An Efficient Hybrid Clustering and Feature Extraction Techniques for Brain Tumor Classification

Most aggressive and common disease is Brain tumors and it leads to very short life expectancy in its highest grade. For proper treatment, such tumors needs to be identified in early stages and detecting brain tumors, medical imaging is used as an important tool. Although, for diagnosing such tumors, MRI (Magnetic Resonance Imaging) is used very often and it is assumed as a highly suitable technique. From brain magnetic resonance imaging (MRI) data, edema and tumor inference is a challenging task due to brain tumors blurred boundaries, complex structure and external factors like noise. For alleviating noise sensitivity and enhancing segmentation stability, a hybrid clustering algorithm is proposed in this research work. Certain processes like classification, feature extraction, hybrid clustering and pre-processing are included in this proposed model. For segmentation of brain tumors, proposed a morphological operation. Skull stripping and contrast enhancement are two process performed in pre-processing stage. It is possible to detect high contrast regions under contrast enhancement. In second stage, Enhanced K- means algorithm is combined with Fuzzy C- Means Clustering (FCM), where images are segmented as clusters. Algorithm’s stability can be enhanced using this clustering techniques while minimizing clustering parameter’s sensitivity. Segmented objects are converted into representations using representation and feature extraction techniques. Major attributes and features are described in a better manner using these techniques. The Fast Discrete Curvelet Transform (FDCT) is used for performing feature extraction in this technique for minimizing complexity and enhancing performance. At last, for classification, deep belief network (DBN) is used in this work. And it uses the concept of optimized DBN, for which Improved dragonfly optimisation algorithm (IDOA) is utilized. This proposed model is termed as IDOA-DBN model. When compared with other classification techniques, brain tumors can be detected effectively using proposed model.

A robust hybrid fusion segmentation approach for automated tumor diagnosis and classification in brain MR images

In today’s world, Brain Tumor diagnosis plays a significant role in the field of Oncology. The earlier identification of brain tumors increases the compatibility of treatment of patients and offers an efficient diagnostic recommendation from medical practitioners. Nevertheless, accurate segmentation and feature extraction are the vital challenges in brain tumor diagnosis where the handling of higher resolution images increases the processing time of existing classifiers. In this paper, a new robust weighted hybrid fusion classifier has been proposed to identify and classify the tumefaction in the brain which is of the hybridized form of SVM, NB, and KNN (SNK) classifiers. Primarily, the proposed methodology initiates the preprocessing technique such as adaptive fuzzy filtration and skull stripping in order to remove the noises as well as unwanted regions. Subsequently, an automated hybrid segmentation strategy can be carried out to acquire the initial segmentation results, and then their outcomes are compiled together using fusion rules to accurately localize the tumor region. Finally, a Hybrid SNK classifier is implemented in the proposed methodology for categorizing the type of tumefaction in the brain. The hybrid classifier has been compared with the existing state-of-the-art classifier which shows a higher accuracy result of 99.18% while distinguishing the benign and malignant tumors from brain Magnetic Resonance (MR) images.

Preprocessing and Skull Stripping of Brain Tumor Extraction from Magnetic Resonance Imaging Images Using Image Processing

Many neuroimaging processing functions believe the preprocessing and skull strip (SS) to be an important step in brain tumor diagnosis. For complex physical reasons intensity changes in brain structure and magnetic resonance imaging of the brain, a proper preprocessing and SS is an important part. The method of removing the skull is relayed to the taking away of the skull area in the brain for medical investigation. It is more correct and necessary techniques for distinguishing between brain regions and cranial regions and this is believed a demanding task. This paper gives detailed review on the preprocessing and traditional transition to machine learning and deep learning-based automatic SS techniques of magnetic resonance imaging.

Automated Detection of Brain Tumor through Magnetic Resonance Images Using Convolutional Neural Network

Brain tumor is a fatal disease, caused by the growth of abnormal cells in the brain tissues. Therefore, early and accurate detection of this disease can save patient’s life. This paper proposes a novel framework for the detection of brain tumor using magnetic resonance (MR) images. The framework is based on the fully convolutional neural network (FCNN) and transfer learning techniques. The proposed framework has five stages which are preprocessing, skull stripping, CNN-based tumor segmentation, postprocessing, and transfer learning-based brain tumor binary classification. In preprocessing, the MR images are filtered to eliminate the noise and are improve the contrast. For segmentation of brain tumor images, the proposed CNN architecture is used, and for postprocessing, the global threshold technique is utilized to eliminate small nontumor regions that enhanced segmentation results. In classification, GoogleNet model is employed on three publicly available datasets. The experimental results depict that the proposed method is achieved average accuracies of 96.50%, 97.50%, and 98% for segmentation and 96.49%, 97.31%, and 98.79% for classification of brain tumor on BRATS2018, BRATS2019, and BRATS2020 datasets, respectively. The outcomes demonstrate that the proposed framework is effective and efficient that attained high performance on BRATS2020 dataset than the other two datasets. According to the experimentation results, the proposed framework outperforms other recent studies in the literature. In addition, this research will uphold doctors and clinicians for automatic diagnosis of brain tumor disease.

MeTiS: a modular pipeline for extracting 3D-printable brain-surface models from conventional and ultra-high field MRI

Aim: To develop a modular software pipeline for robustly extracting 3D brain-surface models from MRIs for visualization or printing. No other end-to-end pipeline specialized for neuroimaging does this directly with an interchangeable combination of methods. Materials & methods: A software application was developed to dynamically generate Nipype workflows using interfaces from the Analysis of Functional NeuroImages, Advanced Normalization Tools, FreeSurfer, BrainSuite, Nighres and the FMRIB Software Library suites. The application was deployed for public use via the LONI pipeline environment. Results: In a small, head-to-head comparison test, a pipeline using FreeSurfer for both the skull stripping and cortical-mesh extraction stages earned the highest subjective quality scores. Conclusion: We have deployed a publicly available and modular software tool for extracting 3D models from brain MRIs to use in medical education.

Automated skull stripping in mouse fMRI analysis using 3D U-Net

Skull stripping is an initial and critical step in the pipeline of mouse fMRI analysis. Manual labeling of the brain usually suffers from intra- and inter-rater variability and is highly time-consuming. Hence, an automatic and efficient skull-stripping method is in high demand for mouse fMRI studies. In this study, we investigated a 3D U-Net based method for automatic brain extraction in mouse fMRI studies. Two U-Net models were separately trained on T2-weighted anatomical images and T2*-weighted functional images. The trained models were tested on both interior and exterior datasets. The 3D U-Net models yielded a higher accuracy in brain extraction from both T2-weighted images (Dice > 0.984, Jaccard index > 0.968 and Hausdorff distance < 7.7) and T2*-weighted images (Dice > 0.964, Jaccard index > 0.931 and Hausdorff distance < 3.3), compared with the two widely used mouse skull-stripping methods (RATS and SHERM). The resting-state fMRI results using automatic segmentation with the 3D U-Net models are identical to those obtained by manual segmentation for both the seed-based and group independent component analysis. These results demonstrate that the 3D U-Net based method can replace manual brain extraction in mouse fMRI analysis.

Brain Tumor Detection Using Gray Level Co-Occurrence Matrix Feature Extraction Technique

From each and every passing year, the world has always witnessed a rise in the number of cases of brain tumor. Brain tumor classification and detection is that the most critical and strenuous task within the field of medical image processing while human aided manual detection leads to imperfect divination and diagnosing. Brain tumors have high heterogeneity in appearance and there is a same feature between tumor and non-tumor tissues and thus the extraction of tumor regions from MRI scan images becomes unyielding. A Gray Level Co-occurrence Matrix(GLCM) is applied on MRI scan images to detect tumor and non-tumor regions in brain. The main aim of medical imaging is to extract meaningful information accurately from the images. The method of detecting brain tumor from an MRI scan images are often classified into four categories: Pre-Processing, Skull Stripping, Segmentation and have Feature Extraction.

MRI Brain Abnormality Detection Using Conventional Neural Network (CNN)

Brain tumours has huge heterogeneity and there is always a familiarity between normal and abnormal tissues and hence the extraction of tumour portions from normal images becomes persistent. In this paper, MRI brain tumor detection is performed from a brain images using Fuzzy C-means(FCM) algorithm and sebsequently Convolutional Neural Network(CNN) algorithm is employed. Here, firstly preprocessing step is performed by Skull Stripping algorithm followed by Segmentation process. Fuzzy C-means algorithm is used to segment the Cerebrospinal Fluid(CSF), Grey matter(GM) and White Matter(WM) from the database. The third part is to extract features to find whether the tumor is present or not, here eleven features are extracted like mean, entropy, S.D(Standard Deviation). The final part is the classification process done by Convolutional Neural Network(CNN) in which it is able to differentiate whether the input image is normal image or an abnormal image. Compared to other methods, here the values of the features extracted are higher for normal images than for abnormal Images and it is shown from the graphs drawn from the extracted features.

Explainable Brain Disease Classification and Relevance-Guided Deep Learning

Deep neural networks are increasingly used for neurological disease classification by MRI, but the networks' decisions are not easily interpretable by humans. Heat mapping by deep Taylor decomposition revealed that (potentially misleading) image features even outside of the brain tissue are crucial for the classifier's decision. We propose a regularization technique to train convolutional neural network (CNN) classifiers utilizing relevance-guided heat maps calculated online during training. The method was applied using T1-weighted MR images from 128 subjects with Alzheimer's disease (mean age=71.9+-8.5 years) and 290 control subjects (mean age=71.3+-6.4 years). The developed relevance-guided framework achieves higher classification accuracies than conventional CNNs but more importantly, it relies on less but more relevant and physiological plausible voxels within brain tissue. Additionally, preprocessing effects from skull stripping and registration are mitigated, rendering this practically useful in deep learning neuroimaging studies. Understanding the decision mechanisms underlying CNNs, these results challenge the notion that unprocessed T1-weighted brain MR images in standard CNNs yield higher classification accuracy in Alzheimer's disease than solely atrophy.

Brain Tumor Detection and Segmentation Using Watershed Segmentation and Morphological Operation

In the field of medical image processing, detection of brain tumor from magnetic resonance image (MRI) brain scan has become one of the most active research. Detection of the tumor is the main objective of the system. Detection plays a critical role in biomedical imaging. In this paper, MRI brain image is used to tumor detection process. This system includes test the brain image process, image filtering, skull stripping, segmentation, morphological operation, calculation of the tumor area and determination of the tumor location. In this system, morphological operation of erosion algorithm is applied to detect the tumor. The detailed procedures are implemented using MATLAB. The proposed method extracts the tumor region accurately from the MRI brain image. The experimental results indicate that the proposed method efficiently detected the tumor region from the brain image. And then, the equation of the tumor region in this system is effectively applied in any shape of the tumor region.