Segmentation, Feature Extraction, and Multiclass Brain Tumor Classification

Abstract

Multiclass brain tumor classification is performed by using a diversified dataset of 428 post-contrast T1-weighted MR images from 55 patients. These images are of primary brain tumors namely astrocytoma (AS), glioblastoma multiforme (GBM), childhood tumor-medulloblastoma (MED), meningioma (MEN), secondary tumor-metastatic (MET), and normal regions (NR). Eight hundred fifty-six regions of interest (SROIs) are extracted by a content-based active contour model. Two hundred eighteen intensity and texture features are extracted from these SROIs. In this study, principal component analysis (PCA) is used for reduction of dimensionality of the feature space. These six classes are then classified by artificial neural network (ANN). Hence, this approach is named as PCA-ANN approach. Three sets of experiments have been performed. In the first experiment, classification accuracy by ANN approach is performed. In the second experiment, PCA-ANN approach with random sub-sampling has been used in which the SROIs from the same patient may get repeated during testing. It is observed that the classification accuracy has increased from 77 to 91 %.PCA-ANN has delivered high accuracy for each class: A S -9 0 . 7 4 % , G B M -8 8 . 4 6 % , M E D -8 5 % , MEN-90.70 %, MET-96.67 %, and NR-93.78 %. In the third experiment, to remove bias and to test the robustness of the proposed system, data is partitioned in a manner such that the SROIs from the same patient are not common for training and testing sets. In this case also, the proposed system has performed well by delivering an overall accuracy of 85.23 %. The individual class accuracy for each class is: AS-86.15 %, GBM-65.1 %, MED-63.36 %, MEN-91.5 %, MET-65.21 %, and NR-93.3 %. A computer-aided diagnostic system comprising of developed methods for segmentation, feature extraction, and classification of brain tumors can be beneficial to radiologists for precise localization, diagnosis, and interpretation of brain tumors on MR images.

Classification of Malignant and Benign Tumors

“…In contrast, region-based features are derived from within a tumor region, which include the shape, texture, or the frequency domain information of the tumor. Some examples of region-based features are the tumor size, image moment features [31], wavelet-based features [29], and texture features [28].…”

“…For example, in [27], effective thickness and effective volume were defined on the physical properties of MCs in mammogram images and were demonstrated to be useful for diagnosis. In [28], image intensity and texture features were extracted from post-contrast T1-weighted MR images and were shown to be helpful for brain tumor classification. In [29], wavelet features were compared with Haralick features [30] for MC classification.…”

Computer Aided Diagnosis System-A Decision Support System for Clinical Diagnosis of Brain Tumours

“…Sachdeva et al [18] In this papers, these above limitations are surmounted with the help of GUI developed for ROI segregation. 371 texture and intensity features are obtained from the ROI(s) extracted from the database of post-contrast T1 weighted MR-images of 10 patients.…”

MRI brain scan classification using novel 3-D statistical features

“…The classification was performed using SVM, such that, 86%, 68% and 50% were the maximum classification accuracy of T2-w MRI brain images, mammograms and retina respectively. Similarly, Sachdeva, et al [14] used five techniques for texture features extraction to classify the MRI brain tumors into multiclass. These five techniques were Laplacian of Gaussian (LoG), GLCM, rotation invariant local binary patterns (RILBP), intensity-based features (IBF), and directional Gabor texture features (DGTF).…”