基于多尺度特征融合与注意力的肝脏分割方法  

Liver segmentation method based on multi-scale feature fusion and attention

作　　者：冉梅子 胡小军 姜晓燕 范应方 王航 王海玲 高永彬 RAN Meizi;HU Xiaojun;JIANG Xiaoyan;FAN Yingfang;WANG Hang;WANG Hailing;GAO Yongbin(School of Electronic and Electrical Engineering,Shanghai University of Engineering Science,Shanghai 201620,China;Department of Hepatobiliary Surgery,the Fifth Affiliated Hospital of Southern Medical University,Guangzhou 510000,China)

机构地区：[1]上海工程技术大学电子电气工程学院,上海201620 [2]南方医科大学第五附属医院肝胆外科,广东广州510000

出　　处：《中国医学物理学杂志》2024年第6期739-746,共8页Chinese Journal of Medical Physics

基　　金：广州市科技计划项目(202206010093);上海市科委社会发展项目“科技创新行动计划”(21DZ1204900)。

摘　　要：由于CT影像对比度低、肝脏形状不规则、相邻器官边界模糊,目前基于卷积神经网络的方法在肝脏分割任务上的表现不佳,尤其是在边界识别和小目标检测方面。基于此,提出一种基于多尺度特征融合与注意力的肝脏分割方法(MFFA UNet)。首先,利用多尺度特征融合获取丰富的分割信息,同时使用空间和通道注意力机制捕获全局空间和通道间的关系。其次,通过深度监督模块充分利用中间隐藏层的输出,增强网络的学习能力,加快网络收敛速度。此外,采用一种混合损失函数,以解决类别不平衡的问题,进一步提升模型的分割效能。实验结果表明,所提出的MFFA UNet方法在公共数据集LITS上的表现超越当前主流分割网络,分割结果更接近真实值。Due to the low contrast of CT images,irregular shape of the liver,and blurred boundaries with adjacent organs,the existing methods based on convolutional neural network underperform in liver segmentation tasks,especially for boundary recognition and small object detection.A novel liver segmentation method is proposed based on multi-scale feature fusion and attention,namelyMFFAUNet.Multi-scale feature fusion is firstly employed to acquire abundant segmentation details,while spatial and channel attention mechanisms are utilized to capture global spatial and inter-channel relationships.Additionally,a deep supervision module fully leverages the output of intermediate hidden layers,enhancing the learning capability of the network,which in turn accelerates the network's convergence speed.Moreover,a hybrid loss function is adopted to address the issue of class imbalance,further boosting the model's segmentation efficacy.Experimental results demonstrate that the proposed MFFA UNet outperforms the prevailing segmentation networks on the public LITS dataset,producing results that are closer to the ground truth.

关 键 词：肝脏分割 注意力机制 多尺度特征融合 深度监督 MFFA UNet 

分 类 号：R318[医药卫生—生物医学工程]