Semantic Constraint Based Unsupervised Domain Adaptation for Cardiac Segmentation

The segmentation of unlabeled medical images is troublesome due to the high cost annotation, and unsupervised domain adaptation one solution this. In this paper, an improved method was proposed. proposed considered both global alignment category-wise alignment. First, we aligned appearance two domains by image transformation. Second, output maps in a way. Then, decomposed semantic prediction map category, aligning manner. Finally, evaluated on 2017 Multi-Modality Whole Heart Segmentation Challenge dataset, obtained 82.1 dice similarity coefficient 4.6 average symmetric surface distance, demonstrating effectiveness combination