access icon free Automatic grading of brain tumours using LSTM neural networks on magnetic resonance spectroscopy signals

Brain tumours have increased rapidly in recent years as in other tumour types. Therefore, early and accurate diagnosis of brain tumour is vital for treatment. Magnetic resonance imaging (MRI) and histopathological assessments are the most common methods used in the detection of brain tumours. The research studies on non-invasive imaging methods such as MRI and magnetic resonance spectroscopy (MRS) have become widespread in recent years for brain tumour detection. In this study, a computer-assisted method is proposed for automatic grading of brain tumours on MRS signals. The classification of brain tumours with different grades is performed using long short term memory (LSTM) neural networks. In addition, additional features from MRS signals based on spectral entropy and instantaneous frequency are extracted. As a result of the experimental studies on the international MRS database (INTERPRET), it is seen that grading is achieved using the proposed method with average accuracy of 98.20%, sensitivity of 100%, and specificity of 97.53% performance results in three test studies carried out for the classification of brain tumour. Furthermore, in the grading of brain tumours using the proposed method, the average area under of the receiver operating characteristic curve is measured with high performance of 0.9936.

Inspec keywords: object detection; image classification; magnetic resonance spectroscopy; biomedical MRI; brain; entropy; recurrent neural nets; medical image processing; tumours

Other keywords: histopathological assessments; brain tumour classification; long short term memory neural network; malignant brain tumours; spectral entropy; magnetic resonance imaging; magnetic resonance database; brain tumour diagnosis; automatic grading; computer-assisted method; magnetic resonance spectroscopy signals; brain tumour detection; pattern recognition; LSTM neural networks

Subjects: Medical magnetic resonance imaging and spectroscopy; Neural computing techniques; Biomedical magnetic resonance imaging and spectroscopy; Patient diagnostic methods and instrumentation; Image recognition; Computer vision and image processing techniques; Biology and medical computing

References

    1. 1)
      • 4. Louis, D.N., Perry, A., Reifenberger, G., et al: ‘The 2016 world health organization classification of tumors of the central nervous system: a summary’, Acta Neuropathol., 2016, 131, (6), pp. 803820.
    2. 2)
      • 60. Graves, A.: ‘Generating sequences with recurrent neural networks’, arXiv preprint arXiv:1308.0850, 2013.
    3. 3)
      • 63. Wu, C.-Y., Ahmed, A., Beutel, A., et al: ‘Recurrent recommender networks’. The Tenth ACM int. Conf. on Web Search and Data Mining, Cambridge, UK, 2017, pp. 495503.
    4. 4)
      • 7. El-Dahshan, E.-S.A., Mohsen, H.M., Revett, K., et al: ‘Computer-aided diagnosis of human brain tumor through MRI: a survey and a new algorithm’, Expert Syst Appl, 2014, 41, (11), pp. 55265545.
    5. 5)
      • 31. Liu, H., Hall, W.A., Martin, A.J., et al: ‘MR-guided and MR-monitored neurosurgical procedures at 1.5 T’, J. Comput. Assist. Tomogr., 2000, 24, (6), pp. 909918.
    6. 6)
      • 1. Causes of death. Available at https://ourworldindata.org/causes-of-death, accessed 27 October 2019.
    7. 7)
      • 56. Yu, R., Gao, J., Yu, M., et al: ‘LSTM-EFG for wind power forecasting based on sequential correlation features’, Future Gener. Comput. Syst., 2019, 93, pp. 3342.
    8. 8)
      • 64. Misra, H., Ikbal, S., Bourlard, H., et al: ‘Spectral entropy based feature for robust ASR’. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, Montreal, Quebec, Canada, 2004, p. I-193.
    9. 9)
      • 34. Weis, J., Ring, P., Olofsson, T., et al: ‘Short echo time MR spectroscopy of brain tumors: grading of cerebral gliomas by correlation analysis of normalized spectral amplitudes’, J. Magn. Reson. Imag., 2010, 31, (1), pp. 3945.
    10. 10)
      • 36. Meyerand, M.E., Pipas, J.M., Mamourian, A., et al: ‘Classification of biopsy-confirmed brain tumors using single-voxel MR spectroscopy’, Am. J. Neuroradiol., 1999, 20, (1), pp. 117123.
    11. 11)
      • 61. Salehinejad, H., Sankar, S., Barfett, J., et al: ‘Recent advances in recurrent neural networks’, arXiv preprint arXiv:1801.01078, 2017.
    12. 12)
      • 8. Georgiadis, P., Cavouras, D., Kalatzis, I., et al: ‘Improving brain tumor characterization on MRI by probabilistic neural networks and non-linear transformation of textural features’, Comput. Methods Programs Biomed., 2008, 89, (1), pp. 2432.
    13. 13)
      • 12. Möller-Hartmann, W., Herminghaus, S., Krings, T., et al: ‘Clinical application of proton magnetic resonance spectroscopy in the diagnosis of intracranial mass lesions’, Neuroradiology, 2002, 44, (5), pp. 371381.
    14. 14)
      • 43. Afshar, P., Mohammadi, A., Plataniotis, K.N.: ‘Brain tumor type classification via capsule networks’. 2018 25th IEEE Int. Conf. on Image Processing (ICIP), Athens, Greece, 2018, pp. 31293133.
    15. 15)
      • 42. Zou, Q.-G., Xu, H.-B., Liu, F., et al: ‘In the assessment of supratentorial glioma grade: the combined role of multivoxel proton MR spectroscopy and diffusion tensor imaging’, Clin. Radiol., 2011, 66, (10), pp. 953960.
    16. 16)
      • 2. Cancer today: data visualization tools for exploring the global cancer burden in 2018. Available at http://gco.iarc.fr/today/home, accessed 27 October 2019.
    17. 17)
      • 29. Nelson, S.J., Graves, E., Pirzkall, A., et al: ‘In vivo molecular imaging for planning radiation therapy of gliomas: an application of 1H MRSI’, J. Magn. Reson. Imag., 2002, 16, (4), pp. 464476.
    18. 18)
      • 28. Zonari, P., Baraldi, P., Crisi, G.: ‘Multimodal MRI in the characterization of glial neoplasms: the combined role of single-voxel MR spectroscopy, diffusion imaging and echo-planar perfusion imaging’, Neuroradiology, 2007, 49, (10), pp. 795803.
    19. 19)
      • 37. Law, M., Yang, S., Wang, H., et al: ‘Glioma grading: sensitivity, specificity, and predictive values of perfusion MR imaging and proton MR spectroscopic imaging compared with conventional MR imaging’, Am. J. Neuroradiol., 2003, 24, (10), pp. 19891998.
    20. 20)
      • 15. O'Donnell-Luria, A.H., Lin, A.P., Merugumala, S.K., et al: ‘Brain MRS glutamine as a biomarker to guide therapy of hyperammonemic coma’, Mol. Genet. Metab., 2017, 121, (1), pp. 915.
    21. 21)
      • 33. Majos, C., Aguilera, C., Alonso, J., et al: ‘Proton MR spectroscopy improves discrimination between tumor and pseudotumoral lesion in solid brain masses’, Am. J. Neuroradiol., 2009, 30, (3), pp. 544551.
    22. 22)
      • 11. Zeng, Q., Liu, H., Zhang, K., et al: ‘Noninvasive evaluation of cerebral glioma grade by using multivoxel 3D proton MR spectroscopy’, Magn. Reson. Imaging, 2011, 29, (1), pp. 2531.
    23. 23)
      • 6. Logeswari, T., Karnan, M.: ‘An improved implementation of brain tumor detection using segmentation based on hierarchical self organizing map’, Int. J. Comput. Theor. Eng., 2010, 2, (4), p. 591.
    24. 24)
      • 59. Li, X., Yu, C., Su, F., et al: ‘Novel training algorithms for long short-term memory neural network’, IET Signal Process., 2018, 13, (3), pp. 304308.
    25. 25)
      • 10. Bernstein, M., Parrent, A.G.: ‘Complications of CT-guided stereotactic biopsy of intra-axial brain lesions’, J. Neurosurg., 1994, 81, (2), pp. 165168.
    26. 26)
      • 55. Tian, Y., Zhang, K., Li, J., et al: ‘LSTM-based traffic flow prediction with missing data’, Neurocomputing, 2018, 318, pp. 297305.
    27. 27)
      • 39. Arizmendi, C., Vellido, A., Romero, E.: ‘Classification of human brain tumours from MRS data using discrete wavelet transform and Bayesian neural networks’, Expert Syst. Appl., 2012, 39, (5), pp. 52235232.
    28. 28)
      • 22. Arizmendi, C., Sierra, D.A., Vellido, A., et al: ‘Automated classification of brain tumours from short echo time in vivo MRS data using Gaussian decomposition and Bayesian neural networks’, Expert Syst. Appl., 2014, 41, (11), pp. 52965307.
    29. 29)
      • 14. Yüksel, C., Öngür, D.: ‘Magnetic resonance spectroscopy studies of glutamate-related abnormalities in mood disorders’, Biol. Psychiatry, 2010, 68, (9), pp. 785794.
    30. 30)
      • 25. Goebell, E., Paustenbach, S., Vaeterlein, O., et al: ‘Low-grade and anaplastic gliomas: differences in architecture evaluated with diffusion-tensor MR imaging’, Radiology, 2006, 239, (1), pp. 217222.
    31. 31)
      • 65. Abta. Available at https://www.abta.org/wp-content/uploads/2018/03/newly-diagnosed-1.pdf, accessed 27 October 2019.
    32. 32)
      • 20. Devos, A., Lukas, L., Suykens, J., et al: ‘Classification of brain tumours using short echo time 1H MR Spectra’, J. Magn. Reson., 2004, 170, (1), pp. 164175.
    33. 33)
      • 51. Skoch, A., Jiru, F., Bunke, J.: ‘Spectroscopic imaging: basic principles’, Eur. J. Radiol., 2008, 67, (2), pp. 230239.
    34. 34)
      • 41. Manias, K., Gill, S.K., Zarinabad, N., et al: ‘Evaluation of the added value of 1H-magnetic resonance spectroscopy for the diagnosis of pediatric brain lesions in clinical practice’, Neurooncol. Pract., 2017, 5, (1), pp. 1827.
    35. 35)
      • 19. González-Vélez, H., Mier, M., Julià-Sapé, M., et al: ‘HealthAgents: distributed multi-agent brain tumor diagnosis and prognosis’, Appl. Intell., 2009, 30, (3), pp. 191202.
    36. 36)
      • 47. Wang, L., Wan, S., Sun, Y., et al: ‘Automatic classification of brain tumor by in vivo MRS data based on LDA and SVM’. Seventh Int. Conf. on Measuring Technology and Mechatronics Automation, Nanchang, China, 2015, pp. 213216.
    37. 37)
      • 5. Bray, F., Ferlay, J., Soerjomataram, I., et al: ‘Global cancer statistics 2018: Globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries’, CA-Cancer J. Clin., 2018, 68, (6), pp. 394424.
    38. 38)
      • 3. Amin, J., Sharif, M., Yasmin, M., et al: ‘A distinctive approach in brain tumor detection and classification using MRI’, Pattern Recognit. Lett., 2017, to appear.
    39. 39)
      • 53. Kwock, L.: ‘Localized MR spectroscopy: basic principles’, Neuroimaging Clin. N. Am., 1998, 8, (4), pp. 713731.
    40. 40)
      • 54. Callot, V., Galanaud, D., Le Fur, Y., et al: ‘1H MR spectroscopy of human brain tumours: a practical approach’, Clin. Imag., 2008, 67, (2), pp. 268274.
    41. 41)
      • 21. Howe, F.A., Opstad, K.S.: ‘1 h MR spectroscopy of brain tumours and masses’, NMR Biomed., 2003, 16, (3), pp. 123131.
    42. 42)
      • 16. Hagberg, G.: ‘From magnetic resonance spectroscopy to classification of tumors. A review of pattern recognition methods’, NMR Biomed., 1998, 11, (4–5), pp. 148156.
    43. 43)
      • 30. Dowling, C., Bollen, A.W., Noworolski, S.M., et al: ‘Preoperative proton MR spectroscopic imaging of brain tumors: correlation with histopathologic analysis of resection specimens’, Am. J. Neuroradiol., 2001, 22, (4), pp. 604612.
    44. 44)
      • 9. Kondziolka, D., Lunsford, L.D., Martinez, A.J.: ‘Unreliability of contemporary neurodiagnostic imaging in evaluating suspected adult supratentorial (low-grade) astrocytoma’, J. Neurosurg., 1993, 79, (4), pp. 533536.
    45. 45)
      • 44. International network for pattern recognition of tumours using magnetic resonance’, Available at http://gabrmn.uab.es/interpret/, accessed 27 October 2019.
    46. 46)
      • 13. Bulik, M., Jancalek, R., Vanicek, J., et al: ‘Potential of MR spectroscopy for assessment of glioma grading’, Clin. Neurol. Neurosurg., 2013, 115, (2), pp. 146153.
    47. 47)
      • 18. Tate, A.R., Underwood, J., Acosta, D.M., et al: ‘Development of a decision support system for diagnosis and grading of brain tumours using in vivo magnetic resonance single voxel spectra’, NMR Biomed., 2006, 19, (4), pp. 411434.
    48. 48)
      • 50. Cheng, J., Huang, W., Cao, S., et al: ‘Enhanced performance of brain tumor classification via tumor region augmentation and partition’, PLOS One, 2015, 10, (10), p. e0140381.
    49. 49)
      • 62. Karpathy, A., Johnson, J., Fei-Fei, L.: ‘Visualizing and understanding recurrent networks’, arXiv preprint arXiv:1506.02078, 2015.
    50. 50)
      • 45. Chen, W., Lou, H., Zhang, H., et al: ‘Grade classification of neuroepithelial tumors using high-resolution magic-angle spinning proton nuclear magnetic resonance spectroscopy and pattern recognition’, Sci. Chin. Life Sci., 2011, 54, (7), pp. 606616.
    51. 51)
      • 27. Stadlbauer, A., Gruber, S., Nimsky, C., et al: ‘Preoperative grading of gliomas by using metabolite quantification with high-spatial-resolution proton MR spectroscopic imaging’, Radiology, 2006, 238, (3), pp. 958969.
    52. 52)
      • 66. Grup d'aplicacions biomèdiques De La ressonància magnètica nuclear (GABRMN) interpret DSS. Available at http://gabrmn.uab.es/dss, accessed 27 October 2019.
    53. 53)
      • 26. Server, A., Kulle, B., Gadmar, Ø.B., et al: ‘Measurements of diagnostic examination performance using quantitative apparent diffusion coefficient and proton MR spectroscopic imaging in the preoperative evaluation of tumor grade in cerebral gliomas’, Eur. J. Radiol., 2011, 80, (2), pp. 462470.
    54. 54)
      • 23. Dimou, I., Tsougos, I., Tsolaki, E., et al: ‘Brain lesion classification using 3t MRS spectra and paired SVM kernels’, Biomed. Signal Proc. Control, 2011, 6, (3), pp. 314320.
    55. 55)
      • 46. Julià-Sapé, M., Coronel, I., Majós, C., et al: ‘Prospective diagnostic performance evaluation of single-voxel 1H MRS for typing and grading of brain tumours’, NMR Biomed., 2012, 25, (4), pp. 661673.
    56. 56)
      • 38. Ishimaru, H., Morikawa, M., Iwanaga, S., et al: ‘Differentiation between high-grade glioma and metastatic brain tumor using single-voxel proton MR spectroscopy’, Eur. Radiol., 2001, 11, (9), pp. 17841791.
    57. 57)
      • 48. Anaraki, A.K., Ayati, M., Kazemi, F.: ‘Magnetic resonance imaging-based brain tumor grades classification and grading via convolutional neural networks and genetic algorithms’, Biocybern. Biomed. Eng., 2019, 39, (1), pp. 6374.
    58. 58)
      • 52. Hajek, M., Dezortova, M.: ‘Introduction to clinical in vivo MR spectroscopy’, Eur. J. Radiol., 2008, 67, (2), pp. 185193.
    59. 59)
      • 17. Tate, A.R., Majós, C., Moreno, A., et al: ‘Automated classification of short echo time in in vivo 1H brain tumor spectra: a multicenter study’, Magn. Reson. Med., 2003, 49, (1), pp. 2936.
    60. 60)
      • 24. Vicente, J., Fuster-Garcia, E., Tortajada, S., et al: ‘Accurate classification of childhood brain tumours by in vivo 1H MRS – a multi-centre study’, Eur. J. Cancer, 2013, 49, (3), pp. 658667.
    61. 61)
      • 58. Jian, C., Yang, M., Zhang, M.: ‘Mobile terminal trajectory recognition based on improved LSTM model’, IET Image Process., 2019, 13, (11), pp. 19141921.
    62. 62)
      • 40. Naser, R.K.A., Hassan, A.A.K., Shabana, A.M., et al: ‘Role of magnetic resonance spectroscopy in grading of primary brain tumors’, Egypt. J. Radiol. Nucl. Med., 2016, 47, (2), pp. 577584.
    63. 63)
      • 49. Sajjad, M., Khan, S., Muhammad, K., et al: ‘Multi-grade brain tumor classification using deep CNN with extensive data augmentation’, J. Comput. Sci., 2019, 30, pp. 174182.
    64. 64)
      • 32. Dimou, I., Tsougos, I., Tsolaki, E., et al: ‘Classification of pathological human brain lesions using magnetic resonance spectroscopy at 3T’. World Congress on Medical Physics and Biomedical Engineering, 7–12 September 2009, Munich, Germany, 2009, pp. 13681370.
    65. 65)
      • 35. Luts, J., Heerschap, A., Suykens, J.A., et al: ‘A combined MRI and MRSI based multiclass system for brain tumour recognition using LS-SVMs with class probabilities and feature selection’, Artif. Intell. Med., 2007, 40, (2), pp. 87102.
    66. 66)
      • 57. Cao, J., Li, Z., Li, J.: ‘Financial time series forecasting model based on CEEMDAN and LSTM’, Physica A, 2019, 519, pp. 127139.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2019.1416
Loading

Related content

content/journals/10.1049/iet-ipr.2019.1416
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading