Abstract
Some multiple sclerosis (MS) lesions may have great similarities with neoplastic brain lesions in magnetic resonance (MR) imaging and thus wrong diagnoses may occur. In this study, differentiation of MS and low-grade brain tumors was performed with computer-aided diagnosis (CAD) methods by magnetic resonance spectroscopy (MRS) data. MRS data belonging to 51 MS and 39 low-grade brain tumor patients were obtained. The feature extraction from MRS data was performed by the help of peak integration (PI) and full spectra (FS) methods and the most significant features were identified. For the classification step, artificial neural network (ANN), support vector machine (SVM), and linear discriminant analysis (LDA) methods were used and the differentiation between MS and brain tumor was performed automatically. Examining the results, one can conclude that data which belong to MS and low-grade brain tumor cases were automatically differentiated from each other with the help of ANN with 100% accuracy, 100% sensitivity, and 100% specificity. Using of MR spectroscopy and artificial intelligence methods may be useful as a complementary imaging technique to MR imaging in the differentiation of MS lesions and low-grade brain tumors.
Similar content being viewed by others
References
Altıntaş A, Esen F (2008) Immunopathogenesis of multiple sclerosis. Arch Neuropsychiatry 45(Suppl):10–14
Gabelic T, Skoric MK, Adamec I et al (2013) Tongue somatosensory-evoked potentials: evaluation of the afferent trigeminal pathway in patients with early multiple sclerosis. Clin EEG Neurosci 44:286–290
Khan O, Bao F, Bernitsas E et al (2004) Prospective multi-modal MRI study to examine the effect of natalizumab on tissue injury in the brain and spinal cord in patients with RRMS. Mult Scler 20(1 Suppl):285–496
Cha S, Pierce S, Knopp EA, Johnson G, Yang C, Ton A, Litt AW, Zagzag D (2001) Dynamic contrast-enhanced T2*-weighted MR imaging of tumefactive demyelinating lesions. Am J Neuroradiol 22:1109–1116
Huisman TA (2009) Tumor-like lesions of the brain. Cancer Imaging (Special issue A) S10
Kilic AK, Kurne AT, Oguz KK et al (2012) Mass lesions in the brain: tumor or multiple sclerosis? Clinical and imaging characteristics and course from a single reference center. Turk Neurosurg 23(6):728–735
Turatti M, Gajofatto A, Bianchi MR, Ferrari S, Monaco S, Benedetti MD (2013) Benign course of tumour-like multiple sclerosis. Report of five cases and literature review. J Neurol Sci 324(1):156–162
Capello E, Roccatagliata L, Pagano F et al (2001) Tumor-like multiple sclerosis (MS) lesions: neuropathological clues. Neurol Sci 22:113–116
Carvalho AT, Linhares P, Castro L, Sá MJ (2014) Multiple sclerosis and oligodendroglioma: an exceptional association. Case Rep Neurol Med:1–5
Green AJ, Bollen AW, Berger MS, Oksenberg JR, Hauser SL (2001) Multiple sclerosis and oligodendroglioma. Mult Scler 7(4):269–273
Abdoli M, Freedman MS (2015) Neuro-oncology dilemma: tumour or tumefactive demyelinating lesion. J Mult Scler 2(137):2376–0389
Kes VB, Cesarik M, Ćorić L et al (2012) Tumor-like multiple sclerosis. Acta Clin Croat 51(1):113–116
Plantone D, Renna R, Sbardella E et al (2015) Concurrence of multiple sclerosis and brain tumors. Front Neurol 6:1–4
Ponnada AN (2005) Magnetic resonance spectroscopy in the monitoring of multiple sclerosis. J Neuroimaging 15(4 Suppl):46–57
De Stefano N, Narayanan S, Matthews PM et al (2000) Proton MR spectroscopy to assess axonal damage in multiple sclerosis and other white matter disorders. J Neuro-Oncol 6(2):121
Ge Y (2006) Multiple sclerosis: the role of MR imaging. Am J Neuroradiol 27:1165–1176
Bitscha A, Bruhna H, Vougioukasa V et al (1999) Inflammatory CNS demyelination: histopathologic correlation with in vivo quantitative proton MR spectroscopy. Am J Neuroradiol 20:1619–1627
Georgiadis P, Kostopoulos S, Cavouras D, Glotsos D, Kalatzis I, Sifaki K, Malamas M, Solomou E, Nikiforidis G (2011) Quantitative combination of volumetric MR imaging and MR spectroscopy data for the discrimination of meningiomas from metastatic brain tumors by means of pattern recognition. Magn Reson Imaging 29:525–535
Ranjith G, Parvathy R, Vikas V, Chandrasekharan K, Nair S (2015) Machine learning methods for the classification of gliomas: initial results using features extracted from MR spectroscopy. Neuroradiol J 28(2):106–111
Astrakas L, Blekas KD, Constantinou C (2011) Combining magnetic resonance spectroscopy and molecular genomics offers better accuracy in brain tumor typing and prediction of survival than either methodology alone. Int J Oncol 38:1113–1127
International network for pattern recognition of tumours using magnetic resonance, http://gabrmn.uab.es/interpret/. Accessed 03 Jan 2016
Johnson DR, Guerin JB, Giannini C, Morris JM, Eckel LJ, Kaufmann TJ (2017) 2016 updates to the WHO brain tumor classification system: what the radiologist needs to know. RadioGraphics 37:2164–2180
Fuster-Garcia E, Navarro C, Vicente J, Tortajada S, García-Gómez JM, Sáez C, Calvar J, Griffiths J, Julià-Sapé M, Howe FA, Pujol J, Peet AC, Heerschap A, Moreno-Torres À, Martínez-Bisbal MC, Martínez-Granados B, Wesseling P, Semmler W, Capellades J, Majós C, Alberich-Bayarri À, Capdevila A, Monleón D, Martí-Bonmatí L, Arús C, Celda B, Robles M (2011) Compatibility between 3T 1H SV-MRS data and automatic brain tumour diagnosis support systems based on databases of 1.5T 1H SV-MRS spectra. MAGMA 24:35–42
Gill SK (2013) Single voxel proton magnetic resonance spectroscopy of childhood brain tumours. PhD Thesis, University of Birmingham
Cangelosi R, Goriely A (2007) Component retention in principal component analysis with application to cDNA microarray data. Biol Direct 2:1–21
Callot V, Galanaud D, Le Fur Y et al (2008) 1H MR spectroscopy of human brain tumours: a practical approach. Eur J Radiol 67(2):268–274
Saindane AM, Cha S, Law M, Xue X, Knopp EA, Zagzag D (2002) Proton MR spectroscopy of tumefactive demyelinating lesions. Am J Neuroradiol 23:1378–1386
Cianfoni A, Niku S, Imbesi SG (2007) Metabolite findings in tumefactive demyelinating lesions utilizing short echo time proton magnetic resonance spectroscopy. Am J Neuroradiol 28:272–277
Majos C, Aguilera C, Alonso J et al (2009) Proton MR spectroscopy improves discrimination between tumor and pseudotumoral lesion in solid brain masses. Am J Neuroradiol 30:544–551
Malhotra HS, Jain KK, Agarwal A (2009) Characterization of tumefactive demyelinating lesions using MR imaging and in-vivo proton MR spectroscopy. Mult Scler 15:193–203
Butteriss DJ, Ismail A, Ellison DW et al (2014) Use of serial proton magnetic resonance spectroscopy to differentiate low grade glioma from tumefactive plaque in a patient with multiple sclerosis. Br J Radiol
Acknowledgments
This study was supported by Sakarya University BAPK (Project No: 2015-50-02-012). The authors wish to thank all patients included in the study for their approval to the use of their MRS data for research and educational purposes.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Ethical approval
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Ekşi, Z., Özcan, M.E., Çakıroğlu, M. et al. Differentiation of multiple sclerosis lesions and low-grade brain tumors on MRS data: machine learning approaches. Neurol Sci 42, 3389–3395 (2021). https://doi.org/10.1007/s10072-020-04950-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10072-020-04950-0