Mambav3d: A mamba-based virtual 3D module stringing semantic information between layers of medical image slices

Xiaoxiao Liu, Yan Zhao, Shigang Wang, Jian Wei

Abstract: Highlights•• Efficiently and cost-effectively incorporate 3D information into 2D medical image segmentation tasks.•• A module for correlating interlayer information of 3D medical image slices is proposed.•• Combine the properties of the state space model with visual perspective shifting.•• The proposed method is tested on three datasets, obtaining competitive results.