摘要
脑肿瘤是一种严重威胁人类健康的疾病,脑肿瘤精确分割在临床诊疗中非常重要。由于脑肿瘤形状大小各异、位置不固定和边界模糊等,实现高精度脑肿瘤自动分割仍是一项具有挑战性的任务。近年来,U-Net凭借其简洁的架构和优秀的性能成为解决医学图像分割任务的主流模型,但其也存在局部感受野有限、空间信息丢失和未充分利用上下文信息等问题。为此,提出一种基于动态卷积和非局部注意力机制的级联U-Net新模型(CDAU-Net)用于脑肿瘤分割任务。首先,将两阶段级联三维U-Net作为主体架构,来重建更精细的高分辨率脑肿瘤空间信息;进而,在级联网络横向连接上添加期望最大化注意力,通过提高网络捕获长距离依赖能力来更好利用肿瘤上下文信息;最后,在级联网络中将普通卷积替换为具有局部自适应能力的动态卷积,可进一步增强网络局部特征捕获能力。在公开的BraTS2019-2020数据集上进行了大量实验并与其他代表性方法进行对比,实验结果表明了所提方法在脑肿瘤分割任务上的有效性。其中,在BraTS2019/2020验证集上获得的全部肿瘤、肿瘤核心和增强肿瘤分割Dice值分别为0.897/0.903,0.826/0.828和0.781/0.786,表现出了良好的脑肿瘤分割性能。
Brain tumor is a common brain disease that heavily threatens human health,so accurate brain tumor segmentation is vital for clinic diagnosis and treatment of patients.Due to different shapes and sizes,unstable positions and fuzzy boundaries of brain tumors,it is a challenging task to achieving high-precision automatic brain tumors segmentation.Recently,U-Net has become the mainstream model for medical image segmentation due to its concise architecture and excellent performance.But it also has some problems,such as limited local receptive field,spatial information loss and insufficient use of context information.Therefore,we propose a new cascade U-Net model based on dynamic convolution and non-local attention mechanism,named CDAU-Net.Firstly,a two-stage cascade 3D U-Net architecture is proposed to reconstruct more detailed and high-resolution spatial information of brain tumors.Then,the expectation-maximization attention is added to the skip connection of CDAU-Net,and the tumor context information is better utilized by improving the network’s ability to capture long-distance dependencies.Finally,the normal convolution is replaced by the dynamic convolution with local adaptive ability in CDAU-Net,which can further enhance the local feature capture ability of the network.Extensive experiments are conducted on public dataset BraTS 2019/2020 and compared with other representative methods,and experimental results show that the proposed method is effective in brain tumor segmentation.The CDAU-Net obtained the Dice values of whole tumor,tumor core and enhancing tumor segmentation on BraTS 2019/2020 verification sets are 0.897/0.903,0.826/0.828 and 0.781/0.786,respectively,which achieves good brain tumor segmentation performance.
作者
陈柏年
韩雨童
何涛
刘斌
张建新
CHEN Bonian;HAN Yutong;HE Tao;LIU Bin;ZHANG Jianxin(School of Computer Science and Engineering,Dalian Minzu University,Dalian,Liaoning 116600,China;Institute of Machine Intelligence and Bio-computing,Dalian Minzu University,Dalian,Liaoning 116600,China;International School of Information Science and Engineering,Dalian University of Technology,Dalian,Liaoning 116620,China)
出处
《计算机科学》
CSCD
北大核心
2023年第S02期1019-1025,共7页
Computer Science
基金
国家自然科学基金(61972062)
国家民委中青年英才培养计划项目
辽宁省应用基础研究计划项目。
关键词
脑肿瘤分割
U-Net
级联网络
动态卷积
期望最大化注意力
Brain tumor segmentation
U-Net
Cascade network
Dynamic convolution
Expectation-maximizing attention
