Yang Lijuan, Dong Qiumei, Lin Da, Tian Chunfang, Lü Xinliang
Department of Rheumatology, Inner Mongolia Autonomous Region Hospital of Traditional Chinese Medicine, Hohhot, China.
College of Traditional Chinese Medicine, Inner Mongolia Medical University, Hohhot, China.
Front Comput Neurosci. 2025 Jan 29;19:1513059. doi: 10.3389/fncom.2025.1513059. eCollection 2025.
Brain tumors are one of the major health threats to humans, and their complex pathological features and anatomical structures make accurate segmentation and detection crucial. However, existing models based on Transformers and Convolutional Neural Networks (CNNs) still have limitations in medical image processing. While Transformers are proficient in capturing global features, they suffer from high computational complexity and require large amounts of data for training. On the other hand, CNNs perform well in extracting local features but have limited performance when handling global information. To address these issues, this paper proposes a novel network framework, MUNet, which combines the advantages of UNet and Mamba, specifically designed for brain tumor segmentation. MUNet introduces the SD-SSM module, which effectively captures both global and local features of the image through selective scanning and state-space modeling, significantly improving segmentation accuracy. Additionally, we design the SD-Conv structure, which reduces feature redundancy without increasing model parameters, further enhancing computational efficiency. Finally, we propose a new loss function that combines mIoU loss, Dice loss, and Boundary loss, which improves segmentation overlap, similarity, and boundary accuracy from multiple perspectives. Experimental results show that, on the BraTS2020 dataset, MUNet achieves DSC values of 0.835, 0.915, and 0.823 for enhancing tumor (ET), whole tumor (WT), and tumor core (TC), respectively, and Hausdorff95 scores of 2.421, 3.755, and 6.437. On the BraTS2018 dataset, MUNet achieves DSC values of 0.815, 0.901, and 0.815, with Hausdorff95 scores of 4.389, 6.243, and 6.152, all outperforming existing methods and achieving significant performance improvements. Furthermore, when validated on the independent LGG dataset, MUNet demonstrated excellent generalization ability, proving its effectiveness in various medical imaging scenarios. The code is available at https://github.com/Dalin1977331/MUNet.
脑肿瘤是对人类健康的主要威胁之一，其复杂的病理特征和解剖结构使得精确分割和检测至关重要。然而，现有的基于Transformer和卷积神经网络（CNN）的模型在医学图像处理中仍存在局限性。虽然Transformer擅长捕捉全局特征，但它们计算复杂度高，需要大量数据进行训练。另一方面，CNN在提取局部特征方面表现出色，但在处理全局信息时性能有限。为了解决这些问题，本文提出了一种新颖的网络框架MUNet，它结合了UNet和Mamba的优点，专门用于脑肿瘤分割。MUNet引入了SD-SSM模块，通过选择性扫描和状态空间建模有效地捕捉图像的全局和局部特征，显著提高了分割精度。此外，我们设计了SD-Conv结构，在不增加模型参数的情况下减少特征冗余，进一步提高计算效率。最后，我们提出了一种新的损失函数，将mIoU损失、Dice损失和边界损失相结合，从多个角度提高分割重叠度、相似度和边界精度。实验结果表明，在BraTS2020数据集上，MUNet在增强肿瘤（ET）、全肿瘤（WT）和肿瘤核心（TC）上的DSC值分别达到0.835、0.915和0.823，Hausdorff95分数分别为2.421、3.755和6.437。在BraTS2018数据集上，MUNet的DSC值分别为0.815、0.901和0.815，Hausdorff95分数分别为4.389、6.243和6.152，均优于现有方法并实现了显著的性能提升。此外，在独立的LGG数据集上进行验证时，MUNet表现出出色的泛化能力，证明了其在各种医学成像场景中的有效性。代码可在https://github.com/Dalin1977331/MUNet获取。
