Explainable COVID-19 Detection Using Chest CT Scans and Deep Learning

TLDR

The study investigates whether deep learning models trained on chest CT images can rapidly and automatically diagnose COVID‑19, using advanced architectures and a transfer‑learning strategy with custom‑sized inputs. The authors trained advanced deep networks with a transfer‑learning strategy on two CT datasets (SARS‑CoV‑2 CT‑scan and COVID19‑CT) and used visualization methods to explain model predictions. The models achieved superior performance, with average accuracy, precision, sensitivity, specificity, and F1‑score of 99.4 %, 99.6 %, 99.8 %, 99.6 %, and 99.4 % on SARS‑CoV‑2 and 92.9 %, 91.3 %, 93.7 %, 92.2 %, and 92.5 % on COVID19‑CT, and visualizations showed well‑separated clusters and accurate localization of COVID‑19 regions.

Abstract

This paper explores how well deep learning models trained on chest CT images can diagnose COVID-19 infected people in a fast and automated process. To this end, we adopted advanced deep network architectures and proposed a transfer learning strategy using custom-sized input tailored for each deep architecture to achieve the best performance. We conducted extensive sets of experiments on two CT image datasets, namely, the SARS-CoV-2 CT-scan and the COVID19-CT. The results show superior performances for our models compared with previous studies. Our best models achieved average accuracy, precision, sensitivity, specificity, and F1-score values of 99.4%, 99.6%, 99.8%, 99.6%, and 99.4% on the SARS-CoV-2 dataset, and 92.9%, 91.3%, 93.7%, 92.2%, and 92.5% on the COVID19-CT dataset, respectively. For better interpretability of the results, we applied visualization techniques to provide visual explanations for the models’ predictions. Feature visualizations of the learned features show well-separated clusters representing CT images of COVID-19 and non-COVID-19 cases. Moreover, the visualizations indicate that our models are not only capable of identifying COVID-19 cases but also provide accurate localization of the COVID-19-associated regions, as indicated by well-trained radiologists.