BRAIN TUMOR SEGMENTATION BASED ON SUPERPIXELS AND HYBRID CLUSTERING WITH FAST GUIDED FILTER

2020 ◽  
Vol 20 (06) ◽  
pp. 2050032
Author(s):  
CHONG ZHANG ◽  
XUANJING SHEN ◽  
HAIPENG CHEN
Keyword(s):  
Brain Tumor ◽  
Clustering Algorithm ◽  
Guided Filter ◽  
Gaussian Kernel ◽  
Tumor Segmentation ◽  
Brain Tumor Segmentation ◽  
Hybrid Clustering ◽  
Simple Linear Iterative Clustering ◽  
The Stability ◽  
Sensitivity Specificity

Brain tumor segmentation from magnetic resonance (MR) image is vital for both the diagnosis and treatment of brain cancers. To alleviate noise sensitivity and improve stability of segmentation, an effective hybrid clustering algorithm combined with fast guided filter is proposed for brain tumor segmentation in this paper. Preprocessing is performed using adaptive Wiener filtering combined with a fast guided filter. Then simple linear iterative clustering (SLIC) is utilized for pre-segmentation to effectively remove scatter. During the clustering, K-means[Formula: see text] and Gaussian kernel-based fuzzy C-means (K[Formula: see text]GKFCM) clustering algorithm are combined to segment, and the fast-guided filter is introduced into the clustering. The proposed algorithm not only improves the robustness of the algorithm to noise, but also improves the stability of the segmentation. In addition, the proposed algorithm is compared with other current segmentation algorithms. The results show that the proposed algorithm performs better in terms of accuracy, sensitivity, specificity and recall.

scholarly journals Brain Tumor Segmentation Based on Hybrid Clustering and Morphological Operations

2019 ◽  
Vol 2019 ◽  
pp. 1-11 ◽  
Author(s):  
Chong Zhang ◽  
Xuanjing Shen ◽  
Hang Cheng ◽  
Qingji Qian
Keyword(s):  
Brain Tumors ◽  
Clustering Algorithm ◽  
Complex Structure ◽  
Brain Magnetic Resonance Imaging ◽  
Gaussian Kernel ◽  
Tumor Segmentation ◽  
Morphological Operations ◽  
Brain Tumor Segmentation ◽  
Hybrid Clustering ◽  
Sensitivity Specificity

Inference of tumor and edema areas from brain magnetic resonance imaging (MRI) data remains challenging owing to the complex structure of brain tumors, blurred boundaries, and external factors such as noise. To alleviate noise sensitivity and improve the stability of segmentation, an effective hybrid clustering algorithm combined with morphological operations is proposed for segmenting brain tumors in this paper. The main contributions of the paper are as follows: firstly, adaptive Wiener filtering is utilized for denoising, and morphological operations are used for removing nonbrain tissue, effectively reducing the method’s sensitivity to noise. Secondly, K-means++ clustering is combined with the Gaussian kernel-based fuzzy C-means algorithm to segment images. This clustering not only improves the algorithm’s stability, but also reduces the sensitivity of clustering parameters. Finally, the extracted tumor images are postprocessed using morphological operations and median filtering to obtain accurate representations of brain tumors. In addition, the proposed algorithm was compared with other current segmentation algorithms. The results show that the proposed algorithm performs better in terms of accuracy, sensitivity, specificity, and recall.

scholarly journals Brain Tumor Segmentation using K-Means Clustering and Detection using Convolutional Neural Network

2020 ◽  
Vol 9 (5) ◽  
pp. 1452-1455
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Brain Tumor ◽  
Convolutional Neural Network ◽  
Clustering Algorithm ◽  
Tumor Segmentation ◽  
Brain Tumor Segmentation ◽  
Mri Scans ◽  
Two Phases ◽  
Processing Techniques

This paper presents brain tumor detection and segmentation using image processing techniques. Convolutional neural networks can be applied for medical research in brain tumor analysis. The tumor in the MRI scans is segmented using the K-means clustering algorithm which is applied of every scan and the feed it to the convolutional neural network for training and testing. In our CNN we propose to use ReLU and Sigmoid activation functions to determine our end result. The training is done only using the CPU power and no GPU is used. The research is done in two phases, image processing and applying neural network.

Sign in / Sign up

Export Citation Format

Share Document