A Novel Implementation of Machine Learning for the Efficient, Explainable Diagnosis of COVID-19 from Chest CT

Abstract

In a worldwide health crisis as severe as COVID-19, there is a pressing need for rapid, reliable diagnostics. Currently, popular testing methods such as reverse transcription polymerase chain reaction (RT-PCR) can have high false negative rates. Consequently, COVID-19 patients are not accurately identified nor treated quickly enough to prevent transmission of the virus. However, the recent rise of medical CT data has presented promising avenues, since CT manifestations contain key characteristics indicative of COVID-19. This study aimed to take a novel approach in the machine learning-based detection of COVID-19 from chest CT scans. First, the dataset utilized in this study was derived from three major sources, comprising a total of 17,698 chest CT slices across 923 patient cases. Additionally, image preprocessing algorithms were developed to reduce noise by excluding irrelevant features. Transfer learning was also implemented with the EfficientNetB7 pre-trained model to provide a backbone architecture and save computational resources. Lastly, several explainability techniques were leveraged to qualitatively validate model performance by localizing infected regions and highlighting fine-grained pixel details. The proposed model attained an overall accuracy of 92.71% and a sensitivity of 95.79%. Explainability measures showed that the model correctly distinguished between relevant, critical features pertaining to COVID-19 chest CT images and normal controls. Deep learning frameworks provide efficient, human-interpretable COVID-19 diagnostics that could complement a radiologist’s decision or serve as an alternative screening tool. Future endeavors could provide insight into infection severity, patient risk stratification, and more precise visualizations.