Fig. 2: Heatmaps (Layer-wise Relevance Propagation/LRP for convolutional networks and attention rollout for Vision Transformer) for positive COVID-19, Pneumonia, and tuberculosis.

The image’s true class is stated above the figures, the DNN that produced the heatmap is identified on the left. For LRP, red colors indicate areas that the DNN associated to the true class, while blue colors are areas that decreased the network confidence for the class. For attention rollout, red indicates the DNN attention. White represents areas with little influence over the classifiers. DNN focus on the images' foregrounds (lungs), which results in whiter heatmap backgrounds, is desirable. Examples of background bias are markings over the right shoulder in the pneumonia X-ray, a letter R in the neck region of the left TB X-ray, and an L over the left shoulder in the other tuberculosis X-ray. Only the heatmaps for the ISNet and the U-Net + DenseNet show no attention to these biases. Body regions outside of the lungs also represent background bias, which the ISNet ignored as well.