用胸部X射线图像进行转移学习模型的COVID-19患者的ICU入院的分类
Yun-Chi Lin1, Yu-Hua Dean Fang2,3
1Department of Biomedical Engineering, University of Alabama at Birmingham, Birmingham, AL 35294, USA.
Diagnostics (Basel, Switzerland)
|April 12, 2025
概括
人工智能 (AI) 模型改进了使用COVID-19胸部X射线预测重症监护室 (ICU) 住院的预测. 医学图像预训练和数据扩展提高了人工智能性能,帮助在疫情期间分配资源.
科学领域:
- 医学成像人工智能 医学成像人工智能
- 医疗保健中的深度学习
- 流行病的准备 流行病的准备
背景情况:
- 预测COVID-19患者的重症监护室 (ICU) 住院率对于大流行期间的资源配置至关重要.
- 为此任务开发人工智能 (AI) 模型是具有挑战性的,因为培训数据有限.
- 转移学习和数据增强是克服医疗AI数据短缺的关键策略.
研究的目的:
- 探索AI在数据有限的场景中用于ICU入院预测的模型开发策略.
- 利用转移学习和数据集扩展来提高AI模型性能,使用COVID-19患者的胸部X射线.
- 提高人工智能模型的准确性和效率,以便在传染病爆发期间进行早期干预和资源管理.
主要方法:
- 利用在自然图像和胸部X射线上预先训练的卷积神经网络 (CNN).
- 在有限的COVID-19肺部细分胸部X射线 (COVID-19-NY-SBU) 数据集上微调模型.
- 通过整合一个额外的数据集 (MIDRC-RICORD-1c) 与相关标签来解决数据稀缺问题,实施了数据集扩展战略.
主要成果:
- 与基线 (AUC 0.66) 相比,经过数据扩展的X射线预训练模型实现了更好的ICU入院分类性能 (AUC 0.77-0.78).
- 改进的模型显示增加了预测ICU入院的灵敏度 (58-62%) 和特异性 (78-80%).
- 梯度加权类激活映射 (Grad-CAM) 证实了对相关肺部区域的重点改进,减少了分心.
结论:
- 医疗图像特定的预训练和战略数据集扩展显著提高AI模型在医学成像中的性能.
- 这种方法展示了利用多样化,有限的数据源来克服医疗保健中的AI模型开发挑战的潜力.
- 开发的AI模型和培训策略可以在未来的传染性呼吸道疾病爆发期间改善患者管理和资源分配.
关键词:
在 COVID-19 疫情中,密集的网络121这是Grad-CAM.接受ICU治疗的患者胸部X射线 胸部X射线 胸部X射线数据集扩展数据集扩展深度学习是一种深度学习.医疗图像分析分析转移学习转移学习更多相关视频
14:08Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
Published on: April 13, 2013
42.4K
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
8.2K
相关概念视频
01:30Radiological Investigation I: X-ray and CT
180
Radiological investigations, including X-rays and computed tomography (CT) scans, are critical for diagnosing and evaluating various medical conditions. These imaging techniques provide valuable insights into the body's internal structures, aiding in the detection of abnormalities, assessment of disease progression, and development of treatment strategies. This article delves into two primary radiological investigations, chest X-rays and CT scans, outlining their purpose, procedures, and...
180
01:20Imaging Studies for Cardiovascular System III: X-Ray
114
The most common cardiovascular diagnostic test is an X-ray. It produces images of the heart, blood vessels, and adjacent structures.
Definition and Purpose
An X-ray, or radiograph, is a non-invasive method that uses ionizing radiation to take images of internal structures. It is mainly used in cardiac imaging to examine the heart, lungs, and major blood vessels, aiming to identify abnormalities in the heart's size, shape, and position, such as heart failure, congenital defects, and vascular...
Definition and Purpose
An X-ray, or radiograph, is a non-invasive method that uses ionizing radiation to take images of internal structures. It is mainly used in cardiac imaging to examine the heart, lungs, and major blood vessels, aiming to identify abnormalities in the heart's size, shape, and position, such as heart failure, congenital defects, and vascular...
114