Issues associated with deploying CNN transfer learning to detect COVID-19 from chest X-rays.
Issues associated with deploying CNN transfer learning to detect COVID-19 from chest X-rays.
复制标题
DOI：
10.1007/s13246-020-00934-8
复制
发表时间：
2020-12
影响因子：
4.4
通讯作者：
Asaad A
中科院分区：
文献类型：
--
作者：
Majeed T;Rashid R;Ali D;Asaad A
2019冠状病毒病于2019年12月首次在中国武汉发生。随后，该病毒在全球蔓延，截至2020年6月，确诊病例总数超过470万例，死亡人数超过315，000人。建立在X射线摄影图像上的机器学习算法可以用作决策支持机制，以帮助放射科医生加快诊断过程。这项工作的目的是进行批判性分析，以研究卷积神经网络（CNN）在胸部X射线图像中检测COVID-19的适用性，并强调直接在整个图像上使用CNN的问题。为了完成这一任务，我们在3个公开的胸部X射线数据库上使用了12个现成的CNN架构，并提出了一个浅层CNN架构，在这个架构中，我们从头开始训练它。胸部X射线图像被馈送到CNN模型中，而无需任何预处理，以复制以这种方式使用胸部X射线的研究。然后进行定性调查，使用称为类激活图（CAM）的技术检查CNN做出的决策。使用CAM，人们可以将有助于CNN决策的激活映射回原始图像，以可视化输入图像上最具鉴别力的区域。我们的结论是，尽管CNN的分类准确率很高，但不应该考虑CNN的决定，直到临床医生可以目视检查并批准CNN使用的输入图像的区域，从而导致其预测。
Covid-19 first occurred in Wuhan, China in December 2019. Subsequently, the virus spread throughout the world and as of June 2020 the total number of confirmed cases are above 4.7 million with over 315,000 deaths. Machine learning algorithms built on radiography images can be used as a decision support mechanism to aid radiologists to speed up the diagnostic process. The aim of this work is to conduct a critical analysis to investigate the applicability of convolutional neural networks (CNNs) for the purpose of COVID-19 detection in chest X-ray images and highlight the issues of using CNN directly on the whole image. To accomplish this task, we use 12-off-the-shelf CNN architectures in transfer learning mode on 3 publicly available chest X-ray databases together with proposing a shallow CNN architecture in which we train it from scratch. Chest X-ray images are fed into CNN models without any preprocessing to replicate researches used chest X-rays in this manner. Then a qualitative investigation performed to inspect the decisions made by CNNs using a technique known as class activation maps (CAM). Using CAMs, one can map the activations contributed to the decision of CNNs back to the original image to visualize the most discriminating region(s) on the input image. We conclude that CNN decisions should not be taken into consideration, despite their high classification accuracy, until clinicians can visually inspect and approve the region(s) of the input image used by CNNs that lead to its prediction.
登录
查看更多内容
影响因子：
19.5
作者：
Russakovsky, Olga;Deng, Jia;Fei-Fei, Li
通讯作者：
Fei-Fei, Li
影响因子：
3.9
作者：
Nguyen, Kien;Fookes, Clinton;Sridharan, Sridha
通讯作者：
Sridharan, Sridha
影响因子：
4.4
作者：
Apostolopoulos, Ioannis D.;Mpesiana, Tzani A.
通讯作者：
Mpesiana, Tzani A.
影响因子：
8
作者：
Gu, Jiuxiang;Wang, Zhenhua;Chen, Tsuhan
通讯作者：
Chen, Tsuhan
影响因子：
7.7
作者：
Ozturk, Tulin;Talo, Muhammed;Acharya, U. Rajendra
通讯作者：
Acharya, U. Rajendra