DB-MSMUNet: Dual Branch Multi-Scale Mamba UNet for Pancreatic CT Scans Segmentation

2025-12-15

IEEE International Conference on Bioinformatics and Biomedicine

AI Summary

Pancreas and lesion segmentation in CT images remains highly challenging due to low contrast, blurred boundaries, irregular morphology, and small volume. To address this, this work proposes DB-MSMUNet, a dual-branch multi-scale Mamba UNet architecture that innovatively integrates state space models with deformable convolutions to construct a multi-scale Mamba module, jointly modeling global context and local deformations. The network further incorporates dedicated edge and region decoders to enhance boundary accuracy and preserve fine details, respectively, while auxiliary deep supervision is introduced to strengthen multi-scale feature discriminability. Evaluated on the NIH, MSD, and a clinical pancreatic tumor dataset, the method achieves Dice scores of 89.47%, 87.59%, and 89.02%, respectively, significantly outperforming existing approaches in segmentation accuracy, boundary fidelity, and cross-dataset robustness.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multi-instance/Multi-view Learning
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Web Mining and Content Analysis: Large pretrained models with web data
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Accurate segmentation of the pancreas and its lesions in CT scans is crucial for the precise diagnosis and treatment of pancreatic cancer. However, it remains a highly challenging task due to several factors such as low tissue contrast with surrounding organs, blurry anatomical boundaries, irregular organ shapes, and the small size of lesions. To tackle these issues, we propose DB-MSMUNet (Dual-Branch Multi-scale Mamba UNet), a novel encoder-decoder architecture designed specifically for robust pancreatic segmentation. The encoder is constructed using a Multi-scale Mamba Module (MSMM), which combines deformable convolutions and multi-scale state space modeling to enhance both global context modeling and local deformation adaptation. The network employs a dual-decoder design: the edge decoder introduces an Edge Enhancement Path (EEP) to explicitly capture boundary cues and refine fuzzy contours, while the area decoder incorporates a Multi-layer Decoder (MLD) to preserve fine-grained details and accurately reconstruct small lesions by leveraging multi-scale deep semantic features. Furthermore, Auxiliary Deep Supervision (ADS) heads are added at multiple scales to both decoders, providing more accurate gradient feedback and further enhancing the discriminative capability of multi-scale features. We conduct extensive experiments on three datasets: the NIH Pancreas dataset, the MSD dataset, and a clinical pancreatic tumor dataset provided by collaborating hospitals. DB-MSMUNet achieves Dice Similarity Coefficients of $89.47 \%, 87.59 \%$, and 89.02 %, respectively, outperforming most existing state-of-the-art methods in terms of segmentation accuracy, edge preservation, and robustness across different datasets. These results demonstrate the effectiveness and generalizability of the proposed method for real-world pancreatic CT segmentation tasks.

Problem

• pancreatic segmentation
• CT scans
• low tissue contrast
• blurry boundaries
• small lesions

Innovation

• Multi-scale Mamba
• Dual-branch Decoder
• Edge Enhancement Path
• Auxiliary Deep Supervision
• State Space Modeling