Self-Supervised Learning Application on COVID-19 Chest X-ray Image Classification Using Masked AutoEncoder.
Self-Supervised Learning Application on COVID-19 Chest X-ray Image Classification Using Masked AutoEncoder.
复制标题
使用 Masked AutoEncoder 对 COVID-19 胸部 X 射线图像分类的自监督学习应用。
DOI：
10.3390/bioengineering10080901
复制
发表时间：
2023-07-29
影响因子：
4.6
通讯作者：
Lin, Ai-Ling
中科院分区：
文献类型：
--
作者：
Xing, Xin;Liang, Gongbo;Wang, Chris;Jacobs, Nathan;Lin, Ai-Ling
COVID-19疫情凸显了对人工智能（AI）促进的快速准确诊断的迫切需求，特别是在使用医学成像的计算机辅助诊断方面。然而，这种情况带来了两个显著的挑战：高诊断准确性需求和用于训练AI模型的医疗数据有限。为了解决这些问题，我们提出了一个掩蔽自动编码器（MAE），一种创新的自我监督学习方法，用于分类2D胸部X射线图像的实现。我们的方法涉及使用Vision Transformer（ViT）模型作为特征编码器，与自定义解码器配对进行成像重建。此外，我们使用标记的医疗数据集作为骨干，对预训练的ViT编码器进行了微调。为了评估我们的方法，我们对三种不同的训练方法进行了比较分析：从头开始训练，迁移学习和基于MAE的训练，所有这些训练都使用了COVID-19胸部X射线图像。结果表明，基于MAE的训练产生了上级性能，实现了0.985的准确度和0.9957的AUC。我们探索了掩模比率对MAE的影响，发现比率= 0.4显示了最佳性能。此外，我们说明了MAE在应用于标记数据时表现出显着的效率，提供了与仅利用原始训练数据集的30%相当的性能。总体而言，我们的研究结果突出了使用MAE实现的显着性能增强，特别是在使用有限数据集时。这种方法对未来的疾病诊断具有深远的意义，特别是在成像信息稀缺的情况下。
The COVID-19 pandemic has underscored the urgent need for rapid and accurate diagnosis facilitated by artificial intelligence (AI), particularly in computer-aided diagnosis using medical imaging. However, this context presents two notable challenges: high diagnostic accuracy demand and limited availability of medical data for training AI models. To address these issues, we proposed the implementation of a Masked AutoEncoder (MAE), an innovative self-supervised learning approach, for classifying 2D Chest X-ray images. Our approach involved performing imaging reconstruction using a Vision Transformer (ViT) model as the feature encoder, paired with a custom-defined decoder. Additionally, we fine-tuned the pretrained ViT encoder using a labeled medical dataset, serving as the backbone. To evaluate our approach, we conducted a comparative analysis of three distinct training methods: training from scratch, transfer learning, and MAE-based training, all employing COVID-19 chest X-ray images. The results demonstrate that MAE-based training produces superior performance, achieving an accuracy of 0.985 and an AUC of 0.9957. We explored the mask ratio influence on MAE and found ratio = 0.4 shows the best performance. Furthermore, we illustrate that MAE exhibits remarkable efficiency when applied to labeled data, delivering comparable performance to utilizing only 30% of the original training dataset. Overall, our findings highlight the significant performance enhancement achieved by using MAE, particularly when working with limited datasets. This approach holds profound implications for future disease diagnosis, especially in scenarios where imaging information is scarce.
登录
查看更多内容
DOI：
10.33696/immunology.3.123
发表时间：
2021
期刊：
Journal of cellular immunology
影响因子：
--
作者：
Hammond TC;Xing X;Yanckello LM;Stromberg A;Chang YH;Nelson PT;Lin AL
通讯作者：
Lin AL
影响因子：
5.9
作者：
Hammond, Tyler C.;Xing, Xin;Lin, Ai-Ling
通讯作者：
Lin, Ai-Ling
影响因子：
22.7
作者：
Krizhevsky, Alex;Sutskever, Ilya;Hinton, Geoffrey E.
通讯作者：
Hinton, Geoffrey E.
DOI：
10.1007/s42979-021-00782-7
发表时间：
2021
期刊：
SN computer science
影响因子：
--
作者：
Hasan N;Bao Y;Shawon A;Huang Y
通讯作者：
Huang Y