Brain Tumor MR Research Articles

IDSS-based Two stage classification of brain tumor using SVM

The computer and image processing has a significant role in detecting tumor area. The decision support systems for human brain MR images are essentially encouraged with the requirement of attaining maximal achievable efficiency and the motivation of the approach which is to enhance the performance of Computer-Aided Diagnosis (CAD) system to detect a tumor in the human brain. Even though numerous support systems have been introduced in the past, this is still an open problem seeking for an accurate and robust decision support system. The Interactive Diagnosis Support System (IDSS) approach has addressed the limitations of nonillumination and low contrast of a brain tumor MR image that influences the procedure of accurate image classification. Thus, the IDSS is implemented in three phases namely image preprocessing for enhancing non-illuminated features, feature extraction and image classification which is accomplished using two-stage interactive SVM Classification. The local binary patterns are detected in the feature extraction for accurate classification of usual and unusual brain MR Images. The experimental outcomes for this approach are carried out using MATLAB R2016a and evaluated using the brain images downloaded from the Internet. The performance metrics such as structured similarity index, sensitivity, specificity and accuracy were used to assess the IDSS-based tumor classification system. When compared with the traditional classifiers such as ANFIS, Backpropagation and K-NN, the IDSS approach has significant brain tumor classification accuracy.

Brain Tumor Segmentation from Multi-modality MRI Data Based on Tamura Texture

A segmentation algorithm of brain tumor MR image based on Tamura texture feature and BP Neural Network is proposed in this paper. Firstly, the local grayscale features of four modal MR images are combined with the Tamura texture metrics in the algorithm. The information in the image is extracted as much as possible. Then, the known samples are input into the BP Neural Network and classifier training is performed. Finally, other brain tumor images are processed with the trained BP Neural Network. The experiment was performed on the images of 30 patients. From the obtained data, the method proposed in this paper can segment the brain tumor region accurately and effectively and show strong self-adaptability to the difference of the brain tumor images.

Optimization of the brain tumor MR images classification accuracy using the optimal threshold, PCA and training ANFIS with different repetitions

Introduction: One of the leading causes of death among people is brain tumors. Accurate tumor classification leads to appropriate decision-making and providing the most efficient treatment to the patients. This study aims to optimize of the brain tumor MR images classification accuracy using the optimal threshold, PCA and training Adaptive Neuro Fuzzy Inference System (ANFIS) with different repetitions. Materials and Methods: This procedure used in this study consists of five steps: (1) T1, T2 weighted images collection, (2) tumor separation with different threshold levels, (3) feature extraction, (4) presence and absence of feature reduction applying principal component analysis (PCA) and (5) ANFIS classification with 0, 20, and 200 training repetitions. Results: ANFIS accuracy was 40%, 80% and 97% for all features and 97%, 98.5% and 100% for the 6 selected features by PCA in 0, 20 and 200 training repetitions, respectively. Conclusion: The findings of the present study showed that accuracy can be raised up to 100% by using an optimized threshold method, PCA and increasing training repetitions.

Denoising of skull stripped brain tumor MR images

Denoising of skull stripped brain tumor MR images

An uniformizing method of MR image intensity transformation

The scanner-dependent variations effect fluctuation of intensities of MR images, even under the fixed condition of key parameters: the scanner, the patient, the body region and the type of MRI protocol. The inherent variation causes the lack of a standard and quantifiable interpretation of image intensities. Moreover, the unbalanced distribution of intensity values lowers accuracy and sensitivity of automatic analysis and segmentation based on MR images. As such, we proposed a uniformizing method to make the distribution even while ensuring that similar intensities of MR images reflect the same tissue after processed. Our experiments based on the 3D brain tumor MR images proved that this method can significantly improve labeling and segmentation accuracy as compared to conventional preprocessed methods.

Optimization of Brain Tumor MR Image Classification Accuracy Using Optimal Threshold, PCA and Training ANFIS with Different Repetitions

One of the leading causes of death is brain tumors. Accurate tumor classification leads to appropriate decision making and providing the most efficient treatment to the patients. This study aims to optimize brain tumor MR images classification accuracy using optimal threshold, PCA and training Adaptive Neuro Fuzzy Inference System (ANFIS) with different repetitions. The procedure used in this study consists of five steps: (1) T1, T2 weighted images collection, (2) tumor separation with different threshold levels, (3) feature extraction, (4) presence and absence of feature reduction applying principal component analysis (PCA) and (5) ANFIS classification with 0, 20 and 200 training repetitions. ANFIS accuracy was 40%, 80% and 97% for all features and 97%, 98.5% and 100% for the 6 selected features by PCA in 0, 20 and 200 training repetitions, respectively. The findings of the present study demonstrated that accuracy can be raised up to 100% by using an optimized threshold method, PCA and increasing training repetitions.

Overcoming blood-brain barrier by HER2-targeted nanosystem to suppress glioblastoma cell migration, invasion and tumor growth.

Efficient therapy of glioblastoma remains a big clinical challenge due to the existence of a blood-brain barrier (BBB) that prevents the delivery of anti-cancer drugs to the brain. In this study, a HER2 antibody-conjugated selenium nanoparticle platform was rationally designed and synthesised and was found to be capable of overcoming the BBB efficiently and delivering anti-cancer cargoes precisely to brain tissues. The BBB-overcoming efficacy of the nanosystem (HER2@NPs) was evaluated using in vitro cell co-culture model and in vivo mouse model. The results demonstrated that HER2 functionalization effectively enhanced BBB permeability of the NPs, which could significantly inhibit the growth of U251 glioblastoma tumor spheroids. Examination of the action mechanisms revealed that HER2@NPs entered the cancer cells through receptor-mediated endocytosis and then triggered DNA damage-mediated p53 signalling pathways. Moreover, by using superparamagnetic iron oxide nanoparticles (SPIONs) as a probe in a clinically used magnetic resonance imaging (MRI) system, we found that HER2@NPs effectively deliver SPIONs into the brain. Taken together, this study provides a cancer-targeting nanosystem for the delivery of anti-cancer drugs and MRI contrast agents overcoming the BBB to enable a precise future theranosis of malignant glioma in humans.

Relative Investigation of Machine Learning Algorithms for Performance Analysis on Brain MR Images

The world is moving exponential towards the technical growth in every field. The most obliging and gifted is the field of Healthcare and medical diagnosis with the advanced techniques of Artificial Intelligence and Machine Learning; it’s a boon to the patients affected by cancer. Brain Tumor is one of the severe syndrome causes for the death of Human beings. Magnetic Resonance Imaging is vital medical diagnosis tool for revealing of tumors. Precise segmentation and classification of the tumors yet relics a puzzling task because of its large structural and spatial erraticism among tumors. In this paper an effort is made to discuss and implement the different Machine Learning classification algorithms on Brain Tumor MR Images for 20 Patients i.e 150*20 Slices of MR Sequences (MR Images) for thirteen attributes (statistical features), using the Dataset of BRATS 2015. Contribution to the heart of technology that can be used for tumor classification exhausting the machine learning algorithms namely the Naive Bayes, Logistic Regression, Multi-layer Perceptron, Support Vector Machine and Decision tree using the Waikato Environment for Knowledge Analysis tool and MATLAB. The experimental outcomes of proposed technique have been assessed for performance and quality examination on magnetic resonance brain images.

A novel fully automatic multilevel thresholding technique based on optimized intuitionistic fuzzy sets and tsallis entropy for MR brain tumor image segmentation.

In the present paper, a hybrid multilevel thresholding technique that combines intuitionistic fuzzy sets and tsallis entropy has been proposed for the automatic delineation of the tumor from magnetic resonance images having vague boundaries and poor contrast. This novel technique takes into account both the image histogram and the uncertainty information for the computation of multiple thresholds. The benefit of the methodology is that it provides fast and improved segmentation for the complex tumorous images with imprecise gray levels. To further boost the computational speed, the mutation based particle swarm optimization is used that selects the most optimal threshold combination. The accuracy of the proposed segmentation approach has been validated on simulated, real low-grade glioma tumor volumes taken from MICCAI brain tumor segmentation (BRATS) challenge 2012 dataset and the clinical tumor images, so as to corroborate its generality and novelty. The designed technique achieves an average Dice overlap equal to 0.82010, 0.78610 and 0.94170 for three datasets. Further, a comparative analysis has also been made between the eight existing multilevel thresholding implementations so as to show the superiority of the designed technique. In comparison, the results indicate a mean improvement in Dice by an amount equal to 4.00% (p < 0.005), 9.60% (p < 0.005) and 3.58% (p < 0.005), respectively in contrast to the fuzzy tsallis approach.

Quality of clinical brain tumor MR spectra judged by humans and machine learning tools.

To investigate and compare human judgment and machine learning tools for quality assessment of clinical MR spectra of brain tumors. A very large set of 2574 single voxel spectra with short and long echo time from the eTUMOUR and INTERPRET databases were used for this analysis. Original human quality ratings from these studies as well as new human guidelines were used to train different machine learning algorithms for automatic quality control (AQC) based on various feature extraction methods and classification tools. The performance was compared with variance in human judgment. AQC built using the RUSBoost classifier that combats imbalanced training data performed best. When furnished with a large range of spectral and derived features where the most crucial ones had been selected by the TreeBagger algorithm it showed better specificity (98%) in judging spectra from an independent test-set than previously published methods. Optimal performance was reached with a virtual three-class ranking system. Our results suggest that feature space should be relatively large for the case of MR tumor spectra and that three-class labels may be beneficial for AQC. The best AQC algorithm showed a performance in rejecting spectra that was comparable to that of a panel of human expert spectroscopists. Magn Reson Med 79:2500-2510, 2018. © 2017 International Society for Magnetic Resonance in Medicine.

Groupwise registration of MR brain images with tumors

A novel groupwise image registration framework is developed for registering MR brain images with tumors. Our method iteratively estimates a normal-appearance counterpart for each tumor image to be registered and constructs a directed graph (digraph) of normal-appearance images to guide the groupwise image registration. Particularly, our method maps each tumor image to its normal appearance counterpart by identifying and inpainting brain tumor regions with intensity information estimated using a low-rank plus sparse matrix decomposition based image representation technique. The estimated normal-appearance images are groupwisely registered to a group center image guided by a digraph of images so that the total length of ‘image registration paths’ to be the minimum, and then the original tumor images are warped to the group center image using the resulting deformation fields. We have evaluated our method based on both simulated and real MR brain tumor images. The registration results were evaluated with overlap measures of corresponding brain regions and average entropy of image intensity information, and Wilcoxon signed rank tests were adopted to compare different methods with respect to their regional overlap measures. Compared with a groupwise image registration method that is applied to normal-appearance images estimated using the traditional low-rank plus sparse matrix decomposition based image inpainting, our method achieved higher image registration accuracy with statistical significance (p = 7.02 × 10−9).

RETRACTED ARTICLE: A novel feature selection method for brain tumor MR image classification based on the Fisher criterion and parameter-free Bat optimization

The present paper proposes a novel feature selection technique for the MR brain tumor image classification that aims to choose the optimal feature subset with maximum discriminatory ability in the minimum amount of time. It is based on the fusion of the Fisher and the parameter-free Bat (PFree Bat) optimization algorithm. As the conventional Bat algorithm is bad at exploration, a modification is proposed that guides the Bat by the pulse frequency, global best and the local best position. This improved version of Bat referred to as the PFree Bat algorithm eliminates the velocity equation and directly updates the Bat position. Subsequently, this method in conjunction with the Fisher criteria has been used to select the best set of features for brain tumor classification. The chosen features are then fed to the commonly used least square (LS) support vector machine (SVM) classifier to categorize the area of interest into the high or low grade. For the evaluation of the proposed attribute selection method, tenfold cross-validation has been conducted on a set of 95 ROIs taken from the BRATS 2012 dataset. On an extensive comparison with the other hybrid approaches, the proposed approach brought about the 100% recognition rate in the smallest amount of time. Furthermore, an integrated index is proposed that uniquely identifies the best performing algorithm, taking into account the accuracy, number of features and the computational time. For the fair comparison, the performance of the proposed method has also been examined on breast cancer dataset taken from UCI repository. The obtained results validate that the designed algorithm has better average accuracy than existing state-of-the-art works.

Automatic classification of MR brain tumor images using KNN, ANN, SVM and CNN

A brain tumor classification system has been designed and developed. This work presents a new approach to the automated classification of astrocytoma, medulloblastoma, glioma, glioblastoma multiforme and craniopharyngioma type of brain tumors based on first order statistics and gray level co-occurrence matrix, in magnetic resonance images. The magnetic resonance feature image used for the tumor detection consists of T2-weighted magnetic resonance images for each axial slice through the head. To remove the unwanted noises in the magnetic resonance image, median filtering is used. First order statistics and gray level co-occurrence matrix-based features are extracted. Finally, k-nearest neighbor, artificial neural network, support vector machine and convolutional neural networks are used to classify the brain tumor images. The application of the proposed method for tracking tumor is demon­strated to help pathologists distinguish its type of tumor. A classification with an accuracy of 89%, 90%, 91% and 95% has been obtained by, k-nearest neighbor, artificial neural network, support vector machine and convolutional neural networks.

Computer-Extracted Texture Features to Distinguish Cerebral Radionecrosis from Recurrent Brain Tumors on Multiparametric MRI: A Feasibility Study.

Despite availability of advanced imaging, distinguishing radiation necrosis from recurrent brain tumors noninvasively is a big challenge in neuro-oncology. Our aim was to determine the feasibility of radiomic (computer-extracted texture) features in differentiating radiation necrosis from recurrent brain tumors on routine MR imaging (gadolinium T1WI, T2WI, FLAIR). A retrospective study of brain tumor MR imaging performed 9 months (or later) post-radiochemotherapy was performed from 2 institutions. Fifty-eight patient studies were analyzed, consisting of a training (n = 43) cohort from one institution and an independent test (n = 15) cohort from another, with surgical histologic findings confirmed by an experienced neuropathologist at the respective institutions. Brain lesions on MR imaging were manually annotated by an expert neuroradiologist. A set of radiomic features was extracted for every lesion on each MR imaging sequence: gadolinium T1WI, T2WI, and FLAIR. Feature selection was used to identify the top 5 most discriminating features for every MR imaging sequence on the training cohort. These features were then evaluated on the test cohort by a support vector machine classifier. The classification performance was compared against diagnostic reads by 2 expert neuroradiologists who had access to the same MR imaging sequences (gadolinium T1WI, T2WI, and FLAIR) as the classifier. On the training cohort, the area under the receiver operating characteristic curve was highest for FLAIR with 0.79; 95% CI, 0.77-0.81 for primary (n = 22); and 0.79, 95% CI, 0.75-0.83 for metastatic subgroups (n = 21). Of the 15 studies in the holdout cohort, the support vector machine classifier identified 12 of 15 studies correctly, while neuroradiologist 1 diagnosed 7 of 15 and neuroradiologist 2 diagnosed 8 of 15 studies correctly, respectively. Our preliminary results suggest that radiomic features may provide complementary diagnostic information on routine MR imaging sequences that may improve the distinction of radiation necrosis from recurrence for both primary and metastatic brain tumors.

Localized active contour model with background intensity compensation applied on automatic MR brain tumor segmentation

This paper presents a Localized Active Contour Model (LACM) integrating an additional step of background intensity compensation. The region-based active contour models that use statistical intensity information are more sensitive to the high mean intensity distance between consecutive regions. In Magnetic Resonance Imaging (MRI) this distance is great between the foreground and the background, hence it leads to an incorrect delineation of the target. In order to resolve this problem, an automatic process is introduced in our model for balancing the mean intensity distance between an image foreground and its background. The aim is to minimize the attraction effect of the active contour model to the undesired borderlines defined by these two mentioned image regions. By using this approach not only the obtained accuracy outperforms the traditional localized mean separation active contour model, but also it reduces the computation time of the segmentation task. In addition, this method was efficiently applied on automatic brain tumor segmentation in multimodal MRI data. The Hierarchical Centroid Shape Descriptor (HCSD) was used for detecting the region of interest i.e. abnormal tissue so as to automatically initialize the active contour. The validation of experiments was carried out on synthetic images and the quantitative evaluation was performed on the BRATS2012 database. Finally, the accuracy achieved by the proposed method was compared to the localized mean separation intensity, the localized Chan-Vese, the local Gaussian distribution fitting and the local binary fitting models by using the Dice coefficient, Sensitivity, Specificity and the Hausdorff distance. The computation time of the methods was also measured for comparison purposes. The obtained results show that the proposed model outperforms the accuracy of the selected state of the art methods. Moreover, it is also faster than the comparative methods in the medical image segmentation task.

A.197 - Clinical support in radiation therapy scenarios: MR brain tumor segmentation using an unsupervised fuzzy C-Means clustering technique

A.197 - Clinical support in radiation therapy scenarios: MR brain tumor segmentation using an unsupervised fuzzy C-Means clustering technique

Gamma Knife treatment planning: MR brain tumor segmentation and volume measurement based on unsupervised Fuzzy C-Means clustering

Nowadays, radiation treatment is beginning to intensively use MRI thanks to its greater ability to discriminate healthy and diseased soft-tissues. Leksell Gamma Knife® is a radio-surgical device, used to treat different brain lesions, which are often inaccessible for conventional surgery, such as benign or malignant tumors. Currently, the target to be treated with radiation therapy is contoured with slice-by-slice manual segmentation on MR datasets. This approach makes the segmentation procedure time consuming and operator-dependent. The repeatability of the tumor boundary delineation may be ensured only by using automatic or semiautomatic methods, supporting clinicians in the treatment planning phase. This article proposes a semiautomatic segmentation method, based on the unsupervised Fuzzy C-Means clustering algorithm. Our approach helps segment the target and automatically calculates the lesion volume. To evaluate the performance of the proposed approach, segmentation tests on 15 MR datasets were performed, using both area-based and distance-based metrics, obtaining the following average values: Similarity Index = 95.59%, Jaccard Index = 91.86%, Sensitivity = 97.39%, Specificity = 94.30%, Mean Absolute Distance = 0.246[pixels], Maximum Distance = 1.050[pixels], and Hausdorff Distance = 1.365[pixels]. © 2015 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 25, 213–225, 2015

Characterization and Area Estimation of MR Brain Tumor Images

Brain Tumors are detected efficiently by using the Magnetic Resonance Imaging (MRI) techniques. The extracted MRI image is sensitive to noise which limits the visibility of certain characteristics of the image. This unwanted noise can be disintegrated and curtailed from the original Image by using the non linear digital median filter. The intensification is achieved by using the combination of discrete wavelet transform (DWT) and stationary wavelet transform (SWT) augmented with Bi-cubic interpolation algorithm. The quality of the resolute image is analyzed with the possible static parameters. Segmentation and clustering approaches are applied on the resultant sharpened high resolution image to estimate the tumor area. The results obtained with the proposed Optimized Hybrid Clustering (OHC) algorithm are compared with the existing K-Means, Pillar K-Means and Fuzzy C-means (FCM) approaches. The tumor sensitivity and accuracy of the test parameters with the OHC approach are estimated. In-order to deliver the drug to kill the aberrant tissue, the number of tumor cells is estimated against its radius.

Magnetic resonance spectroscopic evaluation of intracranial tumors in adults

Abstract Background and Aims: There is a lot of scope for Magnetic Resonance spectroscopy as a tool in diagnosing brain tumors in conjunction with conventional Magnetic Resonance sequences. It is considered to be a non invasive way to get the neurochemistry which will predict the histopathological diagnosis thereby preventing unnecessary surgery and associated morbidity. Here, a Magnetic Resonance spectroscopic imaging study of intra cranial tumors in adults was undertaken to assess the diagnostic usefulness of magnetic resonance spectroscopy in brain tumors. Materials &amp; Methods: In the present study, 40 cases of brain tumors were included, among which 25 were male and rest were female with mean age 45 years. Results: The pathological 'H-MRS (proton magnetic resonance spectroscopy) spectra for various types of brain tumor were studied and tabulated. Conclusion: Magnetic Resonance Spectroscopy is a noninvasive, cost effective and easily repeatable when compared to the conventional brain biopsy procedure. Therefore brain tumor MR imaging should always complemented with dedicated spectroscopy sequences to deal with diagnostic dilemmas and improve patient treatment.

Paramagnetic, pH and temperature-sensitive polymeric particles for anticancer drug delivery and brain tumor magnetic resonance imaging

Dually responsive polymeric particles for brain tumor (glioma) MR imaging and anticancer drug delivery.