Image segmentation of magnetic resonance image (MRI) is a crucial process for visualisation and examination of abnormal tissues, especially during clinical analysis. Complexity and variations of the tumour structure magnify the challenges in the automated detection of a brain tumour in MRIs. This study presents an automatic lesion recognition method in the MRI followed by classification. In the proposed multistage image segmentation method, the intent region initialisation is performed using low-level information by the keypoint descriptors. A set of the linear filter is used to transform low-level information into higher-level image features. The set of features and filter training data are accomplished to track the tumour region. The authors adopt a possibilistic model for region growing, and disparity map for the refinement process to grave consist boundary. Further, the features are extracted using the Fisher vector and autoencoder. A set of handcrafted features is also extracted using a segmentation-based localised region to train and test the support vector machine and multilayer perceptron classifiers. The experiments that are performed using five MRI datasets confirm the superiority of proposal as that of the state-of-the-art methods. It reports 94.5 and 91.76%, average accuracy of segmentation and classification, respectively.

References

1. 1)
  - 20. Zhou, H., Yuan, Y., Shi, C.: ‘Object tracking using sift features and mean shift’, Comput. Vis. Image Underst, 2009, 113, (3), pp. 345–352.
2. 2)
  - 7. Pereira, S., Pinto, A., Alves, V., et al: ‘Brain tumor segmentation using convolutional neural networks in MRI images’, IEEE Trans. Med. Imaging, 2016, 35, (5), pp. 1240–1252.
3. 3)
  - 49. Pedregosa, F., Varoquaux, G., Gramfort, A., et al: ‘Scikit-learn: machine learning in python’, J. Mach. Learn. Res., 2011, 384, (12), pp. 2825–2830.
4. 4)
  - 35. Jiao, J., Wang, R., Wang, W., et al: ‘Color image-guided boundary-inconsistent region refinement for stereo matching’, IEEE Trans. Circuits Syst. Video Technol., 2017, 27, (5), pp. 1155–1160.
5. 5)
  - 57. Kurmi, Y., Chaurasia, V.: ‘Multifeature-based medical image segmentation’, IET Image Process., 2018, 12, (8), pp. 1491–1498.
6. 6)
  - 47. Keras: ‘Keras documentation’, 2018, Available at https://keras.io, accessed 02 February 2018.
7. 7)
  - 27. Collins, R.T., Liu, Y., Leordeanu, M.: ‘Online selection of discriminative tracking features’, IEEE Trans. Pattern Anal. Mach. Intell., 2005, 27, (10), pp. 1631–1644.
8. 8)
  - 43. Perronnin, F., Sánchez, J., Mensink, T.: ‘Improving the fisher kernel for large-scale image classification’. Proc. ECCV, (Springer) Berlin, Heidelberg, 2010, vol. 6314, pp. 143–156.
9. 9)
  - 19. Yu, X., Yang, J., Wang, T., et al: ‘Key point detection by max pooling for tracking’, IEEE Trans. Cybern., 2015, 45, (3), pp. 444–453.
10. 10)
  - 30. Hernando, D., Haldar, J., Sutton, B., et al: ‘Joint estimation of water/fat images and field inhomogeneity map’, Magn. Reson. Med., 2008, 59, (3), pp. 571–580.
11. 11)
  - 13. Cheng, J., Yang, W., Huang, M., et al: ‘Retrieval of brain tumors by adaptive spatial pooling and fisher vector representation’, PLOS One, 2016, 11, (6), p. e0157112.
12. 12)
  - 10. Vezhnevets, V., Konouchine, V.: ‘Growcut-interactive multi-label N-D image segmentation by cellular automata’ (the Graphicon, Novosibirsk Akademgorodok, Russia, 2005), pp. 1–7.
13. 13)
  - 44. Chang, C.-C., Lin, C.-J.: ‘Libsvm: A library for support vector machines’, ACM Trans. Intell. Syst. Technol., 2011, 2, (3), pp. 1–27.
14. 14)
  - 6. Hamamci, A., Kucuk, N., Karaman, K., et al: ‘Tumor-cut: segmentation of brain tumors on contrast enhanced MR images for radiosurgery application’, IEEE Trans. Med. Imaging, 2012, 31, (3), pp. 790–805.
15. 15)
  - 12. Paul, J.S., Plassard, A.J., Landman, B.A., et al: ‘Deep learning for brain tumor classification’, Proc. SPIE, Med. Image, Biomed. Appl. Mol., Struct., Funct. Imaging, 2017, 10137, (1013710), pp. 1–29.
16. 16)
  - 4. Ahmed, M., Yamany, S., Mohamed, N., et al: ‘A modified fuzzy c-means algorithm for bias field estimation and segmentation of MRI data’, IEEE Trans. Med. Image Process., 2002, 21, (3), pp. 193–199.
17. 17)
  - 3. Bezdek, J.: ‘Pattern recognition with fuzzy objective function algorithms’ (Plenum, New York, 1981).
18. 18)
  - 16. Latif, G., Iskandar, D.N.F.A., Alghazo, J.M., et al: ‘Enhanced MR image classification using hybrid statistical and wavelets features’, IEEE Access, 2019, 7, pp. 9634–9644.
19. 19)
  - 53. Cheng, J., Huang, W., Cao, S., et al: ‘Enhanced performance of brain tumor classification via tumor region augmentation and partition’, PloS One, 2015, 10, (12), p. e0144479.
20. 20)
  - 1. El-Melegy, M.T., Mokhtar, H.M.: ‘Tumor segmentation in brain MRI using a fuzzy approach with class center priors’, J. Image Video Process., 2014, 2014, (21), pp. 1–14.
21. 21)
  - 59. Dice, L.R.: ‘Measures of the amount of ecologic association between species’, Ecology, 1945, 26, (3), pp. 297–302.
22. 22)
  - 45. Raji, C.G., Chandra, S.S.V.: ‘Long-term forecasting the survival in liver transplantation using multilayer perceptron networks’, IEEE Trans. Syst. Man Cybern. Syst., 2017, 47, (8), pp. 2318–2329.
23. 23)
  - 18. Chen, Y., Ding, J., Hsiao, C., et al: ‘A region adaptive encoding algorithm for simple image compression’, IEEE Asia Pac. Conf. Circuits Syst., 2014, pp. 595–598.
24. 24)
  - 24. Yang, J., Yu, K., Gong, Y., et al: ‘Linear spatial pyramid matching using sparse coding for image classification’. Proc. IEEE Conf. CVPR, Miami, FL, USA, 2009, pp. 1794–1801.
25. 25)
  - 48. G.B. team: ‘Tensorflow’, 2018, Available at https://www.tensorflow.org/, accessed 02 February 2018.
26. 26)
  - 55. Clark, K., Vendt, B., Smith, K., et al: ‘The cancer imaging archive (TCIA): maintaining and operating a public information repository’, J. Digit. Imaging, 2013, 26, (6), pp. 1045–1057.
27. 27)
  - 31. Vailaya, A., Figueiredo, M.A.T., Jain, A.K., et al: ‘Image classification for content-based indexing’, IEEE Trans. Image Process, 2001, 10, (1), pp. 117–130.
28. 28)
  - 5. Maksoud, E.A., Elmogy, M., Awadi, R.A.: ‘Brain tumor segmentation based on a hybrid clustering technique’, Egypt. Inform. J., 2015, 16, pp. 71–81.
29. 29)
  - 14. Sultan, H.H., Salem, N.M., Al-Atabany, W.: ‘Multi-classification of brain tumor images using deep neural network’, IEEE Access, 2019, 7, pp. 69215–69225.
30. 30)
  - 32. Rudemo, M.: ‘Empirical choice of histograms and kernel density estimators’, Scand. J. Statist., 1982, 9, (2), pp. 65–78.
31. 31)
  - 15. Bahadure, N., Ray, A., Thethi, H.P.: ‘Image analysis for MRI based brain tumor detection and feature extraction using biologically inspired BWT and SVM’, Int. J. Biomed. Imaging, 2017, 2017, pp. 1–12.
32. 32)
  - 51. ‘Virtual Skeleton, BRATS 2013’. Available at https://www.virtualskeleton.ch/BRATS/Start2013, accessed 30 September 2017.
33. 33)
  - 22. Alsahwa, B., Solaiman, B., Almouahed, S., et al: ‘Iterative refinement of possibility distributions by learning for pixel-based classification’, IEEE Trans. Med. Imaging, 2016, 25, (8), pp. 3533–3546.
34. 34)
  - 40. Shin, H., Orton, M., Collins, D.J., et al: ‘Autoencoder in time-series analysis for unsupervised tissues characterisation in a large unlabelled medical image dataset’. Intern. Conf. Machine Learning and Appli. and Workshops, Honolulu, HI, 2011, pp. 259–264.
35. 35)
  - 29. Yu, H., Reeder, S., Shimakawa, A., et al: ‘Field map estimation with a region growing scheme for iterative 3-point water-fat decomposition’, Magn. Reson. Med., 2005, 54, (4), pp. 1032–1039.
36. 36)
  - 17. Nayak, D.R., Dash, R., Chang, X., et al: ‘Automated diagnosis of pathological brain using fast curvelet entropy features’, IEEE Trans. Sustain. Comput., 2018, Early Access, pp. 1–12 doi: 10.1109/TSUSC.2018.2883822.
37. 37)
  - 52. ‘NIH center for information technology’. Available at http://mipav.cit.nih.gov, accessed 14 September 2017.
38. 38)
  - 38. Comaniciu, D., Meer, P.: ‘Mean shift: A robust approach toward feature space analysis’, IEEE Trans. Pattern Anal. Mach. Intell., 2002, 24, (5), pp. 603–619.
39. 39)
  - 41. Lee, T., Atkins, M.: ‘New approach to measure border irregularity for melanocytic lesions’. Proc. of SPIE, San Diego, CA, USA, 2000, vol. 3979, pp. 1–8.
40. 40)
  - 2. Anitha, V., Murugavalli, S.: ‘Brain tumor classification using two-tier classifier with adaptive segmentation technique’, IET Comput. Vis., 2016, 10, (1), pp. 9–17.
41. 41)
  - 33. Dubois, D., Foulloy, L., Mauris, G., et al: ‘Probability-possibility transformations, triangular fuzzy sets, and probabilistic inequalities’, Rel. Comput., 2004, 10, (4), pp. 273–297.
42. 42)
  - 23. Galdames, F.J., Jaillet, F., Perez, C.A.: ‘An accurate skull stripping method based on simplex meshes and histogram analysis for magnetic resonance images’, J. Neurosci. Methods, 2012, 206, (2), pp. 103–119.
43. 43)
  - 8. Cordier, N., Delingette, H., Ayache, N.: ‘A patch-based approach for the segmentation of pathologies: application to glioma labelling’, IEEE Trans. Med. Imaging, 2016, 35, (4), pp. 1066–1077.
44. 44)
  - 36. Ma, Z., He, K., Wei, Y., et al: ‘Constant time weighted median filtering for stereo matching and beyond’. 2013 IEEE Int. Conf. on Computer Vision, Sydney, NSW, 2013, pp. 49–56.
45. 45)
  - 37. Scharstein, D., Szeliski, R., Zabih, R.: ‘A taxonomy and evaluation of dense two-frame stereo correspondence algorithms’. Proc. IEEE Workshop on Stereo and Multi-Baseline Vision (SMBV 2001), Kauai, HI, USA, 2001, pp. 131–140.
46. 46)
  - 9. Gao, Y., Wang, K., Jiang, S., et al: ‘Bioluminescence tomography based on Gaussian weighted Laplace prior regularization for In vivo morphological imaging of glioma’, IEEE Trans. Med. Imaging, 2017, 36(11), pp. 2343–2355.
47. 47)
  - 42. Yang, W., Wang, K., Zuo, W.: ‘Neighborhood component feature selection for high-dimensional data’, JCP, 2012, 7, pp. 161–168.
48. 48)
  - 11. Boykov, Y., Jolly, M.-P.: ‘Interactive graph cuts for optimal boundary and region segmentation of objects in n-d images’. Proc. ICCV, Vancouver, BC, Canada, 2001, pp. 105–112.
49. 49)
  - 56. Scarpace, L., Flanders, A., Jain, R., et al: ‘Data from REMBRANDT. The cancer imaging archive’, 2015. doi: 10.7937/K9/TCIA.2015.588OZUZB, accessed 30 May 2019.
50. 50)
  - 39. Liu, L., Wang, P., Shen, C., et al: ‘Compositional model based fisher vector coding for image classification’, IEEE Trans. Pattern Anal. Mach. Intell., 2017, 39, (12), pp. 2335–2348.
51. 51)
  - 28. LeCun, Y., Bengio, Y., Hinton, G.: ‘Deep learning’, Nature, 2015, 521, (7553), pp. 436–444.
52. 52)
  - 26. Freund, Y., Dasgupta, S., Kabra, M., et al: ‘Learning the structure of manifolds using random projections’, Adv. Neural Inf. Process. Syst., 2007, 20, pp. 473–480.
53. 53)
  - 54. Cheng, J.: ‘Brain tumor dataset’, April 2, 2017. Distributed by Figshare. Available at https://_gshare.com/articles/brain_tumor_dataset/1512427/5, accessed 30 May 2019.
54. 54)
  - 50. Brain Web: ‘Simulated brain database’. Available at http://brainweb.bic.mni.mcgill.ca/brainweb/, accessed 12 January 2017.
55. 55)
  - 25. Boureau, Y.L., Bach, F., LeCun, Y., et al: ‘Learning mid-level features for recognition’. Proc. IEEE Conf. CVPR, San Francisco, CA, USA, 2010, pp. 2559–2566.
56. 56)
  - 46. Klein, A., Falkner, S., Bartels, S., et al: ‘Fast Bayesian optimization of machine learning hyperparameters on large datasets’, ArXiv, abs/1605.07079, 2016.
57. 57)
  - 34. Nagao, M., Matsuyama, T.: ‘Edge preserving smoothing’, Comput. Graph. Image Process., 1979, 9, (4), pp. 394–407.
58. 58)
  - 21. Huang, F., Narayan, S., Wilson, D., et al: ‘A fast iterated conditional modes algorithm for water–fat decomposition in MRI’, IEEE Trans. Med. Imaging, 2011, 30, (8), pp. 1480–1493.
59. 59)
  - 58. Kurmi, Y., Chaurasia, V., Ganesh, N.: ‘Tumor malignancy detection using histopathology imaging’, J. Med. Image Rad. Sci., 2019, 50, (4), pp. 514–528.

Classification of magnetic resonance images for brain tumour detection

References

Related content