Image Analysis for MRI Based Brain Tumor Detection and Feature Extraction Using Biologically Inspired BWT and SVM.

The detection of a brain tumor and its classification from modern imaging modalities is a primary concern, but a time-consuming and tedious work was performed by radiologists or clinical supervisors. The accuracy of detection and classification of tumor stages performed by radiologists is depended on their experience only, so the computer-aided technology is very important to aid with the diagnosis accuracy. In this study, to improve the performance of tumor detection, we investigated comparative approach of different segmentation techniques and selected the best one by comparing their segmentation score. Further, to improve the classification accuracy, the genetic algorithm is employed for the automatic classification of tumor stage. The decision of classification stage is supported by extracting relevant features and area calculation. The experimental results of proposed technique are evaluated and validated for performance and quality analysis on magnetic resonance brain images, based on segmentation score, accuracy, sensitivity, specificity, and dice similarity index coefficient. The experimental results achieved 92.03% accuracy, 91.42% specificity, 92.36% sensitivity, and an average segmentation score between 0.82 and 0.93 demonstrating the effectiveness of the proposed technique for identifying normal and abnormal tissues from brain MR images. The experimental results also obtained an average of 93.79% dice similarity index coefficient, which indicates better overlap between the automated extracted tumor regions with manually extracted tumor region by radiologists.

In order to keep subscribers up‐to‐date with the latest developments in their field, John Wiley & Sons are providing a current awareness service in each issue of the journal. The bibliography contains newly published material in the field of NMR in biomedicine. Each bibliography is divided into 11 sections: 1 Books, Reviews ' Symposia; 2 General; 3 Technology; 4 Contrast Agents; 5 Brain and Nerves; 6 Neuropathology; 7 Cancer; 8 Cardiac, Vascular and Respiratory Systems; 9 Liver, Kidney and Other Organs; 10 Muscle and Orthopaedic; 11 Plants, Micro‐organisms and Parasites; 12 Others. Within each section, articles are listed in alphabetical order with respect to author. If, in the preceding period, no publications are located relevant to any one of these headings, that section will be omitted.

The segmentation, identification, and extraction of contaminated tumour regions from magnetic resonance (MR) images is a serious problem, but it is a time-consuming and labor-intensive operation carried out by radiologists or clinical experts, whose accuracy is totally reliant on their knowledge. As a consequence, using computer-assisted technologies to circumvent these limits becomes more vital. In this study, we looked into Berkeley wavelet transformation (BWT) based brain tumour segmentation to improve performance and reduce the complexity of the medical image segmentation process. Furthermore, relevant properties are extracted from each segmented tissue to improve the support vector machine (SVM) based classifier's accuracy and quality rate. The experimental results of the recommended technique have been examined and validated for performance and quality analysis on magnetic resonance brain pictures based on accuracy, sensitivity, specificity, and dice similarity index coefficient. With 96.51 percent accuracy, 94.2 percent specificity, and 97.72 percent sensitivity, the recommended technique for discriminating normal and diseased tissues from brain MR images was shown to be effective. The results of the testing revealed an average dice similarity index coefficient of 0.82, showing that the automated (machine) extracted tumour area coincided with the manually determined tumour region by radiologists. The simulation results show the relevance of quality parameters and accuracy when compared to state-of-the-art approaches. The main objective is to develop a smartphone app for identifying brain tumours.

In this study, we have presented image analysis for the brain tumour segmentation and detection based on Berkeley wavelet transformation, enabled by genetic algorithm and support vector machine. The proposed system uses double classification analysis to conclude tumour type. The proposed system also investigated auto-report generation technique using user-friendly graphical user interface in MATLAB. The experimental results of proposed technique is been evaluated and validated for performance and quality analysis on magnetic resonance (MR) medical images based on accuracy, sensitivity, specificity and dice similarity index coefficient. The experimental results achieved 97.77% accuracy, 98.98% sensitivity, 94.44% specificity and an average of 0.9849 dice similarity index coefficient, demonstrating the effectiveness of the proposed technique for identifying normal and abnormal tissues from MR images. The experimental result is validated by extracting 89 features and selecting the relevant features appropriately using genetic algorithm optimise by support vector machine.

Magnetic resonance imaging (MRI) is a non-invasive technology for examining, diagnosing, and treating tumor regions in the medical field. An early detection of a brain tumor can save a patient's life if appropriate therapy is given. The correct detection of tumors in MRI slices is a difficult problem, and this suggested approach can effectively classify and segment the tumor region. In the field of computer vision, machine learning has played a critical role. It has numerous uses in the realm of illness detection, particularly in the diagnosis of brain tumors. Relevant features are extracted from each segmented tissue to improve the accuracy and quality rate of the support vector machine (SVM)-based classifier in brain tumor identification. The experimental results of the recommended technique on magnetic resonance brain imaging have been examined and validated for performance and quality analysis. An SVM classifier was used to identify brain tumors.

Medical image processing is the most challenging and emerging field nowadays. Magnetic Resonance Images (MRI) act as the source for the development of classification system. The extraction, identification and segmentation of infected region from Magnetic Resonance (MR) brain image is significant concern but a dreary and time-consuming task performed by radiologists or clinical experts, and the final classification accuracy depends on their experience only. To overcome these limitations, it is necessary to use computer-aided techniques. To improve the efficiency of classification accuracy and reduce the recognition complexity involves in the medical image segmentation process, we have proposed Threshold Based Region Optimization (TBRO) based brain tumor segmentation. The experimental results of proposed technique have been evaluated and validated for classification performance on magnetic resonance brain images, based on accuracy, sensitivity, and specificity. The experimental results achieved 96.57% accuracy, 94.6% specificity, and 97.76% sensitivity, shows the improvement in classifying normal and abnormal tissues among given images. Detection, extraction and classification of tumor from MRI scan images of the brain is done by using MATLAB software.

The identification of multiple sclerosis disease (MSD) is very crucial because it is a neurological disease in young people where an early detection is recommended. Accurate classification and segmentation using distinct machine learning techniques plays significant role in identifying MSD based on brain magnetic resonance (MR) images. In this work, a performance comparative analysis of various supervised and unsupervised machine learning techniques on eighteen gray level textural feature matrix (GLTFM) of brain MR images has been performed. Supervised machine learning (k-nearest neighbor, support vector machine and ensemble learning) classification techniques are utilized for MSD identification and compared with unsupervised machine learning-based clustering techniques (k-mean clustering and Gaussian mixture model). Accuracy has been evaluated for measuring proposed system’s execution on unhealthy brain magnetic resonance (MR) images from the e-health dataset and healthy control brain magnetic resonance (MR) images from private clinical dataset. These metrics are also compared with various state-of-the-art techniques. It has been verified that MSD identification from healthy and unhealthy brain MR images based on the proposed methodology using supervised machine learning techniques yields accuracy of 96.55% which is better than existing state-of-the-art techniques and unsupervised machine learning techniques.

Automated tissue segmentation of brain magnetic resonance (MR) images has attracted extensive research attention. Many segmentation algorithms have been proposed for this issue. However, due to the existence of noise and intensity inhomogeneity in brain MR images, the accuracy of the segmentation results is usually unsatisfactory. In this paper, a high-accuracy brain MR image segmentation algorithm based on the information bottleneck (IB) method is presented. In this approach, the MR image is first mapped into a “local-feature space”, then the IB method segments the brain MR image through an information theoretic formulation in this local-feature space. It automatically segments the image into several clusters of voxels, by taking the intensity information and spatial information of voxels into account. Then, after the IB-based clustering, each cluster of voxels is classified into one type of brain tissue by threshold methods. The performance of the algorithm is studied based on both simulated and real T1-weighted 3D brain MR images. Our results show that, compared with other well-known brain image segmentation algorithms, the proposed algorithm can improve the accuracy of the segmentation results substantially.

This chapter discusses multi-fractal texture estimation and characterization of brain lesions (necrosis, edema, enhanced tumor, non-enhanced tumor, etc.) in magnetic resonance (MR) images. This work formulates the complex texture of tumor in MR images using a stochastic model known as multi-fractional Brownian motion (mBm). Mathematical derivations of the mBm model and corresponding algorithm to extract the spatially varying multi-fractal texture feature are discussed. Extracted multi-fractal texture feature is fused with other effective features to enhance the tissue characteristics. Segmentation of the tissues is performed by using a feature-based classification method. The efficacy of the mBm texture feature in segmenting different abnormal tissues is demonstrated using a large-scale publicly available clinical dataset. Experimental results and performance of the methods confirm the efficacy of the proposed technique in an automatic segmentation of abnormal tissues in multimodal (T1, T2, Flair, and T1contrast) brain MRIs.

A new methodology to detect pathologies in human brain magnetic resonance (MR) images is investigated. It is based on edge extraction in the Hilbert domain and subsequent analysis by means of fractal dimension and spectral energy distribution high order statistics. The technique is particularly suitable for pathologies characterized by bright structures in the MR images as do Glioma and Metastatic bronchogenic carcinoma. When classifying normal versus abnormal images dues to these two pathologies, ANOVA statistics show that the suggested features have strong between-classes differences, and the obtained classification accuracy by support vector machines is 99.9%±0.006. In comparison, applying a standard feature extraction technique based on the discrete wavelet transform (DWT) and principal component analysis (PCA) yielded 85.2%±0.05 accuracy.

This chapter discusses multifractal texture estimation and characterization of brain lesions (necrosis, edema, enhanced tumor, nonenhanced tumor, etc.) in magnetic resonance (MR) images. This work formulates the complex texture of tumor in MR images using a stochastic model known as multifractional Brownian motion (mBm). Mathematical derivations of the mBm model and corresponding algorithm to extract the spatially varying multifractal texture feature are discussed. Extracted multifractal texture feature is fused with other effective features to enhance the tissue characteristics. Segmentation of the tissues is performed using a feature-based classification method. The efficacy of the mBm texture feature in segmenting different abnormal tissues is demonstrated using a large-scale publicly available clinical dataset. Experimental results and performance of the methods confirm the efficacy of the proposed technique in an automatic segmentation of abnormal tissues in multimodal (T1, T2, Flair, and T1contrast) brain MRIs.

Chapter 4 - An optimal and robust segmentation framework for analysis and detection of brain tumor in MRI images

An automated computer-aided diagnosis system for classification of MR images using texture features and gbest-guided gravitational search algorithm

Multiple Sclerosis Identification Based on Ensemble Machine Learning Technique

Morbidity and mortality after pediatric cardiac arrest are chiefly due to hypoxic-ischemic brain injury. Brain features seen on magnetic resonance imaging (MRI) and magnetic resonance spectroscopy (MRS) after arrest may identify injury and aid in outcome assessments. To analyze the association of brain lesions seen on T2-weighted MRI and diffusion-weighted imaging and N-acetylaspartate (NAA) and lactate concentrations seen on MRS with 1-year outcomes after pediatric cardiac arrest. This multicenter cohort study took place in pediatric intensive care units at 14 US hospitals between May 16, 2017, and August 19, 2020. Children aged 48 hours to 17 years who were resuscitated from in-hospital or out-of-hospital cardiac arrest and who had a clinical brain MRI or MRS performed within 14 days postarrest were included in the study. Data were analyzed from January 2022 to February 2023. Brain MRI or MRS. The primary outcome was an unfavorable outcome (either death or survival with a Vineland Adaptive Behavior Scales, Third Edition, score of <70) at 1 year after cardiac arrest. MRI brain lesions were scored according to region and severity (0 = none, 1 = mild, 2 = moderate, 3 = severe) by 2 blinded pediatric neuroradiologists. MRI Injury Score was a sum of T2-weighted and diffusion-weighted imaging lesions in gray and white matter (maximum score, 34). MRS lactate and NAA concentrations in the basal ganglia, thalamus, and occipital-parietal white and gray matter were quantified. Logistic regression was performed to determine the association of MRI and MRS features with patient outcomes. A total of 98 children, including 66 children who underwent brain MRI (median [IQR] age, 1.0 [0.0-3.0] years; 28 girls [42.4%]; 46 White children [69.7%]) and 32 children who underwent brain MRS (median [IQR] age, 1.0 [0.0-9.5] years; 13 girls [40.6%]; 21 White children [65.6%]) were included in the study. In the MRI group, 23 children (34.8%) had an unfavorable outcome, and in the MRS group, 12 children (37.5%) had an unfavorable outcome. MRI Injury Scores were higher among children with an unfavorable outcome (median [IQR] score, 22 [7-32]) than children with a favorable outcome (median [IQR] score, 1 [0-8]). Increased lactate and decreased NAA in all 4 regions of interest were associated with an unfavorable outcome. In a multivariable logistic regression adjusted for clinical characteristics, increased MRI Injury Score (odds ratio, 1.12; 95% CI, 1.04-1.20) was associated with an unfavorable outcome. In this cohort study of children with cardiac arrest, brain features seen on MRI and MRS performed within 2 weeks after arrest were associated with 1-year outcomes, suggesting the utility of these imaging modalities to identify injury and assess outcomes.