脊柱MR图像自动分割方法的研究

doi:10.3778/j.issn.1002-8331.2105-0052

摘要/Abstract

摘要： 脊柱磁共振（magnetic resonance，MR）图像精确分割是脊柱配准、三维重建等技术的前提。传统脊柱MR图像分割方法过程繁琐，精度低。为克服传统方法弊端，提出了一种基于深度学习的脊柱MR图像自动分割方法。该方法构建对称通道卷积神经网络提取多尺度图像特征，通过残差连接解决训练中网络退化问题，同时用跳跃连接层连接中间层特征减少信息丢失。在搭建的网络模型中加入卷积块注意力机制关注空间和通道中的有效特征。实验结果表明，该模型在测试集上的平均DSC系数为0.861?9，相比FCN、U-Net、DeeplabV3+和UNet++网络模型分别提高了15.34%、7.08%、5.79%、3.1%。该模型可应用于临床实践中提升脊柱MR图像的分割精度。

关键词: 图像分割, 对称通道卷积网络, 残差连接, 深度学习, 多尺度特征

Abstract: Accurate segmentation of spinal magnetic resonance（MR） images is the premise of spinal registration and 3D reconstruction. The traditional spinal MR image segmentation methods are complicated and low precision. To overcome the disadvantages of traditional methods, an automatic spinal MR image segmentation method based on deep learning is proposed. In this method, a symmetric channel convolutional neural network is designed to extract multi-scale image features. The residual connection solves the problem of network degradation in training and uses the jump connection layer to connect the features of the middle layer to reduce information loss. On this basis, the convolutional block attention mechanism is added to the proposed model to extract spatial and channel features more effectively. The experimental results show that the average DSC coefficient of this model on the test set is 0.8619, which is 15.34%, 7.08%, 5.79% and 3.1% higher than that of FCN, U-Net, DeeplabV3+ and UNet++ network models, respectively. The segmentation results can be applied in clinical practice to improve the segmentation accuracy of spinal MR images.

Key words: image segmentation, symmetric channel convolutional neural network, residual connection, deep learning, multi-scale feature

于文涛, 张俊华, 梅建华, 罗旭东. 脊柱MR图像自动分割方法的研究[J]. 计算机工程与应用, 2022, 58(22): 203-209.

YU Wentao, ZHANG Junhua, MEI Jianhua, LUO Xudong. Research on Automatic Segmentation Method of Spinal MR Images[J]. Computer Engineering and Applications, 2022, 58(22): 203-209.

参考文献

[1] 顾菊平，程天宇，华亮.面向脊柱生物建模的图像分割与配准研究综述[J].系统仿真学报，2019，31（2）：167-173.
GU J P，CHENG T Y，HUA L.A review of image segment-ation and registration for spinal biometrics[J].Journal of System Simulation，2019，31（2）：167-173.
[2] YANG P，SONG W，ZHAO X B，et al.An improved Otsu threshold segmentation algorithm[J].International Journal of Computational Science and Engineering，2020，22（1）：146-153.
[3] ZHANG K L，LU W M，MARZILIANO P.Automatic knee cartilage segmentation from multi-contrast MR images using support vector machine classification with spatial dependencies[J].Magnetic Resonance Imaging，2013，31（10）：1731-1743.
[4] TRIPOLITI E E，FOTIADIS D I，ARGYROPOULOU M.Automated segmentation and quantification of inflammatory tissue of the hand in rheumatoid arthritis patients using magnetic resonance imaging data[J].Artificial Intelligence in Medicine，2007，40（2）：65-85.
[5] ZUKIC D，VLASAAK A，EGGER J，et al.Robust detection and segmentation for diagnosis of vertebral diseases using routine MR images[J].Computer Graphics Forum，2014，33（6）：190-204.
[6] CHU C，BELAVY D L，ARMBRECHT G，et al.Fully automatic localization and segmentation of 3D vertebral bodies from CT/MR images via a learning-based method[J].PLoS One，2015，10（11）：e0143327.
[7] LONG J，SHELHAMER E，DARRELL T，et al.Fully convolutional networks for semantic segmentation[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition，2015：3431-3440.
[8] JANSSENS R，ZENG G，ZHENG G.Fully automatic segmentation of lumbar vertebrae from CT images using cascaded 3D fully convolutional networks[C]//IEEE 15th International Symposium on Biomedical Imaging，2018：893-897.
[9] RONNEBERGER O，FISCHER P，BROX T.U-Net：convolutional networks for biomedical image segmentation[C]//18th International Conference on Medical Image Computing and Computer-Assisted Intervention，2015：234-241.
[10] HORNG M H，KUOK C P，FU M J，et al.Cobb angle measurement of spine from X-ray images using convolutional neural network[J].Computational and Mathematical Methods in Medicine，2019：6357171.
[11] ZHAO H S，SHI J P，QI X J，et al.Pyramid scene parsing network[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition，2017：6230-6239.
[12] ZHOU Z，SIDDIQUEE M M R，TAJBAKHSH N，et al.UNet++：redesigning skip connections to exploit multiscale features in image segmentation[J].IEEE Transactions on Medical Imaging，2019，39（6）：1856-1867.
[13] SEKUBOYINA A，VALENTINITSCH A，KIRSCHKE J S，et al.A localisation-segmentation approach for multi-label annotation of lumbar vertebrae using deep nets[J].arXiv：1703.04347，2017.
[14] SZEGEDY C，IOFFE S，VANHOUCKE V，et al.Inception-v4，Inception-ResNet and the impact of residual connections on learning[C]//31st AAAI Conference on Artificial Intelligence，2017：4278-4284.
[15] SZEGED C，VANHOUCKE V，IOFFE S，et al.Rethinking the Inception architecture for computer vision[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition，2016：2818-2826.
[16] IBTEHAZ N，RAHMAN M S.MultiResUNet：rethinking the U-Net architecture for multimodal biomedical image segmentation[J].Neural Networks，2020，121：74-87.
[17] HE K M，ZHANG X Y，REN S Q，et al.Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition，2016：770-778.
[18] HU J，SHEN L，SUN G，et al.Squeeze-and-excitation networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition，2018：7132-7141.
[19] BRUCH S，WANG X，BENDERSKY M，et al.An analysis of the softmax cross entropy loss for learning-to-rank with binary relevance[C]//2019 ACM SIGIR International Conference on Theory of Information Retrieval，2019：75-78.
[20] VAN LEEMPUT K，MAES F，VANDERMEULEN D，et al.Automated model-based bias field correction of MR images of the brain[J].IEEE Transactions on Medical Imaging，1999，18（10）：885-896.
[21] JANGID M，SRIVASTAVA S.Accuracy enhancement of Devanagari character recognition by gray level normalization[C]//7th International Conference on Computing Communication and Networking Technologies，2016：1-5.