Abstract
Deep Learning (DL) is a well-established pipeline for feature extraction in medical and non-medical imaging tasks, such as object detection, segmentation, and classification. However, DL faces the issue of explainability, which prohibits reliable utilisation in everyday clinical practice. The present study employs the well-established Grad-CAM algorithm to assess the decisions of a Deep Learning framework in various medical image classification tasks. Seven datasets are utilised, involving images from SPECT, CT, Microscopy, and X-Ray, which correspond to numerous diseases, including Lung Cancer, Coronary Artery Disease, and COVID-19. The main conclusion of the research is that DL with Grad-CAM might reveal important image features. However, it is observed that on many occasions, Grad-CAM shows the model’s inefficiency in discovering the right locations, even in the classification accuracy is at a top level.
