Zhou Gangyi, Li Xiaowei, Zeng Hongran, Zhang Chongyang, Wu Guohang, Zhao Wuxiang
College of Electronics and Information Engineering, Sichuan University, Chengdu 610017, China.
Sensors (Basel). 2025 Aug 1;25(15):4740. doi: 10.3390/s25154740.
Recent advancements in deep learning have significantly enhanced brain tumor segmentation from MRI data, providing valuable support for clinical diagnosis and treatment planning. However, challenges persist in effectively integrating prior medical knowledge, capturing global multimodal features, and accurately delineating tumor boundaries. To address these challenges, the Hybrid Network for Multimodal Brain Tumor Segmentation (HN-MBTS) is proposed, which incorporates prior medical knowledge to refine feature extraction and boundary precision. Key innovations include the Two-Branch, Two-Model Attention (TB-TMA) module for efficient multimodal feature fusion, the Linear Attention Mamba (LAM) module for robust multi-scale feature modeling, and the Residual Attention (RA) module for enhanced boundary refinement. Experimental results demonstrate that this method significantly outperforms existing approaches. On the BraT2020 and BraT2023 datasets, the method achieved average Dice scores of 87.66% and 88.07%, respectively. These results confirm the superior segmentation accuracy and efficiency of the approach, highlighting its potential to provide valuable assistance in clinical settings.
深度学习的最新进展显著提高了从MRI数据中进行脑肿瘤分割的能力，为临床诊断和治疗规划提供了有价值的支持。然而，在有效整合先验医学知识、捕捉全局多模态特征以及准确描绘肿瘤边界方面，挑战依然存在。为应对这些挑战，提出了用于多模态脑肿瘤分割的混合网络（HN-MBTS），该网络结合先验医学知识以优化特征提取和边界精度。关键创新包括用于高效多模态特征融合的双分支双模型注意力（TB-TMA）模块、用于稳健多尺度特征建模的线性注意力曼巴（LAM）模块以及用于增强边界细化的残差注意力（RA）模块。实验结果表明，该方法显著优于现有方法。在BraT2020和BraT2023数据集上，该方法分别取得了87.66%和88.07%的平均Dice分数。这些结果证实了该方法卓越的分割准确性和效率，凸显了其在临床环境中提供有价值帮助的潜力。
