scholarly journals An Optimized Approach for Prostate Image Segmentation Using K-Means Clustering Algorithm with Elbow Method

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Rachid Sammouda ◽  
Ali El-Zaart
Keyword(s):  
Prostate Cancer ◽  
Image Segmentation ◽  
Clustering Algorithm ◽  
Near Infrared ◽  
Optimum Number ◽  
Cancer Disease ◽  
Number Of Clusters ◽  
Segmented Images ◽  
Segmentation Approach ◽  
Noninvasive Therapy

Prostate cancer disease is one of the common types that cause men’s prostate damage all over the world. Prostate-specific membrane antigen (PSMA) expressed by type-II is an extremely attractive style for imaging-based diagnosis of prostate cancer. Clinically, photodynamic therapy (PDT) is used as noninvasive therapy in treatment of several cancers and some other diseases. This paper aims to segment or cluster and analyze pixels of histological and near-infrared (NIR) prostate cancer images acquired by PSMA-targeting PDT low weight molecular agents. Such agents can provide image guidance to resection of the prostate tumors and permit for the subsequent PDT in order to remove remaining or noneradicable cancer cells. The color prostate image segmentation is accomplished using an optimized image segmentation approach. The optimized approach combines the k-means clustering algorithm with elbow method that can give better clustering of pixels through automatically determining the best number of clusters. Clusters’ statistics and ratio results of pixels in the segmented images show the applicability of the proposed approach for giving the optimum number of clusters for prostate cancer analysis and diagnosis.

scholarly journals Segmentation of image based on k-means and modified subtractive clustering

2021 ◽  
Vol 22 (3) ◽  
pp. 1396
Author(s):  
Simon Tongbram ◽  
Benjamin A. Shimray ◽  
Loitongbam Surajkumar Singh
Keyword(s):  
Image Segmentation ◽  
Clustering Algorithm ◽  
Medical Science ◽  
Cluster Center ◽  
Subtractive Clustering ◽  
Cluster Centroid ◽  
Segmentation Methods ◽  
Segmentation Approach ◽  
Data Points

Image segmentation has widespread applications in medical science, for example, classification of different tissues, identification of tumors, estimation of tumor size, surgery planning, and atlas matching. Clustering is a widely implemented unsupervised technique used for image segmentation mainly because of its simplicity and fast computation. However, the quality and efficiency of clustering-based segmentation is highly depended on the initial value of the cluster centroid. In this paper, a new hybrid segmentation approach based on k-means clustering and modified subtractive clustering is proposed. K-means clustering is a very efficient and powerful algorithm but it requires initialization of cluster centroid. And, the consistency of the clustering outcomes of k-means algorithm depends on the initial selection of the cluster center. To overcome this drawback, a modified subtractive clustering algorithm based on distance relations between cluster centers and data points is proposed which finds a more accurate cluster centers compared to the conventional subtractive clustering. These cluster centroids obtained from the modified subtractive clustering are used in k-means algorithm for segmentation of the image. The proposed method is compared with other existing conventional segmentation methods by using several synthetic and real images and experimental finding validates the superiority of the proposed method.

scholarly journals Spatial Modification in the Parameters of Mountain Image Clustering Algorithm

2019 ◽  
Vol 22 (1) ◽  
pp. 55-58
Author(s):  
Nahla Ibraheem Jabbar
Keyword(s):  
Clustering Algorithm ◽  
Spatial Information ◽  
Clustering Algorithms ◽  
Large Data ◽  
Large Data Sets ◽  
Image Clustering ◽  
Optimum Number ◽  
Data Sets ◽  
Number Of Clusters ◽  
Pixel Value

Our proposed method used to overcome the drawbacks of computing values parameters in the mountain algorithm to image clustering. All existing clustering algorithms are required values of parameters to starting the clustering process such as these algorithms have a big problem in computing parameters. One of the famous clustering is a mountain algorithm that gives expected number of clusters, we presented in this paper a new modification of mountain clustering called Spatial Modification in the Parameters of Mountain Image Clustering Algorithm. This modification in the spatial information of image by taking a window mask for each center pixel value to compute distance between pixel and neighborhood for estimation the values of parameters σ, β that gives a potential optimum number of clusters requiring in image segmentation process. Our experiments show ability the proposed algorithm in image brain segmentation with a quality in the large data sets

scholarly journals Application of grid-based k-means clustering algorithm for optimal image processing

2012 ◽  
Vol 9 (4) ◽  
pp. 1679-1696 ◽  
Author(s):  
Tingna Shi ◽  
Penglong Wang ◽  
Jeenshing Wang ◽  
Shihong Yue
Keyword(s):  
Image Processing ◽  
Image Segmentation ◽  
Clustering Algorithm ◽  
Optimal Number ◽  
Number Of Clusters ◽  
General Index ◽  
Benchmark Datasets ◽  
Basic Characteristics ◽  
Grid Based

The effectiveness of K-means clustering algorithm for image segmentation has been proven in many studies, but is limited in the following problems: 1) the determination of a proper number of clusters. If the number of clusters is determined incorrectly, a good-quality segmented image cannot be guaranteed; 2) the poor typicality of clustering prototypes; and 3) the determination of an optimal number of pixels. The number of pixels plays an important role in any image processing, but so far there is no general and efficient method to determine the optimal number of pixels. In this paper, a grid-based K-means algorithm is proposed for image segmentation. The advantages of the proposed algorithm over the existing K-means algorithm have been validated by some benchmark datasets. In addition, we further analyze the basic characteristics of the algorithm and propose a general index based on maximizing grey differences between investigated objective grays and background grays. Without any additional condition, the proposed index is robust in identifying an optimal number of pixels. Our experiments have validated the effectiveness of the proposed index by the image results that are consistent with the visual perception of the datasets.

scholarly journals K-Hyperline Clustering-Based Color Image Segmentation Robust to Illumination Changes

Symmetry ◽  
2018 ◽  
Vol 10 (11) ◽  
pp. 610 ◽  
Author(s):  
Senquan Yang ◽  
Pu Li ◽  
HaoXiang Wen ◽  
Yuan Xie ◽  
Zhaoshui He
Keyword(s):  
Image Processing ◽  
Image Segmentation ◽  
Clustering Algorithm ◽  
Color Image ◽  
Clustering Algorithms ◽  
Color Image Segmentation ◽  
Color Classification ◽  
Clustering Problem ◽  
Illumination Changes ◽  
Segmentation Approach

Color image segmentation is very important in the field of image processing as it is commonly used for image semantic recognition, image searching, video surveillance or other applications. Although clustering algorithms have been successfully applied for image segmentation, conventional clustering algorithms such as K-means clustering algorithms are not sufficiently robust to illumination changes, which is common in real-world environments. Motivated by the observation that the RGB value distributions of the same color under different illuminations are located in an identical hyperline, we formulate color classification as a hyperline clustering problem. We then propose a K-hyperline clustering algorithm-based color image segmentation approach. Experiments on both synthetic and real images demonstrate the outstanding performance and robustness of the proposed algorithm as compared to existing clustering algorithms.

Color Image Segmentation of Live Grouper Fish with Complex Background in Seawater

2015 ◽  
Vol 743 ◽  
pp. 293-302 ◽  
Author(s):  
G.Q. Ma ◽  
Y.C. Tian ◽  
X.L. Li ◽  
K.Z. Xing ◽  
Su Xu
Keyword(s):  
Image Segmentation ◽  
Clustering Algorithm ◽  
Color Image ◽  
Color Images ◽  
Color Image Segmentation ◽  
Segmentation Method ◽  
Complex Background ◽  
Segmented Images ◽  
Rgb Images ◽  
True Color

The color live fish image segmentation is a important procedure of the understanding fish behavior. We have introduced an simple segmentation method of live Grouper Fish color images with seawater background and presented a segmentation framework to extract the whole fish image from the complex background of seawater. Firstly, we took true color pictures of live Grouper fish in seawater using waterproof camera and save these pictures files as RGB format files, called True-color Images. Secondly, we extracted R,G and B planes of a true color Grouper fish image, painted and compared their histograms of R,G and B planes. Thirdly, we segmented these RGB images and the R,G and B planes of a true color Grouper fish image with the k-means clustering algorithm, using the kmeans () function which is packaged by the Clustering Analysis ToolBox of Matlab 2012(a). Finally, we analyzed the relationships between these histograms and segmented images, and then got a conclusion is that : using the B plane of these RGB images as Input-matrix to do clustering segmentation algorithm by the kmeans () function of Matlab Clustering ToolBox, can got a fulfilling segmentation results.

scholarly journals IMPLEMENTASI ALGORITMA MODIFIED GUSTAFSON-KESSEL UNTUK CLUSTERING TWEETS PADA AKUN TWITTER LAZADA INDONESIA

2019 ◽  
Vol 8 (3) ◽  
pp. 285-295
Author(s):  
Ratna Kencana Putri ◽  
Budi Warsito ◽  
Mustafid Mustafid
Keyword(s):  
Social Media ◽  
Partition Coefficient ◽  
Clustering Algorithm ◽  
Optimum Number ◽  
Number Of Clusters ◽  
Online Social Media ◽  
Internet Users ◽  
Algorithm Validation ◽  
Twitter Account ◽  
Product Segmentation

Online social media is a new kind of media which is steadily growing and has become publicly popular. Due to its ability to spread informations rapidly and its easiness to access for internet users, social media provides new alternative to conduct advertising and product segmentation. Twitter is one of the most favored social media with 19.5 million users in Indonesia to the date. In this research, the application of text mining to cluster tweets from the @LazadaID Twitter account is done using the Modified Gustafson-Kessel clustering algorithm. The clustering process is executed five times with the number of cluster starts from two to six cluster. The results of this research indicate that the optimum number of clusters formed based on the Partition Coefficient and Classification Entropy validation index are three clusters. Those three clusters are tweets containing electronic stuff offers, discounts, and prize quizes. Tweets with the most retweets and likes are prize quiz tweets. PT Lazada Indonesia could use this kind of tweet to conduct advertising on social media Twitter because the prize quiz tweets are liked by the @LazadaID Twitter account followers.Keywords: Twitter, advertising, Lazada Indonesia, Gustafson-Kessel Clustering algorithm, validation index

An approach to the development of a core set of germplasm using a mixture of qualitative and quantitative data

2014 ◽  
Vol 13 (2) ◽  
pp. 96-103 ◽  
Author(s):  
Rupam Kumar Sarkar ◽  
Prabina Kumar Meher ◽  
S. D. Wahi ◽  
T. Mohapatra ◽  
A. R. Rao
Keyword(s):  
Quantitative Data ◽  
Qualitative Data ◽  
Clustering Algorithm ◽  
Crop Improvement ◽  
Distance Measures ◽  
Absolute Difference ◽  
Optimum Number ◽  
Number Of Clusters ◽  
Core Set ◽  
Average Cluster

Development of a representative and well-diversified core with minimum duplicate accessions and maximum diversity from a larger population of germplasm is highly essential for breeders involved in crop improvement programmes. Most of the existing methodologies for the identification of a core set are either based on qualitative or quantitative data. In this study, an approach to the identification of a core set of germplasm based on the response from a mixture of qualitative (single nucleotide polymorphism genotyping) and quantitative data was proposed. For this purpose, six different combined distance measures, three for quantitative data and two for qualitative data, were proposed and evaluated. The combined distance matrices were used as inputs to seven different clustering procedures for classifying the population of germplasm into homogeneous groups. Subsequently, an optimum number of clusters based on all clustering methodologies using different combined distance measures were identified on a consensus basis. Average cluster robustness values across all the identified optimum number of clusters under each clustering methodology were calculated. Overall, three different allocation methods were applied to sample the accessions that were selected from the clusters identified under each clustering methodology, with the highest average cluster robustness value being used to formulate a core set. Furthermore, an index was proposed for the evaluation of diversity in the core set. The results reveal that the combined distance measure A1B2 – the distance based on the average of the range-standardized absolute difference for quantitative data with the rescaled distance based on the average absolute difference for qualitative data – from which three clusters that were identified by using the k-means clustering algorithm along with the proportional allocation method was suitable for the identification of a core set from a collection of rice germplasm.

Sign in / Sign up

Export Citation Format

Share Document