A wide range of diagnostic tasks can benefit from an automatic system that is able to segment and label individual ribs on chest X-ray (CXR) images. To this end, traditional approaches (Candemir et al., 2016) exploited hand-crafted features to identify the ribs, but failed with anterior ribs. Recently, deep learning (DL) has shown superior performance to other methods in the segmentation and labeling of individual ribs (Wessel et al., 2019). However, developing DL algorithms for this task requires annotated images for each rib structure at pixel-level. To the best of our knowledge, there exists no such benchmark
datasets and protocols. Hence, we present VinDr-RibCXR – a benchmark dataset for the automatic segmentation and labeling of individual ribs on CXRs. This work also reports performance of several state of-the-art DL-based segmentation models on the VinDr-RibCXR dataset. The dataset and codes will be made publicly available to encourage new advances.