Aiming at the problems of intensity inhomogeneity, boundary blurring and noise interference in the segmentation of three-dimensional volume data (such as medical images and industrial CT data). In this paper, the hidden Markov random field based on Gaussian mixture model is used for the initial segmentation of volume data, and the statistical and spatial information of the image is effectively used to obtain a reasonable initial contour and region division. Then, the level set method is used for fine segmentation to accurately capture the complex boundary shape in the image, which has good adaptability to the change of the target boundary and makes the segmentation boundary more accurately fit the target area. This improvement takes into account the rationality of the initial segmentation and the accuracy of the fine segmentation. The experimental results verify the effectiveness of the proposed method in image segmentation.
Cite this paper
Liang, D. and Liu, C. (2026). 3D CT Image Segmentation Based on HMRF-EM and Level Set. Open Access Library Journal, 13, e14708. doi: http://dx.doi.org/10.4236/oalib.1114708.
Peng, J., Li, W., Liao, S. and Zhu, Y. (2024) Microcrack Segmentation of 3D CT Images Based on Multi-Task Learning. IEEE Access, 12, 138192-138200. https://doi.org/10.1109/access.2024.3431529
Yang, F., Zhang, D., Huang, K., Shi, W. and Wang, X. (2018) Scattering Estimation for Cone-Beam CT Using Local Measurement Based on Compressed Sensing. IEEE Transactions on Nuclear Science, 65, 941-949. https://doi.org/10.1109/tns.2018.2803739
Tang, S., Huang, K., Cheng, Y., Mou, X. and Tang, X. (2018) Optimization Based Beam-Hardening Correction in CT under Data Integral Invariant Constraint. Physics in Medicine & Biology, 63, Article ID: 135015. https://doi.org/10.1088/1361-6560/aaca14
Liu, C., Liu, W. and Xing, W. (2019) A Weighted Edge-Based Level Set Method Based on Multi-Local Statistical Information for Noisy Image Segmentation. Journal of Visual Communication and Image Representation, 59, 89-107. https://doi.org/10.1016/j.jvcir.2019.01.001
Zheng, J., Zhang, D., Huang, K. and Sun, Y. (2018) A CBCT Series Slice Image Segmentation Method. Journal of X-Ray Science and Technology: Clinical Applications of Diagnosis and Thera-peutics, 26, 815-832. https://doi.org/10.3233/xst-180393
Qian Zhao, Y., Hong Wang, X., Fang Wang, X. and Shih, F.Y. (2014) Retinal Vessels Seg-mentation Based on Level Set and Region Growing. Pattern Recognition, 47, 2437-2446. https://doi.org/10.1016/j.patcog.2014.01.006
Zheng, J., Tang, C. and Sun, Y. (2024) Thresholding-Accelerated Convolutional Neural Network for Aeroengine Turbine Blade Segmentation. Expert Systems with Ap-plications, 238, Article ID: 122387. https://doi.org/10.1016/j.eswa.2023.122387
Zhang, W., Wang, X., You, W., Chen, J., Dai, P. and Zhang, P. (2020) RESLS: Region and Edge Synergetic Level Set Framework for Image Segmentation. IEEE Transactions on Image Processing, 29, 57-71. https://doi.org/10.1109/tip.2019.2928134
Liu, G., Jiang, Y., Chang, B. and Liu, D. (2022) Superpixel-Based Active Contour Model via a Local Similarity Factor and Saliency. Measurement, 188, Article ID: 110442. https://doi.org/10.1016/j.measurement.2021.110442
Daimary, D., Bo-ra, M.B., Amitab, K. and Kandar, D. (2020) Brain Tumor Segmentation from MRI Images Using Hybrid Convolutional Neural Networks. Procedia Computer Science, 167, 2419-2428. https://doi.org/10.1016/j.procs.2020.03.295
Ranjbarzadeh, R., Bagherian Kasgari, A., Jafarzadeh Ghoushchi, S., Anari, S., Naseri, M. and Ben-dechache, M. (2021) Brain Tumor Segmentation Based on Deep Learning and an Attention Mechanism Using MRI Multi-Modalities Brain Images. Scientific Reports, 11, Article No. 10930. https://doi.org/10.1038/s41598-021-90428-8
Huang, K., Li, Z., Tang, S., Zeng, Y., Ye, W. and Yang, F. (2024) A Level-Set Method with the 3D Multiplica-tive-Additive Model for CT Volume Data Segmentation. Measurement, 229, Ar-ticle ID: 114442. https://doi.org/10.1016/j.measurement.2024.114442
Osher, S. and Sethian, J.A. (1988) Fronts Propagating with Curvature-Dependent Speed: Al-gorithms Based on Hamilton-Jacobi Formulations. Journal of Computational Physics, 79, 12-49. https://doi.org/10.1016/0021-9991(88)90002-2
Paragios, N. and Deriche, R. (2000) Geodesic Active Contours and Level Sets for the Detection and Tracking of Moving Objects. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22, 266-280. https://doi.org/10.1109/34.841758
Fubin He, and Yi Sun, (2015) Seg-mentation of Noisy CT Volume Data Using Improved 3D Chan-Vese Model. 2015 IEEE 7th International Conference on Awareness Science and Technology (iC-AST), Qinhuangdao, 22-24 September 2015, 31-36. https://doi.org/10.1109/icawst.2015.7314016
Lei Zhang, and Qiang Ji, (2010) Image Segmentation with a Unified Graphical Model. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32, 1406-1425. https://doi.org/10.1109/tpami.2009.145
Wang, Q. and Boyer, K.L. (2012) The Active Geometric Shape Model: A New Robust Deformable Shape Model and Its Applications. Computer Vision and Image Understanding, 116, 1178-1194. https://doi.org/10.1016/j.cviu.2012.08.004
Wang, Q. (2012) HMRF-EM-Image: Implementation of the Hidden Markov Random Field Model and Its Expectation-Maximization Algorithm. Computer Science, 94, 222-233.
Li, C.M., Huang, R., Ding, Z.H., Gatenby, J.C., Metaxas, D.N. and Gore, J.C. (2011) A Level Set Method for Image Segmentation in the Presence of Intensity Inhomogeneities with Application to MRI. IEEE Transactions on Image Processing, 20, 2007-2016. https://doi.org/10.1109/tip.2011.2146190
