Deep learning for COVID-19 lung pathology segmentation

Abstract

COVID-19 pandemic has impacted billions of lives and created a challenge for the healthcare systems. Detection of pathologies from computed tomography (CT) images offers a great way to assist the traditional healthcare for tackling COVID-19. Pathologies such as ground-glass opacification and consolidations are region of interests which the doctors use to diagnosis the patients. In this work, we have developed and tested various segmentation model using transfer learning to find such pathologies. U-Net [15] is the foundation of the models which we have tested. Along with U-Net we have changed the encoder section of the said model, to various classification models such as VGG, ResNet and MobileNet. As these model have won ImageNet Challenge, there core component have been used for feature extraction and usage of their pretrained weights will help in faster convergence. A small subset of studies which has been annotated with binary pixel masks depicting regions of interests in MosMedData [12] Chest CT Scans dataset have been used to train the segmentation model. The best segmentation model achieved a mean dice score of 0.6029.