PDMambaNet: Poisson Denoising-Aided Twin-Path Mamba for Brain MRI Image Segmentation

Dayong Ren, Feifei Zhang, Fei Shi, Aoxue Chen

Abstract: Brain tissue segmentation is critical for diagnosing and treating brain diseases, but noise introduced during MRI image acquisition can compromise downstream tasks. To address this, we introduce a Poisson denoising module to eliminate Poisson and mixed noise. However, Poisson denoising may blur local brain tissue details and edges, impacting segmentation accuracy. To overcome this, we propose PDMambaNet, which integrates Poisson denoising, the Mamba architecture, and a Twin-Path Decoder (TPD). One decoder focuses on global detail recovery, while the other restores texture and edge information. This structure minimizes detail loss and improves the model’s ability to capture multi-level features. The collaborative effect of TPD reduces over-smoothing and artifact generation, ensuring the preservation of cross-scale spatial information. Extensive subjective and objective evaluations demonstrate that PDMambaNet outperforms existing methods in segmentation performance. The code is available in the supplementary material.

External IDs:dblp:conf/icmcs/RenZSC25