COVID-19 Infection Map Generation and Detection from Chest X-Ray Images

TL;DR

This work tackles automatic COVID-19 detection and localization from chest X-rays by introducing infection maps generated from segmentation models trained on a large, publicly released ground-truth dataset. A novel collaborative human-machine annotation workflow yields high-quality infection masks for QaTa-COV19, the largest CXR COVID-19 dataset to date. The proposed three-stage pipeline—infection-region segmentation, infection-map generation, and COVID-19 detection—achieves high sensitivity and specificity (up to ~99%) and provides localized infection visualization with severity cues. The results demonstrate that infection maps outperform activation maps from classification models and support real-time deployment, with broad public data availability to advance clinical research and evaluation.

Abstract

Computer-aided diagnosis has become a necessity for accurate and immediate coronavirus disease 2019 (COVID-19) detection to aid treatment and prevent the spread of the virus. Numerous studies have proposed to use Deep Learning techniques for COVID-19 diagnosis. However, they have used very limited chest X-ray (CXR) image repositories for evaluation with a small number, a few hundreds, of COVID-19 samples. Moreover, these methods can neither localize nor grade the severity of COVID-19 infection. For this purpose, recent studies proposed to explore the activation maps of deep networks. However, they remain inaccurate for localizing the actual infestation making them unreliable for clinical use. This study proposes a novel method for the joint localization, severity grading, and detection of COVID-19 from CXR images by generating the so-called infection maps. To accomplish this, we have compiled the largest dataset with 119,316 CXR images including 2951 COVID-19 samples, where the annotation of the ground-truth segmentation masks is performed on CXRs by a novel collaborative human-machine approach. Furthermore, we publicly release the first CXR dataset with the ground-truth segmentation masks of the COVID-19 infected regions. A detailed set of experiments show that state-of-the-art segmentation networks can learn to localize COVID-19 infection with an F1-score of 83.20%, which is significantly superior to the activation maps created by the previous methods. Finally, the proposed approach achieved a COVID-19 detection performance with 94.96% sensitivity and 99.88% specificity.

Figures (7)

• Figure 1: The COVID-19 sample CXR images, their corresponding ground-truth segmentation masks which are annotated by the collaborative human-machine approach, and the generated infection maps from the state-of-the-art segmentation models.
• Figure 2: The pipeline of the proposed approach has three stages: COVID-19 infected region segmentation, infection map generation, and COVID-19 detection. The CXR image is the input to the trained E-D CNN and the network's probabilistic prediction is used to generate infection maps. The generated infection maps are used for COVID-19 detection.
• Figure 3: The COVID-19 CXR samples from the benchmark QaTa-COV19 dataset.
• Figure 4: The two stages of the human-machine collaborative approach. Stage I: A subset of CXR images with manually drawn segmentation masks are used to train three different deep networks in a 5-fold cross-validation scheme. The manually drawn ground-truth (a), and the three predictions (b, c, d) are blindly shown to MDs, and they select the best ground-truth mask. Stage II: Five deep networks are trained over the best segmentation masks selected. Then, they are used to produce the segmentation masks for the rest of the CXR dataset (a, b, c, d, e), which are shown to MDs.
• Figure 5: The three COVID-19 CXR test samples, $\mathbf{X}$ with the corresponding ground-truth masks, $\mathbf{Y}$. The color-coded network predictions, $\mathbf{\hat{Y}_{R, G, B}}$ are reflected translucent onto the $\mathbf{X}$ to generate an infection map on the lungs, where $\mathbf{\hat{Y}}>0$.