目标:医学研究面临着由专家间差异和机器提取标签等因素引起的噪声标签带来的重大挑战。尽管如此,标签噪声管理的采用仍然有限,标签噪声在很大程度上被忽视。为此,迫切需要进行一项聚焦于该问题空间的范围综述。本范围综述旨在全面回顾基于深度学习的医学预测问题中的标签噪声管理,包括标签噪声检测、标签噪声处理和评估。涉及标签不确定性的研究也被纳入其中。方法:我们的范围综述遵循系统综述和荟萃分析的首选报告项目(PRISMA)指南。我们检索了4个数据库,包括PubMed、IEEE Xplore、Google Scholar和Semantic Scholar。我们的检索词包括“noisy label AND medical / healthcare / clinical”、“un-certainty AND medical / healthcare / clinical”和“noise AND medical / healthcare / clinical”。结果:在2016年至2023年间,共有60篇论文符合纳入标准。我们调查了医学研究中的一系列实际问题,包括标签噪声的来源、标签噪声的影响、标签噪声的检测、标签噪声处理技术及其评估。提供了标签噪声检测方法和处理技术的分类。讨论:从方法论的角度来看,我们观察到医学界一直与更广泛的深度学习界保持同步,因为大多数技术都已在医学数据上进行了评估。我们建议将标签噪声视为医学研究中的标准元素,即使它不是专门用于处理噪声标签的。初始实验可以从易于实现的方法开始,例如噪声鲁棒损失函数、加权和课程学习。
英文摘要:
Objectives: Medical research faces substantial challenges from noisy labels attributed to factors like inter-expert variability and machine-extracted labels. Despite this, the adoption of label noise management remains limited, and label noise is largely ignored. To this end, there is a critical need to conduct a scoping review focusing on the problem space. This scoping review aims to comprehensively review label noise management in deep learning-based medical prediction problems, which includes label noise detection, label noise handling, and evaluation. Research involving label uncertainty is also included.
Methods: Our scoping review follows the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. We searched 4 databases, including PubMed, IEEE Xplore, Google Scholar, and Semantic Scholar. Our search terms include "noisy label AND medical / healthcare / clinical", "un-certainty AND medical / healthcare / clinical", and "noise AND medical / healthcare / clinical".
Results: A total of 60 papers met inclusion criteria between 2016 and 2023. A series of practical questions in medical research are investigated. These include the sources of label noise, the impact of label noise, the detection of label noise, label noise handling techniques, and their evaluation. Categorization of both label noise detection methods and handling techniques are provided.
Discussion: From a methodological perspective, we observe that the medical community has been up to date with the broader deep-learning community, given that most techniques have been evaluated on medical data. We recommend considering label noise as a standard element in medical research, even if it is not dedicated to handling noisy labels. Initial experiments can start with easy-to-implement methods, such as noise-robust loss functions, weighting, and curriculum learning.
Deep Learning for Longitudinal Medical Imaging: A Scoping Review
Mass General Brigham(麻省总医院布莱根医疗体系);Harvard Medical School(哈佛医学院);Dana-Farber Cancer Institute(丹娜-法伯癌症研究所);Brigham and Women’s Hospital(布莱根妇女医院);University of California, San Francisco(加州大学旧金山分校);Inselspital, Bern University Hospital(伯尔尼大学医院( Inselspital ));University of Bern(伯尔尼大学)
Differential privacy for medical deep learning: methods, tradeoffs, and deployment implications
Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg(埃朗根-纽伦堡弗里德里希-亚历山大大学模式识别实验室);Department of Diagnostic and Interventional Radiology, University Hospital RWTH Aachen(亚琛大学诊断与介入放射科);Department of Radiology, Stanford University(斯坦福大学放射科);Department of Urology, Stanford University(斯坦福大学泌尿科)
RelativeFlow: Taming Medical Image Denoising Learning with Noisy Reference
School of Computer Science and Engineering, Southeast University, China(东南大学计算机科学与工程学院,中国);Department of Biomedical Engineering, Case Western Reserve University, USA(凯斯西储大学生物医学工程系,美国);School of Instrument Science and Engineering, Southeast University, China(东南大学仪器科学与工程学院,中国);Department of Optical Sciences, University of Arizona, USA(亚利桑那大学光学科学系,美国)
Federated and distributed learning applications for electronic health records and structured medical data: A scoping review
Duke-NUS Medical School(杜克-新加坡国立大学医学院);National Dental Research Institute Singapore(新加坡国家牙科研究所);National Dental Centre Singapore(新加坡国家牙科中心);Oral Health Academic Clinical Programme, Duke-NUS Medical School(杜克-新加坡国立大学医学院口腔健康学术临床项目);Programme in Health Services and Systems Research, Duke-NUS Medical School(杜克-新加坡国立大学医学院卫生服务与系统研究项目);National University of Singapore(新加坡国立大学);Duke University(杜克大学);Singapore National Eye Centre(新加坡国家眼科中心);Singapore Eye Research Institute(新加坡眼科研究所);Imperial College London(伦敦帝国理工学院);Singapore General Hospital(新加坡中央医院);Institute of Data Science, National University of Singapore(新加坡国立大学数据科学研究院)
Prompt engineering paradigms for medical applications: scoping review and recommendations for better practices
Geneva University Hospitals(日内瓦大学医院);University of Geneva(日内瓦大学);Université Paris-Saclay(巴黎萨克雷大学);CNRS(法国国家科学研究中心);Sorbonne Université(索邦大学);INSERM(法国国家健康与医学研究院);Université Sorbonne Paris-Nord(索邦巴黎北大学)
Navigating the landscape of multimodal AI in medicine: a scoping review on technical challenges and clinical applications
Radboud University Medical Center(拉德堡德大学医学中心);Oncode Institute(Oncode研究所);Polytechnic University of Turin(都灵理工大学);University of Turin(都灵大学);Erasmus University Medical Centre(伊拉斯姆斯大学医学中心)
Stochastic Parrots or ICU Experts? Large Language Models in Critical Care Medicine: A Scoping Review
National Institute of Health Data Science, Peking University(北京大学健康医疗大数据国家研究院);Institute of Medical Technology, Peking University Health Science Center(北京大学医学部医学技术研究院);Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院);Advanced Institute of Information Technology, Peking University(北京大学信息技术高等研究院);Peking University Third Hospital(北京大学第三医院);University of Liverpool(利物浦大学);Johns Hopkins School of Medicine(约翰斯·霍普金斯大学医学院);University of California, Los Angeles(加州大学洛杉矶分校);Peking University People’s Hospital(北京大学人民医院)
Bridging Data Gaps in Healthcare: A Scoping Review of Transfer Learning in Biomedical Data Analysis
Duke-NUS Medical School(杜克-新加坡国立大学医学院);Duke University(杜克大学);Singapore General Hospital(新加坡中央医院);Columbia University Mailman School of Public Health(哥伦比亚大学梅尔曼公共卫生学院);National University of Singapore(新加坡国立大学)
A Review on Generative AI Models for Synthetic Medical Text, Time Series, and Longitudinal Data
Mälardalen University(梅拉达伦大学);Servicehälsan Familjeläkare i Västerås AB(韦斯特罗斯家庭医生服务公司);Turku University of Applied Sciences(图尔库应用科技大学);Linköping University(林雪平大学)
How does self-supervised pretraining improve robustness against noisy labels across various medical image classification datasets?
Center for Imaging Science, RIT(罗切斯特理工学院成像科学中心);University of Aberdeen(阿伯丁大学);NepAl Applied Mathematics and Informatics Institute for Research (NAAMII)(尼泊尔应用数学与信息学研究所);Biomedical Engineering, RIT(罗切斯特理工学院生物医学工程系)
Active Label Refinement for Robust Training of Imbalanced Medical Image Classification Tasks in the Presence of High Label Noise
Center for Imaging Science, Rochester Institute of Technology(罗切斯特理工学院成像科学中心);University of Aberdeen(阿伯丁大学);Biomedical Engineering, Rochester Institute of Technology(罗切斯特理工学院生物医学工程系)
Consensus Neural Network for Medical Imaging Denoising with Only Noisy Training Samples
Center for Advanced Medical Computing and Analysis, Massachusetts General Hospital and Harvard Medical School(麻省总医院与哈佛医学院高级医学计算与分析中心);Gordon Center for Medical Imaging, Massachusetts General Hospital and Harvard Medical School(麻省总医院与哈佛医学院戈登医学成像中心)
FedGSCA: Medical Federated Learning with Global Sample Selector and Client Adaptive Adjuster under Label Noise
Academy for Engineering and Technology, Fudan University(复旦大学工程学院);School of Computer Science, China University of Geosciences(中国地质大学(武汉)计算机学院);College of Science, Beijing Forestry University(北京林业大学理学院)
BoMD: Bag of Multi-label Descriptors for Noisy Chest X-ray Classification
Australian Institute for Machine Learning, University of Adelaide(阿德莱德大学澳大利亚机器学习研究所);Harvard Medical School, Harvard University(哈佛医学院);Centre for Vision, Speech and Signal Processing, University of Surrey(萨里大学视觉、语音与信号处理中心)
ProCNS: Progressive Prototype Calibration and Noise Suppression for Weakly-Supervised Medical Image Segmentation
Southern University of Science and Technology(南方科技大学);University of Hong Kong(香港大学);Jiaxing Research Institute, Southern University of Science and Technology(南方科技大学嘉兴研究院)
Pick-and-Learn: Automatic Quality Evaluation for Noisy-Labeled Image Segmentation
Department of Electronic Engineering, Tsinghua University, Beijing, China(中国北京清华大学电子工程系);Institute for Precision Medicine, Tsinghua University, Beijing, China(中国北京清华大学精准医学研究院)