Crowdsourcing Airway Annotations in Chest Computed Tomography Images

TL;DR

This study explores the feasibility of using crowdsourcing to annotate airway structures in chest CT scans, comparing crowd annotations to expert measurements, and highlighting challenges and potential for future improvements.

Contribution

It demonstrates that crowdsourcing can produce airway annotations with moderate correlation to experts, but further development is needed for robustness.

Findings

Moderate to strong correlation with expert annotations after filtering

High variability in results across different subjects

Crowdsourcing shows potential but requires refinement for practical use

Abstract

Measuring airways in chest computed tomography (CT) scans is important for characterizing diseases such as cystic fibrosis, yet very time-consuming to perform manually. Machine learning algorithms offer an alternative, but need large sets of annotated scans for good performance. We investigate whether crowdsourcing can be used to gather airway annotations. We generate image slices at known locations of airways in 24 subjects and request the crowd workers to outline the airway lumen and airway wall. After combining multiple crowd workers, we compare the measurements to those made by the experts in the original scans. Similar to our preliminary study, a large portion of the annotations were excluded, possibly due to workers misunderstanding the instructions. After excluding such annotations, moderate to strong correlations with the expert can be observed, although these correlations are slightly lower than inter-expert correlations. Furthermore, the results across subjects in this study are quite variable. Although the crowd has potential in annotating airways, further development is needed for it to be robust enough for gathering annotations in practice. For reproducibility, data and code are available online: \url{http://github.com/adriapr/crowdairway.git}.