Abstract:The purpose of this paper is to evaluate the effect of the combination of magnetic resonance spectroscopic imaging (MRSI) data and magnetic resonance imaging (MRI) data on the classification result of four brain tumor classes. Suppressed and unsuppressed short echo time MRSI and MRI were performed on 24 patients with a brain tumor and four volunteers. Four different feature reduction procedures were applied to the MRSI data: simple quantitation, principal component analysis, independent component analysis and … Show more
“…This study complements previous work in using combined MRI and spectroscopy features in classifying brain tumors [13][14][15][16]. We have chosen to apply similar methods of supervised pattern recognition and computer-aided diagnosis to study a very specific question in glioma imaging, thereby relating machine learning techniques with image segmentation and clinical prediction.…”
Section: Discussionmentioning
confidence: 89%
“…While other researchers have found success in treating each voxel in an image as an separate instance in training [38], others have used prior knowledge of the acquisition procedure to reduce correlations between samples by attempting to choose only the most uncorrelated voxels [14]. The approach used in this study was to condense information from the entire ROI in a single patient, so that correlations between samples in a single patient are largely removed, and each patient contributes equally to the training data.…”
Section: Discussionmentioning
confidence: 99%
“…However, there has been somewhat less work on combining imaging data with spectroscopy. When this combination has been performed, the accuracy of the classification has been shown to be superior to using images or spectroscopy alone [13][14][15][16].…”
Objective: The purpose of this study was to develop a pattern classification algorithm for use in predicting the location of new contrast-enhancement in brain tumor patients using data obtained via multivariate magnetic resonance imaging from a prior scan. We also explore the use of feature selection or weighting in improving the accuracy of the pattern classifier.
Methods and materials:Contrast-enhanced MR images, perfusion images, diffusion images, and proton spectroscopic imaging data were obtained from 26 patients with glioblastoma multiforme brain tumors, divided into a design set and an unseen test set for verification of results. A k-NN algorithm was implemented to classify unknown data based on a set of training data with ground truth derived from post-treatment contrast enhanced images; the quality of the k-NN results was evaluated using a leave-one-out cross-validation method. A genetic algorithm was implemented to select optimal features and feature weights for the k-NN algorithm. The binary representation of the weights was varied from 1 to 4 bits. Each individual parameter was thresholded as a simple classification technique, and the results compared with the k-NN.
Results:The feature selection k-NN was able to achieve a sensitivity of 0.78 ± 0.18 and specificity of 0.79 ± 0.06 on the holdout test data using only 7 of the 38 original features. Similar results were obtained with non-binary weights, but using a larger number of features. Overfitting was also observed in the higher bit representations. The best single-variable classifier, based on a choline-to-NAA abnormality index computed from spectroscopic data, achieved a sensitivity of 0.79 ± 0.20 and specificity of 0.71 ± 0.11. The k-NN results had lower variation across patients than the single-variable classifiers.
Conclusions:We have demonstrated that the an optimized k-NN rule could be used for quantitative analysis of multivariate images, and be applied to a specific clinical research question. Selecting features was found to be useful in improving the accuracy of feature weighting algorithms and improving the comprehensibility of the results. We believe that in addition to
“…This study complements previous work in using combined MRI and spectroscopy features in classifying brain tumors [13][14][15][16]. We have chosen to apply similar methods of supervised pattern recognition and computer-aided diagnosis to study a very specific question in glioma imaging, thereby relating machine learning techniques with image segmentation and clinical prediction.…”
Section: Discussionmentioning
confidence: 89%
“…While other researchers have found success in treating each voxel in an image as an separate instance in training [38], others have used prior knowledge of the acquisition procedure to reduce correlations between samples by attempting to choose only the most uncorrelated voxels [14]. The approach used in this study was to condense information from the entire ROI in a single patient, so that correlations between samples in a single patient are largely removed, and each patient contributes equally to the training data.…”
Section: Discussionmentioning
confidence: 99%
“…However, there has been somewhat less work on combining imaging data with spectroscopy. When this combination has been performed, the accuracy of the classification has been shown to be superior to using images or spectroscopy alone [13][14][15][16].…”
Objective: The purpose of this study was to develop a pattern classification algorithm for use in predicting the location of new contrast-enhancement in brain tumor patients using data obtained via multivariate magnetic resonance imaging from a prior scan. We also explore the use of feature selection or weighting in improving the accuracy of the pattern classifier.
Methods and materials:Contrast-enhanced MR images, perfusion images, diffusion images, and proton spectroscopic imaging data were obtained from 26 patients with glioblastoma multiforme brain tumors, divided into a design set and an unseen test set for verification of results. A k-NN algorithm was implemented to classify unknown data based on a set of training data with ground truth derived from post-treatment contrast enhanced images; the quality of the k-NN results was evaluated using a leave-one-out cross-validation method. A genetic algorithm was implemented to select optimal features and feature weights for the k-NN algorithm. The binary representation of the weights was varied from 1 to 4 bits. Each individual parameter was thresholded as a simple classification technique, and the results compared with the k-NN.
Results:The feature selection k-NN was able to achieve a sensitivity of 0.78 ± 0.18 and specificity of 0.79 ± 0.06 on the holdout test data using only 7 of the 38 original features. Similar results were obtained with non-binary weights, but using a larger number of features. Overfitting was also observed in the higher bit representations. The best single-variable classifier, based on a choline-to-NAA abnormality index computed from spectroscopic data, achieved a sensitivity of 0.79 ± 0.20 and specificity of 0.71 ± 0.11. The k-NN results had lower variation across patients than the single-variable classifiers.
Conclusions:We have demonstrated that the an optimized k-NN rule could be used for quantitative analysis of multivariate images, and be applied to a specific clinical research question. Selecting features was found to be useful in improving the accuracy of feature weighting algorithms and improving the comprehensibility of the results. We believe that in addition to
“…[6] [7]As shown in table normal and abnormal values used in classification are depicted.All research in the field indicates that the metabolite NAA decreases in almost all brain tumours and Cho increases which thereby leads in increased value for the ratio Cho/NAA. In data classification, the classifier is evaluated by a confusion matrix.…”
Section: Experimentation and Results Discussionmentioning
One of the significant applications of image classification is the medical field in which the abnormal brain tumor images are categorized prior to treatment planning. Accurate identification of the type of the brain abnormality is highly essential since the treatment planning is different for all the brain abnormalities. Any false detection may lead to a wrong treatment which ultimately leads to fatal results. By employing the Magnetic Resonance Spectroscopy (MRS) graph and thereby extracting the values of the metabolites from the graph one can classify the tumor based on the values of metabolites. The aim of this research is to identify brain tumour disease pattern from MRS images to perform differential diagnosis. The authors have employed the use of the Naïve -Bayes and J48 classifier for identification of the disease pattern from the three metabolite ratios.
General TermsPattern Recognition
“…Limited work has been carried out in the area of characterization and analysis of 3D (volumetric) textures using MRI, MRS, and both MRI and MRS [5,9,10,24,25]. Dou et al [27] proposed the glial tumor segmentation method using data fusion of MRI and MRS based on fuzzy-based method.…”
This paper investigates the efficacy of automated pattern recognition methods on magnetic resonance data with the objective of assisting radiologists in the clinical diagnosis of brain tissue tumors. In this paper, the sciences of magnetic resonance imaging (MRI) and magnetic resonance spectroscopy (MRS) are combined to improve the accuracy of the classifier, based on the multidimensional co-occurrence matrices to assess the detection of pathological tissues (tumor and edema), normal tissues (white matter -WM and gray matter -GM), and fluid (cerebrospinal fluid -CSF). The results show the ability of the classifier with iterative training to automatically and simultaneously recover tissue-specific spectral and structural patterns and achieve segmentation of tumor and edema and grading of high and low glioma tumor. Here, extreme learning machine -improved particle swarm optimization (ELM-IPSO) neural network classifier is trained with the feature descriptions in brain magnetic resonance (MR) spectra. This has the characteristics of varying the normal spectral pattern associated with tumor patterns along with imaging features. Validation was performed considering 35 clinical studies. The volumetric features extracted from the vectors of this matrix articulate some important elementary structures, which along with spectroscopic metabolite ratios discriminate the tumor grades and tissue classes. The quantitative 3D analysis reveals significant improvement in terms of global accuracy rate for automatic classification in brain tissues and discriminating pathological tumor tissue from structural healthy brain tissue.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.