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.
Abstract (translated)
在CT扫描中准确分割胰腺及其病变对于胰腺癌的精确诊断和治疗至关重要。然而，由于多种因素（如与周围器官对比度低、解剖边界模糊、器官形状不规则以及病灶体积小等），这一任务仍具有高度挑战性。为了应对这些问题，我们提出了DB-MSMUNet（双分支多尺度眼镜蛇U型网络），这是一种专门为稳健胰腺分割而设计的新型编码器-解码器架构。 该模型的编码器采用多尺度眼镜蛇模块（MSMM）构建，结合可变形卷积和多层次状态空间建模技术以增强全局上下文建模能力和局部形变适应能力。网络采用了双解码器设计：边界解码器引入了边缘增强路径(EEP)，旨在明确捕获边界线索并细化模糊轮廓；而区域解码器则整合了多层解码器(MLD)来保留细粒度细节，并通过利用多层次深度语义特征准确重建小病灶。此外，还在两个解码器的多个尺度上增加了辅助深层监督(ADS)头，以便提供更精确的梯度反馈并进一步增强多层次特征的鉴别能力。 我们在三个数据集上进行了广泛的实验：NIH胰腺数据集、MSD数据集和由合作医院提供的临床胰腺肿瘤数据集。DB-MSMUNet在这些数据集中分别达到了89.47%、87.59% 和 89.02% 的Dice相似系数，相较于现有最先进的方法，在分割精度、边缘保持能力及跨不同数据集的鲁棒性方面均表现出色。 这些结果证明了所提出的方法在真实世界胰腺CT图像分割任务中的有效性和泛化性能。
URL
https://arxiv.org/abs/2601.04676
