Lung infection segmentation for COVID-19 pneumonia based on a cascade convolutional network from CT images

The COVID-19 pandemic is a global, national, and local public health which causing a significant outbreak in all countries and regions for both males and females around the world. Automated detection of lung infections and their boundaries from medical images offers a great potential to augment the patient treatment healthcare strategies for tackling COVID-19 and its impacts. Detecting this disease from lung CT scan images is perhaps one of the fastest ways to diagnose the patients. However, finding the presence of infected tissues and segment them from CT slices faces numerous challenges, including similar adjacent tissues, vague boundary, and erratic infections. To overcome the mentioned problems, we propose a two-route convolutional neural network (CNN) by extracting global and local features for detecting and classifying COVID-19 infection from CT images. Each pixel from the image is classified into normal and infected tissue. For improving the classification accuracy, we used two different strategies including Fuzzy c-mean clustering and local directional pattern (LDN) encoding methods to represent the input image differently. This allows us to find a more complex pattern from the image. To overcome the overfitting problems due to small samples, an augmentation approach is utilized. The results demonstrated that the proposed framework achieved Precision 96%, Recall 97%, F-score, average surface distance (ASD) of 2.8\pm0.3\ mm and volume overlap error (VOE) of 5.6\pm1.2%.