Seg-CapNet:心脏MRI图像分割神经网络模型  

Seg-CapNet:neural network model for the cardiac MRI segmentation

作　　者：刘畅[1] 林楠[1] 曹仰杰[1] 杨聪 Liu Chang;Lin Nan;Cao Yangjie;Yang Cong(School of Software,Zhengzhou University,Zhengzhou 450000,China)

机构地区：[1]郑州大学软件学院,郑州450000

出　　处：《中国图象图形学报》2021年第2期452-463,共12页Journal of Image and Graphics

基　　金：国家自然科学基金项目(61972092)。

摘　　要：目的针对现有神经网络模型需要对左心室心肌内膜和外膜单独建模的问题,本文提出了一种基于胶囊结构的心脏磁共振图像(magnetic resonance imaging,MRI)分割模型Seg-CapNet,旨在同时提取心肌内膜和外膜,并保证两者的空间位置关系。方法首先利用胶囊网络将待分割目标转换成包含目标相对位置、颜色以及大小等信息的向量,然后使用全连接将这些向量的空间关系进行重组,最后采用反卷积对特征图进行上采样,将分割图还原为输入图像尺寸。在上采样过程中将每层特征图与卷积层的特征图进行连接,有助于图像细节还原以及模型的反向传播,加快训练过程。Seg-CapNet的输出向量不仅有图像的灰度、纹理等底层图像特征,还包含目标的位置、大小等语义特征,有效提升了目标图像的分割精度。为了进一步提高分割质量,还提出了一种新的损失函数用于约束分割结果以保持多目标区域间的相对位置关系。结果在ACDC(automated cardiac diagnosis challenge)2017、MICCAI(medical image computing and computer-assisted intervention)2013和MICCAI2009等3个心脏MRI分割竞赛的公开数据集上对Seg-CapNet模型进行训练和验证,并与神经网络分割模型U-net和Seg Net进行对比。实验结果表明,相对于U-Net和Seg Net,Seg-CapNet同时分割目标重叠区域的平均Dice系数提升了3.5%,平均豪斯多夫距离(Hausdorff distance,HD)降低了18%。并且Seg-CapNet的参数量仅为U-Net的54%、SegNet的40%,在提升分割精度的同时,降低了训练时间和复杂度。结论本文提出的Seg-CapNet模型在保证同时分割重叠区域目标的同时,降低了参数量,提升了训练速度,并保持了较好的左心室心肌内膜和外膜分割精度。Objective Image segmentation tasks suffer from the problem in which multiple overlapping regions are required to be extracted,such as the division of the endocardium and epicardium of the heart’s left ventricle.Existing neural network segmentation models typically segment the target based on pixel classification due to the overlapping of pixels in the two regions and then convert the segmentation problem into a classification problem.However,the overlapping area of pixels may not be simultaneously classified well.In general,existing neural networks must train model parameters for each target to obtain accurate segmentation results,reducing segmentation efficiency.To address these issues,we propose a segmentation model,called Seg-CapNet,which is based on a capsule network structure.Method Current segmentation models based on convolutional neural networks control the size of feature maps through operations,such as maximum or average pool,and transmit image feature information from the upper layer to the next layer.Such pooling operations lose the spatial information of components in the process of information transmission.Therefore,the proposed Seg-CapNet model uses a capsule network structure to extract vectors that contain spatial,color,size,and other target information.Compared with current network structures,the output of a capsule network is in vector form,and the information of the target is included in the entity vector through routing iteration.Seg-CapNet utilizes this feature to strip overlapping objects from the image space and convert them into noninterference feature vectors,separating objects with overlapping regions.Then,the spatial position relation of multiple target vectors are reconstructed using fully connected layers.Lastly,the reconstructed image is upsampled and the segmented image is restored to the same size as the input image.During up-sampling,the feature graph of the up-sampling layer and that of the convolutional layer are skip-connected.This process is conducive to restoring image det

关 键 词：神经网络 胶囊网络 图像分割 重叠区域目标 心脏磁共振图像 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]