理解基于人工智能的放射学研究：什么是过拟合？
Understanding artificial intelligence based radiology studies: What is overfitting?
机构信息
Columbia University Medical Center, New York Presbyterian Hospital, 622 West 168th Street, PB-1-301, New York, NY 10032, United States of America.
出版信息
Clin Imaging. 2020 Sep;65:96-99. doi: 10.1016/j.clinimag.2020.04.025. Epub 2020 Apr 23.
Abstract
Artificial intelligence (AI) is a broad umbrella term used to encompass a wide variety of subfields dedicated to creating algorithms to perform tasks that mimic human intelligence. As AI development grows closer to clinical integration, radiologists will need to become familiar with the principles of artificial intelligence to properly evaluate and use this powerful tool. This series aims to explain certain basic concepts of artificial intelligence, and their applications in medical imaging starting with a concept of overfitting.
摘要
人工智能（AI）是一个广泛的术语，用于涵盖各种致力于创建算法以执行模拟人类智能任务的子领域。随着人工智能的发展越来越接近临床应用，放射科医生需要熟悉人工智能的原理，以便正确评估和使用这一强大工具。本系列旨在解释人工智能的某些基本概念及其在医学成像中的应用，首先是过拟合的概念。
相似文献
1
Understanding artificial intelligence based radiology studies: What is overfitting?理解基于人工智能的放射学研究：什么是过拟合？
Clin Imaging. 2020 Sep;65:96-99. doi: 10.1016/j.clinimag.2020.04.025. Epub 2020 Apr 23.
2
Understanding artificial intelligence based radiology studies: CNN architecture.理解基于人工智能的放射学研究：CNN 架构。
Clin Imaging. 2021 Dec;80:72-76. doi: 10.1016/j.clinimag.2021.06.033. Epub 2021 Jul 7.
3
Use of artificial intelligence in emergency radiology: An overview of current applications, challenges, and opportunities.人工智能在急诊放射学中的应用：当前应用、挑战和机遇概述。
Clin Imaging. 2022 Sep;89:61-67. doi: 10.1016/j.clinimag.2022.05.010. Epub 2022 May 30.
4
Integrating artificial intelligence into the clinical practice of radiology: challenges and recommendations.将人工智能融入放射科的临床实践：挑战与建议。
Eur Radiol. 2020 Jun;30(6):3576-3584. doi: 10.1007/s00330-020-06672-5. Epub 2020 Feb 17.
5
Artificial Intelligence in Lung Imaging.人工智能在肺部成像中的应用。
Semin Respir Crit Care Med. 2022 Dec;43(6):946-960. doi: 10.1055/s-0042-1755571. Epub 2022 Sep 29.
6
Artificial intelligence in emergency radiology: A review of applications and possibilities.急诊放射学中的人工智能：应用与可能性综述
Diagn Interv Imaging. 2023 Jan;104(1):6-10. doi: 10.1016/j.diii.2022.07.005. Epub 2022 Aug 4.
7
Canadian Association of Radiologists White Paper on Artificial Intelligence in Radiology.加拿大放射学家协会关于放射学人工智能的白皮书。
Can Assoc Radiol J. 2018 May;69(2):120-135. doi: 10.1016/j.carj.2018.02.002. Epub 2018 Apr 11.
8
Clinical applications of artificial intelligence in radiology.人工智能在放射学中的临床应用。
Br J Radiol. 2023 Oct;96(1150):20221031. doi: 10.1259/bjr.20221031. Epub 2023 Apr 26.
9
Artificial intelligence in cardiac radiology.人工智能在心脏放射学中的应用。
Radiol Med. 2020 Nov;125(11):1186-1199. doi: 10.1007/s11547-020-01277-w. Epub 2020 Sep 18.
10
Artificial Intelligence in Radiology: an introduction to the most important concepts.人工智能在放射学中的应用：介绍最重要的概念。
Radiologia (Engl Ed). 2022 May-Jun;64(3):228-236. doi: 10.1016/j.rxeng.2022.03.005.
引用本文的文献
1
Automated Real-time Assessment of Intracranial Hemorrhage Detection AI Using an Ensembled Monitoring Model (EMM).使用集成监测模型（EMM）对颅内出血检测人工智能进行自动实时评估
Res Sq. 2025 May 26:rs.3.rs-6683104. doi: 10.21203/rs.3.rs-6683104/v1.
2
Comparing Auto-Machine Learning and Expert-Designed Models in Diagnosing Vitreomacular Interface Disorders.比较自动机器学习和专家设计模型在诊断玻璃体黄斑界面疾病中的应用
J Clin Med. 2025 Apr 17;14(8):2774. doi: 10.3390/jcm14082774.
3
Revolutionizing total hip arthroplasty: The role of artificial intelligence and machine learning.全髋关节置换术的变革：人工智能与机器学习的作用。
J Exp Orthop. 2025 Mar 22;12(1):e70195. doi: 10.1002/jeo2.70195. eCollection 2025 Jan.
4
Development of artificial intelligence-based algorithms for the process of human identification through dental evidence.开发基于人工智能的算法，用于通过牙齿证据进行身份识别。
Int J Legal Med. 2025 Mar 6. doi: 10.1007/s00414-025-03453-x.
5
Overlooked and underpowered: a meta-research addressing sample size in radiomics prediction models for binary outcomes.被忽视且样本量不足：一项针对二元结局的放射组学预测模型样本量的元研究。
Eur Radiol. 2025 Mar;35(3):1146-1156. doi: 10.1007/s00330-024-11331-0. Epub 2025 Jan 9.
6
Band Visibility in High-Resolution Optical Coherence Tomography Assessed With a Custom Review Tool and Updated, Histology-Derived Nomenclature.使用定制的评估工具和更新的组织学衍生命名法评估高分辨率光学相干断层扫描中的带可见性。
Transl Vis Sci Technol. 2024 Dec 2;13(12):19. doi: 10.1167/tvst.13.12.19.
7
Comparative analysis of deep learning algorithms for dental caries detection and prediction from radiographic images: a comprehensive umbrella review.基于X线影像的深度学习算法用于龋齿检测和预测的比较分析：一项全面的系统综述
PeerJ Comput Sci. 2024 Nov 12;10:e2371. doi: 10.7717/peerj-cs.2371. eCollection 2024.
8
Diagnostic accuracy of radiomics and artificial intelligence models in diagnosing lymph node metastasis in head and neck cancers: a systematic review and meta-analysis.放射组学和人工智能模型在诊断头颈部癌淋巴结转移中的诊断准确性：一项系统评价和荟萃分析。
Neuroradiology. 2025 Feb;67(2):449-467. doi: 10.1007/s00234-024-03485-x. Epub 2024 Nov 11.
9
Adding the third dimension: 3D convolutional neural network diagnosis of temporal lobe epilepsy.增添第三维度：颞叶癫痫的三维卷积神经网络诊断
Brain Commun. 2024 Oct 10;6(5):fcae346. doi: 10.1093/braincomms/fcae346. eCollection 2024.
10
An early sepsis prediction model utilizing machine learning and unbalanced data processing in a clinical context.一种在临床环境中利用机器学习和不平衡数据处理的早期脓毒症预测模型。
Prev Med Rep. 2024 Aug 2;45:102841. doi: 10.1016/j.pmedr.2024.102841. eCollection 2024 Sep.
本文引用的文献
1
Transfer Learning Assisted Classification and Detection of Alzheimer's Disease Stages Using 3D MRI Scans.基于 3D MRI 扫描的迁移学习辅助阿尔茨海默病阶段分类与检测
Sensors (Basel). 2019 Jun 11;19(11):2645. doi: 10.3390/s19112645.
2
End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography.基于低剂量 CT 的三维深度学习肺癌全流程筛查。
Nat Med. 2019 Jun;25(6):954-961. doi: 10.1038/s41591-019-0447-x. Epub 2019 May 20.
3
A Roadmap for Foundational Research on Artificial Intelligence in Medical Imaging: From the 2018 NIH/RSNA/ACR/The Academy Workshop.人工智能在医学影像领域基础研究路线图：来自 2018 年 NIH/RSNA/ACR/美国学院联合研讨会
Radiology. 2019 Jun;291(3):781-791. doi: 10.1148/radiol.2019190613. Epub 2019 Apr 16.
4
Accuracy of Distinguishing Atypical Ductal Hyperplasia From Ductal Carcinoma In Situ With Convolutional Neural Network-Based Machine Learning Approach Using Mammographic Image Data.基于卷积神经网络的机器学习方法利用乳腺钼靶图像数据区分非典型导管增生与导管原位癌的准确性
AJR Am J Roentgenol. 2019 May;212(5):1166-1171. doi: 10.2214/AJR.18.20250. Epub 2019 Mar 12.
5
Explaining Deep Features Using Radiologist-Defined Semantic Features and Traditional Quantitative Features.使用放射科医生定义的语义特征和传统定量特征解释深度特征
Tomography. 2019 Mar;5(1):192-200. doi: 10.18383/j.tom.2018.00034.
6
Design Characteristics of Studies Reporting the Performance of Artificial Intelligence Algorithms for Diagnostic Analysis of Medical Images: Results from Recently Published Papers.研究报告用于医学图像诊断分析的人工智能算法性能的设计特点：近期发表论文的结果。
Korean J Radiol. 2019 Mar;20(3):405-410. doi: 10.3348/kjr.2019.0025.
7
Predicting Breast Cancer Molecular Subtype with MRI Dataset Utilizing Convolutional Neural Network Algorithm.利用卷积神经网络算法对 MRI 数据集进行乳腺癌分子亚型预测。
J Digit Imaging. 2019 Apr;32(2):276-282. doi: 10.1007/s10278-019-00179-2.
8
Deep learning in radiology: An overview of the concepts and a survey of the state of the art with focus on MRI.深度学习在放射学中的应用：概念概述及磁共振成像技术的研究现状综述。
J Magn Reson Imaging. 2019 Apr;49(4):939-954. doi: 10.1002/jmri.26534. Epub 2018 Dec 21.
9
Artificial Intelligence for Medical Image Analysis: A Guide for Authors and Reviewers.人工智能在医学图像分析中的应用：作者和审稿人指南。
AJR Am J Roentgenol. 2019 Mar;212(3):513-519. doi: 10.2214/AJR.18.20490. Epub 2018 Dec 17.
10
Deep learning and artificial intelligence in radiology: Current applications and future directions.放射学中的深度学习与人工智能：当前应用及未来方向。
PLoS Med. 2018 Nov 30;15(11):e1002707. doi: 10.1371/journal.pmed.1002707. eCollection 2018 Nov.
Zotero 插件