Spatial Fuzzy Clustering Research Articles

Network and attribute-based clustering of tennis players and tournaments

AbstractThis paper aims at targeting some relevant issues for clustering tennis players and tournaments: (i) it considers players, tournaments and the relation between them; (ii) the relation is taken into account in the fuzzy clustering model based on the Partitioning Around Medoids (PAM) algorithm through spatial constraints; (iii) the attributes of the players and of the tournaments are of different nature, qualitative and quantitative. The proposal is novel for the methodology used, a spatial Fuzzy clustering model for players and for tournaments (based on related attributes), where the spatial penalty term in each clustering model depends on the relation between players and tournaments described in the adjacency matrix. The proposed model is compared with a bipartite players-tournament complex network model (the Degree-Corrected Stochastic Blockmodel) that considers only the relation between players and tournaments, described in the adjacency matrix, to obtain communities on each side of the bipartite network. An application on data taken from the ATP official website with regards to the draws of the tournaments, and from the sport statistics website Wheelo ratings for the performance data of players and tournaments, shows the performances of the proposed clustering model.

Possibilistic exponential spatial fuzzy clustering based cancer segmentation in multi-parametric prostate MRI

Possibilistic exponential spatial fuzzy clustering based cancer segmentation in multi-parametric prostate MRI

Improved detection and analysis of Macular Edema using modified guided image filtering with modified level set spatial fuzzy clustering on Optical Coherence Tomography images

Background and Objective: The hypo-reflective Optical Coherence Tomography (OCT) imaging of the pseudo retinal layer strengthens the analysis of various retinal disorders, including Macular Edema (ME)/Diabetic Macular Edema (DME). The primary challenge in the automatic identification and analysis of ME cases is the presence of multiplicative speckle noise and variational edge boundaries. This paper presents an automated algorithm for detecting ME and cyst segmentation. Methods: The algorithm is implemented in three steps. The first step includes the removal of OCT’s predominating speckle noise. In this regard, edge-preserving modified guided image filtering (mGIF) has been employed. After that, the boundaries of retinal layers are segmented using a modified level set spatial fuzzy clustering (LSFCM) algorithm. This process identifies the inner limiting membrane and retinal pigment epithelium layer. The macular thickness between these layers is essential for the detection of edema cases. The third step identifies the presence of cystoid fluid inside positive edema cases using a modified Nick’s threshold, followed by modified LSFCM, applied to mGIF filtered green channel OCT images. Results: The algorithm is tested on a local database (DS1) containing 260 OCT (187 normal and 73 diseased) images. The algorithm’s performance is validated using standard database verification protocols considering the Duke University DME database (DS2) and OPTIMA database (DS3). The databases are annotated by two professional ophthalmologists. The method records an average 97.37% accuracy and an F1-score of 98.69% in detecting ME cases in the DS1 and DS2 databases. The average sensitivity, specificity, accuracy, precision, recall, and F1-score obtained for cyst detection are 98.92%, 99.22%, 98.95%, 98.33%, 98.92% and 98.25%, respectively, obtained from DS1, DS2 database positive ME cases, and DS3 database. The algorithm enhances OCT analysis with comparable efficiency over current state-of-the-art methodologies. Conclusion: The algorithm enhances OCT analysis with efficient speckle noise removal and variational boundary detection of the OCT layer with comparable efficiency over current state-of-the-art methodologies.

Large-scale investigation of deep learning approaches for ventilated lung segmentation using multi-nuclear hyperpolarized gas MRI

Respiratory diseases are leading causes of mortality and morbidity worldwide. Pulmonary imaging is an essential component of the diagnosis, treatment planning, monitoring, and treatment assessment of respiratory diseases. Insights into numerous pulmonary pathologies can be gleaned from functional lung MRI techniques. These include hyperpolarized gas ventilation MRI, which enables visualization and quantification of regional lung ventilation with high spatial resolution. Segmentation of the ventilated lung is required to calculate clinically relevant biomarkers. Recent research in deep learning (DL) has shown promising results for numerous segmentation problems. Here, we evaluate several 3D convolutional neural networks to segment ventilated lung regions on hyperpolarized gas MRI scans. The dataset consists of 759 helium-3 (3He) or xenon-129 (129Xe) volumetric scans and corresponding expert segmentations from 341 healthy subjects and patients with a wide range of pathologies. We evaluated segmentation performance for several DL experimental methods via overlap, distance and error metrics and compared them to conventional segmentation methods, namely, spatial fuzzy c-means (SFCM) and K-means clustering. We observed that training on combined 3He and 129Xe MRI scans using a 3D nn-UNet outperformed other DL methods, achieving a mean ± SD Dice coefficient of 0.963 ± 0.018, average boundary Hausdorff distance of 1.505 ± 0.969 mm, Hausdorff 95th percentile of 5.754 ± 6.621 mm and relative error of 0.075 ± 0.039. Moreover, limited differences in performance were observed between 129Xe and 3He scans in the testing set. Combined training on 129Xe and 3He yielded statistically significant improvements over the conventional methods (p < 0.0001). In addition, we observed very strong correlation and agreement between DL and expert segmentations, with Pearson correlation of 0.99 (p < 0.0001) and Bland–Altman bias of − 0.8%. The DL approach evaluated provides accurate, robust and rapid segmentations of ventilated lung regions and successfully excludes non-lung regions such as the airways and artefacts. This approach is expected to eliminate the need for, or significantly reduce, subsequent time-consuming manual editing.

ANALYSIS OF SPECIFIC PARAMETERS FOR SKIN TUMOR CLASSIFICATION

During the last years, computer vision-based diagnosis systems have been widely used in several hospitals and dermatology clinics, aiming mostly at the early detection of malignant melanoma tumor, which is among the most frequent types of skin cancer, versus other types of nonmalignant cutaneous diseases. They grow in melanocytes, the cells responsible for pigmentation. This type of cancer is increasing rapidly and its related mortality rate is increasing more modestly, and inversely proportional to the tumor’s thickness. The mortality rate can be decreased by earlier detection of suspicious lesions and better prevention. In this work, we are interested in extracting all specific attributes which can be used for computer-aided diagnosis of melanoma. In the first step of the proposed work, we applied the Dull Razor [Lee T et al., Dullrazor: A software approach to hair removal from images, Cancer Control Research, British Columbia Cancer Agency, Vancouver, Canada, Vol. 21, No. 6, pp. 533–543, 1997] technique to images to reduce the influence of small structures, hairs, bubbles, light reflection. In the second step, a new fuzzy level set algorithm is proposed in order to facilitate the medical image segmentation task. It is able to directly evolve from the initial segmentation proposed that uses a spatial fuzzy clustering approach. The controlling parameters of the level set evolution are also estimated from the results of the fuzzy clustering step. This step is essential to characterize the shape of the lesion and also to locate the tumor to be analyzed. In this paper, we have also treated the necessity to extract all the specific attributes used to develop a characterization methodology that enables specialists to take the best possible diagnosis. For this purpose, our proposal relies largely on visual observation of the tumor while dealing with some characteristics as color, texture or form. The method used in this paper is called ABCD. It requires calculating four factors: Asymmetry ([Formula: see text], Border ([Formula: see text], Color ([Formula: see text], and Diversity ([Formula: see text]. Finally, these parameters are used to construct a classification module based on artificial neural network for the recognition of malignant melanoma.

Spatial information of fuzzy clustering based mean best artificial bee colony algorithm for phantom brain image segmentation

Fuzzy c-means algorithm (FCM) is among the most commonly used in the medical image segmentation process. Nevertheless, the traditional FCM clustering approach has been several weaknesses such as noise sensitivity and stuck in local optimum, due to FCM hasn’t able to consider the information of contextual. To solve FCM problems, this paper presented spatial information of fuzzy clustering-based mean best artificial bee colony algorithm, which is called SFCM-MeanABC. This proposed approach is used contextual information in the spatial fuzzy clustering algorithm to reduce sensitivity to noise and its used MeanABC capability of balancing between exploration and exploitation that is explore the positive and negative directions in search space to find the best solutions, which leads to avoiding stuck in a local optimum. The experiments are carried out on two kinds of brain images the Phantom MRI brain image with a different level of noise and simulated image. The performance of the SFCM-MeanABC approach shows promising results compared with SFCM-ABC and other stats of the arts.

Robust semi-supervised spatial picture fuzzy clustering with local membership and KL-divergence for image segmentation

Robust semi-supervised spatial picture fuzzy clustering with local membership and KL-divergence for image segmentation

Semi-automated and interactive segmentation of contrast-enhancing masses on breast DCE-MRI using spatial fuzzy clustering

Multiparametric Magnetic Resonance Imaging (MRI) is the most sensitive imaging modality for breast cancer detection and is increasingly playing a key role in lesion characterization. In this context, accurate and reliable quantification of the shape and extent of breast cancer is crucial in clinical research environments. Since conventional lesion delineation procedures are still mostly manual, automated segmentation approaches can improve this time-consuming and operator-dependent task by annotating the regions of interest in a reproducible manner. In this work, a semi-automated and interactive approach based on the spatial Fuzzy C-Means (sFCM) algorithm is proposed, used to segment masses on dynamic contrast-enhanced (DCE) MRI of the breast. Our method was compared against existing approaches based on classic image processing, namely (i) Otsu’s method for thresholding-based segmentation, and (ii) the traditional FCM algorithm. A further comparison was performed against state-of-the-art Convolutional Neural Networks (CNNs) for medical image segmentation, namely SegNet and U-Net, in a 5-fold cross-validation scheme. The results showed the validity of the proposed approach, by significantly outperforming the competing methods in terms of the Dice similarity coefficient (84.47±4.75). Moreover, a Pearson’s coefficient of ρ=0.993 showed a high correlation between segmented volume and the gold standard provided by clinicians. Overall, the proposed method was confirmed to outperform the competing literature methods. The proposed computer-assisted approach could be deployed into clinical research environments by providing a reliable tool for volumetric and radiomics analyses.

SEGMENTATION OF BRAIN STRUCTURES IN ALZHEIMER MR IMAGES USING SPATIAL FUZZY CLUSTERING LEVEL SET

Alzheimer’s Disease (AD) is an irreversible neurodegenerative disorder that affects brain structures. Corpus Callosum (CC) atrophy and Lateral ventricle (LV) enlargement are useful structural biomarkers in distinguishing the preclinical stages of AD. The shape of CC appears to be homogeneous from normal controls to AD images and LV shows shape dissimilarity across subjects. Therefore, effective methods to segment CC and LV are essential to characterize the magnitude of morphometric changes. In this study, an attempt has been made to segment CC and LV from MR brain images using the Spatial Fuzzy Clustering based Level Set (SFC-LS) method. For this, T1-weighted MR images of AD, Mild Cognitive Impairment (MCI), and normal controls are obtained from a public database. Spatial fuzzy clustering forms the initial contour for the level set and regularizes the evolution of curve. The segmented images are validated against ground truth using standard measures. Results indicate that SFC-LS is able to segment CC and LV with automated contour initialization. The final contours obtained are sharp and distinct with a high validation performance of accuracy and specificity greater than 97% for normal controls, MCI, and AD. A dice score of 83% and 84% is achieved in segmenting CC and LV respectively. As structural changes in CC and LV have the potential to predict the early stages of AD, the proposed approach seems to be clinically significant.

Spatial Fuzzy Clustering and Its Application for MRI and CT Image Segmentation

Due to the low segmentation accuracy and sensitivity to initial contour in image segmentation of CV model, an image segmentation algorithm based on CV model combined with spatial fuzzy c-means was proposed for MRI and CT image segmentation with unclear boundary, artifact and high noise. Based on the rough segmentation of the image by using the fuzzy c-means clustering algorithm in the spatial domain, the initial contour is set by using the clustering information to assist the CV model, and the target region is segmented by iterative evolution. The experimental results showed that when the number of iterations was only 50, the Dice coefficient of our algorithm for segmentation of brain MRI images was 89.17%, 38.9% higher than the traditional CV model. It can be seen that the algorithm has higher discrimination and better segmentation effect for medical images.

Ship Target Image Segmentation Algorithm Based on Fuzzy Level Set

The effective recognition of ship target is very important for the protection of ocean rights, and the image segmentation is the precondition of the ship target recognition. To solve the two problems existing in the traditional level set graph, namely the increase of image segmentation and the increase of computation, the Fuzzy C-Means (FCM) and level set are introduced. A new algorithm for image segmentation based on fuzzy level set is proposed in this paper. The algorithm can use spatial fuzzy clustering to realize the parameter estimation and evolutionary adjustment. The algorithm is applied to optical remote sensing ship target image segmentation in complex sea environment, and the effectiveness of the proposed algorithm is verified by experiment results.

MRI images segmentation using improved spatial FCM clustering and pillar algorithms

The segmentation of brain tissue from MRI images is a vast subject of study, a critical task and a very important issue for different medical applications; however, its numerous problems remain relatively open. In this paper, the main purpose of the project is to carry out a new segmentation technique based on a combined method between pillar algorithm and spatial fuzzy c-means clustering. The proposed approach applies FCM clustering to image segmentation after optimised by pillar algorithm in terms of initial centres precision and computational time. The features of the segmented brain image are extracted in different classes [white matter (WM), gray matter (GM) and cerebrospinal fluid (CSF)] using the integrating elements interpreted to get partially or fully automated tools allowing a correct extraction of the cerebral tissue. The developed algorithm has been implemented and the program is run through a Simulink in MATLAB. All experimental results are very satisfactory which allows us to clarify that using a combined method of several segmentation algorithms allow to get better results and improve the classification.

MRI images segmentation using improved spatial FCM clustering and pillar algorithms

The segmentation of brain tissue from MRI images is a vast subject of study, a critical task and a very important issue for different medical applications; however, its numerous problems remain relatively open. In this paper, the main purpose of the project is to carry out a new segmentation technique based on a combined method between pillar algorithm and spatial fuzzy c-means clustering. The proposed approach applies FCM clustering to image segmentation after optimised by pillar algorithm in terms of initial centres precision and computational time. The features of the segmented brain image are extracted in different classes [white matter (WM), gray matter (GM) and cerebrospinal fluid (CSF)] using the integrating elements interpreted to get partially or fully automated tools allowing a correct extraction of the cerebral tissue. The developed algorithm has been implemented and the program is run through a Simulink in MATLAB. All experimental results are very satisfactory which allows us to clarify that using a combined method of several segmentation algorithms allow to get better results and improve the classification.

Application of MRI images based on Spatial Fuzzy Clustering Algorithm guided by Neuroendoscopy in the treatment of Tumors in the Saddle Region.

Objective:The paper applies spatial fuzzy clustering algorithm to explore the role and value of neuroendoscopic assisted technology in the operation of tumors in the saddle region, and analyze the MRI image characteristics of tumors in the saddle region.Methods:The clinical data of 63 patients from our hospital who underwent neuroendoscopic assisted microscopy to remove tumors in the saddle area from 2017 to 2019 (neuroendoscopy-assisted group) were collected. Seventy six patients who occupied the saddle area by microscopic resection only in the same period (Simple microscope group) clinical data. By comparing the patient’s tumor resection rate, postoperative complication rate and postoperative recurrence rate, the surgical effect was evaluated.Results:The total resection rates of the tumors in the neuroendoscopy-assisted group and the microscope-only group were 95.24% (60/63) and 80.26% (61/76). The incidence of postoperative vasospasm was 3.17% (2/63) and 13.16% (10/76), the incidence of nerve injury was 0 (0/63) and 6.58% (5/76), the difference was statistically significant (P <0.05). There was no significant difference in the incidence of postoperative infection, cerebrospinal fluid leakage and postoperative recurrence rate between the two groups (P> 0.05).Conclusion:Neuroendoscopy-assisted microscopy-based removal of the saddle area occupying space based on spatial fuzzy clustering algorithm can increase the total tumor resection rate and reduce the incidence of complications.

Revisiting social vulnerability analysis in Indonesia: An optimized spatial fuzzy clustering approach

In previous social vulnerability studies, the use of indices in assessing social vulnerability can only describe conditions of social vulnerability in general without being able to indicate which factors are dominant in measuring the level of social vulnerability. Therefore this study aims to fill the gap by implementing the relative approach using the clustering method to characterize the dominant factors of social vulnerability in Indonesia at the district level utilizing hybridization of the Fuzzy Geographically Weighted Clustering (FGWC) with Intelligent Firefly Algorithm (IFA). Then the Kruskal-Wallis test is used to obtain the dominant factor of social vulnerability in each formed cluster. The study found that each district in Indonesia has its own prevailing social vulnerability problems. The majority of regions on the west coast of Sumatera Island, such as Nias and Mentawai District and Eastern Indonesia, such as Sumba Barat Daya and Intan Jaya District, are the districts with the most problem, particularly in socioeconomic aspects. The results of this study can be used to support the prevention, mitigation, response, and recovery for reduction disaster programs in Indonesia.

Fuzzy SLIC: Fuzzy Simple Linear Iterative Clustering

Most superpixel methods are sensitive to noise and cannot control the superpixel number precisely. To solve these problems, in this paper, we propose a robust superpixel method called fuzzy simple linear iterative clustering (Fuzzy SLIC), which adopts a local spatial fuzzy C-means clustering and dynamic fuzzy superpixels. We develop a fast and precise superpixel number control algorithm called onion peeling (OP) algorithm. Fuzzy SLIC is insensitive to most types of noise, including Gaussian, salt and pepper, and multiplicative noise. The OP algorithm can control the superpixel number accurately without reducing much computational efficiency. In the validation experiments, we tested the Fuzzy SLIC and OP algorithm and compared them with state-of-the-art methods on the BSD500 and Pascal VOC2007 benchmarks. The experiment results show that our methods outperform state-of-the-art techniques in both noise-free and noisy environments.

A Deep Learning Method for Change Detection in Synthetic Aperture Radar Images

With the rapid development of various technologies of satellite sensor, synthetic aperture radar (SAR) image has been an import source of data in the application of change detection. In this paper, a novel method based on a convolutional neural network (CNN) for SAR image change detection is proposed. The main idea of our method is to generate the classification results directly from the original two SAR images through a CNN without any preprocessing operations, which also eliminate the process of generating the difference image (DI), thus reducing the influence of the DI on the final classification result. In CNN, the spatial characteristics of the raw image can be extracted and captured by automatic learning and the results with stronger robustness can be obtained. The basic idea of the proposed method includes three steps: it first produces false labels through unsupervised spatial fuzzy clustering. Then we train the CNN through proper samples that are selected from the samples with false labels. Finally, the final detection results are obtained by the trained convolutional network. Although training the convolutional network is a supervised learning fashion, the whole process of the algorithm is an unsupervised process without priori knowledge. The theoretical analysis and experimental results demonstrate the validity, robustness, and potential of our algorithm in simulated and real data sets. In addition, we try to apply our algorithm to the change detection of heterogeneous images, which also achieves satisfactory results.

Detection of Liver Cancer Using Modified Fuzzy Clustering and Decision Tree Classifier in CT Images

Manual detection and characterization of liver cancer using computed tomography (CT) scan images is a challenging task. In this paper, we have presented an automatic approach that integrates the adaptive thresholding and spatial fuzzy clustering approach for detection of cancer region in CT scan images of liver. The algorithm was tested in a series of 123 real-time images collected from the different subjects at Institute of Medical Science and SUM Hospital, India. Initially the liver was separated from other parts of the body with adaptive thresholding and then the cancer affected lesions from liver was segmented with spatial fuzzy clustering. The informative features were extracted from segmented cancerous region and were classified into two types of liver cancers i.e., hepatocellular carcinoma (HCC) and metastatic carcinoma (MET) using multilayer perceptron (MLP) and C4.5 decision tree classifiers. The performance of the classifiers was evaluated using 10-fold cross validation process in terms of sensitivity, specificity, accuracy and dice similarity coefficient. The method was effectively detected the lesion with accuracy of 89.15% in MLP classifier and of 95.02% in C4.5 classifier. This results proves that the spatial fuzzy c-means (SFCM) based segmentation with C4.5 decision tree classifier is an effective approach for automatic recognition of the liver cancer.

Fully Automatic Spectral–Spatial Fuzzy Clustering Using an Adaptive Multiobjective Memetic Algorithm for Multispectral Imagery

Clustering of remote sensing imagery is a tough task due to the particular and complex structure of remote sensing images and the shortage of known information. In this paper, we propose a fully automatic spectral–spatial fuzzy clustering method using an adaptive multiobjective memetic algorithm (AMOMA) for multispectral remote sensing imagery. This approach is made up of two automatic layers: an automatic determination layer and an automatic clustering layer. The first layer seeks the optimal number of clusters through a self-adaptive differential evolution algorithm. The second layer then takes advantage of the AMOMA for spectral–spatial clustering using the optimal number of clusters. The knee point from the Pareto front is then selected through the angle-based method in every generation, and we then compare the knee points between generations to output the final optimal solution. The effectiveness of the proposed method is verified by the experimental results obtained with three remote sensing data sets.

Preface

Preface