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

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.

Transfer learning-based approach for detecting COVID-19 ailment in lung CT scan

“…The underlying framework that enabled this platform to find the best way to train deep learning models has been called Neural Architecture Search (NAS). To achieve the best performance, Alshazly et al [ 19 ] used advanced deep network architecture and suggested a transfer learning strategy that utilized custom-sized input optimized for deep architecture. Silva et al [ 20 ] proposed Efficient CovidNet, a model for detecting COVID-19 patterns in CT images that involves a voting-based approach and cross-dataset analysis.…”

Machine Learning for Prediction of Survival Outcomes with Immune-Checkpoint Inhibitors in Urothelial Cancer

“…Machine learning (ML), a form of artificial intelligence, is an emerging alternative that may efficiently develop accurate clinical prediction models that can deal with high-dimensional data, and identify complex relationships between variables and outcomes that may be unidentifiable with traditional statistical approaches [ 11 , 12 , 13 ]. There were several recent breakthroughs demonstrating how using ML to rapidly interrogate complex data delivers a more efficient use of healthcare resources, including the detection of COVID-19 infection by ML interrogation of CT and X-ray images [ 14 , 15 ]. With respect to cancer, there are several ML-based algorithms that can process time-to-event survival outcome data, so identifying a suitable best-performing learning algorithm is critical to developing accurate prediction models of survival.…”

COVID-19 Diagnosis from chest CT Scans: A Weakly Supervised CNN-LSTM Approach

“…The healthcare providers are facing intense workload due to the pandemic [8]. To relieve the overwhelming workload, AI systems are being used to detect and identify COVID-19 using medical imaging technologies [9][10][11][12][13][14][15][16][17]. Recent studies on radiology demonstrate promising results on COVID-19 pneumonia classification using chest CTs with the help of deep learning methodologies.…”

“…There are different class definition approaches in the COVID-19 related studies like binary or multiclass. Binary classification is usually applied as Covid pneumonia and non-Covid pneumonia [12,17] or Covid positive and Covid negative [14,16]. Multiclass classification separates Covid negative further into Covid pneumonia, non-Covid pneumonia and no pneumonia [9][10][11]13,15].…”

“…Another important difference in the methods applied among the related studies is the use of slice-based or patient-level labeling. While most of the COVID-19 classification studies exploit slice-based CT image labels [10,12,13,[15][16][17] because of its convenience, it has a big labour cost requiring manual labelling of slices by radiologists. Therefore, patient-level labelling has also been used [9,11,14] instead of slice-based labelling where slice-based features can be obtained with the help of deep learning methods.…”