利用深度转移学习和可解释的AI进行准确的COVID-19诊断:来自多国胸部CT扫描研究的见解
Nhat Truong Pham1, Jinsol Ko2, Masaud Shah3
1Department of Integrative Biotechnology, College of Biotechnology and Bioengineering, Sungkyunkwan University, Suwon, 16419, Gyeonggi-do, Republic of Korea.
Computers in biology and medicine
|December 4, 2024
概括
这项研究介绍了XCT-COVID,这是一种使用深度转移学习的新型框架,用于在胸部CT扫描中准确检测COVID-19. 它确保了可解释性和可重现性,在各种数据集上表现优于现有的方法.
科学领域:
- 医疗成像医学成像
- 人工智能的人工智能
- 计算机辅助诊断 计算机辅助诊断
背景情况:
- 手动解释COVID-19胸部CT扫描是耗时和主观的.
- 自动计算机辅助诊断 (CAD) 系统提供了效率,但往往缺乏可重现性.
- 现有的机器/深度学习模型可能会受到偏见和方法上的缺陷的影响.
研究的目的:
- 开发一种可解释,可转移和可重现的CAD框架 (XCT-COVID) 来从CT扫描中准确预测COVID-19.
- 解决当前深度学习模型在可重现性和偏差方面存在的局限性.
- 创建一个统一的框架,能够利用各种数据集进行强大的模型开发.
主要方法:
- 在一个大,尚未探索的数据集和两个较小的数据集上利用了五个卷积神经网络架构的深度转移学习.
- 通过网格搜索和5倍交叉验证 (CV) 采用了广泛的超参数优化.
- 集成的可解释的人工智能 (XAI) 技术用于模型解释性,并为较小的数据集开发了专门的模型 (XCT-COVID-S1,XCT-COVID-S2).
主要成果:
- 使用预训练重量的VGG16架构 (XCT-COVID-L) 在大型数据集上实现了卓越的性能.
- XCT-COVID-L证明了可转移到具有类似数据分布的外部数据集.
- 专门的模型 (XCT-COVID-S1,XCT-COVID-S2) 在较小,质量较差的数据集上表现优于现有方法.
结论:
- 通过CT扫描,XCT-COVID提供了一种准确,可解释和可重复的方法来检测COVID-19.
- 通过专门的模型,框架的适应性提高了它在各种数据集中的实用性.
- 公众对XCT-COVID实施的可访问性促进了进一步的研究和临床应用.
相关概念视频
Imaging Studies for Cardiovascular System V: CT
3
Cardiac computed tomography (CT) scanning is an advanced cardiac imaging technique that utilizes CT technology, with or without intravenous (IV) contrast, to produce accurate cross-sectional virtual slices of specific areas of the heart, coronary circulation, and major blood vessels such as the aorta, pulmonary veins, and arteries. The computer processes these slices to generate three-dimensional images. Multidetector CT (MDCT) is a rapid form of CT scanning that captures multiple slices...
3
Radiological Investigation I: X-ray and CT
209
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...
209
Computed Tomography
4.3K
Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
4.3K


