SVM Optimization for Brain Tumor Identification Using Infrared Spectroscopic Samples

Abstract

The work presented in this paper is focused on the use of spectroscopy to identify the type of tissue of human brain samples employing support vector machine classifiers. Two different spectrometers were used to acquire infrared spectroscopic signatures in the wavenumber range between 1200–3500 cm−1. An extensive analysis was performed to find the optimal configuration for a support vector machine classifier and determine the most relevant regions of the spectra for this particular application. The results demonstrate that the developed algorithm is robust enough to classify the infrared spectroscopic data of human brain tissue at three different discrimination levels.

Revising Fourier-transform infrared (FT-IR) and Raman spectroscopy towards brain cancer detection

“…Several studies have used FT-IR or Raman spectroscopy to investigate biological samples, either tissues or biofluids, to detect brain cancers and their subtypes. For example, Qu et al [29] used FT-IR spectroscopy for rapid diagnosis of gliomas based on serum samples; Fabelo et al [30] used FT-IR spectroscopy to detect brain tumour tissue samples; Depciuch et al [31] used FT-IR and Raman spectroscopy to detect glioblastoma in tissue samples; Kopec et al [32] used Raman imaging to detect various types of human brain tumours; Riva et al [33] used Raman spectroscopy to detect gliomas based on fresh tissue samples; Zhang et al [34] used Raman spectroscopy to detect gliomas based on serum samples; and, Galli et al [35] used Raman spectroscopy to detect brain cancers in tumour biopsies.…”

DA-Based Parameter Optimization of Combined Kernel Support Vector Machine for Cancer Diagnosis

“…The grid search method was employed to search for the optimal parameters in this study. Himar Fabelo et al [31] used radial basis function (RBF) kernel function, linear kernel function, polynomial kernel function, and Processes 2019, 7, 263 3 of 17 sigmoid kernel function to construct SVM classifiers to recognize brain tumors, respectively, and the cross-validation method was utilized to find the optimum parameters of SVM classifiers. By comparing the classification effects of four different models, the results proved that polynomial kernel had advantages in a few evaluation metrics, but in general RBF kernel function got the best classification results.…”

Automatic breast lesion segmentation in phase preserved DCE-MRIs

“…The purpose of supervised learning is to create a trained model that can differentiate between distinct object labels [ 16 – 18 ]. Some popular supervised approaches in the literature are K-Nearest Neighbors (KNN) [ 19 , 20 ], random forests (RF) [ 21 ], SVM [ 22 ], Bayesian, and deep learning, which is an advanced supervised technique [ 23 – 25 ], are some of the popular supervised approaches in the literature. Because supervised methods necessitate huge labelled datasets, they are a time-consuming and computationally expensive method of attaining an efficient outcome [ 26 , 27 ].…”