Real-Time Bronchoscope Localization Using Machine Learning To Improve Lung Cancer Diagnosis

使用机器学习实时支气管镜定位来改善肺癌诊断

• 批准号: 10676966
• 负责人: Inbar Fried
• 金额: $ 4.59万
• 依托单位: UNIV OF NORTH CAROLINA CHAPEL HILL
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-01 至 2026-05-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10676966
• 关键词: 3-Dimensional; 3D Print; Accounting; Address; Algorithms; Anatomy; Area; Biopsy; Bronchoscopes; Bronchoscopy; Cancer Etiology; Cessation of life; Clinical; Clinical Skills; Complication; Computational algorithm; Computer Simulation; Computer Vision Systems; Coupled; Data; Data Set; Devices; Diagnosis; Diagnostic; Diameter; Disease; Distal; Drops; Early Diagnosis; Electromagnetics; Ensure; Environment; Equipment; Family suidae; Freedom; Frequencies; Future; Health Benefit; Hour; Human; Individual; Lesion; Localized Disease; Localized Lesion; Location; Lung; Machine Learning; Malignant Neoplasms; Malignant neoplasm of lung; Measurement; Medical; Medicine; Mentors; Minor; Modeling; Morbidity - disease rate; Motion; Needles; Neoplasm Metastasis; Neural Network Simulation; Nodule; North Carolina; Operative Surgical Procedures; Patient observation; Patients; Physicians; Positioning Attribute; Preparation; Procedures; Psyche structure; Public Health; Puncture procedure; Radial; Reproducibility; Research; Robot; Robotics; Scientist; Secondary to; Site; Survival Rate; System; Techniques; Technology; Time; Tissues; Trachea; Training; United States; Universities; Woman; Work; X-Ray Computed Tomography; cancer diagnosis; career; chest computed tomography; computer science; data-driven model; deep neural network; experience; experimental study; follow-up; improved; in vivo; laboratory experiment; large datasets; lung cancer screening; lung lesion; machine learning model; men; millimeter; minimally invasive; mortality; real time model; screening guidelines; simulation; skills; software development; success; tool; ultrasound; virtual; virtual human

Project Summary/Abstract Lung cancer 5-year survival rates drop from 61% for early stage diagnosis to just 6% for late stage diagnosis. Currently, fewer than 1 in 5 cases are diagnosed at an early stage. The increasing frequency of chest CT scans and changes in lung cancer screening guidelines are expected to increase the number of incidentally discovered lung lesions, representing an opportunity for earlier lung cancer diagnosis. Bronchoscopy is currently the safest, least invasive, and least expensive diagnostic option, but its poor diagnostic yield greatly limits its procedural benefit. Even when advanced techniques like radial endobronchial ultrasound and electromagnetic navigation are used, the diagnostic yield is just 50-60%. This is primarily due to challenges with intraoperative localization of the bronchoscope prior to needle deployment. Additionally, access to these techniques is limited because they require expensive equipment and unique expertise. Efforts relying on the bronchoscope's built-in camera require no additional equipment or specialization, but have struggled with generalizability across individuals in part due to limited data availability and assumptions about airway features. The objective of this proposal is to improve the success rate of traditional bronchoscopes by addressing limita- tions in intraoperative localization using a data-driven model that is robust to differences in human anatomy. This work has potential for significant public health benefit by (1) increasing early lung cancer detection, (2) reducing morbidity and mortality by reducing the number of invasive procedures, and (3) making minimally invasive bron- choscopy more accessible in areas without expert bronchoscopists. The proposed work will be accomplished via two Specific Aims. In Aim 1, a dataset will be generated of virtual and real bronchoscopy videos with video-frame matched six degrees-of-freedom poses (position and orientation in three-dimensions) of the bronchoscope's dis- tal tip. This data will be made publicly available as the first large dataset of its kind to promote future research and reproducibility. In Aim 2, a real-time bronchoscope localization model will be developed using advances in ma- chine learning, including deep neural networks, that have shown success in camera localization for non-medical applications. These models will regress the pose of the bronchoscope's distal tip using current and past video frames of the bronchoscope's built-in camera. The clinical utility of the system will be evaluated in simulation, 3D printed lung phantoms, and ex-vivo porcine lung experiments. The research, tightly coupled clinical experience, and associated training plan will provide a unique interdisciplinary skill-set in computer science, medical robotics, and procedural medicine. The outstanding research and clinical environment for this training at the University of North Carolina at Chapel Hill ensures exceptional preparation for a career conducting cutting-edge research as a physician-scientist in medical robotics.

项目概要/摘要 肺癌的 5 年生存率从早期诊断的 61% 降至晚期诊断的仅为 6%。 目前，只有不到五分之一的病例能够在早期得到诊断。胸部 CT 扫描频率不断增加 肺癌筛查指南的变化预计会增加偶然发现的数量 肺部病变，代表了早期肺癌诊断的机会。支气管镜检查是目前最安全的 侵入性最小且最便宜的诊断选择，但其较差的诊断率极大地限制了其程序 好处。即使采用径向支气管内超声和电磁导航等先进技术 使用时，诊断率仅为 50-60%。这主要是由于术中定位的挑战 在针部署之前检查支气管镜。此外，对这些技术的访问受到限制，因为它们 需要昂贵的设备和独特的专业知识。依靠支气管镜内置摄像头的工作需要 没有额外的设备或专业化，但在个体之间的普遍性方面遇到了困难，部分原因是 有限的数据可用性和有关气道特征的假设。 该提案的目的是通过解决传统支气管镜的局限性来提高传统支气管镜的成功率。 使用数据驱动的模型进行术中定位，该模型对人体解剖学的差异具有鲁棒性。这 这项工作有可能通过以下方式给公众健康带来重大益处：(1) 增加早期肺癌检测，(2) 减少 通过减少侵入性操作的数量来降低发病率和死亡率，以及（3）使微创支气管治疗 在没有支气管镜专家的地区更容易进行支气管镜检查。拟议的工作将通过以下方式完成 两个具体目标。在目标 1 中，将使用视频帧生成虚拟和真实支气管镜检查视频的数据集 匹配支气管镜显示的六个自由度姿势（三维位置和方向） 塔尔小费。该数据将作为同类第一个大型数据集公开提供，以促进未来的研究和 再现性。在目标 2 中，将利用先进的先进技术开发实时支气管镜定位模型。 中国学习，包括深度神经网络，在非医疗领域的相机定位方面取得了成功 应用程序。这些模型将使用当前和过去的视频来回归支气管镜远端尖端的姿势 支气管镜内置摄像头的框架。该系统的临床效用将通过模拟、3D 评估 打印的肺模型和离体猪肺实验。研究与临床经验紧密结合， 相关的培训计划将提供计算机科学、医疗机器人、 和程序医学。伦敦大学为本次培训提供了出色的研究和临床环境 北卡罗来纳州教堂山分校确保为从事尖端研究的职业生涯做好特殊准备 医疗机器人领域的医师科学家。