Foreign object segmentation in chest x-rays through anatomy-guided shape insertion

TL;DR

This paper introduces a method for foreign object segmentation in chest X-rays using synthetic data generation guided by anatomy labels, significantly reducing manual annotation needs while maintaining high performance.

Contribution

It presents a novel anatomy-guided synthetic data generation approach for foreign object segmentation, reducing manual labeling by 93% without sacrificing accuracy.

Findings

Achieves comparable performance to fully supervised models.

Reduces manual annotation by 93%.

Enables effective segmentation with minimal labeled data.

Abstract

In this paper, we tackle the challenge of instance segmentation for foreign objects in chest radiographs, commonly seen in postoperative follow-ups with stents, pacemakers, or ingested objects in children. The diversity of foreign objects complicates dense annotation, as shown in insufficient existing datasets. To address this, we propose the simple generation of synthetic data through (1) insertion of arbitrary shapes (lines, polygons, ellipses) with varying contrasts and opacities, and (2) cut-paste augmentations from a small set of semi-automatically extracted labels. These insertions are guided by anatomy labels to ensure realistic placements, such as stents appearing only in relevant vessels. Our approach enables networks to segment complex structures with minimal manually labeled data. Notably, it achieves performance comparable to fully supervised models while using 93\% fewer manual annotations.