Annotation-Efficient COVID-19 Pneumonia Lesion Segmentation using Error-Aware Unified Semi-supervised and Active Learning

As the coronavirus disease 2019 (COVID-19) pandemic continues, fast and automatic COVID-19 related pneumonia lesion segmentation method is in urgent need. The current state-of-the-art methods for segmentation generally require sufficient amounts of annotated data for training. However, human expert annotation of such lesion on chest CT scans is time-consuming and labor-intensive, due to its heterogeneous appearance, ambiguous boundary, and large number of slices in 3D CT images. Therefore, the purpose of this study is to present a novel annotation efficient learning method for COVID-19 pneumonia lesion segmentation on CT. To make the best use of limited human expert annotation resources, we propose an error-aware unified semi-supervised and active learning (abbreviated as EA-SSAL) method. A novel error estimation network is proposed to estimate voxelwise segmentation loss map, which is used to guide learning from unlabeled data for semi-supervised learning and choose the most informative images to annotate next for active learning. Validation is carried out on segmenting pneumonia lesions in 110 chest CT scans. The experimental result demonstrates that the proposed method significantly boosts the segmentation accuracy given limited amount of human annotation, compared to a conventional fully supervised baseline (60.9% Dice to 72.0% at 30% labeled data). The performance is also competitive compared to other state-of-the-art annotation-efficient segmentation methods. The proposed method can significantly reduce the annotation effort needed to achieve accurate COVID-19 pneumonia lesion segmentation.