{"title":"Effectiveness of Comprehensive Video Datasets","authors":"Tomohiko Waki MD, Yukina Sato BE, Kazuya Tsukamoto MD, Eriku Yamada MD, PhD, Akiko Yamamoto MD, PhD, Takuya Ibara PhD, Toru Sasaki MD, PhD, Tomoyuki Kuroiwa MD, PhD, Akimoto Nimura MD, PhD, Yuta Sugiura PhD, Koji Fujita MD, PhD, Toshitaka Yoshii MD, PhD","doi":"10.1002/jum.16619","DOIUrl":null,"url":null,"abstract":"<div>\n \n <section>\n \n <h3> Objectives</h3>\n \n <p>Advances in diagnosing carpal tunnel syndrome (CTS) using ultrasonography (US) and artificial intelligence (AI) aim to replace nerve conduction studies. However, a method for accurate severity diagnosis remains unachieved. We explored the potential of comprehensive video data formats for constructing an effective model for diagnosing CTS severity.</p>\n </section>\n \n <section>\n \n <h3> Methods</h3>\n \n <p>We studied 75 individuals (52 with CTS) from 2019 to 2022, categorizing them into 3 groups based on disease severity. We recorded 132 US videos of carpal tunnel during finger movement. Features of the median nerve (MN) were extracted from automatically segmented US video frames, from which 3 datasets were created: a comprehensive video dataset with full information, a key metrics dataset, and an initial frame dataset with the least information. We compared the accuracy of machine learning algorithms for classifying CTS severity into 3 groups across these datasets using 63-fold cross-validation.</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>The cross-sectional area of the MN correlated with severity (<i>P</i> < .05) but MN displacement did not. The algorithm using the comprehensive video dataset exhibited the highest sensitivity (1.00) and accuracy (0.75).</p>\n </section>\n \n <section>\n \n <h3> Conclusions</h3>\n \n <p>Our study demonstrated that utilizing comprehensive video data enables a more accurate US-based diagnosis of CTS severity. This underscores the value of capturing the patterns of MN deformation and movement, which cannot be captured by representative metrics such as medians or maximums. By further developing an AI model based on our findings, a simpler and painless method for assessing CTS severity can be achieved.</p>\n </section>\n </div>","PeriodicalId":17563,"journal":{"name":"Journal of Ultrasound in Medicine","volume":"44 3","pages":"557-566"},"PeriodicalIF":2.1000,"publicationDate":"2024-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/jum.16619","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Ultrasound in Medicine","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/jum.16619","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ACOUSTICS","Score":null,"Total":0}
引用次数: 0
Abstract
Objectives
Advances in diagnosing carpal tunnel syndrome (CTS) using ultrasonography (US) and artificial intelligence (AI) aim to replace nerve conduction studies. However, a method for accurate severity diagnosis remains unachieved. We explored the potential of comprehensive video data formats for constructing an effective model for diagnosing CTS severity.
Methods
We studied 75 individuals (52 with CTS) from 2019 to 2022, categorizing them into 3 groups based on disease severity. We recorded 132 US videos of carpal tunnel during finger movement. Features of the median nerve (MN) were extracted from automatically segmented US video frames, from which 3 datasets were created: a comprehensive video dataset with full information, a key metrics dataset, and an initial frame dataset with the least information. We compared the accuracy of machine learning algorithms for classifying CTS severity into 3 groups across these datasets using 63-fold cross-validation.
Results
The cross-sectional area of the MN correlated with severity (P < .05) but MN displacement did not. The algorithm using the comprehensive video dataset exhibited the highest sensitivity (1.00) and accuracy (0.75).
Conclusions
Our study demonstrated that utilizing comprehensive video data enables a more accurate US-based diagnosis of CTS severity. This underscores the value of capturing the patterns of MN deformation and movement, which cannot be captured by representative metrics such as medians or maximums. By further developing an AI model based on our findings, a simpler and painless method for assessing CTS severity can be achieved.
期刊介绍:
The Journal of Ultrasound in Medicine (JUM) is dedicated to the rapid, accurate publication of original articles dealing with all aspects of medical ultrasound, particularly its direct application to patient care but also relevant basic science, advances in instrumentation, and biological effects. The journal is an official publication of the American Institute of Ultrasound in Medicine and publishes articles in a variety of categories, including Original Research papers, Review Articles, Pictorial Essays, Technical Innovations, Case Series, Letters to the Editor, and more, from an international bevy of countries in a continual effort to showcase and promote advances in the ultrasound community.
Represented through these efforts are a wide variety of disciplines of ultrasound, including, but not limited to:
-Basic Science-
Breast Ultrasound-
Contrast-Enhanced Ultrasound-
Dermatology-
Echocardiography-
Elastography-
Emergency Medicine-
Fetal Echocardiography-
Gastrointestinal Ultrasound-
General and Abdominal Ultrasound-
Genitourinary Ultrasound-
Gynecologic Ultrasound-
Head and Neck Ultrasound-
High Frequency Clinical and Preclinical Imaging-
Interventional-Intraoperative Ultrasound-
Musculoskeletal Ultrasound-
Neurosonology-
Obstetric Ultrasound-
Ophthalmologic Ultrasound-
Pediatric Ultrasound-
Point-of-Care Ultrasound-
Public Policy-
Superficial Structures-
Therapeutic Ultrasound-
Ultrasound Education-
Ultrasound in Global Health-
Urologic Ultrasound-
Vascular Ultrasound