Automatic Rib Fracture Detection in Pediatric Radiography to Identify Non-Accidental Trauma

儿科放射线照相中的自动肋骨骨折检测以识别非意外创伤

• 批准号: 9976563
• 负责人: Adam M Alessio
• 金额: $ 17.81万
• 依托单位: MICHIGAN STATE UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-07-12 至 2022-06-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9976563
• 关键词: Assessment tool; Cause of Death; Cessation of life; Chest; Child; Child Abuse; Childhood; Clinical; Computer Assisted; Data; Detection; Diagnostic; Diagnostic radiologic examination; Ensure; Face; Fracture; Goals; Hospitals; Image; Image Analysis; Infant; Injury; Institutional Review Boards; Label; Lead; Lung; Machine Learning; Mediastinal; Medical Imaging; Methodology; Methods; Modeling; Non-accidental; Outcome; Patient imaging; Pediatric Hospitals; Pediatric Radiology; Performance; Population; Positioning Attribute; Respiratory Diaphragm; Rib Fractures; Role; Sentinel; Site; Structure; Supervision; Testing; Thoracic cavity structure; Time; Training; Translations; Trauma; United States; Vendor; Work; bone; child physical abuse; clinical practice; convolutional neural network; cost; deep learning; detector; experience; follow-up; hands-on learning; imaging platform; imaging study; improved; machine learning method; mortality; multimodality; novel; patient population; physical abuse; radiologist; rapid technique; rib bone structure; soft tissue; supervised learning; tool

ABSTRACT Automatic Rib Fracture Detection in Pediatric Radiography to Identify Non-Accidental Trauma PI: Adam M. Alessio Non-accidental trauma caused by physical abuse is a leading cause of death in children in the United States. Because rib fractures are highly predictive of child abuse and chest radiographs are commonly performed for multiple indications, pediatric chest radiographs can have a critical role in the identification of abuse. Detection of rib fractures on pediatric radiographs is challenging and a high percentage of fractures are missed, particularly in imaging centers with limited pediatric radiology experience. Currently, there are no viable computer assisted strategies for rib fracture detection on chest radiographs. The purpose of this proposal is to develop machine learning methodology to detect rib fractures on pediatric radiographs using images from a network of hospitals. These methods will rely on a two-stage approach including a thoracic cavity segmentation stage followed by a fracture detection stage. We will explore two fracture detection strategies using novel supervised learning approaches: a heterogeneous U-net and a multi-modal regional-convolutional neural network. These methods will be trained and tested with a large set of fracture-absent radiographs (N=1000) from Seattle Children's Hospital and a diverse set of labelled fracture-present radiographs (N=500) from collaborating sites. These methods will be developed with an intentionally diverse set of radiographs, representative of the variety of fracture presentations and image quality in clinical practice, in order to position this rib fracture detection method for rapid translation to clinical practice. The ultimate goal of this proposal is to provide a computer assisted rib fracture assessment tool that would be a rapid and widely-available add-on to all pediatric chest radiograph exams, improving detection of rib fractures and potentially leading to improved identification of child abuse.

抽象的 小儿射线照相中的自动肋骨骨折检测，以识别非事故创伤 PI：Adam M. Alessio 由身体虐待引起的非事故创伤是美国儿童的主要死亡原因。 因为肋骨骨折高度预测虐待儿童，并且通常进行胸部X光片 多种迹象，小儿胸部X光片在识别滥用方面可能起关键作用。检测 小儿X光片上的肋骨骨折是具有挑战性的，缺少骨折的比例很高， 特别是在小儿放射学经验有限的成像中心。目前，没有可行的 计算机辅助策略，用于胸部X光片上的肋骨断裂检测。该提议的目的是 开发机器学习方法，以使用来自儿科射线照相的肋骨骨折 医院网络。这些方法将依赖于两个阶段的方法，包括胸腔腔分段 阶段，然后是断裂检测阶段。我们将使用新颖 监督学习方法：一种异质的U-NET和多模式区域跨跨神经 网络。这些方法将接受大量骨折X光片（n = 1000）的训练和测试 来自西雅图儿童医院，以及一套不同的标签骨折射线照片（n = 500） 协作网站。这些方法将使用有意的X光片组合开发， 代表临床实践中各种断裂表现和图像质量的代表，以定位 这种肋骨断裂检测方法用于快速转化为临床实践。该提议的最终目标是 提供计算机辅助肋骨断裂评估工具，该工具将是一个快速且广泛可用的附加组件 在所有儿科胸部X光片检查中，改善肋骨骨折的检测并有可能改善 识别虐待儿童。