利用深度学习技术在膝关节前路X光片上准确识别椎体骨折

Jacob F. Oeding M.S. , Ayoosh Pareek M.D. , Kyle N. Kunze M.D. , Benedict U. Nwachukwu M.D., M.B.A. , Harry G. Greditzer IV M.D. , Christopher L. Camp M.D. , Bryan T. Kelly M.D. , Andrew D. Pearle M.D. , Anil S. Ranawat M.D. , Riley J. Williams III M.D. , HSS ACL Reconstruction Registry
{"title":"利用深度学习技术在膝关节前路X光片上准确识别椎体骨折","authors":"Jacob F. Oeding M.S. ,&nbsp;Ayoosh Pareek M.D. ,&nbsp;Kyle N. Kunze M.D. ,&nbsp;Benedict U. Nwachukwu M.D., M.B.A. ,&nbsp;Harry G. Greditzer IV M.D. ,&nbsp;Christopher L. Camp M.D. ,&nbsp;Bryan T. Kelly M.D. ,&nbsp;Andrew D. Pearle M.D. ,&nbsp;Anil S. Ranawat M.D. ,&nbsp;Riley J. Williams III M.D. ,&nbsp;HSS ACL Reconstruction Registry","doi":"10.1016/j.asmr.2024.100940","DOIUrl":null,"url":null,"abstract":"<div><h3>Purpose</h3><p>To develop a deep learning model for the detection of Segond fractures on anteroposterior (AP) knee radiographs and to compare model performance to that of trained human experts.</p></div><div><h3>Methods</h3><p>AP knee radiographs were retrieved from the Hospital for Special Surgery ACL Registry, which enrolled patients between 2009 and 2013. All images corresponded to patients who underwent anterior cruciate ligament reconstruction by 1 of 23 surgeons included in the registry data. Images were categorized into 1 of 2 classes based on radiographic evidence of a Segond fracture and manually annotated. Seventy percent of the images were used to populate the training set, while 20% and 10% were reserved for the validation and test sets, respectively. Images from the test set were used to compare model performance to that of expert human observers, including an orthopaedic surgery sports medicine fellow and a fellowship-trained orthopaedic sports medicine surgeon with over 10 years of experience.</p></div><div><h3>Results</h3><p>A total of 324 AP knee radiographs were retrieved, of which 34 (10.4%) images demonstrated evidence of a Segond fracture. The overall mean average precision (mAP) was 0.985, and this was maintained on the Segond fracture class (mAP = 0.978, precision = 0.844, recall = 1). The model demonstrated 100% accuracy with perfect sensitivity and specificity when applied to the independent testing set and the ability to meet or exceed human sensitivity and specificity in all cases. Compared to an orthopaedic surgery sports medicine fellow, the model required 0.3% of the total time needed to evaluate and classify images in the independent test set.</p></div><div><h3>Conclusions</h3><p>A deep learning model was developed and internally validated for Segond fracture detection on AP radiographs and demonstrated perfect accuracy, sensitivity, and specificity on a small test set of radiographs with and without Segond fractures. The model demonstrated superior performance compared with expert human observers.</p></div><div><h3>Clinical Relevance</h3><p>Deep learning can be used for automated Segond fracture identification on radiographs, leading to improved diagnosis of easily missed concomitant injuries, including lateral meniscus tears. Automated identification of Segond fractures can also enable large-scale studies on the incidence and clinical significance of these fractures, which may lead to improved management and outcomes for patients with knee injuries.</p></div>","PeriodicalId":34631,"journal":{"name":"Arthroscopy Sports Medicine and Rehabilitation","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666061X24000580/pdfft?md5=08c9d375b9d6d728f6d38e20ff69efbe&pid=1-s2.0-S2666061X24000580-main.pdf","citationCount":"0","resultStr":"{\"title\":\"Segond Fractures Can Be Identified With Excellent Accuracy Utilizing Deep Learning on Anteroposterior Knee Radiographs\",\"authors\":\"Jacob F. Oeding M.S. ,&nbsp;Ayoosh Pareek M.D. ,&nbsp;Kyle N. Kunze M.D. ,&nbsp;Benedict U. Nwachukwu M.D., M.B.A. ,&nbsp;Harry G. Greditzer IV M.D. ,&nbsp;Christopher L. Camp M.D. ,&nbsp;Bryan T. Kelly M.D. ,&nbsp;Andrew D. Pearle M.D. ,&nbsp;Anil S. Ranawat M.D. ,&nbsp;Riley J. Williams III M.D. ,&nbsp;HSS ACL Reconstruction Registry\",\"doi\":\"10.1016/j.asmr.2024.100940\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Purpose</h3><p>To develop a deep learning model for the detection of Segond fractures on anteroposterior (AP) knee radiographs and to compare model performance to that of trained human experts.</p></div><div><h3>Methods</h3><p>AP knee radiographs were retrieved from the Hospital for Special Surgery ACL Registry, which enrolled patients between 2009 and 2013. All images corresponded to patients who underwent anterior cruciate ligament reconstruction by 1 of 23 surgeons included in the registry data. Images were categorized into 1 of 2 classes based on radiographic evidence of a Segond fracture and manually annotated. Seventy percent of the images were used to populate the training set, while 20% and 10% were reserved for the validation and test sets, respectively. Images from the test set were used to compare model performance to that of expert human observers, including an orthopaedic surgery sports medicine fellow and a fellowship-trained orthopaedic sports medicine surgeon with over 10 years of experience.</p></div><div><h3>Results</h3><p>A total of 324 AP knee radiographs were retrieved, of which 34 (10.4%) images demonstrated evidence of a Segond fracture. The overall mean average precision (mAP) was 0.985, and this was maintained on the Segond fracture class (mAP = 0.978, precision = 0.844, recall = 1). The model demonstrated 100% accuracy with perfect sensitivity and specificity when applied to the independent testing set and the ability to meet or exceed human sensitivity and specificity in all cases. Compared to an orthopaedic surgery sports medicine fellow, the model required 0.3% of the total time needed to evaluate and classify images in the independent test set.</p></div><div><h3>Conclusions</h3><p>A deep learning model was developed and internally validated for Segond fracture detection on AP radiographs and demonstrated perfect accuracy, sensitivity, and specificity on a small test set of radiographs with and without Segond fractures. The model demonstrated superior performance compared with expert human observers.</p></div><div><h3>Clinical Relevance</h3><p>Deep learning can be used for automated Segond fracture identification on radiographs, leading to improved diagnosis of easily missed concomitant injuries, including lateral meniscus tears. Automated identification of Segond fractures can also enable large-scale studies on the incidence and clinical significance of these fractures, which may lead to improved management and outcomes for patients with knee injuries.</p></div>\",\"PeriodicalId\":34631,\"journal\":{\"name\":\"Arthroscopy Sports Medicine and Rehabilitation\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-06-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S2666061X24000580/pdfft?md5=08c9d375b9d6d728f6d38e20ff69efbe&pid=1-s2.0-S2666061X24000580-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Arthroscopy Sports Medicine and Rehabilitation\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2666061X24000580\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"Medicine\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Arthroscopy Sports Medicine and Rehabilitation","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2666061X24000580","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Medicine","Score":null,"Total":0}
引用次数: 0

摘要

目的开发一种深度学习模型,用于检测膝关节前后位(AP)X光片上的Segond骨折,并将模型性能与训练有素的人类专家的性能进行比较。所有图像都与接受前交叉韧带重建术的患者相对应,这些患者由注册数据中的 23 名外科医生中的 1 名进行了手术。根据 Segond 骨折的放射学证据,图像被分为两类中的一类,并进行人工标注。70%的图像用于填充训练集,20%和 10%的图像分别用于验证集和测试集。测试集中的图像用于将模型性能与人类专业观察者的性能进行比较,人类专业观察者包括一名矫形外科运动医学研究员和一名受过研究培训、拥有 10 年以上经验的矫形外科运动医学外科医生。结果 共检索到 324 张 AP 膝关节 X 光片,其中 34 张(10.4%)图像显示有 Segond 骨折的证据。总体平均精确度(mAP)为 0.985,在赛刚骨折类别上保持了这一精确度(mAP = 0.978,精确度 = 0.844,召回率 = 1)。该模型在应用于独立测试集时,准确率达到 100%,具有完美的灵敏度和特异性,在所有情况下都能达到或超过人类的灵敏度和特异性。与一名骨科外科运动医学研究员相比,该模型评估和分类独立测试集中的图像所需的总时间仅为0.3%。结论开发了一种深度学习模型,并对其进行了内部验证,用于在AP射线照片上检测Segond骨折,该模型在有Segond骨折和无Segond骨折的小型射线照片测试集中表现出完美的准确性、灵敏度和特异性。该模型的性能优于人类专家观察者。临床意义深度学习可用于在X光片上自动识别Segond骨折,从而提高对容易漏诊的并发损伤(包括外侧半月板撕裂)的诊断率。Segond骨折的自动识别还有助于对这些骨折的发生率和临床意义进行大规模研究,从而改善膝关节损伤患者的管理和治疗效果。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
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
Segond Fractures Can Be Identified With Excellent Accuracy Utilizing Deep Learning on Anteroposterior Knee Radiographs

Purpose

To develop a deep learning model for the detection of Segond fractures on anteroposterior (AP) knee radiographs and to compare model performance to that of trained human experts.

Methods

AP knee radiographs were retrieved from the Hospital for Special Surgery ACL Registry, which enrolled patients between 2009 and 2013. All images corresponded to patients who underwent anterior cruciate ligament reconstruction by 1 of 23 surgeons included in the registry data. Images were categorized into 1 of 2 classes based on radiographic evidence of a Segond fracture and manually annotated. Seventy percent of the images were used to populate the training set, while 20% and 10% were reserved for the validation and test sets, respectively. Images from the test set were used to compare model performance to that of expert human observers, including an orthopaedic surgery sports medicine fellow and a fellowship-trained orthopaedic sports medicine surgeon with over 10 years of experience.

Results

A total of 324 AP knee radiographs were retrieved, of which 34 (10.4%) images demonstrated evidence of a Segond fracture. The overall mean average precision (mAP) was 0.985, and this was maintained on the Segond fracture class (mAP = 0.978, precision = 0.844, recall = 1). The model demonstrated 100% accuracy with perfect sensitivity and specificity when applied to the independent testing set and the ability to meet or exceed human sensitivity and specificity in all cases. Compared to an orthopaedic surgery sports medicine fellow, the model required 0.3% of the total time needed to evaluate and classify images in the independent test set.

Conclusions

A deep learning model was developed and internally validated for Segond fracture detection on AP radiographs and demonstrated perfect accuracy, sensitivity, and specificity on a small test set of radiographs with and without Segond fractures. The model demonstrated superior performance compared with expert human observers.

Clinical Relevance

Deep learning can be used for automated Segond fracture identification on radiographs, leading to improved diagnosis of easily missed concomitant injuries, including lateral meniscus tears. Automated identification of Segond fractures can also enable large-scale studies on the incidence and clinical significance of these fractures, which may lead to improved management and outcomes for patients with knee injuries.

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
CiteScore
2.70
自引率
0.00%
发文量
218
审稿时长
45 weeks
期刊最新文献
Continuous Meniscal Repair Technique Allows for Shorter Operative Time and Learning Curve Compared With Traditional Vertical Mattress Technique in Controlled Arthroscopic Training in Porcine Model Concomitant Popliteomeniscal Fascicles Tears Are Found in 21% of Professional Soccer Players With Acute Anterior Cruciate Ligament Injuries Mini-Open Technique for Gluteus Medius Tendon Repairs Is Associated With Low Complication Rates and Sustained Improvement in Patient Reported Outcomes at 2-Year Follow-Up The Top-20 Studies About Anterior Shoulder Instability From an Altmetric Analysis Had Higher Levels of Evidence Than Those From a Traditional Bibliometric Analysis Medial Patellofemoral Ligament Augmented With a Reinforced Bioinductive Implant Is Biomechanically Similar to the Native Medial Patellofemoral Ligament at Time Zero in a Cadaveric Model
×
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