医学中可靠人工智能的数据特征描述
Data Characterization for Reliable AI in Medicine.
作者信息
Rajaraman Sivaramakrishnan, Zamzmi Ghada, Yang Feng, Xue Zhiyun, Antani Sameer K
机构信息
Computational Health Research Branch, National Library of Medicine, National Institutes of Health, Bethesda MD 20894, USA.
出版信息
Recent Trends Image Process Pattern Recogn (2022). 2023;1704:3-11. doi: 10.1007/978-3-031-23599-3_1. Epub 2023 Jan 11.
Abstract
Research in Artificial Intelligence (AI)-based medical computer vision algorithms bear promises to improve disease screening, diagnosis, and subsequently patient care. However, these algorithms are highly impacted by the characteristics of the underlying data. In this work, we discuss various data characteristics, namely , and that impact the design, reliability, and evolution of machine learning in medical computer vision. Further, we discuss each characteristic and the recent works conducted in our research lab that informed our understanding of the impact of these characteristics on the design of medical decision-making algorithms and outcome reliability.
摘要
基于人工智能（AI）的医学计算机视觉算法的研究有望改善疾病筛查、诊断以及后续的患者护理。然而，这些算法受到基础数据特征的极大影响。在这项工作中，我们讨论了各种数据特征，即[此处原文缺失具体特征内容]，这些特征会影响医学计算机视觉中机器学习的设计、可靠性和发展。此外，我们还讨论了每个特征以及我们研究实验室最近开展的工作，这些工作使我们了解了这些特征对医学决策算法设计和结果可靠性的影响。
相似文献
1
Data Characterization for Reliable AI in Medicine.医学中可靠人工智能的数据特征描述
Recent Trends Image Process Pattern Recogn (2022). 2023;1704:3-11. doi: 10.1007/978-3-031-23599-3_1. Epub 2023 Jan 11.
2
Promoting Artificial Intelligence for Global Breast Cancer Risk Prediction and Screening in Adult Women: A Scoping Review.促进人工智能用于成年女性全球乳腺癌风险预测与筛查：一项范围综述
J Clin Med. 2024 Apr 25;13(9):2525. doi: 10.3390/jcm13092525.
3
AAPM task group report 273: Recommendations on best practices for AI and machine learning for computer-aided diagnosis in medical imaging.AAPM 工作组报告 273：关于医学影像计算机辅助诊断中人工智能和机器学习的最佳实践建议。
Med Phys. 2023 Feb;50(2):e1-e24. doi: 10.1002/mp.16188. Epub 2023 Jan 6.
4
Machine learning in medicine: what clinicians should know.机器学习在医学中的应用：临床医生应该了解的知识。
Singapore Med J. 2023 Feb;64(2):91-97. doi: 10.11622/smedj.2021054. Epub 2021 May 19.
5
Artificial intelligence for breast cancer detection and its health technology assessment: A scoping review.用于乳腺癌检测的人工智能及其健康技术评估：一项范围综述。
Comput Biol Med. 2025 Jan;184:109391. doi: 10.1016/j.compbiomed.2024.109391. Epub 2024 Nov 22.
6
Nongenerative Artificial Intelligence in Medicine: Advancements and Applications in Supervised and Unsupervised Machine Learning.医学中的非生成式人工智能：监督式和非监督式机器学习的进展与应用
Mod Pathol. 2025 Mar;38(3):100680. doi: 10.1016/j.modpat.2024.100680. Epub 2024 Dec 13.
7
The Medicine Revolution Through Artificial Intelligence: Ethical Challenges of Machine Learning Algorithms in Decision-Making.通过人工智能实现的医学革命：机器学习算法在决策中的伦理挑战
Cureus. 2024 Sep 14;16(9):e69405. doi: 10.7759/cureus.69405. eCollection 2024 Sep.
8
Consensus statements on the current landscape of artificial intelligence applications in endoscopy, addressing roadblocks, and advancing artificial intelligence in gastroenterology.关于人工智能在内窥镜检查中的当前应用情况、解决障碍以及推动胃肠病学领域人工智能发展的共识声明。
Gastrointest Endosc. 2025 Jan;101(1):2-9.e1. doi: 10.1016/j.gie.2023.12.003. Epub 2024 Apr 17.
9
Future Medical Artificial Intelligence Application Requirements and Expectations of Physicians in German University Hospitals: Web-Based Survey.德国大学医院的未来医学人工智能应用要求和医生期望：基于网络的调查。
J Med Internet Res. 2021 Mar 5;23(3):e26646. doi: 10.2196/26646.
10
Artificial Intelligence-Assisted Gastroenterology- Promises and Pitfalls.人工智能辅助消化内镜学：前景与挑战。
Am J Gastroenterol. 2019 Mar;114(3):422-428. doi: 10.1038/s41395-018-0268-4.
引用本文的文献
1
Editorial on Special Issue "Artificial Intelligence in Image-Based Screening, Diagnostics, and Clinical Care".关于“基于图像的筛查、诊断和临床护理中的人工智能”特刊的社论
Diagnostics (Basel). 2024 Sep 7;14(17):1984. doi: 10.3390/diagnostics14171984.
2
Cleaning and Harmonizing Medical Image Data for Reliable AI: Lessons Learned from Longitudinal Oral Cancer Natural History Study Data.为可靠的人工智能清理和协调医学图像数据：从纵向口腔癌自然史研究数据中吸取的经验教训。
Proc SPIE Int Soc Opt Eng. 2024 Feb;12931. doi: 10.1117/12.3005875. Epub 2024 Apr 2.
3
Cross Dataset Analysis of Domain Shift in CXR Lung Region Detection.胸部X光肺部区域检测中域转移的跨数据集分析
Diagnostics (Basel). 2023 Mar 11;13(6):1068. doi: 10.3390/diagnostics13061068.
本文引用的文献
1
UMS-Rep: Unified modality-specific representation for efficient medical image analysis.UMS-Rep：用于高效医学图像分析的统一模态特定表示
Inform Med Unlocked. 2021;24. doi: 10.1016/j.imu.2021.100571. Epub 2021 Apr 20.
2
Deep Cervix Model Development from Heterogeneous and Partially Labeled Image Datasets.基于异构和部分标记图像数据集的深部宫颈模型开发
Front ICT Healthc (2002). 2023;519:679-688. doi: 10.1007/978-981-19-5191-6_55. Epub 2023 Apr 25.
3
Open World Active Learning for Echocardiography View Classification.用于超声心动图视图分类的开放世界主动学习
Proc SPIE Int Soc Opt Eng. 2022 Feb-Mar;12033. doi: 10.1117/12.2612578. Epub 2022 Apr 4.
4
Annotations of Lung Abnormalities in Shenzhen Chest X-ray Dataset for Computer-Aided Screening of Pulmonary Diseases.用于肺部疾病计算机辅助筛查的深圳胸部X光数据集肺部异常标注
Data (Basel). 2022 Jul;7(7). doi: 10.3390/data7070095. Epub 2022 Jul 13.
5
Image Quality Classification for Automated Visual Evaluation of Cervical Precancer.用于子宫颈癌前病变自动视觉评估的图像质量分类
Med Image Learn Ltd Noisy Data (2022). 2022 Sep;13559:206-217. doi: 10.1007/978-3-031-16760-7_20. Epub 2022 Sep 15.
6
Real-time echocardiography image analysis and quantification of cardiac indices.实时超声心动图图像分析和心功能指数的定量评估。
Med Image Anal. 2022 Aug;80:102438. doi: 10.1016/j.media.2022.102438. Epub 2022 Jun 9.
7
Analysis of digital noise and reduction methods on classifiers used in automated visual evaluation in cervical cancer screening.宫颈癌筛查中自动视觉评估所用分类器的数字噪声分析及降噪方法
Proc SPIE Int Soc Opt Eng. 2022 Jan-Feb;11950. doi: 10.1117/12.2610235. Epub 2022 Mar 2.
8
A Deep Clustering Method For Analyzing Uterine Cervix Images Across Imaging Devices.一种用于跨成像设备分析子宫颈图像的深度聚类方法。
Proc IEEE Int Symp Comput Based Med Syst. 2021 Jun;2021:527-532. doi: 10.1109/cbms52027.2021.00085. Epub 2021 Jul 12.
9
Detecting Tuberculosis-Consistent Findings in Lateral Chest X-Rays Using an Ensemble of CNNs and Vision Transformers.使用卷积神经网络（CNN）和视觉Transformer的集成在胸部侧位X光片中检测与肺结核一致的表现。
Front Genet. 2022 Feb 24;13:864724. doi: 10.3389/fgene.2022.864724. eCollection 2022.
10
Differentiating between drug-sensitive and drug-resistant tuberculosis with machine learning for clinical and radiological features.利用机器学习根据临床和放射学特征鉴别药物敏感型和耐药型肺结核。
Quant Imaging Med Surg. 2022 Jan;12(1):675-687. doi: 10.21037/qims-21-290.
Zotero 插件