Semi-Automated Glioblastoma Tumor Detection Based on Different Classifiers Using Magnetic Resonance Spectroscopy
Abstract
Purpose: Glioblastoma Multiform (GBM) is one of the most common and deadly malignant brain tumors. Surgery is the primary treatment, and careful surgery can minimize recurrence odds. Magnetic Resonance Imaging (MRI) imaging with Magnetic Resonance Spectroscopy (MRS) is used to diagnose various types of tumors in the Central Nervous System (CNS). In this study, several classification methods were used to separate tumor and healthy tissue.
Materials and Methods: This study examined the MRI and MRS results of seven people enrolled in this study in 2018. The data was obtained with a prescription from a neurologist and neurosurgeon. Choline (Cho) and N-Acetylaspartate (NAA) metabolite signals were selected as the reference signal after preprocessing and removing the water signal. With the support of 3 radiologists, each tumor and healthy vesicles were identified for every patient. Then, tumor and healthy voxels were separated based on Multilayer Perceptron (MLP), linear Support Vector Machine (SVM), Gaussian SVM, and Fuzzy system using the obtained values and four different methods.
Results: Data extracted from Cho and NAA metabolites were fed into MLP, linear SVM, Gaussian and Fuzzy SVM as input, and the amounts of accuracy, sensitivity, and specificity were determined for each method. The maximum accuracy for training mode and test mode was equal to 89.7% and 87%, respectively, specific to classification using Gaussian SVM. The results also showed that the classification accuracy can be significantly increased by increasing the number of fuzzy membership functions from 2 to 6.
Conclusion: The results of this study suggested that a more complex classification system, such as SVM with a Gaussian kernel and fuzzy system can be more efficient and reliable when it comes to separating tumor tissue from healthy tissues from MRS data.
2- E. T. Ha et al., "Chronic inflammation drives glioma growth: cellular and molecular factors responsible for an immunosuppressive microenvironment," vol. 1, pp. 66-76, 2014.
3- J. C. Peeken, J. Hesse, B. Haller, K. A. Kessel, F. Nüsslin, and S. E. J. S. u. O. Combs, "Semantic imaging features predict disease progression and survival in glioblastoma multiforme patients," vol. 194, no. 6, pp. 580-590, 2018.
4- P. Gandhi, R. Khare, H. VasudevGulwani, S. J. I. j. o. m. Kaur, and c. medicine, "Circulatory YKL-40 & NLR: Underestimated Prognostic Indicators in Diffuse Glioma," vol. 7, no. 2, p. 111, 2018.
5- H. Houson, B. Kasten, K. Jiang, J. Rao, and J. J. J. o. N. M. Warram, "MMP-14 as a noninvasive marker for PET and NIRF imaging of glioblastoma multiforme," vol. 60, no. supplement 1, pp. 1033-1033, 2019.
6- A. Allahverdi, S. Akbarzadeh, A. K. Moghaddam, and A. Allahverdy, "Differentiating Tumor and Edema in Brain Magnetic Resonance Images Using a Convolutional Neural Network," Frontiers in Biomedical Technologies, vol. 5, no. 1-2, pp. 44-50, 2018.
7- Y. Xia et al., "Exploring the key genes and signaling transduction pathways related to the survival time of glioblastoma multiforme patients by a novel survival analysis model," BMC genomics, vol. 18, no. 1, p. 950, 2017.
8- T. N. Le et al., "Characterization of an Orthotopic Rat Model of Glioblastoma Using Multiparametric Magnetic Resonance Imaging and Bioluminescence Imaging," Tomography, vol. 4, no. 2, p. 55, 2018.
9- E.-M. Ratai et al., "ACRIN 6684: Multicenter, phase II assessment of tumor hypoxia in newly diagnosed glioblastoma using magnetic resonance spectroscopy," PloS one, vol. 13, no. 6, p. e0198548, 2018.
10- R. Wanner, A. Abaei, V. Rasche, and B. J. F. i. n. Knöll, "Three-dimensional in vivo Magnetic Resonance Imaging (MRI) of mouse facial nerve regeneration," vol. 10, 2019.
11- J. Klein, W. W. Lam, G. J. Czarnota, and G. J. J. O. Stanisz, "Chemical exchange saturation transfer MRI to assess cell death in breast cancer xenografts at 7T," vol. 9, no. 59, p. 31490, 2018.
12- W. T. Choi et al., "Metabolomics of mammalian brain reveals regional differences," BMC systems biology, vol. 12, no. 8, p. 127, 2018.
13- G. Reynolds, M. Wilson, A. Peet, and T. N. J. M. R. i. M. A. O. J. o. t. I. S. f. M. R. i. M. Arvanitis, "An algorithm for the automated quantitation of metabolites in in vitro NMR signals," vol. 56, no. 6, pp. 1211-1219, 2006.
14- M. Wilson et al., "Methodological consensus on clinical proton MRS of the brain: Review and recommendations," Magnetic resonance in medicine, vol. 82, no. 2, pp. 527-550, 2019.
15- A. G. Costigan, K. Umla‐Runge, C. J. Evans, C. J. Hodgetts, A. D. Lawrence, and K. S. Graham, "Neurochemical correlates of scene processing in the precuneus/posterior cingulate cortex: A multimodal fMRI and 1H‐MRS study," Human brain mapping, vol. 40, no. 10, pp. 2884-2898, 2019.
16- N. M. Simard, "TECHNICAL CONSIDERATIONS FOR 1H-MAGNETIC RESONANCE SPECTROSCOPY (1H-MRS) MEASUREMENT OF SPINAL CORD GAMMA-AMINOBUTYRIC ACID (GABA)," 2019.
17- S. Mitra et al., "Proton magnetic resonance spectroscopy lactate/N-acetylaspartate within 2 weeks of birth accurately predicts 2-year motor, cognitive and language outcomes in neonatal encephalopathy after therapeutic hypothermia," Archives of Disease in Childhood-Fetal and Neonatal Edition, vol. 104, no. 4, pp. F424-F432, 2019.
18- D. Soares and M. Law, "Magnetic resonance spectroscopy of the brain: review of metabolites and clinical applications," Clinical radiology, vol. 64, no. 1, pp. 12-21, 2009.
19- A. Allahverdy, A. M. Nasrabadi, and M. R. Mohammadi, "Detecting ADHD children using symbolic dynamic of nonlinear features of EEG," in Electrical Engineering (ICEE), 2011 19th Iranian Conference on, 2011: IEEE, pp. 1-4.
20- M. F. Santarelli et al., "How the signal‐to‐noise ratio influences hyperpolarized 13C dynamic MRS data fitting and parameter estimation," vol. 25, no. 7, pp. 925-934, 2012.
21- G. S. J. P. i. M. Payne and Biology, "Clinical applications of in vivo magnetic resonance spectroscopy in oncology," vol. 63, no. 21, p. 21TR02, 2018.
22- M. Wilson, G. Reynolds, R. A. Kauppinen, T. N. Arvanitis, and A. C. J. M. r. i. m. Peet, "A constrained least‐squares approach to the automated quantitation of in vivo 1H magnetic resonance spectroscopy data," vol. 65, no. 1, pp. 1-12, 2011.
23- F. R. Lima-Junior and L. C. R. J. I. J. o. P. E. Carpinetti, "Predicting supply chain performance based on SCOR® metrics and multilayer perceptron neural networks," vol. 212, pp. 19-38, 2019.
24- S. Chen et al., "Rapid determination of soil classes in soil profiles using vis–NIR spectroscopy and multiple objectives mixed support vector classification," vol. 70, no. 1, pp. 42-53, 2019.
25- A. A. Torres-García, C. A. Reyes-García, L. Villaseñor-Pineda, and G. J. E. S. w. A. García-Aguilar, "Implementing a fuzzy inference system in a multi-objective EEG channel selection model for imagined speech classification," vol. 59, pp. 1-12, 2016.
26- M. Jarrar, A. Kerkeni, A. B. Abdallah, and M. H. Bedoui, "MLP neural network classifier for medical image segmentation," in 2016 13th International Conference on Computer Graphics, Imaging and Visualization (CGiV), 2016: IEEE, pp. 88-93.
27- S. Ulmer, M. Backens, and F. J. J. J. o. c. a. t. Ahlhelm, "Basic principles and clinical applications of magnetic resonance spectroscopy in neuroradiology," vol. 40, no. 1, pp. 1-13, 2016.
28- P. A. J. J. o. V. Keith and I. Radiology, "ct and Mri of the Whole Body, 2-volume Set," vol. 20, no. 10, p. 1397, 2009.
29- N. A. Parra et al., "Volumetric spectroscopic imaging of glioblastoma multiforme radiation treatment volumes," vol. 90, no. 2, pp. 376-384, 2014.
30- H. Xu et al., "Evaluation of neuron-glia integrity by in vivo proton magnetic resonance spectroscopy: Implications for psychiatric disorders," vol. 71, pp. 563-577, 2016.
| Files | ||
| Issue | Vol 8 No 3 (2021) | |
| Section | Original Article(s) | |
| DOI | https://doi.org/10.18502/fbt.v8i3.7113 | |
| Keywords | ||
| Magnetic Resonance Spectroscopy Support Vector Machine Fuzzy Multi-Layer Perceptron | ||
| Rights and permissions | |
|
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
