CT Images Segmentation of Lungs with COVID-۱۹ Infection Using Mask R-CNN

The coronavirus (COVID-۲۰۱۹) pandemic has caused a catastrophic effect on health and global economy. The most common standard for confirming the virus relies on RT-PCR tests. As a complement to RT-PCR, Computed tomography (CT) can be used for diagnosing COVID-۱۹. We describe the R-CNN (area-based torsional neural network) approach to segmentation of CT images of the lungs of people with COVID-۱۹ using a variety of augmentation methods. The class imbalance problem leads to inefficient training, which makes model degenerated. In this paper, we have used a method based on Mask R-CNN to segment Left lung, right lung, Covid-۱۹ infection. In our model, the Focal Loss function is used to suppress well-classified examples.The model is tested on COVID-۱۹-CT-Seg-۲۰cases dataset and the results showed that the accuracy reaches ۸۷.۹۳%. Compared with the smooth loss function in Mask R-CNN it improves by ۵%. Therefore, this model will aid health professionals to fasten the screening and validation of the initial assessment towards COVID-۱۹ patients.

Keywords:

Covid-۱۹ , Deep Learning , Segmentation , Mask R-CNN , Computed Tomography.