An explainable AI system for automated COVID-19 assessment and lesion categorization from CT-scans

Abstract

COVID-19 infection caused by SARS-CoV-2 pathogen has been a catastrophic pandemic outbreak all over the world, with exponential increasing of confirmed cases and, unfortunately, deaths. In this work we propose an AI-powered pipeline, based on the deep-learning paradigm, for automated COVID-19 detection and lesion categorization from CT scans. We first propose a new segmentation module aimed at automatically identifying lung parenchyma and lobes. Next, we combine the segmentation network with classification networks for COVID-19 identification and lesion categorization. We compare the model's classification results with those obtained by three expert radiologists on a dataset of 166 CT scans. Results showed a sensitivity of 90.3% and a specificity of 93.5% for COVID-19 detection, at least on par with those yielded by the expert radiologists, and an average lesion categorization accuracy of about 84%. Moreover, a significant role is played by prior lung and lobe segmentation, that allowed us to enhance classification performance by over 6 percent points. The interpretation of the trained AI models reveals that the most significant areas for supporting the decision on COVID-19 identification are consistent with the lesions clinically associated to the virus, i.e., crazy paving, consolidation and ground glass. This means that the artificial models are able to discriminate a positive patient from a negative one (both controls and patients with interstitial pneumonia tested negative to COVID) by evaluating the presence of those lesions into CT scans. Finally, the AI models are integrated into a user-friendly GUI to support AI explainability for radiologists, which is publicly available at http://perceivelab.com/covid-ai. The whole AI system is unique since, to the best of our knowledge, it is the first AI-based software, publicly available, that attempts to explain to radiologists what information is used by AI methods for making decisions and that proactively involves them in the decision loop to further improve the COVID-19 understanding.

Keywords: COVID-19 detection; Deep learning; Lung segmentation.

Fig. 1

The proposed segmentation architecture, consisting of a downsampling path (top) and an upsampling path (bottom), interconnected by skip connections and by the bottleneck layer.

Fig. 2

Example of lung and lobes segmentation.

Fig. 3

Overview of the COVID-19 detection approach for CT scan classification as either COVID-19 positive or negative.

Fig. 4

Overview of COVID-19 lesion categorization approach.$S^c=Re\mathit{LU}(\sum _k{w}_k^c{A}^k$

Fig. 5

The main page of the AI-empowered web GUI for explainable AI. The user is presented with a list of the CT scan classifications reporting the models' prediction.

Fig. 6

The summarized classification result showing the CT slices that the neural network classified as positive or negative.

Fig. 7

The slice inspection screen. In this screen the user can inspect each single slice and the AI models' decisions.

Fig. 8

Lung salient areas identified automatically by the AI model for CT COVID-19 identification.