PMC:7782580 / 61015-61645 JSONTXT

{"project":"LitCovid-sentences","denotations":[{"id":"T458","span":{"begin":0,"end":39},"obj":"Sentence"},{"id":"T459","span":{"begin":40,"end":183},"obj":"Sentence"},{"id":"T460","span":{"begin":184,"end":430},"obj":"Sentence"},{"id":"T461","span":{"begin":431,"end":630},"obj":"Sentence"}],"namespaces":[{"prefix":"_base","uri":"http://pubannotation.org/ontology/tao.owl#"}],"text":"Gradient-weighted class activation maps\nGrad-CAM59 in the Pytorch framework was used to visualize the salient features that contributed the most to the prediction output of the model. Given a target category, the Grad-CAM performed back-propagation to obtain the final CNN feature maps and the gradient of the feature maps; only pixels with positive contributions to the specified category were retained through the ReLU function. The Grad-CAM method was used for all test data set (X-data and CT-data) in the CNNCF without changing the framework structure to obtain a visual output of the framework’s high discriminatory ability."}