Accurate diagnosis of COVID-19 from lung CT images using transfer learning

OBJECTIVE: In this study, it is aimed to classify data by feature extraction from tomographic images for the diagnosis of COVID-19 using image processing and transfer learning. MATERIALS AND METHODS: In the proposed study, CT images are made better detectable by artificial intelligence through preliminary processes such as masking and segmentation. Then, the number of data was increased by applying data augmentation. The size of the dataset contains a large number of images in numerical terms. Therefore, the results of the models are more reliable. The dataset is split into 70% training and 30% testing. In this way, different features of the applied models were found, and positive effects were achieved on the result. Transfer Learning was used to reduce training times and further increase the success rate. To find the best method, many different pre-trained Transfer Learning models have been tried and compared with many different studies. RESULTS: A total of 8,354 images were used in the research. Of these, 2,695 consist of COVID-19 patients and the remaining healthy chest tomography images. All of these images were given to the models through masking and segmentation processes. As a result of the experimental evaluation, the best model was determined to be ResNet-50 and the highest results were found (accuracy 95.7%, precision 94.7%, recall 99.2%, specificity 88.3%, F1 score 96.9%, ROC-AUC score 97%). CONCLUSIONS: The presence of a COVID-19 lesion in the images was identified with high ac- curacy and recall rate using the transfer learning model we developed using thorax CT images. This outcome demonstrates that the strategy will speed up the diagnosis of COVID-19.