[论文解读] A Deep Learning Approach for the Detection of COVID-19 from Chest X-Ray Images using Convolutional Neural Networks

Aditya Saxena, Shamsheer Pal Singh|arXiv (Cornell University)|Jan 24, 2022

COVID-19 diagnosis using AI被引用 4

一句话总结

本研究提出了一种定制的深度卷积神经网络（CNN），用于从胸部X光片中检测COVID-19，使用了五个公开获取的数据集，其验证准确率高于四种预训练模型（COVID-Net、ResNet18、ResNet、MobileNet-V2），证明了微调CNN在资源有限环境下的可扩展、自动化COVID-19筛查潜力。

ABSTRACT

The COVID-19 (coronavirus) is an ongoing pandemic caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The virus was first identified in mid-December 2019 in the Hubei province of Wuhan, China and by now has spread throughout the planet with more than 75.5 million confirmed cases and more than 1.67 million deaths. With limited number of COVID-19 test kits available in medical facilities, it is important to develop and implement an automatic detection system as an alternative diagnosis option for COVID-19 detection that can used on a commercial scale. Chest X-ray is the first imaging technique that plays an important role in the diagnosis of COVID-19 disease. Computer vision and deep learning techniques can help in determining COVID-19 virus with Chest X-ray Images. Due to the high availability of large-scale annotated image datasets, great success has been achieved using convolutional neural network for image analysis and classification. In this research, we have proposed a deep convolutional neural network trained on five open access datasets with binary output: Normal and Covid. The performance of the model is compared with four pre-trained convolutional neural network-based models (COVID-Net, ResNet18, ResNet and MobileNet-V2) and it has been seen that the proposed model provides better accuracy on the validation set as compared to the other four pre-trained models. This research work provides promising results which can be further improvise and implement on a commercial scale.

研究动机与目标

• 开发一种用于从胸部X光片中自动检测COVID-19的深度学习系统，作为RT-PCR检测有限的替代方案。
• 通过利用广泛可用的X光成像技术，解决医疗设施中诊断试剂盒供应不足的挑战。
• 利用大规模、公开获取的胸部X光片数据集，通过深度学习提高诊断准确率和速度。
• 将自定义CNN的性能与已建立的预训练模型（如ResNet和MobileNet-V2）进行比较。

提出的方法

• 在包含正常和COVID-19胸部X光片的五个公开获取数据集上训练了自定义的深度卷积神经网络。
• 采用标准的深度学习训练流程，对二分类任务（正常 vs. COVID-19）进行优化。
• 应用数据增强技术以提高训练集的泛化能力并减少过拟合。
• 在验证集上评估性能，并与四种预训练模型（COVID-Net、ResNet18、ResNet、MobileNet-V2）进行比较。
• 训练过程采用迁移学习原理和超参数调优，以最大化验证准确率。
• 模型架构设计旨在平衡参数效率与医学影像的特征提取能力。

实验结果

研究问题

• RQ1 自定义训练的CNN是否能在从胸部X光片检测COVID-19方面实现高于现有预训练模型的准确率？
• RQ2 微调后的CNN在相同数据集上的性能与ResNet和MobileNet-V2等成熟模型相比如何？
• RQ3 在多个公开获取数据集上训练的深度学习模型，在多大程度上能泛化到实际临床诊断应用？
• RQ4 数据集多样性与数据增强对模型鲁棒性和准确率有何影响？

主要发现

• 所提出的自定义CNN在所有四种测试的预训练模型（包括ResNet18、ResNet、MobileNet-V2和COVID-Net）中均实现了更高的验证准确率。
• 该模型在多种胸部X光片数据集上表现出强大的泛化能力，表明其对数据分布偏移具有鲁棒性。
• 研究结果表明，当在综合的、多源数据集上训练时，专门设计的CNN可优于迁移学习基线模型。
• 本研究提供了证据，表明深度学习模型可作为临床环境中有限检测能力下早期COVID-19检测的可行、可扩展的替代方案。