Exploring the Effect of Domain-Specific Transfer Learning for Thyroid Nodule Classification

IF 4 3区 医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING
Sanaz Vahdati MD , Bardia Khosravi MD, MPH, MHPE , Pouria Rouzrokh MD, MPH, MHPE , Bradley J. Erickson MD, PhD
{"title":"Exploring the Effect of Domain-Specific Transfer Learning for Thyroid Nodule Classification","authors":"Sanaz Vahdati MD , Bardia Khosravi MD, MPH, MHPE , Pouria Rouzrokh MD, MPH, MHPE , Bradley J. Erickson MD, PhD","doi":"10.1016/j.jacr.2024.06.011","DOIUrl":null,"url":null,"abstract":"","PeriodicalId":49044,"journal":{"name":"Journal of the American College of Radiology","volume":"21 11","pages":"Pages 1796-1799"},"PeriodicalIF":4.0000,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of the American College of Radiology","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1546144024005350","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0
探索特定领域迁移学习对甲状腺结节分类的影响。
使用超声波评估甲状腺结节依赖于放射科医生的经验,但深度学习(DL)模型可以提高阅片师之间的一致性。针对小数据集的医学成像开发深度学习模型具有挑战性。迁移学习是一种用于开发 DL 模型的技术,可在数据有限的情况下提高模型性能。在这里,我们利用特定领域的 RadImageNet 数据集和非医学 ImageNet 数据集研究了迁移学习对甲状腺结节良恶性分类的稳健性的影响。我们回顾性地收集了本研究所接受细针穿刺术的甲状腺结节患者的 822 张超声图像。我们对数据进行了拆分,将 101 个病例作为测试集,721 个病例作为交叉验证集。我们训练了一个 Resnet-18 模型,将甲状腺结节分为良性和恶性。然后,我们使用从 ImageNet 和 RadImageNet 转移的权重训练了相同的模型架构。没有转移学习的甲状腺结节分类模型的 AUROC 为 0.69。使用 ImageNet 预训练权重进行迁移学习后,我们模型的 AUROC 为 0.79。通过对 RadImageNet 预训练权重的迁移学习,我们的模型达到了 0.83 的 AUROC。在对 ImageNet 进行迁移学习(p 值 = 0.03)和对 RadImageNet 进行迁移学习(p 值 = 0.03)后,未进行迁移学习的分类模型的 AUROC 有了明显改善。
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
Journal of the American College of Radiology
Journal of the American College of Radiology RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING-
CiteScore
6.30
自引率
8.90%
发文量
312
审稿时长
34 days
期刊介绍: The official journal of the American College of Radiology, JACR informs its readers of timely, pertinent, and important topics affecting the practice of diagnostic radiologists, interventional radiologists, medical physicists, and radiation oncologists. In so doing, JACR improves their practices and helps optimize their role in the health care system. By providing a forum for informative, well-written articles on health policy, clinical practice, practice management, data science, and education, JACR engages readers in a dialogue that ultimately benefits patient care.
×
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