Instance Segmentation of Anatomical Structures in Chest Radiographs

Abstract

Automatic and accurate segmentation of anatomical structures in chest radiographs is fundamental and essential for computer-aided diagnosis system. We introduce Mask R-CNN for instance segmentation of lung fields, heart and clavicles. This method efficiently detects different structures and generates accurate segmentation mask for each instance. To the best of our knowledge, we are the first to implement instance segmentation of these three anatomical structures in chest radiographs. We have done extensive experiments on a common benchmark dataset. Results show that the best of our models achieves the state-of-the-art segmentation performance on image resolution of 512 × 512. The Dice and Ω similarity are 0.976 and 0.953 for lung fields, 0.949 and 0.904 for heart, 0.920 and 0.852 for clavicles. And the average contour distance outperforms human observer on both lungs and heart with image resolution of 256 × 256. In addition, it takes only 0.16 and 0.12 seconds per image for the above two resolutions during inference, which is comparable to or even better than current methods.