Chest X-ray(CXR) images are prominent among medical images and are commonlyadministered in emergency diagnosis and treatment corresponding to cardiac andrespiratory diseases. Though there are robust solutions available for medicaldiagnosis, validation of artificial intelligence (AI) in radiology is stillquestionable. Segmentation is pivotal in chest radiographs that aid inimprovising the existing AI-based medical diagnosis process. We provide theCXLSeg dataset: Chest X-ray with Lung Segmentation, a comparatively largedataset of segmented Chest X-ray radiographs based on the MIMIC-CXR dataset, apopular CXR image dataset. The dataset contains segmentation results of243,324 frontal view images of the MIMIC-CXR dataset and corresponding masks.Additionally, this dataset can be utilized for computer vision-related deeplearning tasks such as medical image classification, semantic segmentation andmedical report generation. Models using segmented images yield better resultssince only the features related to the important areas of the image arefocused. Thus images of this dataset can be manipulated to any visual featureextraction process associated with the original MIMIC-CXR dataset and enhancethe results of the published or novel investigations. Furthermore, masksprovided by this dataset can be used to train segmentation models whencombined with the MIMIC-CXR-JPG dataset. The SA-UNet model achieved a 96.80%in dice similarity coefficient and 91.97% in IoU for lung segmentation usingCXLSeg.

Chest X-ray(CXR) images are prominent among medical images and are commonlyadministered in emergency diagnosis and treatment corresponding to cardiac andrespiratory diseases. Though there are robust solutions available for medicaldiagnosis, validation of artificial intelligence (AI) in radiology is stillquestionable. Segmentation is pivotal in chest radiographs that aid inimprovising the existing AI-based medical diagnosis process. We provide theCXLSeg dataset: Chest X-ray with Lung Segmentation, a comparatively largedataset of segmented Chest X-ray radiographs based on the MIMIC-CXR dataset, apopular CXR image dataset. The dataset contains segmentation results of243,324 frontal view images of the MIMIC-CXR dataset and corresponding masks.Additionally, this dataset can be utilized for computer vision-related deeplearning tasks such as medical image classification, semantic segmentation andmedical report generation. Models using segmented images yield better resultssince only the features related to the important areas of the image arefocused. Thus images of this dataset can be manipulated to any visual featureextraction process associated with the original MIMIC-CXR dataset and enhancethe results of the published or novel investigations. Furthermore, masksprovided by this dataset can be used to train segmentation models whencombined with the MIMIC-CXR-JPG dataset. The SA-UNet model achieved a 96.80%in dice similarity coefficient and 91.97% in IoU for lung segmentation usingCXLSeg.