通过深度学习进行肺部疾病分类 增强了胸部X射线成像中的CNN架构
Faiçal Alaoui Abdalaoui Slimani1, M'hamed Bentourkia2
1Department of Medical Imaging and Radiation Sciences, 3001 12th Avenue North, Sherbrooke, Qc, J1H5N4, Canada.
Journal of imaging informatics in medicine
|December 1, 2025
概括
这项研究引入了一种使用离散波波变换 (DWT) 和生成对抗网络 (PGGAN) 的新型深度学习方法,以改进肺部X射线分析. 这种方法增强了COVID-19,肺结核和肺炎等肺病理的细分和分类.
科学领域:
- 医疗成像医学成像
- 人工智能的人工智能
- 放射学 放射学是一门学科.
背景情况:
- 从胸部X射线 (CXR) 来精确细分和分类肺部病理对于诊断至关重要.
- 传统方法面临着细节和有限/可变数据集的挑战.
- 深度学习模型有希望,但需要针对复杂病理进行优化.
研究的目的:
- 开发一个强大的卷积神经网络 (CNN) 以提高肺X射线细分和多重分类.
- 改进细肺结构和病理细节的检测.
- 通过使用先进的数据增强技术来解决数据限制.
主要方法:
- 在U-Net++模型中用离散波量变换 (DWT) 取代了最大聚合,并使用了注意门 (AG) 来进行细分.
- 将DWT集成到DenseNet-201中,用于肺病理 (肺结核,肺炎,COVID-19) 的多重分类.
- 采用逐渐增长的生成对抗网络 (PGGAN) 进行数据增强,以生成现实的合成CXR图像.
主要成果:
- 在JSRT数据集上在肺部细分中实现了99.1%的准确性和97.2%的子系数,优于U-Net和U-Net++.
- 与DenseNet-201相比,通过PGGAN数据增强,证明了2.4%的更高的分类精度.
- 综合的DWT方法增强了细肺结构和病理特征的检测.
结论:
- 拟议的DWT集成CNN方法在肺X射线细分和多分类方面提供了卓越的性能.
- PGGAN数据增强有效地丰富了数据集,提高了模型的稳定性和诊断精度.
- 这种方法代表了对各种肺病理的自动CXR分析的重大进步.
相关概念视频
01:30Radiological Investigation I: X-ray and CT
1.0K
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...
1.0K
01:20Imaging Studies for Cardiovascular System III: X-Ray
454
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...
454