A Modified Expectation-Maximization Approach for HMRF-Based Brain MRI Classification


Authors : Hussaini Ahmed; Jamila Suleiman; Michael Oluwaseun Dada; Omotayo Bamidele Awojoyogbe

Volume/Issue : Volume 10 - 2025, Issue 5 - May

Google Scholar : https://tinyurl.com/2s3k22yc

DOI : https://doi.org/10.38124/ijisrt/25may401

PlumX Metrics

Semantic Scholar

ResearchGate

OUCI

Scilit

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Accurate segmentation of brain tissues in magnetic resonance imaging (MRI) is essential for clinical diagnosis, pathological assessment, prognosis evaluation, and brain development studies. However, tissue heterogeneity resulting from bias field distortion, partial volume effects, noise, and magnetic field inhomogeneities poses significant challenges. In this study, we propose a Hidden Markov Random Field model combined with a Modified Expectation-Maximization algorithm (HMRF-EM) to improve segmentation accuracy by accounting for neighborhood correlation and signal intensity non- uniformity. The algorithm was implemented in R and evaluated on T1-weighted simulated Brain Web data. The model effectively segmented cerebrospinal fluid (CSF), gray matter (GM), and white matter (WM) with tissue proportions of 35%, 47%, and 18%, respectively. Validation results demonstrated a mean square error of 0.0290, misclassification rate of 0.0870, and tissue volume errors of 0.0578 (CSF), 0.0246 (GM), and 0.0063 (WM). Dice similarity coefficients were 0.9244, 0.9086, and 0.9134 for CSF, GM, and WM, respectively. These findings indicate that the proposed HMRF-EM approach yields reliable and accurate brain tissue classification, making it suitable for clinical and research applications.

Keywords : Magnetic Resonance, Brain Tissue, Segmentation.

References :

  1. J.-S. Long, G.-Z. Ma, E.-M. Song, and R.-C. Jin, “Learning U-Net Based Multi-Scale Features in Encoding-Decoding for MR Image Brain Tissue Segmentation,” Sensors, vol. 21, no. 9, p. 3232, May 2021, doi: 10.3390/s21093232.
  2. Y. Kong, X. Chen, J. Wu, P. Zhang, Y. Chen, and H. Shu, “Automatic brain tissue segmentation based on graph filter,” BMC Med Imaging, vol. 18, no. 1, p. 9, Dec. 2018, doi: 10.1186/s12880-018-0252-x.
  3. B. Jafrasteh, M. Lubián-Gutiérrez, S. P. Lubián-López, and I. Benavente-Fernández, “Enhanced Spatial Fuzzy C-Means Algorithm for Brain Tissue Segmentation in T1 Images,” Neuroinform, vol. 22, no. 4, pp. 407–420, Apr. 2024, doi: 10.1007/s12021-024-09661-x.
  4. L. Dora, S. Agrawal, R. Panda, and A. Abraham, “State-of-the-Art Methods for Brain Tissue Segmentation: A Review,” IEEE Rev. Biomed. Eng., vol. 10, pp. 235–249, 2017, doi: 10.1109/RBME.2017.2715350.
  5. M. Dadar and D. L. Collins, “BISON: Brain tissue segmentation pipeline using T1 ‐weighted magnetic resonance images and a random forest classifier,” Magnetic Resonance in Med, vol. 85, no. 4, pp. 1881–1894, Apr. 2021, doi: 10.1002/mrm.28547.
  6. V. M. Rao et al., “Improving across-dataset brain tissue segmentation for MRI imaging using transformer,” Front. Neuroimaging, vol. 1, p. 1023481, Nov. 2022, doi: 10.3389/fnimg.2022.1023481.
  7. I. F. Almog et al., “Full‐field swept‐source optical coherence tomography and neural tissue classification for deep brain imaging,” Journal of Biophotonics, vol. 13, no. 2, p. e201960083, Feb. 2020, doi: 10.1002/jbio.201960083.
  8. S. Awate, T. Tasdizen, N. Foster, and R. Whitaker, “Adaptive Markov modeling for mutual-information-based, unsupervised MRI brain-tissue classification,” Medical Image Analysis, vol. 10, no. 5, pp. 726–739, Oct. 2006, doi: 10.1016/j.media.2006.07.002.
  9. C. Li, J. Sun, L. Liu, and V. Palade, “A hybrid framework for brain tissue segmentation in magnetic resonance images,” Int J Imaging Syst Tech, vol. 31, no. 4, pp. 2305–2321, Dec. 2021, doi: 10.1002/ima.22637.
  10. D. Feng, L. Tierney, and V. Magnotta, “MRI Tissue Classification Using High-Resolution Bayesian Hidden Markov Normal Mixture Models,” Journal of the American Statistical Association, vol. 107, no. 497, pp. 102–119, Mar. 2012, doi: 10.1198/jasa.2011.ap09529.
  11. S. D. Mikhaĭlova, G. I. Storozhakov, S. I. Gukova, and T. M. Semushkina, “[Mechanism of the antiarrhythmic effect of laser irradiation],” Biull Eksp Biol Med, vol. 113, no. 5, pp. 460–462, May 1992.
  12. M. Tavakoli-Zaniani, Z. Sedighi-Maman, and M. H. Fazel Zarandi, “Segmentation of white matter, grey matter and cerebrospinal fluid from brain MR images using a modified FCM based on double estimation,” Biomedical Signal Processing and Control, vol. 68, p. 102615, Jul. 2021, doi: 10.1016/j.bspc.2021.102615.
  13. A. Fawzi, A. Achuthan, and B. Belaton, “Brain Image Segmentation in Recent Years: A Narrative Review,” Brain Sci, vol. 11, no. 8, p. 1055, Aug. 2021, doi: 10.3390/brainsci11081055.
  14. S. Yazdani, R. Yusof, A. Karimian, Y. Mitsukira, and A. Hematian, “Automatic Region-Based Brain Classification of MRI-T1 Data,” PLoS ONE, vol. 11, no. 4, p. e0151326, Apr. 2016, doi: 10.1371/journal.pone.0151326.
  15. Z. Bian, “MR brain tissue classification based on the spatial information enhanced Gaussian mixture model,” Technol Health Care, vol. 30, no. S1, pp. 81–89, 2022, doi: 10.3233/THC-228008.
  16. H. Tang, E. X. Wu, Q. Y. Ma, D. Gallagher, G. M. Perera, and T. Zhuang, “MRI brain image segmentation by multi-resolution edge detection and region selection,” Computerized Medical Imaging and Graphics, vol. 24, no. 6, pp. 349–357, Nov. 2000, doi: 10.1016/S0895-6111(00)00037-9.
  17. M. M and S. P, “MRI Brain Tumour Segmentation Using Hybrid Clustering and Classification by Back Propagation Algorithm,” Asian Pac J Cancer Prev, vol. 19, no. 11, pp. 3257–3263, Nov. 2018, doi: 10.31557/APJCP.2018.19.11.3257.
  18. M. Sucharitha and K. P. Geetha, “Brain tissue segmentation using fuzzy clustering techniques,” THC, vol. 23, no. 5, pp. 571–580, Sep. 2015, doi: 10.3233/THC-151012.
  19. “A comparison between the fuzzy C-means clustering algorithm and the K-mean clustering algorithm,” Eng. Math. Lett., 2024, doi: 10.28919/eml/8403.
  20. P. Moeskops, M. A. Viergever, M. J. N. L. Benders, and I. Išgum, “Evaluation of an automatic brain segmentation method developed for neonates on adult MR brain images,” presented at the SPIE Medical Imaging, S. Ourselin and M. A. Styner, Eds., Orlando, Florida, United States, Mar. 2015, p. 941315. doi: 10.1117/12.2081833.
  21. P. Guo, “Brain tissue classification method for clinical decision-support systems,” Engineering Applications of Artificial Intelligence, vol. 64, pp. 232–241, Sep. 2017, doi: 10.1016/j.engappai.2017.05.015.
  22. N. B. Bahadure, A. K. Ray, and H. P. Thethi, “Image Analysis for MRI Based Brain Tumor Detection and Feature Extraction Using Biologically Inspired BWT and SVM,” Int J Biomed Imaging, vol. 2017, p. 9749108, 2017, doi: 10.1155/2017/9749108.
  23. H. Al-Dmour and A. Al-Ani, “A clustering fusion technique for MR brain tissue segmentation,” Neurocomputing, vol. 275, pp. 546–559, Jan. 2018, doi: 10.1016/j.neucom.2017.08.051.
  24. N. Varuna Shree and T. N. R. Kumar, “Identification and classification of brain tumor MRI images with feature extraction using DWT and probabilistic neural network,” Brain Inform, vol. 5, no. 1, pp. 23–30, Mar. 2018, doi: 10.1007/s40708-017-0075-5.
  25. M. Azarbad, A. Ebrahimzadeh, and A. Babajani-Feremi, “Brain tissue segmentation using an unsupervised clustering technique based on PSO algorithm,” in 2010 17th Iranian Conference of Biomedical Engineering (ICBME), Isfahan, Iran: IEEE, Nov. 2010, pp. 1–6. doi: 10.1109/ICBME.2010.5704938.
  26. Chien-shiung Wu College, Southeast University, Nanjing, China, Y. Liu, S. Du, and Y. Kong, “Supervoxel Clustering with a Novel 3D Descriptor for Brain Tissue Segmentation,” IJMLC, vol. 10, no. 3, pp. 501–506, May 2020, doi: 10.18178/ijmlc.2020.10.3.964.
  27. K. Thiruvenkadam, K. Nagarajan, and S. Padmanaban, “An automatic self‐initialized clustering method for brain tissue segmentation and pathology detection from magnetic resonance human head scans with graphics processing unit machine,” Concurrency and Computation, vol. 33, no. 6, p. e6084, Mar. 2021, doi: 10.1002/cpe.6084.
  28. F. Zhang et al., “Deep learning based segmentation of brain tissue from diffusion MRI,” Neuroimage, vol. 233, p. 117934, Jun. 2021, doi: 10.1016/j.neuroimage.2021.117934.
  29. Y. Zhang et al., “GSCFN: A graph self-construction and fusion network for semi-supervised brain tissue segmentation in MRI,” Neurocomputing, vol. 455, pp. 23–37, Sep. 2021, doi: 10.1016/j.neucom.2021.05.047.
  30. M. A. Al-Masni and D.-H. Kim, “CMM-Net: Contextual multi-scale multi-level network for efficient biomedical image segmentation,” Sci Rep, vol. 11, no. 1, p. 10191, May 2021, doi: 10.1038/s41598-021-89686-3.
  31. J. Wang, H. Cheng, and S. D. Newman, “Sparse representation of DWI images for fully automated brain tissue segmentation,” J Neurosci Methods, vol. 343, p. 108828, Sep. 2020, doi: 10.1016/j.jneumeth.2020.108828.
  32. M. Zitouni, M. Afif, and M. Zribi, “Tweedie hidden Markov random field and the expectation-method of moments and maximisation algorithm for brain MR image segmentation,” Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, vol. 11, no. 1, pp. 67–79, Jan. 2023, doi: 10.1080/21681163.2022.2045225.
  33. I. Rizwan I Haque and J. Neubert, “Deep learning approaches to biomedical image segmentation,” Informatics in Medicine Unlocked, vol. 18, p. 100297, 2020, doi: 10.1016/j.imu.2020.100297.
  34. L. Lönn, G. Starck, M. Alpsten, S. Ekholm, and L. Sjöström, “Determination of tissue volumes. A comparison between CT and MR imaging,” Acta Radiol, vol. 40, no. 3, pp. 314–321, May 1999, doi: 10.3109/02841859909175560.
  35. K. H. Zou et al., “Statistical validation of image segmentation quality based on a spatial overlap index,” Acad Radiol, vol. 11, no. 2, pp. 178–189, Feb. 2004, doi: 10.1016/s1076-6332(03)00671-8

Accurate segmentation of brain tissues in magnetic resonance imaging (MRI) is essential for clinical diagnosis, pathological assessment, prognosis evaluation, and brain development studies. However, tissue heterogeneity resulting from bias field distortion, partial volume effects, noise, and magnetic field inhomogeneities poses significant challenges. In this study, we propose a Hidden Markov Random Field model combined with a Modified Expectation-Maximization algorithm (HMRF-EM) to improve segmentation accuracy by accounting for neighborhood correlation and signal intensity non- uniformity. The algorithm was implemented in R and evaluated on T1-weighted simulated Brain Web data. The model effectively segmented cerebrospinal fluid (CSF), gray matter (GM), and white matter (WM) with tissue proportions of 35%, 47%, and 18%, respectively. Validation results demonstrated a mean square error of 0.0290, misclassification rate of 0.0870, and tissue volume errors of 0.0578 (CSF), 0.0246 (GM), and 0.0063 (WM). Dice similarity coefficients were 0.9244, 0.9086, and 0.9134 for CSF, GM, and WM, respectively. These findings indicate that the proposed HMRF-EM approach yields reliable and accurate brain tissue classification, making it suitable for clinical and research applications.

Keywords : Magnetic Resonance, Brain Tissue, Segmentation.

Video Explanation for Published paper

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe