Deep Learning for Automated Classification of Hip Hardware on Radiographs

IF 2.9 2区 工程技术 Q2 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Journal of Digital Imaging Pub Date : 2024-09-12 DOI:10.1007/s10278-024-01263-y
Yuntong Ma, Justin L. Bauer, Acacia H. Yoon, Christopher F. Beaulieu, Luke Yoon, Bao H. Do, Charles X. Fang
{"title":"Deep Learning for Automated Classification of Hip Hardware on Radiographs","authors":"Yuntong Ma, Justin L. Bauer, Acacia H. Yoon, Christopher F. Beaulieu, Luke Yoon, Bao H. Do, Charles X. Fang","doi":"10.1007/s10278-024-01263-y","DOIUrl":null,"url":null,"abstract":"<p>Purpose: To develop a deep learning model for automated classification of orthopedic hardware on pelvic and hip radiographs, which can be clinically implemented to decrease radiologist workload and improve consistency among radiology reports.</p><p>Materials and Methods: Pelvic and hip radiographs from 4279 studies in 1073 patients were retrospectively obtained and reviewed by musculoskeletal radiologists. Two convolutional neural networks, EfficientNet-B4 and NFNet-F3, were trained to perform the image classification task into the following most represented categories: no hardware, total hip arthroplasty (THA), hemiarthroplasty, intramedullary nail, femoral neck cannulated screws, dynamic hip screw, lateral blade/plate, THA with additional femoral fixation, and post-infectious hip. Model performance was assessed on an independent test set of 851 studies from 262 patients and compared to individual performance of five subspecialty-trained radiologists using leave-one-out analysis against an aggregate gold standard label.</p><p>Results: For multiclass classification, the area under the receiver operating characteristic curve (AUC) for NFNet-F3 was 0.99 or greater for all classes, and EfficientNet-B4 0.99 or greater for all classes except post-infectious hip, with an AUC of 0.97. When compared with human observers, models achieved an accuracy of 97%, which is non-inferior to four out of five radiologists and outperformed one radiologist. Cohen’s kappa coefficient for both models ranged from 0.96 to 0.97, indicating excellent inter-reader agreement.</p><p>Conclusion: A deep learning model can be used to classify a range of orthopedic hip hardware with high accuracy and comparable performance to subspecialty-trained radiologists.</p>","PeriodicalId":50214,"journal":{"name":"Journal of Digital Imaging","volume":null,"pages":null},"PeriodicalIF":2.9000,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Digital Imaging","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1007/s10278-024-01263-y","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0

Abstract

Purpose: To develop a deep learning model for automated classification of orthopedic hardware on pelvic and hip radiographs, which can be clinically implemented to decrease radiologist workload and improve consistency among radiology reports.

Materials and Methods: Pelvic and hip radiographs from 4279 studies in 1073 patients were retrospectively obtained and reviewed by musculoskeletal radiologists. Two convolutional neural networks, EfficientNet-B4 and NFNet-F3, were trained to perform the image classification task into the following most represented categories: no hardware, total hip arthroplasty (THA), hemiarthroplasty, intramedullary nail, femoral neck cannulated screws, dynamic hip screw, lateral blade/plate, THA with additional femoral fixation, and post-infectious hip. Model performance was assessed on an independent test set of 851 studies from 262 patients and compared to individual performance of five subspecialty-trained radiologists using leave-one-out analysis against an aggregate gold standard label.

Results: For multiclass classification, the area under the receiver operating characteristic curve (AUC) for NFNet-F3 was 0.99 or greater for all classes, and EfficientNet-B4 0.99 or greater for all classes except post-infectious hip, with an AUC of 0.97. When compared with human observers, models achieved an accuracy of 97%, which is non-inferior to four out of five radiologists and outperformed one radiologist. Cohen’s kappa coefficient for both models ranged from 0.96 to 0.97, indicating excellent inter-reader agreement.

Conclusion: A deep learning model can be used to classify a range of orthopedic hip hardware with high accuracy and comparable performance to subspecialty-trained radiologists.

Abstract Image

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
利用深度学习对 X 光片上的髋关节硬件进行自动分类
目的:开发一种深度学习模型,用于对骨盆和髋关节X光片上的矫形硬件进行自动分类,该模型可在临床上实施,以减少放射科医生的工作量并提高放射学报告的一致性:肌肉骨骼放射科医生回顾性地获取并审查了 1073 名患者的 4279 张骨盆和髋关节 X 光片。对两个卷积神经网络(EfficientNet-B4 和 NFNet-F3)进行了训练,以便将图像分类为以下最具代表性的类别:无硬件、全髋关节置换术(THA)、半髋关节置换术、髓内钉、股骨颈套管螺钉、动态髋关节螺钉、外侧刀片/钢板、带有额外股骨固定的全髋关节置换术以及感染后髋关节。对来自 262 名患者的 851 项研究的独立测试集进行了模型性能评估,并使用留一分析法将其与五名接受过亚专业培训的放射科医生的个人性能进行了比较:在多类分类中,NFNet-F3 的接收器工作特征曲线下面积 (AUC) 在所有类别中均达到或超过 0.99,EfficientNet-B4 的接收器工作特征曲线下面积 (AUC) 在所有类别中均达到或超过 0.99,感染后髋关节除外,其 AUC 为 0.97。与人类观察者相比,模型的准确率达到了 97%,不逊于五分之四的放射科医生,也优于一位放射科医生。两个模型的科恩卡帕系数在 0.96 到 0.97 之间,表明阅读者之间的一致性非常好:结论:深度学习模型可用于对一系列骨科髋关节硬件进行分类,准确率高,性能可与经过亚专业培训的放射科医生媲美。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Journal of Digital Imaging
Journal of Digital Imaging 医学-核医学
CiteScore
7.50
自引率
6.80%
发文量
192
审稿时长
6-12 weeks
期刊介绍: The Journal of Digital Imaging (JDI) is the official peer-reviewed journal of the Society for Imaging Informatics in Medicine (SIIM). JDI’s goal is to enhance the exchange of knowledge encompassed by the general topic of Imaging Informatics in Medicine such as research and practice in clinical, engineering, and information technologies and techniques in all medical imaging environments. JDI topics are of interest to researchers, developers, educators, physicians, and imaging informatics professionals. Suggested Topics PACS and component systems; imaging informatics for the enterprise; image-enabled electronic medical records; RIS and HIS; digital image acquisition; image processing; image data compression; 3D, visualization, and multimedia; speech recognition; computer-aided diagnosis; facilities design; imaging vocabularies and ontologies; Transforming the Radiological Interpretation Process (TRIP™); DICOM and other standards; workflow and process modeling and simulation; quality assurance; archive integrity and security; teleradiology; digital mammography; and radiological informatics education.
期刊最新文献
Intra-Individual Reproducibility of Automated Abdominal Organ Segmentation—Performance of TotalSegmentator Compared to Human Readers and an Independent nnU-Net Model Teleradiology-Based Referrals for Patients with Gastroenterological Diseases Between Tertiary and Regional Hospitals: A Hospital-to-Hospital Approach Vital Characteristics Cellular Neural Network (VCeNN) for Melanoma Lesion Segmentation: A Biologically Inspired Deep Learning Approach Septic Arthritis Modeling Using Sonographic Fusion with Attention and Selective Transformation: a Preliminary Study Assessment of Age-Related Differences in Lower Leg Muscles Quality Using Radiomic Features of Magnetic Resonance Images
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1