A 3D CNN Network with BERT For Automatic COVID-19 Diagnosis From CT-Scan Images
This work addresses the problem of automated medical diagnosis for COVID-19 patients, but it is incremental as it combines existing methods like 3D CNN and BERT in a new application.
The authors tackled automatic COVID-19 diagnosis from lung CT-scan images by developing a framework that uses a 3D CNN with BERT for classification, achieving an accuracy of 0.9278 and an F1 score of 0.9261 on the validation dataset.
We present an automatic COVID1-19 diagnosis framework from lung CT-scan slice images. In this framework, the slice images of a CT-scan volume are first proprocessed using segmentation techniques to filter out images of closed lung, and to remove the useless background. Then a resampling method is used to select one or multiple sets of a fixed number of slice images for training and validation. A 3D CNN network with BERT is used to classify this set of selected slice images. In this network, an embedding feature is also extracted. In cases where there are more than one set of slice images in a volume, the features of all sets are extracted and pooled into a global feature vector for the whole CT-scan volume. A simple multiple-layer perceptron (MLP) network is used to further classify the aggregated feature vector. The models are trained and evaluated on the provided training and validation datasets. On the validation dataset, the accuracy is 0.9278 and the F1 score is 0.9261.