Development and Validation of an Artificial Intelligence-Based Clinical Decision Support Tool for Videofluoroscopic Swallowing Studies

用于视频透视吞咽研究的基于人工智能的临床决策支持工具的开发和验证

• 批准号: 10679097
• 负责人: Bryan Patrick Bednarz
• 金额: $ 22.66万
• 依托单位: UNIVERSITY OF WISCONSIN-MADISON
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-08-08 至 2024-05-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10679097
• 关键词: 3D Print; Affect; Age Years; Algorithms; Anatomy; Artificial Intelligence; Barium; Biomechanics; Bolus Infusion; Classification; Clinic; Clinical; Computer software; Consumption; Data; Data Set; Deglutition; Deglutition Disorders; Dehydration; Development; Diagnosis; Diagnostic Procedure; Elderly; Environment; Etiology; Functional disorder; Future; Goals; Head and Neck Cancer; Head and neck structure; Health; Health care facility; Human; Image; Impairment; Inpatients; Left; Length of Stay; Lung; Malnutrition; Manuals; Masks; Measures; Medical; Methods; Morphologic artifacts; Nature; Network-based; Neurodegenerative Disorders; Oral cavity; Outcome; Output; Patient imaging; Patients; Pharyngeal structure; Physiology; Pneumonia; Prevalence; Procedures; Quality of life; Reference Values; Research; Resources; Retrospective cohort; Speed; Stroke; Structure; Techniques; Time; United States; Validation; Visualization; Work; acute care; artificial intelligence method; artificial neural network; aspirate; automated segmentation; catalyst; clinical decision support; clinical decision-making; clinical practice; clinically relevant; contrast enhanced; convolutional neural network; cost; design; experience; hospital readmission; image processing; improved; interest; mortality; novel; radiological imaging; segmentation algorithm; support tools; tool

ABSTRACT Dysphagia (swallowing dysfunction) is highly prevalent in a variety of medical conditions and prevalence increases with advancing age. If incorrectly diagnosed or left untreated, dysphagia can lead to serious health consequences, including malnutrition, dehydration, and pneumonia. The most commonly used procedure to diagnose dysphagia is the videofluoroscopic swallow (VFS) study. A VFS study utilizes barium to provide a contrast enhanced fluoroscopic procedure that allows for visualization of anatomy and physiology relevant to swallowing as well as identification of swallowing biomechanical impairments. Current VFS analysis methods used clinically are primarily qualitative in nature and subject to issues with reliability. Quantitative methods to support VFS clinical interpretation do exist but are primarily found in the research environment due to the time- consuming nature of frame by frame analysis required. The overall objective of this application is to develop and validate an artificial neural network-based software that will segment and track clinically important swallowing structures on a frame-by-frame basis within swallowing videos. Segmentation and tracking will automatically occur post acquisition with no needed input or video editing. Frame by frame auto-segmentation of regions of interest will allow for quantitative metrics to be determined algorithmically. To accomplish this objective, two specific aims are proposed: 1) to develop and validate an AI based auto-segmentation algorithm that accurately segments swallowing anatomy and bolus flow in VFS studies from a retrospective cohort of stroke and mixed etiology patients and 2) to apply the auto-segmentation algorithm to derive a variety of clinically relevant metrics in VFS studies and compare to manually derived reference values. To accomplish the first aim, pre-processing techniques will be established to improve image quality and reduce image artifacts using a novel 3D printed anthropomorphic head & neck phantom. Using a robust existing dataset of VFS images, we will then develop a Mask R-Convolutional Neural Network for automatic segmentation of a variety of clinically relevant features on VFS studies and will validate the auto-segmentation against manually derived segmentation. For the second aim, the auto-segmentation algorithm will be applied to derive important swallowing measures and associated metrics from the VFS images. The output of the algorithm will be validated against measures and metrics manually derived from the VFS images by experienced raters with established reliability. Tools developed through this project will reduce the subjectivity of human interpretation of VFS images, which will improve consistency and reliability of dysphagia diagnosis and treatment.

抽象的 吞咽困难（吞咽功能障碍）在多种医疗状况和患病率上非常普遍 随着年龄的增长而增加。如果未正确诊断或未经治疗，吞咽困难会导致严重的健康 后果，包括营养不良，脱水和肺炎。最常用的程序 诊断吞咽困难是视频荧光吞咽（VFS）研究。 VFS研究利用钡提供 对比增强的荧光镜检查，允许可视化解剖学和生理学 吞咽以及吞咽生物力学障碍的识别。当前的VFS分析方法 临床上使用的主要性质主要是定性的，并且遵守可靠性的问题。定量方法 确实存在支持VFS临床解释，但由于时间 - 需要通过框架分析消耗性质。该应用程序的总体目的是开发 并验证一个基于人工神经网络的软件，该软件将细分并跟踪临床重要的 在吞咽视频中以逐框的方式吞咽结构。细分和跟踪将 自动发生后，无需输入或视频编辑。框架自动分段 感兴趣的区域将允许通过算法确定定量指标。实现这一目标 目的，提出了两个具体目标：1）开发和验证基于AI的自动分段算法 从回顾性队列中，在VFS研究中，准确地吞噬了解剖结构和推注。 中风和混合病因患者以及2）应用自动分割算法来得出各种 VFS研究中与临床相关的指标，并与手动得出的参考值进行比较。完成 将建立第一个目的，即预处理技术来提高图像质量并减少图像伪像 使用新颖的3D印刷拟人化头和颈部幻影。使用VFS的现有数据集 图像，然后我们将开发一个面具R-Concontolutional神经网络，以自动分割多样性 VFS研究上临床相关的功能，并将验证自动分割针对手动得出的 分割。为了第二个目标，自动分割算法将用于得出重要的 从VFS图像中吞咽量度和相关指标。算法的输出将是 根据经验丰富的评分者手动从VFS图像中衍生的措施和指标验证 建立的可靠性。通过该项目开发的工具将降低人类解释的主观性 VFS图像，这将提高吞咽困难诊断和治疗的一致性和可靠性。