TypeSeg: A type-aware encoder-decoder network for multi-type ultrasound images co-segmentation

Fang Chen, Haoran Ye, Daoqiang Zhang, Hongen Liao

Abstract: Highlights•Α novel type-aware encoder-decoder network (TypeSeg) is proposed for multi-type ultrasound images co-segmentation.•The TypeSeg model develops the type-aware metric learning and decision modules to fully utilize the tissue type information during semantic segmentation.•The proposed method outperforms all the compared state-of-the-art algorithms for the multi-type ultrasound images co-segmentation task.