Challenges in Brain Magnetic Resonance Image Segmentation

  • Roya Babaie Aghdam Islamic Azad University, North Tehran Branch, Faculty of Engineering, Department of Information Technology
  • Atieh Sadat Bayat Ghiasi Islamic Azad University, North Tehran Branch, Faculty of Engineering, Department of Information Technology
  • Parastoo Fatemi Islamic Azad University, North Tehran Branch, Faculty of Engineering, Department of Information Technology
  • Nazanin Sadat Hashemi Islamic Azad University, North Tehran Branch, Faculty of Engineering, Department of Information Technology
Keywords: Image segmentation, classification, brain imaging, MRI.


Over the past several decades, the application of magnetic resonance imaging (MRI) has been rapidly expanding in the areas of brain research studies and clinical diagnosis. One of the most important steps in brain MRI data preparation is the removal of unwanted brain regions, which is followed by segmentation of the brain into three main regions – white matter (WM), grey matter (GM) and cerebrospinal fluid (CSF) – or into subregions. In brain MRI analysis, image segmentation is commonly used for measuring and visualizing the brain’s anatomical structures, analyzing brain changes, delineating pathological regions, and surgical planning and image-guided interventions. Brain segmentation allows clinicians and researchers to concentrate on a specific region in the brain in their analyses. However, brain segmentation is a difficult task due to high similarities and correlations of image intensity among brain regions. In this review, image segmentation algorithms used for dividing the brain into different sectors were discussed in detail. The potential for using the fuzzy c-means (FCM) unsupervised clustering algorithm and certain hybrid (combined) methods to segment brain MR images was demonstrated. Additionally, certain validation techniques that are required to demonstrate the performance of segmentation methods in terms of accuracy rates were described. 


[1] Si-Yuan Lu, Xing-Xing Zhou, Guang-Shuai Zhang, and Ling Wei., "A Short Survey on MRI Brain Detection," 2015.
[2] Yongyue Zhang, Michael Brady, and Stephen Smith, "Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm," IEEE transactions on medical imaging , vol. 20, no. no. 1 , pp. 45-57, 2001.
[3] Saman Sarraf, Jian Sun, "ADVANCES IN FUNCTIONAL BRAIN IMAGING: A COMPREHENSIVE SURVEY FOR ENGINEERS AND PHYSICAL SCIENTISTS," International Journal of Advanced Research , vol. 4, no. no. 8 , p. 640–660, August 31, 2016.
[4] Reshma Hiralal, Hema P. Menon, "A Survey of Brain MRI Image Segmentation Methods and the Issues Involved," In The International Symposium on Intelligent Systems Technologies and Applications, pp. 245-259, 2016.
[5] J. Dolz, L. Massoptier, M. Vermandel, "Segmentation algorithms of subcortical brain structures on MRI for radiotherapy and radiosurgery: a survey," IRBM , vol. 36, no. no. 4, pp. 200-212, 2015 .
[6] Jamal Ghasemi, Reza Ghaderi, MR Karami Mollaei, S. A. Hojjatoleslami, "A novel fuzzy Dempster–Shafer inference system for brain MRI segmentation," Information Sciences , vol. 223, pp. 205-220, 2013.
[7] Saman Sarraf, Cristina Saverino, Halleh Ghaderi, John Anderson, "Brain network extraction from probabilistic ICA using functional Magnetic Resonance Images and advanced template matching techniques," in Electrical and Computer Engineering (CCECE), 2014 IEEE 27th Canadian Conference, Toronto, 2014.
[8] Saman Sarraf , Cristina Saverino, Ali Mohammad Golestani, "A Robust and Adaptive Decision-Making Algorithm for Detecting Brain Networks Using Functional MRI within the Spatial and Frequency Domain," in The IEEE International Conference on Biomedical and Health Informatics (BHI) , Las Vegas, 2016.
[9] S. Sarraf, "Hair Color Classification in Face Recognition using Machine Learning Algorithms," American Scientific Research Journal for Engineering, Technology, and Sciences (ASRJETS), vol. 26, no. 3, p. 426, 2016.
[10] S. Smith., "Fast robust automated brain extraction," Human Brain Mapping, vol. 17(3), no. November 2002, pp. 143-155, 2002.
[11] Ivana Despotović, Bart Goossens, Wilfried Philips, "MRI segmentation of the human brain: challenges, methods, and applications," Computational and mathematical methods in medicine, 2015.
[12] Mahesh Yambal, Hitesh Gupta, "Image segmentation using fuzzy C means clustering: a survey," International Journal of Advanced Research in Computer and Communication Engineering , vol. 2, no. no. 7, 2013.
[13] Ivana Despotović, Bart Goossens, Ewout Vansteenkiste, Wilfried Philips, "An improved fuzzy clustering approach for image segmentation," in In 2010 IEEE International Conference on Image Processing, pp. 249-252. IEEE, 2010.
[14] R. CameronCraddock, Saad Jbabdi, Chao-Gan Yan, Joshua T. Vogelstein, F. Xavier Castellanos, Adriana Di Martino, Clare Kelly, Keith Heberlein, Stan Colcombe, and Michael P. Milham, "Imaging human connectomes at the macroscale," Nature methods (2013): ., vol. 10, no. no. 6, pp. 524-539, 2013.
[15] Paul Bed, Ramesh Jain, "Segmentation through symbolic surface descriptions," The University of Michigan, 1986.
[16] Saman Sarraf, Ghassem Tofighi, "Deep Learning-based Pipeline to Recognize Alzheimer's Disease using fMRI Data," bioRxiv, vol. 066910, 2016.
[17] Saman Sarraf, John Anderson, Ghassem Tofighi, "DeepAD: Alzheimer′ s Disease Classification via Deep Convolutional Neural Networks using MRI and fMRI," bioRxiv, vol. 070441, 2016.