2020/04/07 by Umut Özkaya, Şaban Öztürk, Ozkaya, Umut +3
Computer Science · Medicine · #AI in cancer detection #COVID-19 diagnosis using AI #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #I.2.0 #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE) #Radiomics and Machine Learning in Medical Imaging #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2004.03698
openalex publication_date 2020/04/07 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
Coronavirus (COVID-19) emerged towards the end of 2019. World Health\nOrganization (WHO) was identified it as a global epidemic. Consensus occurred\nin the opinion that using Computerized Tomography (CT) techniques for early\ndiagnosis of pandemic disease gives both fast and accurate results. It was\nstated by expert radiologists that COVID-19 displays different behaviours in CT\nimages. In this study, a novel method was proposed as fusing and ranking deep\nfeatures to detect COVID-19 in early phase. 16x16 (Subset-1) and 32x32\n(Subset-2) patches were obtained from 150 CT images to generate sub-datasets.\nWithin the scope of the proposed method, 3000 patch images have been labelled\nas CoVID-19 and No finding for using in training and testing phase. Feature\nfusion and ranking method have been applied in order to increase the\nperformance of the proposed method. Then, the processed data was classified\nwith a Support Vector Machine (SVM). According to other pre-trained\nConvolutional Neural Network (CNN) models used in transfer learning, the\nproposed method shows high performance on Subset-2 with 98.27% accuracy, 98.93%\nsensitivity, 97.60% specificity, 97.63% precision, 98.28% F1-score and 96.54%\nMatthews Correlation Coefficient (MCC) metrics.\n