Deep Radiomic Analysis for Predicting Coronavirus Disease 2019 in Computerized Tomography and X-Ray Images

• Published in: IEEE transaction on neural networks and learning systems Vol. 33; no. 1; pp. 3 - 11
• Main Authors: Chaddad, Ahmad, Hassan, Lama, Desrosiers, Christian
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.01.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial neural networks; Chest; Classification; Classifiers; Computed tomography; Convolutional neural network (CNN); Convolutional neural networks; coronavirus disease 2019 (COVID-19); Coronaviruses; COVID-19; COVID-19 - diagnosis; COVID-19 - diagnostic imaging; Diagnosis, Differential; Feature extraction; Gaussian mixture model (GMM); Humans; Image classification; Medical imaging; Neural networks; Neural Networks, Computer; Normal Distribution; Pneumonia - diagnosis; Pneumonia - diagnostic imaging; Predictive models; Predictive Value of Tests; Probabilistic models; Prognosis; Radiomics; Reproducibility of Results; ROC Curve; Tomography; Tomography, X-Ray Computed; Viral diseases; X-ray imaging; X-Rays
• ISSN: 2162-237X; 2162-2388; 2162-2388
• DOI: 10.1109/TNNLS.2021.3119071

This article proposes to encode the distribution of features learned from a convolutional neural network (CNN) using a Gaussian mixture model (GMM). These parametric features, called GMM-CNN, are derived from chest computed tomography (CT) and X-ray scans of patients with coronavirus disease 2019 (COVID-19). We use the proposed GMM-CNN features as input to a robust classifier based on random forests (RFs) to differentiate between COVID-19 and other pneumonia cases. Our experiments assess the advantage of GMM-CNN features compared with standard CNN classification on test images. Using an RF classifier (80% samples for training; 20% samples for testing), GMM-CNN features encoded with two mixture components provided a significantly better performance than standard CNN classification (<inline-formula> <tex-math notation="LaTeX">p < 0.05 </tex-math></inline-formula>). Specifically, our method achieved an accuracy in the range of 96.00%-96.70% and an area under the receiver operator characteristic (ROC) curve in the range of 99.29%-99.45%, with the best performance obtained by combining GMM-CNN features from both CT and X-ray images. Our results suggest that the proposed GMM-CNN features could improve the prediction of COVID-19 in chest CT and X-ray scans.