DAMamba-UNet3D: A Parameter-Efficient Mamba State Space U-Net with Dynamic Adaptive Scan for 3D Medical Image Segmentation

Researchers propose DAMamba-UNet3D, a parameter-efficient state-space model U-Net for 3D medical image segmentation that achieves a mean Dice of 0.815 on BraTS 2020 with ~5.3 million parameters, roughly 13 times fewer than SegMamba's ~70 million parameters. The model introduces Dynamic Adaptive Scan (DAS) for data-dependent reordering in 3D volumes, and a larger variant, DAMamba-L, reaches 0.829 Dice, surpassing SegMamba by 0.5 points.

arXiv:2607.22718v1 Announce Type: new Abstract: We propose parameter-efficient SSM-based U-Net architectures for 3D medical image segmentation. Convolutional U-Nets afford O n local mixing per layer but lack explicit global context; transformers provide global reasoning at O n^2 cost in sequence length $n$. State-space models SSMs , such as Mamba, offer $O n $ global propagation per block. Yet, existing medical SSM segmenters rely on fixed scan patterns and large parameter budgets. Dynamic Adaptive Scan DAS , which learns data-dependent reordering before selective scan, has not been applied to medical imaging or extended to 3D volumes. We propose DAMamba-UNet3D, a hybrid encoder-decoder that integrates tri-plane 3D-DAS blocks at encoder stages E2-E4 while retaining convolutions elsewhere ~5.3M parameters . On BraTS 2020 five-fold cross-validation, DAMamba-UNet3D achieves mean Dice 0.815+/-0.013 full-volume per-case evaluation at ~13x lower parameter cost than SegMamba 0.824+\-0.014, ~70M . At comparable scale, DAMamba-L ~70M , a wide DAS-native variant with encoder-only DAMamba and a convolutional bottleneck, reaches 0.829+\-0.012, surpassing retrained SegMamba by 0.5pt. Component ablations show that encoder-only DAS placement is critical as bottleneck and decoder SSM blocks lower Dice. Together, the results suggest that learned tri-plane DAS in a hybrid U-Net is competitive with, and under our large-scale design may improve upon, SegMamba's fixed Tri-orientated Mamba ToM scanning on BraTS 2020. Code: https://github.com/marafathussain/DAMamba-UNet3D.