scholarly journals Powerful and Novel Tumour Detection in Brain MRI Images Employing Hybrid Computational Techniques

2021 ◽  
Author(s):  
K Lakshmi Narayanan ◽  
R Niranjana ◽  
E Francy Irudaya Rani ◽  
N Subbulakshmi ◽  
R Santhana Krishnan
Keyword(s):  
Image Segmentation ◽  
Graphical User Interface ◽  
Brain Mri ◽  
Computational Techniques ◽  
Discrete Wavelet ◽  
Tumour Detection ◽  
Fundamental Reason ◽  
Global Optimal ◽  
Information Image ◽  
Mri Image

Brain tumour detection is an evergreen topic to attract attention in the examination field of Information Technology innovation with biomedical designing, in view of the gigantic need of proficient and viable strategy for assessment of enormous measure of information. Image segmentation is considered as one of the most vital systems for visualizing tissues in an individual. To robotize image segmentation, we have proposed a calculation to get global optimal thresholding esteem for a specific brain MRI image, utilizing OTSU+Sauvola binarization strategy. The fundamental reason for feature collection is to diminish the quantity of structures utilized in classification while keeping up satisfactory classification exactness. One of the most extra-customary procedures applied for feature extraction is Discrete Wavelet Transform (DWT). Adequately it anticipates the estimation space on a plane to such an extent that the fluctuation of the information is ideally protected. We propose a justifiable model for brain tumours discovery and classification i.e., to classify whether the tumour is benign or malignant, utilizing SVM classification. SVM utilized here deals with basic hazard minimization to group the images for the tumour extraction, and a Graphical User Interface is created for the tumour classification operation, using the MATLAB platform.

Image Segmentation Algorithm Combined with Regularized P-M De-Noising Model and Improved Watershed Algorithm

2020 ◽  
Vol 10 (2) ◽  
pp. 515-521 ◽  
Author(s):  
Guorui Chen
Keyword(s):  
Image Segmentation ◽  
Brain Mri ◽  
Small Region ◽  
Watershed Algorithm ◽  
Segmentation Method ◽  
Segmentation Algorithms ◽  
Segmentation Image ◽  
The Brain ◽  
Image Segmentation Algorithm ◽  
Mri Image

Aiming at the problems of noise sensitivity and unclear contour in existing MRI image segmentation algorithms, a segmentation method combining regularized P-M de-noising model and improved watershed algorithm is proposed. First, the brain MRI image is pre-processed to obtain a brain nuclear image. Then, the brain nuclear image is de-noised by a regularized P-M model. After that, the image is preliminarily segmented by the traditional watershed algorithm to extract the features of each small region. Finally, the small regions are merged by Fuzzy Clustering with Spatial Pattern (FCSP) to obtain the segmentation image with smooth edges. The experimental results show that the algorithm can accurately segment the gray matter (GM), white matter (WM) and cerebrospinal fluid (CSF) regions. The average AOM and ME of the segmentation results on the BrainWeb dataset reached 0.93 and 0.04, respectively.

scholarly journals A Novel Brain MRI Image Segmentation Method Using an Improved Multi-View Fuzzy c-Means Clustering Algorithm

2021 ◽  
Vol 15 ◽  
Author(s):  
Lei Hua ◽  
Yi Gu ◽  
Xiaoqing Gu ◽  
Jing Xue ◽  
Tongguang Ni
Keyword(s):  
Image Segmentation ◽  
Brain Tissue ◽  
Adaptive Learning ◽  
Clustering Algorithm ◽  
Brain Mri ◽  
Segmentation Method ◽  
Learning Mechanism ◽  
Fcm Algorithm ◽  
The Brain ◽  
Mri Image

Background: The brain magnetic resonance imaging (MRI) image segmentation method mainly refers to the division of brain tissue, which can be divided into tissue parts such as white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF). The segmentation results can provide a basis for medical image registration, 3D reconstruction, and visualization. Generally, MRI images have defects such as partial volume effects, uneven grayscale, and noise. Therefore, in practical applications, the segmentation of brain MRI images has difficulty obtaining high accuracy.Materials and Methods: The fuzzy clustering algorithm establishes the expression of the uncertainty of the sample category and can describe the ambiguity brought by the partial volume effect to the brain MRI image, so it is very suitable for brain MRI image segmentation (B-MRI-IS). The classic fuzzy c-means (FCM) algorithm is extremely sensitive to noise and offset fields. If the algorithm is used directly to segment the brain MRI image, the ideal segmentation result cannot be obtained. Accordingly, considering the defects of MRI medical images, this study uses an improved multiview FCM clustering algorithm (IMV-FCM) to improve the algorithm’s segmentation accuracy of brain images. IMV-FCM uses a view weight adaptive learning mechanism so that each view obtains the optimal weight according to its cluster contribution. The final division result is obtained through the view ensemble method. Under the view weight adaptive learning mechanism, the coordination between various views is more flexible, and each view can be adaptively learned to achieve better clustering effects.Results: The segmentation results of a large number of brain MRI images show that IMV-FCM has better segmentation performance and can accurately segment brain tissue. Compared with several related clustering algorithms, the IMV-FCM algorithm has better adaptability and better clustering performance.

Sign in / Sign up

Export Citation Format

Share Document