Artificial Intelligence-Assisted Diagnosis of Anterior Cruciate Ligament Tears From Magnetic Resonance Images: Algorithm Development and Validation Study.

IF 1.2 Q3 INFORMATION SCIENCE & LIBRARY SCIENCE PUBLISHING RESEARCH QUARTERLY Pub Date : 2022-07-26 DOI:10.2196/37508
Kun-Hui Chen, Chih-Yu Yang, Hsin-Yi Wang, Hsiao-Li Ma, Oscar Kuang-Sheng Lee
{"title":"Artificial Intelligence-Assisted Diagnosis of Anterior Cruciate Ligament Tears From Magnetic Resonance Images: Algorithm Development and Validation Study.","authors":"Kun-Hui Chen, Chih-Yu Yang, Hsin-Yi Wang, Hsiao-Li Ma, Oscar Kuang-Sheng Lee","doi":"10.2196/37508","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Anterior cruciate ligament (ACL) injuries are common in sports and are critical knee injuries that require prompt diagnosis. Magnetic resonance imaging (MRI) is a strong, noninvasive tool for detecting ACL tears, which requires training to read accurately. Clinicians with different experiences in reading MR images require different information for the diagnosis of ACL tears. Artificial intelligence (AI) image processing could be a promising approach in the diagnosis of ACL tears.</p><p><strong>Objective: </strong>This study sought to use AI to (1) diagnose ACL tears from complete MR images, (2) identify torn-ACL images from complete MR images with a diagnosis of ACL tears, and (3) differentiate intact-ACL and torn-ACL MR images from the selected MR images.</p><p><strong>Methods: </strong>The sagittal MR images of torn ACL (n=1205) and intact ACL (n=1018) from 800 cases and the complete knee MR images of 200 cases (100 torn ACL and 100 intact ACL) from patients aged 20-40 years were retrospectively collected. An AI approach using a convolutional neural network was applied to build models for the objective. The MR images of 200 independent cases (100 torn ACL and 100 intact ACL) were used as the test set for the models. The MR images of 40 randomly selected cases from the test set were used to compare the reading accuracy of ACL tears between the trained model and clinicians with different levels of experience.</p><p><strong>Results: </strong>The first model differentiated between torn-ACL, intact-ACL, and other images from complete MR images with an accuracy of 0.9946, and the sensitivity, specificity, precision, and F1-score were 0.9344, 0.9743, 0.8659, and 0.8980, respectively. The final accuracy for ACL-tear diagnosis was 0.96. The model showed a significantly higher reading accuracy than less experienced clinicians. The second model identified torn-ACL images from complete MR images with a diagnosis of ACL tear with an accuracy of 0.9943, and the sensitivity, specificity, precision, and F1-score were 0.9154, 0.9660, 0.8167, and 0.8632, respectively. The third model differentiated torn- and intact-ACL images with an accuracy of 0.9691, and the sensitivity, specificity, precision, and F1-score were 0.9827, 0.9519, 0.9632, and 0.9728, respectively.</p><p><strong>Conclusions: </strong>This study demonstrates the feasibility of using an AI approach to provide information to clinicians who need different information from MRI to diagnose ACL tears.</p>","PeriodicalId":44970,"journal":{"name":"PUBLISHING RESEARCH QUARTERLY","volume":"28 1","pages":"e37508"},"PeriodicalIF":1.2000,"publicationDate":"2022-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11135221/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"PUBLISHING RESEARCH QUARTERLY","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2196/37508","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"INFORMATION SCIENCE & LIBRARY SCIENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Background: Anterior cruciate ligament (ACL) injuries are common in sports and are critical knee injuries that require prompt diagnosis. Magnetic resonance imaging (MRI) is a strong, noninvasive tool for detecting ACL tears, which requires training to read accurately. Clinicians with different experiences in reading MR images require different information for the diagnosis of ACL tears. Artificial intelligence (AI) image processing could be a promising approach in the diagnosis of ACL tears.

Objective: This study sought to use AI to (1) diagnose ACL tears from complete MR images, (2) identify torn-ACL images from complete MR images with a diagnosis of ACL tears, and (3) differentiate intact-ACL and torn-ACL MR images from the selected MR images.

Methods: The sagittal MR images of torn ACL (n=1205) and intact ACL (n=1018) from 800 cases and the complete knee MR images of 200 cases (100 torn ACL and 100 intact ACL) from patients aged 20-40 years were retrospectively collected. An AI approach using a convolutional neural network was applied to build models for the objective. The MR images of 200 independent cases (100 torn ACL and 100 intact ACL) were used as the test set for the models. The MR images of 40 randomly selected cases from the test set were used to compare the reading accuracy of ACL tears between the trained model and clinicians with different levels of experience.

Results: The first model differentiated between torn-ACL, intact-ACL, and other images from complete MR images with an accuracy of 0.9946, and the sensitivity, specificity, precision, and F1-score were 0.9344, 0.9743, 0.8659, and 0.8980, respectively. The final accuracy for ACL-tear diagnosis was 0.96. The model showed a significantly higher reading accuracy than less experienced clinicians. The second model identified torn-ACL images from complete MR images with a diagnosis of ACL tear with an accuracy of 0.9943, and the sensitivity, specificity, precision, and F1-score were 0.9154, 0.9660, 0.8167, and 0.8632, respectively. The third model differentiated torn- and intact-ACL images with an accuracy of 0.9691, and the sensitivity, specificity, precision, and F1-score were 0.9827, 0.9519, 0.9632, and 0.9728, respectively.

Conclusions: This study demonstrates the feasibility of using an AI approach to provide information to clinicians who need different information from MRI to diagnose ACL tears.

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
人工智能辅助诊断磁共振图像中的前交叉韧带撕裂:算法开发与验证研究。
背景:前交叉韧带(ACL)损伤在运动中很常见,是需要及时诊断的关键膝关节损伤。磁共振成像(MRI)是检测前交叉韧带撕裂的强有力的无创工具,但需要经过培训才能准确读取。具有不同磁共振成像阅读经验的临床医生需要不同的信息来诊断前交叉韧带撕裂。人工智能(AI)图像处理可能是诊断前交叉韧带撕裂的一种有前途的方法:本研究试图利用人工智能:(1) 从完整的 MR 图像中诊断前交叉韧带撕裂;(2) 从诊断为前交叉韧带撕裂的完整 MR 图像中识别撕裂-前交叉韧带图像;(3) 从选定的 MR 图像中区分完整-前交叉韧带和撕裂-前交叉韧带 MR 图像:方法:回顾性收集了 800 例前交叉韧带撕裂(n=1205)和完整前交叉韧带(n=1018)的矢状面 MR 图像,以及 200 例膝关节完整 MR 图像(100 例前交叉韧带撕裂和 100 例完整前交叉韧带),患者年龄在 20-40 岁之间。采用卷积神经网络的人工智能方法来建立目标模型。200 个独立病例(100 个撕裂的前十字韧带和 100 个完整的前十字韧带)的 MR 图像被用作模型的测试集。从测试集中随机抽取 40 个病例的 MR 图像,用于比较训练有素的模型和具有不同经验水平的临床医生对前交叉韧带撕裂的判读准确性:第一个模型从完整的 MR 图像中区分前交叉韧带撕裂、完整前交叉韧带撕裂和其他图像的准确率为 0.9946,灵敏度、特异性、精确度和 F1 分数分别为 0.9344、0.9743、0.8659 和 0.8980。前交叉韧带撕裂诊断的最终准确率为 0.96。该模型的读取准确率明显高于经验不足的临床医生。第二个模型从完整的 MR 图像中识别出前交叉韧带撕裂图像,诊断准确率为 0.9943,灵敏度、特异性、精确度和 F1 分数分别为 0.9154、0.9660、0.8167 和 0.8632。第三个模型区分撕裂和完好 ACL 图像的准确率为 0.9691,灵敏度、特异性、精确度和 F1 分数分别为 0.9827、0.9519、0.9632 和 0.9728:这项研究证明了使用人工智能方法为临床医生提供信息的可行性,因为临床医生需要从核磁共振成像中获得不同的信息来诊断前交叉韧带撕裂。
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
PUBLISHING RESEARCH QUARTERLY
PUBLISHING RESEARCH QUARTERLY INFORMATION SCIENCE & LIBRARY SCIENCE-
CiteScore
2.20
自引率
22.20%
发文量
75
期刊介绍: Publishing Research Quarterly is an international forum for the publication of original peer-reviewed papers covering significant research on and analyses of the full range of the publishing environment. The journal provides analysis of content development, production, distribution, and marketing of books, magazines, journals, and online information services in relation to the social, political, economic, and technological conditions that shape the publishing process, extending from editorial decision-making to order processing to print and online delivery.  Publishing Research Quarterly publishes significant research reports and analyses of industry trends, covering topics such as product development, marketing, financial aspects, and print and online distribution as well as the relationship between publishing activities and publishing’s constituencies among industry, government, and consumer communities. Scholarly articles, research reports, review papers, essays, surveys, memoirs, statistics, letters, and notes that contribute to knowledge about how different sectors of the publishing industry operate are published as well as book reviews.
期刊最新文献
Authors’ Satisfaction with the Publishing Procedures of the Uongozi Journal of Management Development Dynamics Analyzing the Degree of Changes in Indexed Journals: The Case of SJR Database Trauma in Publishing This Book is Written by ChatGPT: A Quantitative Analysis of ChatGPT Authorships Through Amazon.com The Unnoticed Issue of Coercive Citation Behavior for Authors
×
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