Learning to segment complex vessel-like structures with spectral transformer

Huajun Liu, Jing Yang, Shidong Wang, Hui Kong, Qiang Chen, Haofeng Zhang

Abstract: Highlights•SSNO consisting of feed-forward layer, sparse spectral layer and residual layer.•DAB with SSNO-based scaling attention and self-attention for feature extraction.•U-shaped Spectral Transformer by stacking and arranging multiple DABs.•SpecFormer achieves new state-of-the-art performance on several datasets.