XQA-Chest: Expert-Annotated Chest X-ray Dataset for Pathology Classification and Image Quality Assessment, 2026

Cambridge University Hospitals, NHS Foundation Trust and Fytas, Panagiotis and Breger, Anna (2026). XQA-Chest: Expert-Annotated Chest X-ray Dataset for Pathology Classification and Image Quality Assessment, 2026. [Data Collection]. Colchester, Essex: UK Data Service. 10.5255/UKDA-SN-858610

Data description (abstract)

Chest X-ray (CXR) machine learning relies heavily on automated evaluation using reference standards that aim to approximate clinical judgment. However, commonly used report-derived labels for pathology classification and generic image quality metrics for image reconstruction may not reliably reflect expert clinical assessment. XQA was collected to support systematic investigation of how evaluation choices affect model performance and ranking in both CXR pathology classification and image quality assessment (IQA).

XQA is split into two complementary components. XQA-RR supports research on pathology classification and contains paired expert image-based and report-derived labels for thoracic findings from a clinical cohort at Cambridge University Hospitals NHS Foundation Trust. XQA-IQA supports research on diagnostic image quality assessment and contains expert ratings of CXR image quality for reference images and degraded image variants.

Using XQA, we were able to evaluate supervised image classifiers, self-supervised models, and fine-tuned vision-language models, including ResNet, DenseNet, MedKLIP, GLoRIA, and ConVIRT. The results show that changing the evaluation reference can substantially affect both estimated model performance and model rankings. In parallel, the alignment of IQA measures with expert judgment depends strongly on the choice of measure, with commonly used metrics such as SSIM and PSNR often failing to reflect expert assessments of diagnostic usability.

The collection is intended to support research on clinical AI evaluation, CXR pathology classification, radiology report labelling, image quality assessment, and the clinical suitability of machine learning systems for CXR interpretation. If you use XQA, please cite the dataset repository and the accompanying paper:

Paper DOI: to be added once available.

Downloads

Altmetric