Characterizing hip joint morphology using a multitask deep learning model.

IF 1.4 4区 医学 Q3 ORTHOPEDICS
Journal of Hip Preservation Surgery Pub Date : 2024-12-12 eCollection Date: 2025-01-01 DOI:10.1093/jhps/hnae041
Bardia Khosravi, Lainey G Bukowiec, John P Mickley, Jacob F Oeding, Pouria Rouzrokh, Bradley J Erickson, Rafael J Sierra, Michael J Taunton, Emmanouil Grigoriou, Cody C Wyles
{"title":"Characterizing hip joint morphology using a multitask deep learning model.","authors":"Bardia Khosravi, Lainey G Bukowiec, John P Mickley, Jacob F Oeding, Pouria Rouzrokh, Bradley J Erickson, Rafael J Sierra, Michael J Taunton, Emmanouil Grigoriou, Cody C Wyles","doi":"10.1093/jhps/hnae041","DOIUrl":null,"url":null,"abstract":"<p><p>Deep learning is revolutionizing medical imaging analysis by enabling the classification of various pathoanatomical conditions at scale. Unfortunately, there have been a limited number of accurate and efficient machine learning (ML) algorithms that have been developed for the diagnostic workup of morphological hip pathologies, including developmental dysplasia of the hip and femoroacetabular impingement. The current study reports on the performance of a novel ML model with YOLOv5 and ConvNeXt-Tiny architecture in predicting the morphological features of these conditions, including cam deformity, ischial spine sign, dysplastic appearance, and other abnormalities. The model achieved 78.0% accuracy for detecting cam deformity, 87.2% for ischial spine sign, 76.6% for dysplasia, and 71.6% for all abnormalities combined. The model achieved an Area under the Receiver Operating Curve of 0.89 for ischial spine sign, 0.80 for cam deformity, 0.80 for dysplasia, and 0.81 for all abnormalities combined. Inter-rater agreement among surgeons, assessed using Gwet's AC1, was substantial for dysplasia (0.83) and all abnormalities (0.88), and moderate for ischial spine sign (0.75) and cam deformity (0.61).</p>","PeriodicalId":48583,"journal":{"name":"Journal of Hip Preservation Surgery","volume":"12 1","pages":"27-32"},"PeriodicalIF":1.4000,"publicationDate":"2024-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12051864/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Hip Preservation Surgery","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1093/jhps/hnae041","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"Q3","JCRName":"ORTHOPEDICS","Score":null,"Total":0}
引用次数: 0

Abstract

Deep learning is revolutionizing medical imaging analysis by enabling the classification of various pathoanatomical conditions at scale. Unfortunately, there have been a limited number of accurate and efficient machine learning (ML) algorithms that have been developed for the diagnostic workup of morphological hip pathologies, including developmental dysplasia of the hip and femoroacetabular impingement. The current study reports on the performance of a novel ML model with YOLOv5 and ConvNeXt-Tiny architecture in predicting the morphological features of these conditions, including cam deformity, ischial spine sign, dysplastic appearance, and other abnormalities. The model achieved 78.0% accuracy for detecting cam deformity, 87.2% for ischial spine sign, 76.6% for dysplasia, and 71.6% for all abnormalities combined. The model achieved an Area under the Receiver Operating Curve of 0.89 for ischial spine sign, 0.80 for cam deformity, 0.80 for dysplasia, and 0.81 for all abnormalities combined. Inter-rater agreement among surgeons, assessed using Gwet's AC1, was substantial for dysplasia (0.83) and all abnormalities (0.88), and moderate for ischial spine sign (0.75) and cam deformity (0.61).

使用多任务深度学习模型表征髋关节形态。
深度学习通过对各种病理解剖条件进行大规模分类,正在彻底改变医学成像分析。不幸的是,用于诊断髋关节形态学病变(包括髋关节发育不良和股髋臼撞击)的准确、高效的机器学习(ML)算法数量有限。目前的研究报告了一种具有YOLOv5和ConvNeXt-Tiny结构的新型ML模型在预测这些疾病的形态学特征方面的性能,包括cam畸形、坐骨棘征象、发育不良外观和其他异常。该模型对凸轮畸形的检测准确率为78.0%,对坐骨棘征象的检测准确率为87.2%,对发育不良的检测准确率为76.6%,对所有异常的综合检测准确率为71.6%。该模型的受者操作曲线下面积为坐骨棘征0.89,凸轮畸形0.80,发育不良0.80,所有异常综合0.81。使用Gwet的AC1评估,外科医生之间的评分一致性对发育不良(0.83)和所有异常(0.88)有很大的一致性,对坐骨棘征象(0.75)和脊柱畸形(0.61)有中等程度的一致性。
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 求助全文
来源期刊
自引率
20.00%
发文量
45
审稿时长
12 weeks
×
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