作者投稿
专家审稿
编辑办公
Liver CT Image Segmentation Based on an Improved Region Growing Method
-
摘要: 肝脏CT图像的准确分割能为肝脏疾病的研究及早期诊断提供客观依据，也是医疗计量检定中重要的溯源项目。介绍了一种改进的区域生长进行肝脏CT图像自动分割的方法，详细介绍了各步骤处理流程与实现方案。在改进分割方法中，首先通过阈值分割和非线性映射去除噪声，增强图像信息，利用该方法对随机选取的9个腹部CT序列图像进行了分割处理，并与阈值法进行对比分析；利用Quasi-Monte Carlo（QMC）方法用于区域生长算法中种子点的选择和提高区域生长条件；最后，用形态学方法结合Canny算子和Flood填充算法进行后处理，以平滑肝脏轮廓和肝脏分割结果。结果表明，相比阈值法，区域生长方法的分割正确率高达91.89%，能更准确地进行肝脏分割。同时，分割结果的体积重叠误差(VOE)和相对体积差(RVD)统计结果也验证了该方法的有效性和稳定性，表明该方法能有效应用于肝脏CT图像的分割中，可为临床医学中肝脏疾病的诊断提供可靠依据。Abstract: Accurate segmentation of liver CT images can provide an objective basis for liver disease research and early diagnosis, and it is also an important traceable project in medical metrology. This paper introduces an improved automatic segmentation method for liver CT images using a region growing approach, detailing the processing steps and implementation scheme. In the improved segmentation method, noise is first removed and image information is enhanced through threshold segmentation and nonlinear mapping. This method was used to segment nine randomly selected abdominal CT image sequences and compare the results with the threshold method. The Quasi-Monte Carlo (QMC) method is employed for seed point selection and to enhance the region growing conditions. Finally, morphological methods combined with the Canny operator and Flood fill algorithm are used for post-processing to smooth the liver contour and segmentation results. The results show that compared to the threshold method, the region growing method achieves a segmentation accuracy of up to 91.89%, allowing for more precise liver segmentation. Furthermore, the volume overlap error (VOE) and relative volume difference (RVD) statistics of the segmentation results also verify the effectiveness and stability of this method, indicating that it can be effectively applied in liver CT image segmentation and provide reliable support for the diagnosis of liver diseases in clinical medicine.
-
Key words:
- metrology /
- liver CT images /
- image segmentation /
- region growing method /
- seed point selection /
- thresholding method
-
图 1 基于改进的区域生长的肝脏CT分割流程图
Figure 1. Flow chart of liver CT segmentation based on the improved region growing method
图 5 阈值法和区域生长部分分割结果
Figure 5. Threshold method and region growing partial segmentation results
表 1 两种方法的9组序列的分割结果评价
Table 1. Evaluation of segmentation results of 9 groups of images by two methods
方法 分割正确率 VOE(%) RVD(%) 最大值 最小值 均值 标准差 最大值 最小值 均值 标准差 阈值法 90.44% 11.98 5.92 9.36 2.40 2.37 −8.41 −1.32 3.75 区域生长 91.89% 11.75 7.22 8.86 1.51 12.07 2.71 7.39 3.10 
下载: 导出CSV
-
[1] 廖亚平. 肝脏解剖学[M]. 上海: 上海科学技术出版社, 1982. [2] 吴孟超. 肝脏外科学: [M]. 上海: 上海科学技术出版社, 1982. [3] 王玉新. 肝脏病知识[M]. 上海: 上海出版革命组, 1970. [4] 王希善. 肝脏疾病[M]. 哈尔滨: 黑龙江人民出版社, 1981. [5] 王成林, 周康荣. 肝脏疾病CT与MRI诊断[M]. 北京: 人民卫生出版社, 2007. [6] 梁长虹. 肝脏疾病CT诊断[M]. 北京: 人民卫生出版社, 2009. [7] 黄仟甲, 张恒, 李奇轩, 等. 医学图像分割的研究进展[J]. 中国医学物理学杂志, 2024, 41(8): 939-945. [8] 王爱民, 沈兰荪. 图像分割研究综述[J]. 测控技术, 2000, 5: 1-6. doi: 10.3969/j.issn.1000-8829.2000.05.001 [9] 何俊, 葛红, 王玉峰. 图像分割算法研究综述[J]. 计算机工程与科学, 2009, 12: 58-61. doi: 10.3969/j.issn.1007-130X.2009.12.017 [10] Akram M U, Khanum A, Iqbal K. An automated System for Liver CT Enhancement and Segmentation[J]. ICGSTGVIP Journal, 2010, 10: 5-10. [11] 彭微. 连接门限阈值法在肝脏CT图像分割上的应用[J]. 咸宁学院学报, 2011, 31(6): 72-73. [12] Lim S J, Jeong Y Y, Ho Y S. Automatic liver segmentation for volume measurement in CT Images[J]. Journal of Visual Communication and Image Representation, 2006, 17(4): 860-875. doi: 10.1016/j.jvcir.2005.07.001 [13] 薛斌党, 周锐, 李文岗. 三维CB数学形态学在肝脏CT图像分割中的应用[J]. 中国体视学与图像析, 2010, 15(4): 359-363. [14] 黄展鹏, 易法令, 周苏娟, 等. 基于数学形态学和区域合并的医学CT图像分割[J]. 计算机应用研究, 2010, 27(11): 4360-4362. [15] Lu X, Wu J, Ren X, et al. The study and application of the improved region growing algorithm for liver segmentation[J]. Optik-International Journal for Light and Electron Optics, 2014, 125(9): 2142-2147. doi: 10.1016/j.ijleo.2013.10.049 [16] 胡紫睿, 刘倩. 基于区域生长的肝影像分割系统的设计与研究[J]. 黑龙江科学, 2024, 15(6): 88-92. [17] 张丽娟, 章润, 李东明, 等. 区域生长全卷积神经网络交互分割肝脏CT图像[J]. 液晶与显示, 2021, 36(9): 1294-1304. doi: 10.37188/CJLCD.2020-0338 [18] 仇清涛, 段敬豪, 巩贯忠, 等. 基于三维动态区域生长算法的肝脏自动分割[J]. 中国医学物理学杂志, 2017, 34(7): 660-665. doi: 10.3969/j.issn.1005-202X.2017.07.002 [19] 王小芳, 赵于前. 基于先验形状的CV模型肝脏CT图像分割[J]. 光电子. 激光, 2010, 21(6): 953-956. [20] Heimann T, Meinzer H P, Wolf I. A statistical deformable model for the segmentation of liver CT volumes[J]. 3D Segmentation in the clinic: A grand challenge, 2007, 1: 161-166. [21] 徐丹霞, 吴效明, 岑人经, 等. 水平集方法在肝脏CT图像分割中的应用[J]. 微计算机信息, 2010, 1: 104-105,108. [22] 王梁, 吴斌, 方艳红. 基于区域生长和水平集的肝脏提取分割算法[J]. 科学技术与工程, 2014, 3: 216-221. doi: 10.3969/j.issn.1671-1815.2014.14.042 [23] Lee J, Kim N, Lee H, et al. Efficient liver segmentation exploiting level-set speed images with 2.5 D shape propagation[J]. 3D Segmentation in the Clinic: A grand Challenge, 2007, 12: 189-196. [24] Yang X, Yu H C, Choi Y, et al. A hybrid semi-automatic method for liver segmentation based on level-set methods using multiple seed points[J]. Computer methods and programs in biomedicine, 2014, 113(1): 69-79. doi: 10.1016/j.cmpb.2013.08.019 [25] 赵洁, 黄展鹏, 蒋世忠, 等. 结合改进分水岭和GVF的三维肝脏分割方法[J]. 计算机工程与应用, 2014, 22: 180-182. doi: 10.3778/j.issn.1002-8331.1211-0362 [26] Boykov Y Y, Jolly M P. Interactive graph cuts for optimal boundary & region segmentation of objects in ND images[C]. Eighth IEEE International Conference on IEEE, 2001. [27] 杨勍, 赵于前, 张帆, 等. 基于空间模糊C均值和图割的肝脏CT序列图像分割[J]. 激光与光电子学进展, 2022, 59(12): 430-439. [28] 廖苗, 赵于前, 曾业战, 等. 基于图割和边缘行进的肝脏CT序列图像分割[J]. 电子与信息学报, 2016, 38(6): 1552-1556. [29] 陈津津, 赵于前, 邹润民. 基于超限学习机的腹部CT序列图像肝脏自动分割[J]. 中国医学物理学杂志, 2015, 32(5): 611-616. doi: 10.3969/j.issn.1005-202X.2015.05.001 [30] 夏栋, 张义, 巫彤宁, 等. 深度学习在肝脏肿瘤CT图像分割中的应用[J]. 北京生物医学工程, 2023, 42(3): 308-314. doi: 10.3969/j.issn.1002-3208.2023.03.016 [31] 王坤, 张学良, 张岁霞, 等. 基于机器学习方法的肝癌X射线相衬CT图像分类研究[J]. 中国生物医学工程学报, 2020, 39(5): 621-625. doi: 10.3969/j.issn.0258-8021.2020.05.013 -
点击查看大图
图(5) / 表(1)
计量
- 文章访问数: 19
- HTML全文浏览量: 11
- PDF下载量: 1
- 被引次数: 0
