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.

A Kind of Watershed Image Segmentation Method Based on Combination Pre-Processing

2010 ◽  
Vol 121-122 ◽  
pp. 320-324
Author(s):  
Jin Xi Wang ◽  
Lin Xiang Liu ◽  
Xiu Zheng Li
Keyword(s):  
Image Segmentation ◽  
Segmentation Algorithm ◽  
Watershed Algorithm ◽  
Segmentation Method ◽  
Simple Operation ◽  
Processing Steps ◽  
Segmentation Problem ◽  
Image Segmentation Algorithm

The watershed algorithm has been widely used in image segmentation for its characteristics of accurately positioning edge, simple operation and etc. But it also has drawbacks of easy to over-segmentation and loss important outline for the character of sensitive to noise. Aiming at the problem of over-segmentation of watershed algorithm, the paper brought out an improved image segmentation algorithm based on watershed, which can limit the number of existing regions that are allowed with combination pre-processing steps, so that the over-segmentation problem can be better solved. The result of experiment also verifies the correctness and feasibility of the proposed algorithm in the paper.

Label fusion method based on sparse patch representation for the brain MRI image segmentation

2017 ◽  
Vol 11 (7) ◽  
pp. 502-511 ◽  
Author(s):  
Hong Liu ◽  
Meng Yan ◽  
Enmin Song ◽  
Yuejing Qian ◽  
Xiangyang Xu ◽  
...  
Keyword(s):  
Image Segmentation ◽  
Brain Mri ◽  
Fusion Method ◽  
Label Fusion ◽  
The Brain ◽  
Mri Image

scholarly journals Feasibility of Automatic Seed Generation Applied to Cardiac MRI Image Analysis

Mathematics ◽  
2020 ◽  
Vol 8 (9) ◽  
pp. 1511 ◽  
Author(s):  
Radu Mărginean ◽  
Anca Andreica ◽  
Laura Dioşan ◽  
Zoltán Bálint
Keyword(s):  
Image Analysis ◽  
Image Segmentation ◽  
Regions Of Interest ◽  
Interactive Image Segmentation ◽  
Segmentation Algorithms ◽  
Mri Scans ◽  
Whole Heart ◽  
Image Segmentation Algorithm ◽  
Principal Contribution ◽  
Mri Image

We present a method of using interactive image segmentation algorithms to reduce specific image segmentation problems to the task of finding small sets of pixels identifying the regions of interest. To this end, we empirically show the feasibility of automatically generating seeds for GrowCut, a popular interactive image segmentation algorithm. The principal contribution of our paper is the proposal of a method for automating the seed generation method for the task of whole-heart segmentation of MRI scans, which achieves competitive unsupervised results (0.76 Dice on the MMWHS dataset). Moreover, we show that segmentation performance is robust to seeds with imperfect precision, suggesting that GrowCut-like algorithms can be applied to medical imaging tasks with little modeling effort.

scholarly journals Predicting malignant and benign brain tumor using image processing

2018 ◽  
Vol 7 (2.31) ◽  
pp. 199
Author(s):  
Rishabh Saxena ◽  
Aakriti Johri ◽  
Vikas Deep ◽  
Purushottam Sharma
Keyword(s):  
Image Processing ◽  
Image Segmentation ◽  
Brain Tumor ◽  
Human Brain ◽  
Brain Mri ◽  
Prediction System ◽  
Image Mining ◽  
Mining Algorithms ◽  
The Brain ◽  
Mri Image

Brain is the most important and versatile organ of the human body. One of the most deadly diseases that damage the brain is the accumulation of unwanted and deadly cells near the curvature of brain known as brain tumor. There are two types of brain tumor namely malignant and benign. Malignant is a cancerous tumor and benign is a non cancerous tumor. Primarily brain tumor grows in the brain tissue. The project uses MATLAB to develop a prediction system which uses original hospital brain MRI to predict the brain tumor. Project uses digital image processing to predict the brain tumor. The use of certain image mining algorithms helps in predicting the correct spot and area of brain tumor by image segmentation. The procedure starts with uploading MRI image of human brain, forward by the pre-processing of the image.  

scholarly journals Expression Level of IL-17 in Peripheral Blood of Patients with Late Pregnancy and Diagnosis of Maternal-Fetal Tolerance Based on Brain MRI Image Segmentation Algorithm

2021 ◽  
Vol 37 (6-WIT) ◽  
Author(s):  
Zenying Yu ◽  
Shengyan Zhou ◽  
Zhen Tan ◽  
Guangmin Lu
Keyword(s):  
Image Segmentation ◽  
Peripheral Blood ◽  
Brain Mri ◽  
Late Pregnancy ◽  
Treg Cells ◽  
Severe Preeclampsia ◽  
Segmentation Algorithm ◽  
Reversible Posterior Encephalopathy Syndrome ◽  
Image Segmentation Algorithm ◽  
Mri Image

Objectives: To study the expression of IL-17 in peripheral blood and its effect on maternal-fetal tolerance in patients with eclampsia in late pregnancy using MRI image segmentation algorithm. Methods: Thirty-nine patients with severe preeclampsia and eclampsia with brain symptoms were examined by cranial MRI. Pregnant women with 32 weeks of pregnancy were selected to detect the percentage of Th17 and Treg cells in CD4 + T lymphocytes and the expression of cytokines IL-17 and IL-10 in peripheral blood. Results: MRI examination was normal in 26 cases, 9 cases showed reversible posterior encephalopathy syndrome, three cases were cerebral hemorrhage, and one case was intracranial cavernous sinus thrombosis. two. Compared with the mild preeclampsia group, the relative number of Thl7 cells increased and that of Treg cells decreased in the severe preeclampsia group (P>0.05). Conclusion: The major types of cerebrovascular diseases (CVD) in severe preeclampsia and eclampsia were reversible posterior encephalopathy syndrome and cerebral hemorrhage. It was speculated that the damage to the blood-brain barrier may play an important role in the pathogenesis. The balance of the number of Th17 cells/the number of Treg cells was more inclined to the Th17 cell-mediated pro-inflammatory state, Treg cell-mediated immune tolerance decreases, and it becomes more obvious with the worsening of the disease. doi: https://doi.org/10.12669/pjms.37.6-WIT.4828 How to cite this:Yu Z, Zhou S, Tan Z, Lu G. Expression Level of IL-17 in Peripheral Blood of Patients with Late Pregnancy and Diagnosis of Maternal-Fetal Tolerance Based on Brain MRI Image Segmentation Algorithm. Pak J Med Sci. 2021;37(6):1553-1557.  doi: https://doi.org/10.12669/pjms.37.6-WIT.4828 This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Comparison of Thresholding and Edge Detection Segmentation Techniques

2013 ◽  
Vol 860-863 ◽  
pp. 2783-2786
Author(s):  
Yu Bing Dong ◽  
Hai Yan Wang ◽  
Ming Jing Li
Keyword(s):  
Image Segmentation ◽  
Root Mean Square Error ◽  
Edge Detection ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Experimental Results ◽  
Mean Square ◽  
Segmentation Method ◽  
Segmentation Algorithms

Edge detection and thresholding segmentation algorithms are presented and tested with variety of grayscale images in different fields. In order to analyze and evaluate the quality of image segmentation, Root Mean Square Error is used. The smaller error value is, the better image segmentation effect is. The experimental results show that a segmentation method is not suitable for all images segmentation.

Sign in / Sign up

Export Citation Format

Share Document