Heatmap Template Generation for COVID-19 Biomarker Detection in Chest X-rays

Abstract

Detecting and identifying patterns in chest X-ray images of Covid-19 patients are important tasks for understanding the disease and for making differential diagnosis. Given the relatively small number of available Covid-19 X-ray images and the need to make progress in understanding the disease, we propose a transfer learning technique applied to a pretrained VGG19 neural network to build a deep convolutional model capable of detecting four possible conditions: normal (healthy), bacteria, virus (not Covid-19), and Covid-19. The transformation of the multi-class deep learning output into binary outputs and the detection of Covid-19 image patterns using Grad-CAM technique show promising results. The discovered patterns are consistent across images from a given class of disease and constitute explanations of how the deep learning model makes classification decisions. In the long run, the identified patterns can serve as biomarkers for a given disease in chest X-ray images.

COVID-19 Identification in CLAHE Enhanced CT Scans with Class Imbalance using Ensembled ResNets

“…Gradient-weighted Class Activation Mapping (or GradCAM) [18] algorithms are a generalization of the Class Activation Mapping [19] algorithms used for producing visual explanations for trained deep neural models. The better localization and clear class discriminative saliency maps allow the understanding of the gradient weights built up at the final layer in the deep neural architecture [20].…”