相关实验视频

Updated: May 2, 2026

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

生成对抗网络的应用,以改善超声波图像上的COVID-19分类

Pedro Sérgio Tôrres Figueiredo Silva¹, Antonio Mauricio Ferreira Leite Miranda de Sá², Wagner Coelho de Albuquerque Pereira²

¹Signal Processing Laboratory, Alberto Luiz Coimbra Institute for Graduate Studies and Research in Engineering/Polytechnic School (Coppe/Poli), Technology Center, Federal University of Rio de Janeiro, Av. Horácio Macedo 2030, Rio de Janeiro 21941-914, Brazil.

Journal of imaging

|December 24, 2025

概括

生成对抗网络 (GAN) 创建合成肺部超声波图像,以克服COVID-19查的数据短缺. 在这种合成数据上训练的模型达到96.32%的准确性,大大提高了仅在真实数据上训练的模型.

科学领域:

医疗成像医学成像
人工智能的人工智能
计算生物学计算生物学

背景情况:

肺部超声波是COVID-19查的经济有效工具,但其解释需要专业知识.
深度学习模型可以从超声波自动化COVID-19分类,但由于有限的公共数据而面临挑战.
数据稀缺性阻碍了医疗图像分析强大的深度学习模型的开发.

研究的目的:

通过使用GANs生成合成图像来解决COVID-19肺部超声波查中的数据短缺问题.
为了评估由Wasserstein GANs (WGAN) 和Pix2Pix生成的合成数据的有效性,用于培训分类模型.
通过使用增强数据集,提高COVID-19诊断的深度学习模型的准确性和通用性.

主要方法:

使用瓦瑟斯坦GAN (WGAN) 和Pix2Pix来生成合成肺超声波图像.
训练有素的基于框架的分类模型,使用真实和GAN生成的合成数据.
通过使用特定的分析工具将其分布与原始数据集进行比较,验证合成数据的质量.

主要成果:

由GANs生成的合成数据表现出与原始数据集非常相似的分布.
使用合成数据训练的分类模型达到96.32%±4.17%的峰值准确度.
仅在真实数据上训练的模型达到82.69%±10.42%的最大准确度,这表明合成数据的性能显著改善.

结论:

由GAN生成的合成肺超声波数据有效地减轻了医疗AI中的数据稀缺问题.
拟议的方法显著提高了COVID-19查深度学习模型的性能.
这种方法为开发更准确,更容易获得的AI驱动的医学成像诊断工具提供了有希望的途径.

关键词:

在 COVID-19 疫情中,深度学习是一种深度学习.生成性的对抗性网络.肺部超声波肺部超声波肺部超声波

相关概念视频

Aggregates Classification

Aggregates Classification

Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...

Imaging Studies II: Ultrasonography

Imaging Studies II: Ultrasonography

IntroductionUltrasonography, or renal ultrasound, is a noninvasive medical imaging technique that uses high-frequency sound waves to visualize the kidneys, ureters, bladder, and surrounding tissues.Indications for Urinary System UltrasonographyUrinary system ultrasonography is indicated in various clinical scenarios, such as:Kidney Stones (Urolithiasis): To detect and monitor the size and presence of kidney or urinary tract stones.Hydronephrosis: To assess the dilation of the renal pelvis and...