Semi-Automated Glioblastoma Tumor Detection based on Different Classifiers using Magnetic Resonance Spectroscopy

Ayob  Faramarzi; Nazila  Loghmani; Roqaie Moghadam; Armin  Allahverdy; Meysam  Siyah Mansoory

doi:10.18502/fbt.v8i3.7113

Ayob Faramarzi Department of Biomedical Engineering, School of Medicine, Kermanshah University of Medical Sciences, Kermanshah, Iran
Nazila Loghmani Biomedical Engineering Department, Faculty of Engineering, University of Isfahan, Isfahan, Iran
Roqaie Moghadam Neuroimaging and Analysis Group, Research Center for Molecular and Cellular Imaging, Advanced Medical Technologies and Equipment Institute, Tehran University of Medical Sciences, Tehran, Iran
Armin Allahverdy Department of Radiology, Sari School of Allied Medical Sciences, Mazandaran University of Medical Sciences, Sari, Iran
Meysam Siyah Mansoory Department of Biomedical Engineering, School of Medicine, Kermanshah University of Medical Sciences, Kermanshah, Iran

DOI: https://doi.org/10.18502/fbt.v8i3.7113

Keywords: Magnetic Resonance Spectroscopy; Support Vector Machine; Fuzzy; Multi-Layer Perceptron.

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.