scholarly journals Automatic clustering method to segment COVID-19 CT images

PLoS ONE ◽  
2021 ◽  
Vol 16 (1) ◽  
pp. e0244416
Author(s):  
Mohamed Abd Elaziz ◽  
Mohammed A. A. Al-qaness ◽  
Esraa Osama Abo Zaid ◽  
Songfeng Lu ◽  
Rehab Ali Ibrahim ◽  
...  
Keyword(s):  
Image Segmentation ◽  
Threshold Value ◽  
Ct Images ◽  
Optimal Number ◽  
Clustering Methods ◽  
Segmentation Method ◽  
Density Peaks ◽  
Automatic Clustering ◽  
Proposed Model ◽  
Density Peaks Clustering

Coronavirus pandemic (COVID-19) has infected more than ten million persons worldwide. Therefore, researchers are trying to address various aspects that may help in diagnosis this pneumonia. Image segmentation is a necessary pr-processing step that implemented in image analysis and classification applications. Therefore, in this study, our goal is to present an efficient image segmentation method for COVID-19 Computed Tomography (CT) images. The proposed image segmentation method depends on improving the density peaks clustering (DPC) using generalized extreme value (GEV) distribution. The DPC is faster than other clustering methods, and it provides more stable results. However, it is difficult to determine the optimal number of clustering centers automatically without visualization. So, GEV is used to determine the suitable threshold value to find the optimal number of clustering centers that lead to improving the segmentation process. The proposed model is applied for a set of twelve COVID-19 CT images. Also, it was compared with traditional k-means and DPC algorithms, and it has better performance using several measures, such as PSNR, SSIM, and Entropy.

Research on Image Segmentation Technology with Tissue Section Cell Segmentation Algorithm

2014 ◽  
Vol 1046 ◽  
pp. 88-91
Author(s):  
Chun Bao Huo ◽  
Shuai Tong ◽  
Li Hui Zhao ◽  
Xiang Yun Li
Keyword(s):  
Image Segmentation ◽  
Tissue Section ◽  
Threshold Value ◽  
Cell Segmentation ◽  
Gray Level ◽  
Segmentation Method ◽  
Cell Edge ◽  
Cell Image ◽  
Original Picture ◽  
Maximum Interval

Generally, the effect of cell image that segmented via the threshold value method is not ideal generally; the found cell boundary cannot conform to the cell edge in the original picture well. In this paper, the threshold value segmentation method is improved; apply the judging criterion of gray level difference maximum interval to be the minimum, and conduct secondary treating on the image, and the image’s segmentation effect is more ideal.

Multi-color measurement of printed fabric using the hyperspectral imaging system

2019 ◽  
Vol 90 (9-10) ◽  
pp. 1024-1037
Author(s):  
Jianxin Zhang ◽  
Junkai Wu ◽  
Xudong Hu ◽  
Xinen Zhang
Keyword(s):  
Hyperspectral Imaging ◽  
Imaging System ◽  
Optimal Number ◽  
Color Segmentation ◽  
Color Measurement ◽  
Self Organizing Map ◽  
Density Peaks ◽  
Silhouette Index ◽  
Som Algorithm ◽  
Density Peaks Clustering

Printed fabrics usually have multiple colors and intricate patterns, which make it difficult to directly measure the colors of the printed fabrics with a traditional spectrophotometer. However, a hyperspectral imaging system (HIS) can measure multiple colors since it acquires the spectral reflectance of a continuous band at every point of the fabric. For multiple-color printed fabrics, color segmentation is also very important. In this paper, color measurement of printed fabrics using the HIS was implemented; an algorithm which combines the self-organizing map (SOM) algorithm and the density peaks clustering (DPC) algorithm was then proposed to automatically determine the number of colors on the printed fabric and accurately segment the color regions for measurement. Firstly, the SOM algorithm was used to identify the main clusters, the DPC algorithm with Silhouette Index was then used to identify the optimal number of colors and merge the clusters. Experimental results show that this algorithm not only automatically determines the optimal number of colors for printed fabric and achieves accurate color segmentation, but requires less time for execution.

scholarly journals Automatic morphological characterization of nanobubbles with a novel image segmentation method and its application in the study of nanobubble coalescence

2015 ◽  
Vol 6 ◽  
pp. 952-963 ◽  
Author(s):  
Yuliang Wang ◽  
Huimin Wang ◽  
Shusheng Bi ◽  
Bin Guo
Keyword(s):  
Image Segmentation ◽  
External Disturbance ◽  
Threshold Value ◽  
Morphological Characterization ◽  
Contour Method ◽  
Radius Of Curvature ◽  
Segmentation Method ◽  
Threshold Method ◽  
Modified Method

Nanobubbles (NBs) on hydrophobic surfaces in aqueous solvents have shown great potential in numerous applications. In this study, the morphological characterization of NBs in AFM images was carried out with the assistance of a novel image segmentation method. The method combines the classical threshold method and a modified, active contour method to achieve optimized image segmentation. The image segmentation results obtained with the classical threshold method and the proposed, modified method were compared. With the modified method, the diameter, contact angle, and radius of curvature were automatically measured for all NBs in AFM images. The influence of the selection of the threshold value on the segmentation result was discussed. Moreover, the morphological change in the NBs was studied in terms of density, covered area, and volume occurring during coalescence under external disturbance.

scholarly journals Neural Network for Earthquake Prediction Based on Automatic Clustering in Indonesia

2018 ◽  
Vol 2 (1) ◽  
pp. 37 ◽  
Author(s):  
Mohammad Nur Shodiq ◽  
Dedy Hidayat Kusuma ◽  
Mirza Ghulam Rifqi ◽  
Ali Ridho Barakbah ◽  
Tri Harsono
Keyword(s):  
Neural Network ◽  
Quality Evaluation ◽  
Model Performance ◽  
Optimal Number ◽  
Hill Climbing ◽  
Experimental Result ◽  
Earthquake Occurrence ◽  
Hill Climbing Algorithm ◽  
Automatic Clustering ◽  
Proposed Model

A model of artificial neural networks (ANNs) is presented in this paper to predict aftershock during the next five days after an earthquake occurrence in selected cluster of Indonesia with magnitude equal or larger than given threshold. The data were obtained from Indonesian Agency for Meteorological, Climatological and Geophysics (BMKG) and United States Geological Survey’s (USGS). Six clusters was an optimal number of cluster base-on cluster analysis implementing Valley Tracing and Hill Climbing algorithm, while Hierarchical K-means was applied for datasets clustering. A quality evaluation was then conducted to measure the proposed model performance for two different thresholds. The experimental result shows that the model gave better performance for predicting an aftershock occurrence that equal or larger than 6 Richter’s scale magnitude.

A deep fully residual convolutional neural network for segmentation in EM images

2020 ◽  
Vol 18 (03) ◽  
pp. 2050007
Author(s):  
Juanjuan He ◽  
Song Xiang ◽  
Ziqi Zhu
Keyword(s):  
Neural Network ◽  
Image Segmentation ◽  
Convolutional Neural Network ◽  
Medical Image ◽  
Spatial Information ◽  
State Of The Art ◽  
Ct Images ◽  
Medical Image Segmentation ◽  
Post Process ◽  
Proposed Model

In standard U-net, researchers only use long skip connections to skip features from the encoding path to the decoding path in order to recover spatial information loss during downsampling. However, it would result in gradient vanishing and limit the depth of the network. To address this issue, we propose a novel deep fully residual convolutional neural network that combines the U-net with the ResNet for medical image segmentation. By applying short skip connections, this new extension of U-net decreases the amount of parameters compared to the standard U-net, although the depth of the layer is increased. We evaluate the performance of the proposed model and other state-of-the-art models on the Electron Microscopy (EM) images dataset and the Computed Tomography (CT) images dataset. The result shows that our model achieves competitive accuracy on the EM benchmark without any further post-process. Moreover, the performance of image segmentation on CT images of the lungs is improved in contrast to the standard U-net.

scholarly journals A weakly supervised learning method based on attention fusion for Covid-19 segmentation in CT images

2021 ◽  
pp. 1-12
Author(s):  
Hongyu Chen ◽  
Shengsheng Wang
Keyword(s):  
Image Segmentation ◽  
Supervised Learning ◽  
Ct Images ◽  
Medical Image Segmentation ◽  
Great Success ◽  
Segmentation Method ◽  
Rt Pcr ◽  
Weakly Supervised Learning ◽  
Polymerase Chain ◽  
Weakly Supervised

Since the end of 2019, the COVID-19, which has swept across the world, has caused serious impacts on public health and economy. Although Reverse Transcription-Polymerase Chain Reaction (RT-PCR) is the gold standard for clinical diagnosis, it is very time-consuming and labor-intensive. At the same time, more and more people have doubted the sensitivity of RT-PCR. Therefore, Computed Tomography (CT) images are used as a substitute for RT-PCR. Powered by the research of the field of artificial intelligence, deep learning, which is a branch of machine learning, has made a great success on medical image segmentation. However, general full supervision methods require pixel-level point-by-point annotations, which is very costly. In this paper, we put forward an image segmentation method based on weakly supervised learning for CT images of COVID-19, which can effectively segment the lung infection area and doesn’t require pixel-level labels. Our method is contrasted with another four weakly supervised learning methods in recent years, and the results have been significantly improved.

scholarly journals A Novel Controller Placement Using Petri-Nets for SDNs

2020 ◽  
Vol 19 ◽  
Keyword(s):  
Petri Nets ◽  
Reference Model ◽  
Placement Problem ◽  
Reference Models ◽  
Density Peaks ◽  
Ongoing Work ◽  
Proposed Model ◽  
Controller Placement ◽  
Average Latency ◽  
Density Peaks Clustering

Software defined networking (SDN) separates the control and the data planes. This separation brings flexibility to the network. But the decoupling has some drawbacks such as the controller placement problem (CPP). Controller placement is a crucial task which affects the overall networks’ performance. This paper proposes a novel controller placement model that is based on petri-nets to place the SDN’s controllers. The proposed model is called controller placement using petri-nets for SDNs (CPPNSDN). CPPNSDN aims to reduce the average propagation latency among switches and their associated controllers. CPPNSDN divides the network into sub-networks. Each sub-network is governed by a controller. Experiments were conducted on the Internet2/OS3E topology to evaluate the performance of CPPNSDN. Experiments show that CPPNSDN reduces the average latency significantly compared to two reference models. The first reference model is the Modified Density Peaks Clustering (MDPC) and the Optimized Kmeans model. In terms of the overall average latency, the CPPNSDN has shown promising results as it outperformed the MDPC and optimized Kmeans reference models by 7% and 17% respectively. Confidence Interval (CI) used was 90%. This is an ongoing work and the results are promising for more future investigation

scholarly journals GAUSSIAN MIXTURE MODEL AND RJMCMC BASED RS IMAGE SEGMENTATION

2017 ◽  
Vol XLII-2/W7 ◽  
pp. 647-650 ◽  
Author(s):  
X. Shi ◽  
Q. H. Zhao
Keyword(s):  
Image Segmentation ◽  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Posterior Distribution ◽  
Prior Distribution ◽  
Gaussian Mixture ◽  
Fixed Number ◽  
Optimal Number ◽  
Segmentation Method ◽  
Pixel Intensity

For the image segmentation method based on Gaussian Mixture Model (GMM), there are some problems: 1) The number of component was usually a fixed number, i.e., fixed class and 2) GMM is sensitive to image noise. This paper proposed a RS image segmentation method that combining GMM with reversible jump Markov Chain Monte Carlo (RJMCMC). In proposed algorithm, GMM was designed to model the distribution of pixel intensity in RS image. Assume that the number of component was a random variable. Respectively build the prior distribution of each parameter. In order to improve noise resistance, used Gibbs function to model the prior distribution of GMM weight coefficient. According to Bayes' theorem, build posterior distribution. RJMCMC was used to simulate the posterior distribution and estimate its parameters. Finally, an optimal segmentation is obtained on RS image. Experimental results show that the proposed algorithm can converge to the optimal number of class and get an ideal segmentation results.

A Novel Controller Placement Using Petri-Nets for SDNs

2021 ◽  
Vol 19 ◽  
pp. 268-276
Author(s):  
Wael Hosny Fouad Aly
Keyword(s):  
Petri Nets ◽  
Reference Model ◽  
Placement Problem ◽  
Reference Models ◽  
Density Peaks ◽  
Ongoing Work ◽  
Proposed Model ◽  
Controller Placement ◽  
Average Latency ◽  
Density Peaks Clustering

Software defined networking (SDN) separates the control and the data planes. This separation brings flexibility to the network. But the decoupling has some drawbacks such as the controller placement problem (CPP). Controller placement is a crucial task which affects the overall networks’ performance. This paper proposes a novel controller placement model that is based on petri-nets to place the SDN’s controllers. The proposed model is called controller placement using petri-nets for SDNs (CPPNSDN). CPPNSDN aims to reduce the average propagation latency among switches and their associated controllers. CPPNSDN divides the network into sub-networks. Each sub-network is governed by a controller. Experiments were conducted on the Internet2/OS3E topology to evaluate the performance of CPPNSDN. Experiments show that CPPNSDN reduces the average latency significantly compared to two reference models. The first reference model is the Modified Density Peaks Clustering (MDPC) and the Optimized Kmeans model. In terms of the overall average latency, the CPPNSDN has shown promising results as it outperformed the MDPC and optimized Kmeans reference models by 7% and 17% respectively. Confidence Interval (CI) used was 90%. This is an ongoing work and the results are promising for more future investigation.

scholarly journals Medical Image Segmentation Using Fruit Fly Optimization and Density Peaks Clustering

2018 ◽  
Vol 2018 ◽  
pp. 1-11 ◽  
Author(s):  
Hong Zhu ◽  
Hanzhi He ◽  
Jinhui Xu ◽  
Qianhao Fang ◽  
Wei Wang
Keyword(s):  
Image Segmentation ◽  
Optimization Algorithm ◽  
Medical Image ◽  
Fruit Fly ◽  
Medical Image Segmentation ◽  
Fruit Fly Optimization Algorithm ◽  
Step Size ◽  
Fruit Fly Optimization ◽  
Density Peaks ◽  
Density Peaks Clustering

In this paper, we propose a novel algorithm for medical image segmentation, which combines the density peaks clustering (DPC) with the fruit fly optimization algorithm, and it has the following advantages. Firstly, it avoids the problem of DPC that needs to artificially select parameters (such as the number of clusters) in its decision graph and thus can automatically determine their values. Secondly, our algorithm uses random step size, instead of the fixed step size as in the fruit fly optimization algorithm, which helps avoid falling into local optima. Thirdly, our algorithm selects the cut-off distance and the cluster centers using the image entropy value and can better capture the structures of the image. Experiments on benchmark dataset and proprietary dataset show that our algorithm can adaptively segment medical images with faster convergence and better robustness.

Sign in / Sign up

Export Citation Format

Share Document