髋关节骨关节炎和股骨头骨坏死严重程度分级的x线片诊断性能:深度学习模型与委员会认证的骨科医生

Chen Chen , Peng Liu , Yong Feng , DeXian Ye , Chi-Cheng Fu , Lin Ye , YanYan Song , DongXu Liu , Guoyan Zheng , ChangQing Zhang
{"title":"髋关节骨关节炎和股骨头骨坏死严重程度分级的x线片诊断性能:深度学习模型与委员会认证的骨科医生","authors":"Chen Chen ,&nbsp;Peng Liu ,&nbsp;Yong Feng ,&nbsp;DeXian Ye ,&nbsp;Chi-Cheng Fu ,&nbsp;Lin Ye ,&nbsp;YanYan Song ,&nbsp;DongXu Liu ,&nbsp;Guoyan Zheng ,&nbsp;ChangQing Zhang","doi":"10.1016/j.ostima.2023.100092","DOIUrl":null,"url":null,"abstract":"<div><h3>Objectives</h3><p>To evaluate the diagnostic performance of a single deep learning (DL) model for severity grading of two typical yet challenging hip disorders, primary hip osteoarthritis (PHOA) and osteonecrosis of the femoral head (ONFH), on digital radiography.</p></div><div><h3>Design</h3><p>We conducted a two-center, retrospective study. We trained an XceptionNet-based DL model using a dataset consisting of 56,597 hip images diagnosed as normal, PHOA_I, PHOA_II, PHOA_III, and ONFH_II, ONFH_III, ONFH_IV by a panel of 10 board-certified orthopedic surgeons. The trained model was validated on a separate testing dataset. To demonstrate the model's generalizability, we applied the trained model directly to a dataset consisting of 811 hip images collected from an external clinical center.</p></div><div><h3>Results</h3><p>Accuracy, area under the curve (AUC) of receiver operating characteristics, sensitivity, and specificity were investigated. Validated on the testing dataset, the model achieved an overall AUC of 94.9%, with individual AUC scores of 94.2% for PHOA_I, 95.8% for PHOA_II, 90.9% for PHOA_III, 93.6% for ONFH_II, 93.8% for ONFH_III, and 93.8% for ONFH_IV. The average sensitivity for all classes of the DL algorithm (0.797) was better than the average level of the board-certified orthopedic surgeons (0.756). When applied directly to the external dataset, the AUC of the trained model is degraded.</p></div><div><h3>Conclusion</h3><p>We can train a single DL model to grade the severity of PHOA and ONFH on digital radiographs. The model may be used to provide a second opinion for severity grading of hip disorders on digital radiographs.</p></div>","PeriodicalId":74378,"journal":{"name":"Osteoarthritis imaging","volume":"3 2","pages":"Article 100092"},"PeriodicalIF":0.0000,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Diagnostic performance for severity grading of hip osteoarthritis and osteonecrosis of femoral head on radiographs: Deep learning model vs. board-certified orthopaedic surgeons\",\"authors\":\"Chen Chen ,&nbsp;Peng Liu ,&nbsp;Yong Feng ,&nbsp;DeXian Ye ,&nbsp;Chi-Cheng Fu ,&nbsp;Lin Ye ,&nbsp;YanYan Song ,&nbsp;DongXu Liu ,&nbsp;Guoyan Zheng ,&nbsp;ChangQing Zhang\",\"doi\":\"10.1016/j.ostima.2023.100092\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Objectives</h3><p>To evaluate the diagnostic performance of a single deep learning (DL) model for severity grading of two typical yet challenging hip disorders, primary hip osteoarthritis (PHOA) and osteonecrosis of the femoral head (ONFH), on digital radiography.</p></div><div><h3>Design</h3><p>We conducted a two-center, retrospective study. We trained an XceptionNet-based DL model using a dataset consisting of 56,597 hip images diagnosed as normal, PHOA_I, PHOA_II, PHOA_III, and ONFH_II, ONFH_III, ONFH_IV by a panel of 10 board-certified orthopedic surgeons. The trained model was validated on a separate testing dataset. To demonstrate the model's generalizability, we applied the trained model directly to a dataset consisting of 811 hip images collected from an external clinical center.</p></div><div><h3>Results</h3><p>Accuracy, area under the curve (AUC) of receiver operating characteristics, sensitivity, and specificity were investigated. Validated on the testing dataset, the model achieved an overall AUC of 94.9%, with individual AUC scores of 94.2% for PHOA_I, 95.8% for PHOA_II, 90.9% for PHOA_III, 93.6% for ONFH_II, 93.8% for ONFH_III, and 93.8% for ONFH_IV. The average sensitivity for all classes of the DL algorithm (0.797) was better than the average level of the board-certified orthopedic surgeons (0.756). When applied directly to the external dataset, the AUC of the trained model is degraded.</p></div><div><h3>Conclusion</h3><p>We can train a single DL model to grade the severity of PHOA and ONFH on digital radiographs. The model may be used to provide a second opinion for severity grading of hip disorders on digital radiographs.</p></div>\",\"PeriodicalId\":74378,\"journal\":{\"name\":\"Osteoarthritis imaging\",\"volume\":\"3 2\",\"pages\":\"Article 100092\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-06-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Osteoarthritis imaging\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2772654123000077\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Osteoarthritis imaging","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2772654123000077","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

目的评价一种深度学习(DL)模型对两种典型但具有挑战性的髋关节疾病——原发性髋关节骨关节炎(PHOA)和股骨头坏死(ONFH)——在数字x线摄影上的严重程度分级的诊断性能。设计:我们进行了一项双中心回顾性研究。我们训练了一个基于xceptionnet的深度学习模型,该数据集由56,597张被诊断为正常、PHOA_I、PHOA_II、PHOA_III和ONFH_II、ONFH_III、ONFH_IV的髋关节图像组成,由10名经过委员会认证的骨科医生组成。训练后的模型在单独的测试数据集上进行验证。为了证明模型的可泛化性,我们将训练好的模型直接应用于由811张从外部临床中心收集的髋关节图像组成的数据集。结果考察了受体工作特征的准确度、曲线下面积(AUC)、灵敏度和特异性。在测试数据集上验证,该模型的总体AUC为94.9%,其中PHOA_I的AUC得分为94.2%,PHOA_II的AUC得分为95.8%,PHOA_III的AUC得分为90.9%,ONFH_II的AUC得分为93.6%,ONFH_III的AUC得分为93.8%,ONFH_IV的AUC得分为93.8%。DL算法各类别的平均灵敏度(0.797)优于执业骨科医师的平均水平(0.756)。当直接应用于外部数据集时,训练模型的AUC会降低。结论我们可以训练一个单一的DL模型对数字x线片上的PHOA和ONFH的严重程度进行分级。该模型可用于为数字x线片上髋关节疾病的严重程度分级提供第二种意见。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Diagnostic performance for severity grading of hip osteoarthritis and osteonecrosis of femoral head on radiographs: Deep learning model vs. board-certified orthopaedic surgeons

Objectives

To evaluate the diagnostic performance of a single deep learning (DL) model for severity grading of two typical yet challenging hip disorders, primary hip osteoarthritis (PHOA) and osteonecrosis of the femoral head (ONFH), on digital radiography.

Design

We conducted a two-center, retrospective study. We trained an XceptionNet-based DL model using a dataset consisting of 56,597 hip images diagnosed as normal, PHOA_I, PHOA_II, PHOA_III, and ONFH_II, ONFH_III, ONFH_IV by a panel of 10 board-certified orthopedic surgeons. The trained model was validated on a separate testing dataset. To demonstrate the model's generalizability, we applied the trained model directly to a dataset consisting of 811 hip images collected from an external clinical center.

Results

Accuracy, area under the curve (AUC) of receiver operating characteristics, sensitivity, and specificity were investigated. Validated on the testing dataset, the model achieved an overall AUC of 94.9%, with individual AUC scores of 94.2% for PHOA_I, 95.8% for PHOA_II, 90.9% for PHOA_III, 93.6% for ONFH_II, 93.8% for ONFH_III, and 93.8% for ONFH_IV. The average sensitivity for all classes of the DL algorithm (0.797) was better than the average level of the board-certified orthopedic surgeons (0.756). When applied directly to the external dataset, the AUC of the trained model is degraded.

Conclusion

We can train a single DL model to grade the severity of PHOA and ONFH on digital radiographs. The model may be used to provide a second opinion for severity grading of hip disorders on digital radiographs.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Osteoarthritis imaging
Osteoarthritis imaging Radiology and Imaging
自引率
0.00%
发文量
0
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信