针对有限元建模时大多采用半手工,甚至纯手工方式进行椎体分割的问题,提出了一种自动化分割方法。该方法首先利用一种基于多分辨率组合特征向量的点标记检测算法标记出待分割区域的种子点,然后利用区域生长的方法生长出待分割区域,从而实现脊椎组织的自动分割。实验选取120例脊椎核磁共振图像进行验证,结果表明：本文方法分割结果的相似度系数平均值为90.02%,最高达95.28%,分割时间仅需5.0分钟,相较于手动分割效率提升10倍以上,且优于传统图论分割方法和U-Net算法。结论表明,本文所提方法能够实现脊椎椎体的高效、准确自动分割,具有较好的稳定性和应用前景,可为后续三维重建与有限元分析提供可靠基础。
Abstract
For the problem that finite element modeling mostly uses half manual, even pure manual to conduct vertebra segmentation, this paper proposes an automatic segmentation algorithm. This algorithm firstly marks seed points in segmentation region with the multi-resolution composite feature vector based point landmark algorithm, then grows the segmented regions using the method of region growing, finally achieves the automatic segmentation. Experimental validation using 120 spinal MRI images demonstrates that the proposed method achieves an average similarity coefficient of 90.02% for segmentation results, with a maximum of 95.28%. The segmentation process requires only 5.0 minutes, representing over a tenfold improvement in efficiency compared to manual segmentation and significantly outperforming traditional graph theory-based segmentation methods and U-Net algorithm. Conclusions indicate that the proposed algorithm enables efficient and accurate automatic segmentation of vertebral bodies, demonstrating good stability and application potential. It provides a reliable foundation for subsequent 3D reconstruction and finite element analysis.
关键词
点标记 /
区域生长 /
自动分割
Key words
point marker /
region growing /
automatic segmentation
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 周英杰,赵勇,禚汉杰,等.脊柱相关疾病的概念及疾病谱刍议[J].中国骨伤,2022,35(5):480-483.
[2] Iyama Y,Nakaura T,Iyama A,et al.Feasibility of Iterative Model Reconstruction for Unenhanced Lumbar CT[J].Radiology,2017,284(1):153-160.
[3] 郭丽,赵凯,朱逸峰,等.使用U-Net深度学习网络对腰椎矢状T2WI图像自动分割的可行性研究[J].放射学实践,2022,37(2):229-234.
[4] Zheng G,Nolte L P,Ferguson S J.2D/3D Reconstruction of a Scaled Lumbar Vertebral Model from a Single Fluoroscopic Image[J].Annual International Conference of the IEEE Engineering in Medicine and Biology Society.IEEE Engineering in Medicine and Biology Society.Annual International Conference,2010,2010:4395-4398.
[5] Melih S.Aslan.3D Vertebral Body Segmentation Using Shape Based Graph Cuts[J].ICPR,2010,20th:3951-3954.
[6] Huang L,Ruan S,Denœux T.Application of Belief Functions to Medical Image Segmentation:A Review[J].Information Fusion,2023,91:737-756.
[7] Deng W,Xiao W,Deng H,et al.MRI Brain Tumor Segmentation with Region Growing Method Based on the Gradients and Variances along and Inside of the Boundary Curve[C]//2010 3rd International Conference on Biomedical Engineering and Informatics.IEEE,2010:393-396.
[8] Shuting Yang.Application of the K-means Algorithm in Medical Image Segmentation[J].Journal of Contemporary Medical Practice,2022,9(4):82-85.
[9] Ganga T K,Karthikeyani V.Medical Image Segmentation Using Multi Resolution Histogram[C]//2011 3rd International Conference on Electronics Computer Technology.IEEE,2011:267-269.
[10] Qin X,Zhang S.New Medical Image Sequences Segmentation Based on Level Set Method[C]//2009 International Conference on Image Analysis and Signal Processing.IEEE,2009:22-27.[LinkOut]
[11] Lowe D G.Distinctive Image Features from Scale-Invariant Keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[12] Felzenszwalb P F,Huttenlocher D P.Efficient Graph-Based Image Segmentation[J].International Journal of Computer Vision,2004,59(2):167-181.
[13] 鲍文霞,杜银徕,姚文君,等.基于增强跳跃连接U-Net的肾脏肿瘤分割方法[J].安徽大学学报(自然科学版),2025,49(5):19-28.
[14] van der Graaf J W,van Hooff M L,Buckens C F M,et al.Lumbar Spine Segmentation in MR Images:A Dataset and a Public Benchmark[J].Scientific Data,2024,11:264.
[15] Cai X,Hou Y,Li C,et al.Evaluation of Two Segmentation Methods on MRI Brain Tissue Structures[J].Conference Proceedings,2006,2006:3029-3032.
[16] Macaire L,Vandenbroucke N,Postaire J G.Color Image Segmentation by Analysis of Subset Connectedness and Color Homogeneity Properties[J].Computer Vision and Image Understanding,2006,102(1):105-116.
基金
商丘市科技攻关计划指导性项目“基于多域特征融合的人脸深度伪造检测”,项目编号：2024124; 河南省本科高校智慧教学专项研究项目第二期项目“基于教育大数据的多模态混合式智慧教学模式构建与实践”,立项文件号：教高〔2023〕334号
