Advertisement

Application of MR morphologic, diffusion tensor, and perfusion imaging in the classification of brain tumors using machine learning scheme

  • Shai ShrotEmail author
  • Moshe Salhov
  • Nir Dvorski
  • Eli Konen
  • Amir Averbuch
  • Chen Hoffmann
Diagnostic Neuroradiology

Abstract

Purpose

While MRI is the modality of choice for the assessment of patients with brain tumors, differentiation between various tumors based on their imaging characteristics might be challenging due to overlapping imaging features. The purpose of this study was to apply a machine learning scheme using basic and advanced MR sequences for distinguishing different types of brain tumors.

Methods

The study cohort included 141 patients (41 glioblastoma, 38 metastasis, 50 meningioma, and 12 primary central nervous system lymphoma). A computer-assisted classification scheme, combining morphologic MRI, perfusion MRI, and DTI metrics, was developed and used for tumor classification. The proposed multistep scheme consists of pre-processing, ROI definition, features extraction, feature selection, and classification. Feature subset selection was performed using support vector machines (SVMs). Classification performance was assessed by leave-one-out cross-validation. Given an ROI, the entire classification process was done automatically via computer and without any human intervention.

Results

A binary hierarchical classification tree was chosen. In the first step, selected features were chosen for distinguishing glioblastoma from the remaining three classes, followed by separation of meningioma from metastasis and PCNSL, and then to discriminate PCNSL from metastasis. The binary SVM classification accuracy, sensitivity and specificity for glioblastoma, metastasis, meningiomas, and primary central nervous system lymphoma were 95.7, 81.6, and 91.2%; 92.7, 95.1, and 93.6%; 97, 90.8, and 58.3%; and 91.5, 90, and 96.9%, respectively.

Conclusion

A machine learning scheme using data from anatomical and advanced MRI sequences resulted in high-performance automatic tumor classification algorithm. Such a scheme can be integrated into clinical decision support systems to optimize tumor classification.

Keywords

Computer Artificial intelligence Diagnosis Advance MRI 

Notes

Funding information

No funding was received for this study.

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approval

The study was approved by the institutional research committee.

Informed consent

A wavier for informed consent was approved by institutional research committee.

References

  1. 1.
    Chang SC, Lai PH, Chen WL, Weng HH, Ho JT, Wang JS, Chang CY, Pan HB, Yang CF (2002) Diffusion-weighted MRI features of brain abscess and cystic or necrotic brain tumors: comparison with conventional MRI. Clin Imaging 26:227–236CrossRefGoogle Scholar
  2. 2.
    Lai PH, Hsu SS, Ding SW, Ko CW, Fu JH, Weng MJ et al (2007) Proton magnetic resonance spectroscopy and diffusion-weighted imaging in intracranial cystic mass lesions. Surg Neurol 68(Suppl 1):S25–S36CrossRefGoogle Scholar
  3. 3.
    Tsolaki E, Kousi E, Svolos P, Kapsalaki E, Theodorou K, Kappas C, Tsougos I (2014) Clinical decision support systems for brain tumor characterization using advanced magnetic resonance imaging techniques. World J Radiol 6:72–81CrossRefGoogle Scholar
  4. 4.
    Mabray MC, Barajas RF Jr, Cha S (2015) Modern brain tumor imaging. Brain Tumor Res Treat 3:8–23CrossRefGoogle Scholar
  5. 5.
    Law M, Cha S, Knopp EA, Johnson G, Arnett J, Litt AW (2002) High-grade gliomas and solitary metastases: differentiation by using perfusion and proton spectroscopic MR imaging. Radiology 222:715–721CrossRefGoogle Scholar
  6. 6.
    Svolos P, Kousi E, Kapsalaki E, Theodorou K, Fezoulidis I, Kappas C et al (2014) The role of diffusion and perfusion weighted imaging in the differential diagnosis of cerebral tumors: a review and future perspectives. Cancer Imaging 14:20Google Scholar
  7. 7.
    Svolos P, Tsolaki E, Kapsalaki E, Theodorou K, Fountas K, Fezoulidis I, Tsougos I (2013) Investigating brain tumor differentiation with diffusion and perfusion metrics at 3-T MRI using pattern recognition techniques. Magn Reson Imaging 31:1567–1577CrossRefGoogle Scholar
  8. 8.
    Yang G, Jones TL, Barrick TR, Howe FA (2014) Discrimination between glioblastoma multiforme and solitary metastasis using morphological features derived from the p:q tensor decomposition of diffusion tensor imaging. NMR Biomed 27:1103–1111CrossRefGoogle Scholar
  9. 9.
    Zacharaki EI, Wang S, Chawla S, Soo YD, Wolf R, Melhem ER et al (2009) Classification of brain tumor type and grade using MRI texture and shape in a machine learning scheme. Magn Reson Med 62:1609–1618CrossRefGoogle Scholar
  10. 10.
    Zacharaki EI, Kanas VG, Davatzikos C (2011) Investigating machine learning techniques for MRI-based classification of brain neoplasms. Int J Comput Assist Radiol Surg 6:821–828CrossRefGoogle Scholar
  11. 11.
    Sled JG, Zijdenbos AP, Evans AC (1998) A nonparametric method for automatic correction of intensity nonuniformity in MRI data. IEEE Trans Med Imaging 17:87–97CrossRefGoogle Scholar
  12. 12.
    Tustison N, Gee J (2009) N4ITK: Nick’s N3 ITK implementation for MRI bias field correction. The Insight JournalGoogle Scholar
  13. 13.
    Leemans A, Jeurissen B, Sijbers J, Jones DK (2009) ExploreDTI: a graphical toolbox for processing, analyzing, and visualizing diffusion MR data. 17th Annual Meeting of Intl Soc Mag Reson Med, Hawaii, USA, p 3537Google Scholar
  14. 14.
    Le BD, Mangin JF, Poupon C, Clark CA, Pappata S, Molko N et al (2001) Diffusion tensor imaging: concepts and applications. J Magn Reson Imaging 13:534–546CrossRefGoogle Scholar
  15. 15.
    Papageorgiou TS, Chourmouzi D, Drevelengas A, Kouskouras K, Siountas A (2015) Diffusion tensor imaging in brain tumors: a study on gliomas and metastases. Phys Med 10Google Scholar
  16. 16.
    Lorenz C (2004) Automated perfusion-weighted MRI metrics via localized arterial input functions. Massachusetts Institute of TechnologyGoogle Scholar
  17. 17.
    Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273–297Google Scholar
  18. 18.
    Li B, Meng MQ (2012) Tumor recognition in wireless capsule endoscopy images using textural features and SVM-based feature selection. IEEE Trans Inf Technol Biomed 16:323–329CrossRefGoogle Scholar
  19. 19.
    Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning: data mining, inference, and prediction. Springer, NY, USACrossRefGoogle Scholar
  20. 20.
    Tsougos I, Svolos P, Kousi E, Fountas K, Theodorou K, Fezoulidis I, Kapsalaki E (2012) Differentiation of glioblastoma multiforme from metastatic brain tumor using proton magnetic resonance spectroscopy, diffusion and perfusion metrics at 3 T. Cancer Imaging 12:423–436CrossRefGoogle Scholar
  21. 21.
    Server A, Kulle B, Gadmar OB, Josefsen R, Kumar T, Nakstad PH (2011) 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 80:462–470CrossRefGoogle Scholar
  22. 22.
    Wang S, Kim S, Chawla S, Wolf RL, Knipp DE, Vossough A, O'Rourke DM, Judy KD, Poptani H, Melhem ER (2011) Differentiation between glioblastomas, solitary brain metastases, and primary cerebral lymphomas using diffusion tensor and dynamic susceptibility contrast-enhanced MR imaging. AJNR Am J Neuroradiol 32:507–514CrossRefGoogle Scholar
  23. 23.
    Georgiadis P, Cavouras D, Kalatzis I, Daskalakis A, Kagadis GC, Sifaki K, Malamas M, Nikiforidis G, Solomou E (2008) Improving brain tumor characterization on MRI by probabilistic neural networks and non-linear transformation of textural features. Comput Methods Prog Biomed 89:24–32CrossRefGoogle Scholar
  24. 24.
    Mohsen H, El-Dahshan ES, El-Horbaty ES, Salem AB (2018) Classification using deep learning neural networks for brain tumors. Future Computing and Informatics Journal 3:68–71CrossRefGoogle Scholar
  25. 25.
    Georgiadis P, Cavouras D, Kalatzis I, Glotsos D, Athanasiadis E, Kostopoulos S, Sifaki K, Malamas M, Nikiforidis G, Solomou E (2009) Enhancing the discrimination accuracy between metastases, gliomas and meningiomas on brain MRI by volumetric textural features and ensemble pattern recognition methods. Magn Reson Imaging 27:120–130CrossRefGoogle Scholar
  26. 26.
    Kunimatsu A, Kunimatsu N, Yasaka K, Akai H, Kamiya K, Watadani T et al (2018) Machine learning-based texture analysis of contrast-enhanced MR imaging to differentiate between glioblastoma and primary central nervous system lymphoma. Magn Reson Med Sci:10–0178Google Scholar
  27. 27.
    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 29:525–535CrossRefGoogle Scholar
  28. 28.
    Tsolaki E, Svolos P, Kousi E, Kapsalaki E, Fountas K, Theodorou K, Tsougos I (2013) Automated differentiation of glioblastomas from intracranial metastases using 3-T MR spectroscopic and perfusion data. Int J Comput Assist Radiol Surg 8:751–761CrossRefGoogle Scholar
  29. 29.
    Inano R, Oishi N, Kunieda T, Arakawa Y, Yamao Y, Shibata S, Kikuchi T, Fukuyama H, Miyamoto S (2014) Voxel-based clustered imaging by multiparameter diffusion tensor images for glioma grading. Neuroimage Clin 5:396–407CrossRefGoogle Scholar
  30. 30.
    Citak-Er F, Firat Z, Kovanlikaya I, Ture U, Ozturk-Isik E (2018) Machine-learning in grading of gliomas based on multi-parametric magnetic resonance imaging at 3 T. Comput Biol Med 99:154–160.  https://doi.org/10.1016/j.compbiomed.2018.06.009 CrossRefGoogle Scholar
  31. 31.
    De LC, Beausang A, Cryan J, Loftus T, Buckley PG, Farrell M et al (2018) Machine learning: a useful radiological adjunct in determination of a newly diagnosed glioma's grade and IDH status. J Neuro-Oncol:10–2895Google Scholar
  32. 32.
    Cha S (2006) Update on brain tumor imaging: from anatomy to physiology. AJNR Am J Neuroradiol 27:475–487Google Scholar
  33. 33.
    Hakyemez B, Yildirim N, Erdogan C, Kocaeli H, Korfali E, Parlak M (2006) Meningiomas with conventional MRI findings resembling intraaxial tumors: can perfusion-weighted MRI be helpful in differentiation? Neuroradiology 48:695–702CrossRefGoogle Scholar
  34. 34.
    Kremer S, Grand S, Remy C, Esteve F, Lefournier V, Pasquier B et al (2002) Cerebral blood volume mapping by MR imaging in the initial evaluation of brain tumors. J Neuroradiol 29:105–113Google Scholar
  35. 35.
    Senturk S, Oguz KK, Cila A (2009) Dynamic contrast-enhanced susceptibility-weighted perfusion imaging of intracranial tumors: a study using a 3-T MR scanner. Diagn Interv Radiol 15:3–12Google Scholar
  36. 36.
    Wang S, Kim S, Chawla S, Wolf RL, Zhang WG, O'Rourke DM, Judy KD, Melhem ER, Poptani H (2009) Differentiation between glioblastomas and solitary brain metastases using diffusion tensor imaging. Neuroimage 44:653–660CrossRefGoogle Scholar
  37. 37.
    Inoue T, Ogasawara K, Beppu T, Ogawa A, Kabasawa H (2005) Diffusion tensor imaging for preoperative evaluation of tumor grade in gliomas. Clin Neurol Neurosurg 107:174–180CrossRefGoogle Scholar
  38. 38.
    De Belder FE, Oot AR, Van HW, Venstermans C, Menovsky T, Van M et al (2012) Diffusion tensor imaging provides an insight into the microstructure of meningiomas, high-grade gliomas, and peritumoral edema. J Comput Assist Tomogr 36:577–582CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Department of Diagnostic ImagingSheba Medical CenterRamat GanIsrael
  2. 2.Sackler School of MedicineTel-Aviv UniversityTel-AvivIsrael
  3. 3.School of Computer ScienceTel Aviv UniversityTel AvivIsrael

Personalised recommendations