Deep Learning Models for COVID-19 Detection

Sustainability

Fadi Al-Turjman¹  Sertan Serte²  Mehmet Alp Dirik³ 

[1] Artificial Intelligence Engineering Department, Research Center for AI and IoT, AI and Robotics Institute, Near East University, North Cyprus via Mersin 10, Nicosia 99138, Turkey;Department of Electrical and Electronic Engineering, Near East University, North Cyprus via Mersin 10, Nicosia 99138, Turkey;Department of Radiology, Dr. Suat Günsel University Faculty of Medicine Kyrenia, North Cyprus via Mersin 10, Kyrenia 99300, Turkey;

关键词: convolutional neural networks;    deep learning;    generative adversarial network;   

DOI  :  10.3390/su14105820

来源: DOAJ

【 摘 要 】

Healthcare is one of the crucial aspects of the Internet of things. Connected machine learning-based systems provide faster healthcare services. Doctors and radiologists can also use these systems for collaboration to provide better help to patients. The recently emerged Coronavirus (COVID-19) is known to have strong infectious ability. Reverse transcription-polymerase chain reaction (RT-PCR) is recognised as being one of the primary diagnostic tools. However, RT-PCR tests might not be accurate. In contrast, doctors can employ artificial intelligence techniques on X-ray and CT scans for analysis. Artificial intelligent methods need a large number of images; however, this might not be possible during a pandemic. In this paper, a novel data-efficient deep network is proposed for the identification of COVID-19 on CT images. This method increases the small number of available CT scans by generating synthetic versions of CT scans using the generative adversarial network (GAN). Then, we estimate the parameters of convolutional and fully connected layers of the deep networks using synthetic and augmented data. The method shows that the GAN-based deep learning model provides higher performance than classic deep learning models for COVID-19 detection. The performance evaluation is performed on COVID19-CT and Mosmed datasets. The best performing models are ResNet-18 and MobileNetV2 on COVID19-CT and Mosmed, respectively. The area under curve values of ResNet-18 and MobileNetV2 are $\mathbf{0}.\mathbf{89}\%$ and $\mathbf{0}.\mathbf{84}\%$, respectively.

【 授权许可】

Unknown