Pyramid Feature Adaptation for Semi-supervised Cardiac Bi-ventricle Segmentation

Abstract Cardiac bi-ventricle segmentation (BVS) is an essential task for assessing cardiac indices, such as the ejection fraction and volume of the left ventricle (LV) and right ventricle (RV). However, BVS is extremely challenging due to the high variability of the bi-ventricle structure and lack of labeled data. In this paper, we propose a pyramid feature adaptation based semi-supervised method (PABVS) for cardiac bi-ventricle segmentation. The PABVS first extracts the multiscale pyramid features of bi-ventricle structure to cope with the high variability of bi-ventricle structure. Then, a weighted pyramid feature adaptation strategy is proposed to ensure a smooth feature space among labeled data and unlabeled data. In particular, the PABVS performs weighted feature adaptation at each level of a multiscale pyramid feature based on adversarial learning. It gives less importance to outlier feature layers of labeled data and more importance to representative layers. The experimental results on magnetic resonance images show that our proposed PABVS can achieve Dice values 0.915 for EpiLV with 40% labeled data and the Dice values 0.976 for EpiLV with all labeled data, which outperforms mainstream semi-supervised methods. This endows our PABVS with great potential for the effective clinical application of BVS.