facilitate documentation of endoscopic findings and report generation.

背景和目标：结直肠癌（CRC）是癌症死亡的第二大原因。 美国每年有近 150,000 例新病例和 50,000 例结肠镜息肉切除术死亡病例。 自从切除肿瘤性息肉以来，仍然是结直肠癌筛查和监测的黄金标准 结肠镜检查可改变疾病结果并为后续治疗提供信息。 仍然赞成切除所有可见的息肉以进行组织病理学评估，尽管估计 研究表明，能够可靠地预测息肉，其中近一半是非肿瘤性的。 实时内窥镜病理学可以显着提高成本效益 用于 CRC 的结肠镜检查数量正在增加，并且在 VA 中超过 这一需求在五年内翻了一番，其中不包括约 30% 的后续程序。 因此，结肠镜检查可以从各个层面的效率提高中受益匪浅。 有鉴于此，过去十年内窥镜技术取得了爆炸式的进步， 更准确地诊断和治疗结直肠肿瘤。人工智能（AI）的最新进展， 特别是在深度学习领域及其在内窥镜成像领域的应用，已经显示出希望 用于自动进行内窥镜息肉病理学预测，克服基于操作员的息肉病理学 评估因素，例如观察者之间的差异、技能和经验，最终将成为可能。 为广泛采用节省成本的切除和丢弃以及遗留范例打开大门 美国胃肠内窥镜保存学会提出的小息肉 结合有价值的内窥镜创新，更重要的是结合人工智能。 基于定量图像解释的临床实践，包括在 VA 中，有可能 增加早期癌症检测，从而降低患者的发病率和死亡率是为此目的的主要目标。 拟议研究的目的是利用人工智能，特别是深度学习模型，开发准确且 强大的计算机辅助诊断 (CADx) 平台可实现纯粹的内窥镜光学评估 粘膜病理学，特别是结直肠息肉，同时使用人工智能模型来评估结肠。 将研究已知可影响结肠镜检查质量的粘膜和管腔特征。 方法：该研究将以三个目标为指导：目标 1 预测息肉的稳健分类模型。 将根据现有数据集和临床记录开发标记图像和临床数据， 将用于设计和验证深度学习模型。该设计将包括两个步骤：概述。 图像中包含息肉的区域，并对息肉区域进行后续分析以提供病理学 借用增强现实、病理学预测和估计等方面的预测。 息肉边界将以直观且临床友好的方式作为伪边界呈现给内窥镜医师 颜色叠加，增强模型输出预测的透明度和可解释性。 因此，即时视觉反馈可以为结肠镜检查期间的临床决策提供信息，目标 2 将重点关注使用。 与结直肠肿瘤相关的临床危险因素结合内窥镜成像数据 增强息肉病理学的预测，目标是研究纳入公认的 CRC 临床数据。 在我们的息肉病理学中，从患者的电子健康记录中获得风险因素和生物标志物 最后，在目标 3 中，基于深度学习的检测、分割和预测。 目标 1 中开发的分类框架将适用于对肠道准备进行评分，认识到 盲肠标志和直肠后屈，识别结肠憩室，并描绘内窥镜纹身 这些特征与高质量结肠镜检查的执行有关，为此自动化。 识别可以改善和促进内窥镜检查结果的记录和报告的生成。