Sequential Rib Labeling and Segmentation in Chest X-Ray using Mask R-CNN

Joeran Wessel, Mattias P. Heinrich, Jens von Berg, Astrid Franz, Axel Saalbach

Keywords: Rib Detection, Rib Segmentation, Mask R-CNN, X-ray Images

Abstract:

Mask R-CNN is a state-of-the-art network architecture for the detection and segmentation of object instances in the computer vision domain. In this contribution, it is used to localize, label and segment individual ribs in anterior-posterior chest X-ray images.

For this purpose, several extensions have been made to the original architecture, in order to address the specific challenges of this application. This includes the use of rib specific networks, facilitating dedicated anchor boxes sampled from a training set, as well as a sequential processing of all ribs. Here, the segmentation result of the upper neighbor rib is used as additional input to the network.

This approach is the first addressing both rib segmentation and anatomical labeling in chest radiographs. The results are comparable or even better than existing methods aiming only at segmentation.

Code Of Conduct: I have read and accept the code of conduct.

Remove If Rejected: Remove submission from public view if paper is rejected.