@article{Wei:2026:10.1016/j.eswa.2026.132854,
author = {Wei, X and Liao, Y and Zhu, J and Zhang, S and Yang, G and Jin, Q and Lai, X and Tian, Q},
doi = {10.1016/j.eswa.2026.132854},
journal = {Expert Systems with Applications},
title = {A hybrid CNN–Mamba state space model with pyramid-pooled skip connections for prostate tumor segmentation},
url = {http://dx.doi.org/10.1016/j.eswa.2026.132854},
volume = {327},
year = {2026}
}

Download

TY  - JOUR
AB  - Automatic prostate tumor segmentation in multiparametric magnetic resonance imaging (mpMRI) can support targeted biopsy and therapy planning, but remains challenging due to the small, heterogeneous and low-contrast nature of the lesions. CNN-based encoder-decoder models capture local detail well, but struggle with long-range reasoning. Transformers excel at global interactions, but are computationally expensive. Mamba/state-space models enable efficient global modelling, but often lack boundary-sensitive local refinement. We propose ProMamba: a hybrid CNN-Mamba segmentation framework combining local detail extraction with efficient global dependency modelling within a hierarchical U-Net architecture. Its dual-branch Pro-SSM block incorporates a depthwise dilated convolution module (DDCM) to extract multi-scale boundary cues, as well as a Mamba-based visual state-space (VSS) branch to aggregate multi-directional long-range context. The two branches are fused via channel concatenation and shuffling while preserving the 2D convolutional pathway and avoiding spatial flattening. Pyramid-pooled skip connections further reduce the semantic gap between the encoder and decoder and improve small-lesion delineation. Using five-fold cross-validation at the patient level on Prostate158, PI-CAI 2022 and an ethics-approved private cohort of 110 cases, ProMamba achieves Dice scores of 51.39%, 59.46% and 48.49% respectively, outperforming strong CNN, nnU-Net, efficient Transformer/hybrid and Mamba baselines. ProMamba also shows competitive latency and memory usage and generalizes well to PROMISE12 and ACDC, achieving Dice scores of 91.40% and 92.14%, respectively.
AU  - Wei,X
AU  - Liao,Y
AU  - Zhu,J
AU  - Zhang,S
AU  - Yang,G
AU  - Jin,Q
AU  - Lai,X
AU  - Tian,Q
DO  - 10.1016/j.eswa.2026.132854
PY  - 2026///
SN  - 0957-4174
TI  - A hybrid CNN–Mamba state space model with pyramid-pooled skip connections for prostate tumor segmentation
T2  - Expert Systems with Applications
UR  - http://dx.doi.org/10.1016/j.eswa.2026.132854
VL  - 327
ER  - 

Download