Impact of lung segmentation on the diagnosis and explanation of COVID-19 in chest X-ray images

The COVID-19 pandemic is undoubtedly one of the biggest public health crises our society has ever faced in recent history. One of the main complications caused by COVID-19 is pneumonia, which is diagnosed using imaging exams, such as chest X-ray (CXR) and computed tomography (CT) scan. The CT scan is more precise than the CXR. However, CXR is suitable in particular situations because it is cheaper, faster, more widespread, and exposes the patient to less radiation. This study aims to demonstrate the impact of lung segmentation in COVID-19 identification using CXR images and evaluate which contents of the image decisively contribute to its identification. We performed the lung segmentation using a U-Net CNN architecture, and the classification using three well-known CNN architectures: VGG, ResNet, and Inception. To estimate the impact of lung segmentation, we applied some Explainable Artificial Intelligence (XAI) techniques, specifically LIME and Grad-CAM. To empirically evaluate our approach, we composed a database with three classes: lung opacity (pneumonia), COVID-19, and normal. The segmentation achieved a Jaccard distance of 0.034 and a Dice coefficient of 0.982. The classification using segmented lung achieved an F1-Score of 0.88 for the multi-class setup and 0.83 for COVID-19 identification. Further testing and XAI techniques suggest that segmented CXR images represent a much more realistic and less biased performance. To the best of our knowledge, no other work tried to estimate the impact of lung segmentation in COVID-19 identification using comprehensive XAI techniques.