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

TL;DR

This study evaluates how lung segmentation affects COVID-19 diagnosis from chest X-ray images, showing that segmentation improves classification accuracy but still faces bias from different data sources.

Contribution

It demonstrates the impact of lung segmentation on COVID-19 detection accuracy and analyzes biases from data source variability using explainable AI techniques.

Findings

Segmentation achieved a Dice coefficient of 0.982.

F1-Score of 0.88 for multi-class classification with segmented images.

Cross-dataset COVID-19 identification F1-Score of 0.74.

Abstract

COVID-19 frequently provokes pneumonia, which can be diagnosed using imaging exams. Chest X-ray (CXR) is often useful because it is cheap, fast, widespread, and uses less radiation. Here, we demonstrate the impact of lung segmentation in COVID-19 identification using CXR images and evaluate which contents of the image influenced the most. Semantic segmentation was performed using a U-Net CNN architecture, and the classification using three CNN architectures (VGG, ResNet, and Inception). Explainable Artificial Intelligence techniques were employed to estimate the impact of segmentation. A three-classes database was composed: lung opacity (pneumonia), COVID-19, and normal. We assessed the impact of creating a CXR image database from different sources, and the COVID-19 generalization from one source to another. The segmentation achieved a Jaccard distance of 0.034 and a Dice coefficient of 0.982. The classification using segmented images achieved an F1-Score of 0.88 for the multi-class setup, and 0.83 for COVID-19 identification. In the cross-dataset scenario, we obtained an F1-Score of 0.74 and an area under the ROC curve of 0.9 for COVID-19 identification using segmented images. Experiments support the conclusion that even after segmentation, there is a strong bias introduced by underlying factors from different sources.