SA-Seg: Annotation-Efficient Segmentation for Airway Tree Using Saliency-Based Annotation

Segmentation of the airway tree plays a vital role in clinical practice. However, the complex airway tree structure makes it quite challenging to annotate accurately. Although some annotation-efficient methods have shown promising results in medical image segmentation, most are developed for locally focused segmentation objects and are incompatible with the airway. In this work, we propose an annotation-efficient segmentation method to improve annotation efficiency and tree completeness. It includes a new efficient annotation way and an accompanying segmentation method. The saliency-based annotation method only needs to annotate high-saliency regions, thus greatly improving the annotation efficiency. Inspired by positive-unlabeled learning, we model the dependency relationship between key items in the annotation process to learn from biased weak annotation. The probabilistic model of the annotation process is divided into the score function and the bias function. The score function models the uniform foreground feature representation of the airway, while the bias function models the saliency bias between labeled and unlabeled airway regions. Then, the two models are implemented with convolutional neural networks and optimized by applying an EM algorithm during training. Experimental results reveal that our approach saves 89% annotation time and significantly narrows the performance gap between weak and full annotations. This highlights its potential for clinical applications.