Evaluating volumetric and slice-based approaches for COVID-19 detection in chest CTs.

The paper presents a comparative analysis of several distinct approaches based on deep learning for identifying COVID-19 cases in chest CTs. A first approach is a volumetric one, involving 3D convolutions, while other two approaches perform at first slice-wise classification and then aggregate the results at the volume level. The experiments are carried on the COV19-CT-DB dataset, with the aim of addressing the challenge raised by the MIA-COV19D Competition within ICCV 2021. Our best results reach a macro F1 score of 92:34% on the validation subset and 90.06% on the test set, obtained with the volumetric approach which was ranked second in the competition. Its performance can be further improved by a simple trick, using semi-supervised training in the form of self-training, technique which proved to bring a consistent increase over the reported F1-score on the validation subset.