The Application of Deep Learning Methods for Proximal Humerus Fracture Feature Identification

深度学习方法在肱骨近端骨折特征识别中的应用

• 批准号: 10714170
• 负责人: Sarah Bauer Floyd
• 金额: $ 20.78万
• 依托单位: CLEMSON UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-09-15 至 2028-07-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10714170
• 关键词: Acute; Adoption; Adult; Archives; Area; Caring; Centers of Research Excellence; Cessation of life; Characteristics; Classification; Clinical Practice Guideline; Complex; Computer Models; Computer-Assisted Image Analysis; Computers; Consult; Data; Data Set; Decision Making; Development; Diagnosis; Diagnostic Imaging; Dislocations; E-learning; Elderly; Electronic Health Record; Evidence based treatment; Foundations; Fracture; Future; Generations; Goals; Health; Humeral Fractures; Image; Image Analysis; Individual; Informatics; Injury; Joints; Label; Location; Medical Records; Methods; Modeling; Neural Network Simulation; Operative Surgical Procedures; Orthopedics; Outcome; Pain; Patient-Focused Outcomes; Patients; Pattern; Performance; Persistent pain; Physicians; Process; Quality of Care; ROC Curve; Recommendation; Records; Reporting; Research; Roentgen Rays; Shoulder; Specialist; Standardization; Surgeon; Surgical complication; System; Testing; Training; Trauma; Treatment Effectiveness; United States; Validation; Work; X-Ray Medical Imaging; clinical care; clinical practice; clinically relevant; deep learning; deep learning model; deep neural network; disability; electronic health record system; evidence based guidelines; experience; improved; individual patient; interest; learning strategy; personalized medicine; practice setting; prisma; prognostic value; research and development; therapy development; treatment choice; usability

SUMMARY Proximal humerus fractures (PHFs) are the third most common fracture in the elderly, with an estimated 200,000 occurring each year in the United States. PHFs can lead to pain, poor shoulder function, plus short and long- term disability for patients. Substantial controversy persists regarding initial treatment for elderly adults with this injury. PHFs can be managed conservatively or surgically and great controversy exists over which patients should be treated surgically. A unique challenge with PHFs is that they have variable presentation and range in complexity. Unlike the management of other major joint fractures, the initial treatment choice for PHF is highly dependent on the fracture characteristics. Treatment effectiveness evidence is needed to guide clinical care for individual patients with PHF. The Neer Classification, first developed in 1970, is the most widely used framework to describe and classify PHFs. Although the Neer Classification is the most widely used in practice, it is outdated, incomplete, often incorrectly applied, and suffers from poor interobserver reliability. The absence of a universally accepted, standardized fracture classification system is a critical barrier in the development of treatment effectiveness evidence for PHF. The application of deep learning (DL) computational models can automate and standardize the fracture classification process and identify all relevant fracture characteristics. DL image analysis models have been shown to be highly accurate at identifying features of interest on diagnostic images. An automated, standardized PHF classification system will enhance our ability to universally standardize fracture classification across all orthopaedic clinical care settings, improve the precision and efficiency in fracture care and generate treatment effectiveness evidence to guide clinical practice. The overall objective for this application, is to develop and validate a DL computational model capable of identifying fracture features using X-ray images. Our central hypothesis is that we can develop a DL model that will be as accurate as expert shoulder specialists in identifying important fracture features on X-ray images. In Aim 1 we will modify the Neer Classification framework for fracture feature identification. Aim 2 will be the development of a gold standard dataset for deep learning DL fracture feature identification, and finally Aim 3 will be the training and testing of a DL model to identify fracture features on X-rays.

总结 肱骨近端骨折（PHF）是老年人中第三常见的骨折，估计有20万 每年都发生在美国。PHF会导致疼痛，肩关节功能差，加上短和长- 长期残疾患者。关于老年人的初始治疗存在大量争议， 损伤PHF可以通过保守治疗或手术治疗，对于哪些患者存在很大争议 应该手术治疗PHF的一个独特挑战是，它们具有可变的呈现方式和范围， 复杂性与其他主要关节骨折的治疗不同，PHF的初始治疗选择是高度保守的。 这取决于断裂特征。需要治疗有效性证据来指导临床护理， 个别PHF患者。1970年首次开发的Neer分类是最广泛使用的框架 描述和分类PHF。尽管Neer分类法在实践中使用最广泛，但它已经过时， 不完整，经常被错误地应用，并且观察者之间的可靠性差。没有一个普遍 公认的、标准化的骨折分类系统是治疗发展的关键障碍 PHF的有效性证据。深度学习（DL）计算模型的应用可以自动化， 规范骨折分类过程并识别所有相关骨折特征。DL图像分析 模型在识别诊断图像上感兴趣的特征时已经显示出高度准确。一个 自动化、标准化的PHF分类系统将增强我们普遍标准化骨折的能力 在所有骨科临床护理环境中进行分类，提高骨折护理的精度和效率 并产生治疗有效性证据以指导临床实践。本申请的总体目标是， 是开发和验证能够使用X射线图像识别裂缝特征的DL计算模型。 我们的中心假设是，我们可以开发一个DL模型，将作为专家肩专家准确 在X光图像上识别重要的骨折特征。在目标1中，我们将修改Neer分类 裂缝特征识别框架。目标2将是开发一个黄金标准数据集， 学习DL裂缝特征识别，最后目标3将是DL模型的训练和测试， 在X光片上识别骨折特征。