Abstract

Deep learning models are widely used in the automatic analysis of radiological images. These techniques can train the weights of networks on large datasets as well as fine tuning the weights of pre-trained networks on small datasets. Due to the small COVID-19 dataset available, the pre-trained neural networks can be used for diagnosis of coronavirus. However, these techniques applied on chest CT image is very limited till now. Hence, the main aim of this paper to use the pre-trained deep learning architectures as an automated tool to detection and diagnosis of COVID-19 in chest CT. A DenseNet201 based deep transfer learning (DTL) is proposed to classify the patients as COVID infected or not i.e. COVID-19 (+) or COVID (−). The proposed model is utilized to extract features by using its own learned weights on the ImageNet dataset along with a convolutional neural structure. Extensive experiments are performed to evaluate the performance of the propose DTL model on COVID-19 chest CT scan images. Comparative analyses reveal that the proposed DTL based COVID-19 classification model outperforms the competitive approaches.

Communicated by Ramaswamy H. Sarma

摘要

深度学习模型广泛用于放射影像的自动分析。这些技术可以在大数据集上训练网络的权重，也可以在小数据集上微调预训练网络的权重。由于可用的 COVID-19 数据集较小，预训练的神经网络可用于诊断冠状病毒。然而，这些技术在胸部 CT 图像上的应用到目前为止还非常有限。因此，本文的主要目的是使用预训练的深度学习架构作为自动化工具在胸部 CT 中检测和诊断 COVID-19。提出了基于 DenseNet201 的深度迁移学习 (DTL) 来将患者分类为 COVID 感染与否，即 COVID-19 (+) 或 COVID (-)。所提出的模型用于通过在 ImageNet 数据集上使用其自己学习的权重以及卷积神经结构来提取特征。进行了大量实验以评估所提出的 DTL 模型在 COVID-19 胸部 CT 扫描图像上的性能。比较分析表明，所提出的基于 DTL 的 COVID-19 分类模型优于竞争方法。

由 Ramaswamy H. Sarma 交流