DRLSE-Based Split-Step Liver and Tumor Segmentation Algorithm

doi:10.3778/j.issn.1002-8331.2011-0281

Abstract

Abstract: In order to improve the segmentation accuracy of liver and liver tumors in CT images, a stepwise segmentation method with improved DRLSE is proposed. The first stage: the liver is segmented by the stepwise segmentation method. （1） The liver is coarse-segmented by threshold processing, morphological method and adaptive region growth method. （2） Mathematical morphology is used to optimize the segmentation results for liver segmentation. The second stage：it constructs the distance regularized level set evolution （improved DRLSE） model of parametric gradient morphology and anisotropic diffusion filtering for liver tumor segmentation. In the experiment, the validity of the method is verified by using 3Dircadb data set, and the performance of DICE, VOE, ASD and MSD indexes are calculated to evaluate the segmentation accuracy. The experimental results show that this method does not require the establishment of training process and statistical model, and is particularly effective for CT image segmentation with complex shape and strength changes. The numerical results of quantitative analysis show that the segmentation performance is superior to the comparison algorithm, improves the segmentation accuracy, and has strong robustness, which provides help for doctors to diagnose and treat liver cancer.

Key words: level set, region growing, distance regularized level set evolution（DRLSE）, 3D reconstruction, anisotropic diffusion filtering

摘要： 为了提升CT图像肝脏及肝脏肿瘤的分割精度，提出一种改进DRLSE的分步式肝脏及肿瘤分割方法。第一阶段：采用分步式分割方法对肝脏进行分割，（1）采用阈值处理、形态学方法、自适应区域生长方法进行肝脏的粗分割；（2）采用数学形态对分割结果进行优化，进行肝脏的细分割。第二阶段：构造参数梯度形态学和各向异性扩散滤波的距离正则化水平集演化（改进的DRLSE）模型进行肝脏肿瘤分割。实验利用3Dircadb数据集验证方法的有效性，计算了DICE、VOE、ASD和MSD指标评估分割的性能。实验结果表明该方法无需进行训练过程和统计模型的建立，对于复杂的形状和强度变化的CT图像分割效果尤为明显。由定量分析的数值结果显示，分割性能均优于比较算法，提高了分割准确率，具有较强的鲁棒性，为医生诊断和治疗肝癌提供帮助。

关键词: 水平集, 区域生长算法, 距离正则化水平集演化（DRLSE）, 三维重建, 各向异性扩散滤波

GUO Beibei, MA Ziping, WANG Xingyan, YANG Ke. DRLSE-Based Split-Step Liver and Tumor Segmentation Algorithm[J]. Computer Engineering and Applications, 2022, 58(14): 200-209.

郭贝贝, 马自萍, 王兴岩, 杨珂. 改进DRLSE的分步式肝脏及肿瘤分割方法[J]. 计算机工程与应用, 2022, 58(14): 200-209.

References

[1] THOMAZ R L，CARNEIRO P C，BONIN J E，et al.Liver segmentation from MDCT using region growing based on t location-scale distribution[C]//XXV Congresso Brasileiro de Engenharia Biomédica，2016.
[2] TAN S，LI L，CHOI W，et al.Adaptive region-growing with maximum curvature strategy for tumor segmentation in 18F-FDG PET[J].Physics in Medicine and Biology，2017，62（13）：5383.
[3] ARICA S，AVSAR T S，ERBAY G.A plain segmentation algorithm utilizing region growing technique for automatic partitioning of computed tomography liver images[C]//2018 Medical Technologies National Congress（TIPTEKNO），2018：1-4.
[4] ZENG Y，LIAO S，TANG P，et al.Automatic liver vessel segmentation using 3D region growing and hybrid active contour model[J].Computers in Biology and Medicine，2018，97：63-73.
[5] CHARTRAND G，CRESSON T，CHAV R，et al.Liver segmentation on CT and MR using Laplacian mesh optimization[J].IEEE Transactions on Biomedical Engineering，2016，64（9）：2110-2121.
[6] OSHER S，SETHIAN J.Fronts propagating with curvature dependent speed：algorithms based on the Hamilton-Jacobi formulation[J].Journal of Computational Physics，1988，79（1）：12-49.
[7] ZHENG Z，ZHANG X，XU H，et al.A unified level set framework combining hybrid algorithms for liver and liver tumor segmentation in CT images[J].BioMed Research International，2018：3815346.
[8] LI C Y，WANG X Y，EBERL S，et al.A likelihood and local constraint level set model for liver tumor segmentation from CT volumes[J].IEEE Transactions on Bio-medical Engineering，2013，60（10）：2967-2977.
[9] LI Y，ZHAO Y Q，ZHANG F，et al.Liver segmentation from abdominal CT volumes based on level set and sparse shape composition[J].Computer Methods and Programs in Biomedicine，2020，195：105533.
[10] VIVANTI R，EPHRAT A，JOSKOWICZ L，et al.Automatic liver tumor segmentation in follow-up CT scans：preliminary method and results[C]//International Workshop on Patch-based Techniques in Medical Imaging.Cham：Springer，2015：54-61.
[11] WANG X，ZHANG W，CUI Y.Tumor segmentation in lung CT images based on support vector machine and improved level set[J].Optoelectronics Letters，2015，11（5）：395-400.
[12] 郭雯，鞠忠建，吴青南，等.基于深度学习的器官自动分割研究进展[J].医疗卫生装备，2020，41（1）：85-94.
GUO W，JU Z J，WU Q N，et al.Research progress of automatic organ image segmentation based on deep learning[J].Chinese Medical Equipment Journal，202，41（1）：85-94.
[13] 张丽园.基于CT图像的肝部肿瘤的自动分割算法研究[D].成都：电子科技大学，2019.
ZHANG L Y.Research on automatic segmentation algorithm of liver tumor based on CT image[D].Chengdu：University of Electronic Science and Technology，2019.
[14] 李雯.基于深度卷积神经网络的CT图像肝脏肿瘤分割方法研究[D].深圳：中国科学院深圳先进技术研究院，2016.
LI W.Segmentation of liver tumors in CT images based on deep convolutional neural network[D].Shenzhen：Shenzhen Institute of Advanced Technology，Chinese Academy of Sciences，2016.
[15] HAVAEI M，DAVY A.Brain tumor segmentation with deep neural networks[J].Medical Image Analysis，2017，35：18-31.
[16] LI C M，XU C Y，GUI C F，et al.Distance regularized level set evolution and its application to image segmentation[J].IEEE Transactions on Image Processing，2010，19（12）：3243-3254.
[17] 李阳，赵于前，廖苗，等.基于水平集和形状描述符的腹部CT序列肝脏自动分割[J].自动化学报，2021，47（2）：327-337.
LI Y，ZHAO Y Q，LIAO M，et al.Automatic liver segmentation from CT volumes based on level set and shape descriptor[J].Acta Automatica Sinica，2021，47（2）：327-337.
[18] FAN D，CHENG M，LIU Y，et al.Structure-measure：a new way to evaluate foreground maps[C]//International Conference on Computer Vision，2017：4558-4567.
[19] 杨雪.肝脏CT图像分割并行处理方法的设计与实现[D].大连：大连理工大学，2016.
YANG X.Design and implementation of liver CT image segmentation parallel processing method[D].Dalian：Dalian University of Technology，2016.
[20] 裘静韬，邹俊忠，郭玉成，等.应用化肝脏病灶分割的预测方案[J].计算机工程与应用，2020，56（20）：173-178.
QIU J T，ZOU J Z，GUO Y C，et al.Applicable prediction scheme for segmentation of liver and lesion[J].Computer Engineering and Applications，2020，56（20）：173-178.
[21] 袁勇，张固澜.一种改进的中值滤波方法[J].成都理工大学学报（自然科学版），2013，40（2）：125-129.
YUAN Y，ZHANG G L.An improved median filtering method[J].Journal of Chengdu University of Technology（Science & Technology Edition），2013，40（2）：125-129.
[22] WANG Y，WANG Y J.Anisotropic diffusion filtering method with weighted directional structure tensor[J].Biomedical Signal Processing and Control，2019，53：101590.
[23] HEIMANN T，VAN GINNEKEN B，STYNER M，et al.Comparison and evaluation of methods for liver segmentation from CT datasets[J].IEEE Transactions on Medical Imaging，2009，28（8）：1251-1265.
[24] 牛力丕，毛士艺，陈炜.基于Hausdorff距离的图像配准研究[J].电子与信息学报，2007（1）：35-38.
NIU L P，MAO S Y，CHEN W.Image registration based on Hausdorff distance[J].Journal of Electronics and Information Technology，2007（1）：35-38.
[25] 张杰妹，杨词慧.基于RV-FCN的CT肝脏影像自动分割算法[J].计算机工程，2019，45（7）：258-263.
ZHANG J M，YANG C H.Automatic segmentation algorithm of CT liver image based on RV-FCN[J].Computer Engineering，2019，45（7）：258-263.
[26] RONNEBERGER O，FISCHER P，BROX T，et al.U-Net：convolutional networks for biomedical image segmentation[C]//International Conference on Medical Image Computing and Computer Assisted Intervention，2015：234-241.
[27] LIAO M，ZHAO Y，LIU X，et al.Automatic liver segmentation from abdominal CT volumes using graph cuts and border marching[J].Computer Methods and Programs in Biomedicine，2017，143：1-12.
[28] 谢勤岚，潘先攀.自适应形状约束Graph cuts算法在腹部CT图像分割中的应用[J].中南民族大学学报（自然科学版），2019，38（1）：119-125.
XIE Q L，PAN X P.Adaptive shape constraint based graph cuts and its application on CT images segmentation[J].Journal of South-Central University for Nationalities（Natural Science Edition），2019，38（1）：119-125.
[29] 亢洁，丁菊敏，万永，等.基于分水岭修正与U-Net的肝脏图像分割算法[J].计算机工程，2020，46（1）：255-261.
KANG J，DING J M，WAN Y，et al.Liver image segmentation algorithm based on watershed correction and U-Net[J].Computer Engineering，2020，46（1）：255-261.
[30] 关天民，刘光孟，轩亮.基于ITK和VTK的医学图像分割与重建[J].大连交通大学学报，2019，40（3）：61-65.
GUAN T M，LIU G M，XUAN L.Medical image segmentation and reconstruction based on ITK and VTK[J].Journal of Dalian Jiaotong University，2019，40（3）：61-65.
[31] 李泽宇，陈一民，赵艳，等.拟合正态分布曲线的肺野图像分割与三维重建[J].计算机工程与设计，2017，38（5）：1277-1281.
LI Z Y，CHEN Y M，ZHAO Y，et al.Segmentation and three-dimensional reconstruction of lung field image by fitting normal distribution curve[J].Computer Engineering and Design，2017，38（5）：1277-1281.
[32] 方驰华，卢绮萍，刘允怡.复杂性肝脏肿瘤三维可视化精准诊治指南（2019版）[J].中国实用外科杂志，2019，39（8）：766-774.
FANG C H，LU Q P，LIU Y Y.Guidelines for precision diagnosis and treatment of complex liver tumor guided by three-dimensional visualization technology（version 2019）[J].Chinese Journal of Practical Surgery，2019，39（8）：766-774.
[33] LI G D，CHEN X J，SHI F，et al.Automatic liver segmentation based on shape constraints and deformable graph cut in CT images[J].IEEE Transactions on Image Processing，2015，24（12）：5315-5329.
[34] ERDT M，KIRSCHNER M.Fast automatic liver segmentation combining learned shape priors with observed shape deviation[C]//2010 IEEE 23rd International Symposium on Computer-Based Medical Systems（CBMS），2010：249-254.
[35] 郑洲，张学昌，郑四鸣，等.基于区域增长与统一化水平集的CT肝脏图像分割[J].浙江大学学报（工学版），2018，52（12）：2382-2396.
ZHENG Z，ZHANG X C，ZHENG S M，et al.Liver segmentation in CT images based on regional-growth and unified level set method[J].Journal of Zhejiang University（Engineering Science），2012，52（12）：2382-2396.
[36] 刘洵.延时增强MRI图像左心房分割与心房壁纤维化组织量化分析[D].上海：上海交通大学，2019.
LIU X.Left atrium segmentation and quantitative analysis of atrial wall fibrosis in delayed-enhancement MRI images[D].Shanghai：Shanghai Jiaotong University，2019.
[37] 李冰.基于水平集方法的肝脏CT图像分割算法研究[D].沈阳：东北大学，2015.
LI B.Research on liver CT image segmentation algorithm based on level set method[D].Shenyang：Northeast University，2015.