COVID-19 detection from lung CT-Scans using a fuzzy integral-based CNN ensemble

Improving COVID-19 CT classification of CNNs by learning parameter-efficient representation

“…Despite the various datasets, many CNN-based methods have been developed to continuously boost classification performance. In particular, researchers often use transfer learning [13] , [21] , [22] , [23] , [24] , [25] , [33] , [34] , [35] or ensemble learning [22] , [23] , [25] , [33] , [36] , [37] to overcome data insufficiency in small-scale datasets like SARS-CoV-2 and COVID-CT. For example, Jaiswal et al. [24] and Panwar et al.…”

COVID-19 CT ground-glass opacity segmentation based on attention mechanism threshold

“…The final design is combing the attention mechanism and image enhancement. For example, CNN based on Sugeno fuzzy integral was devoted to detecting GGO in COVID-19 [24] . Anam-net improved by a lightweight CNN was applied to segment GGO [25] , [26] .…”

A fuzzy fine-tuned model for COVID-19 diagnosis

“…Second, some studies have used C.T. images, which have problems such as high cost compared to CXR, limited access in less privileged areas, the need for a specialist to examine the images, and so on [45] , [46] , [47] , [48] . As the disease spread rapidly around the world, there was not enough opportunity for researchers to create a dataset with sufficient data volumes and standard images.…”