Spatial Fuzzy C-means Algorithm Research Articles

Enhanced Spatial Fuzzy C-Means Algorithm for Brain Tissue Segmentation in T1 Images.

Magnetic Resonance Imaging (MRI) plays an important role in neurology, particularly in the precise segmentation of brain tissues. Accurate segmentation is crucial for diagnosing brain injuries and neurodegenerative conditions. We introduce an Enhanced Spatial Fuzzy C-means (esFCM) algorithm for 3D T1 MRI segmentation to three tissues, i.e. White Matter (WM), Gray Matter (GM), and Cerebrospinal Fluid (CSF). The esFCM employs a weighted least square algorithm utilizing the Structural Similarity Index (SSIM) for polynomial bias field correction. It also takes advantage of the information from the membership function of the last iteration to compute neighborhood impact. This strategic refinement enhances the algorithm's adaptability to complex image structures, effectively addressing challenges such as intensity irregularities and contributing to heightened segmentation accuracy. We compare the segmentation accuracy of esFCM against four variants of FCM, Gaussian Mixture Model (GMM) and FSL and ANTs algorithms using four various dataset, employing three measurement criteria. Comparative assessments underscore esFCM's superior performance, particularly in scenarios involving added noise and bias fields.The obtained results emphasize the significant potential of the proposed method in the segmentation of MRI images.

거래사례 기반 기계학습 공간군집화를 이용한 서울 오피스 시장 권역 분석

This study attempts to regionalize the Seoul office market by focusing on the investors’ perspectives. The study uses the transaction price data announced by the Ministry of Land, Infrastructure, and Transport and applies the Fuzzy C-Means algorithms, which are machine learning-based clustering techniques. The study found the following: First, as a result of comparing various algorithms, the Spatial Fuzzy C-Means algorithm performs the best clustering. Second, the three major office districts in Seoul form clusters differentiated from other areas. Third, the number of Dongs belonging to each district is smaller than the general consensus. The traditional business district (CBD) includes only parts of Jongno-Gu and Jung-Gu, the Yeouido business district (YBD) is composed of only Yeouido-Dong, and the Gangnam business district (GBD) comprises not many Dongs of Gangnam-Gu and Seocho-Gu. Fourth, by weakening the criteria, the clustering results in different spatial expansions by district. CBD has expanded to Seodaemun-Gu and Yongsan-Gu, whereas YBD has not expanded to Mapo-Gu or Yeongdeungpo. In particular, GBD expands to a considerable number of Dongs in Gangnam-Gu and Seocho-Gu. Fifth, the range of each district changes by period. When the office price increases rapidly, the range of each district is widened, and vice versa. These results show that, unlike the general perception of office districts, the CBD is expanding to Seodaemun-Gu and Yongsan-Gu. Moreover, Yeouido and nearby Mapo-Gu and Yeongdeungpo are not homogenous enough to be viewed as one district, and GBD is not linear but rectangular. Furthermore, Songpa-Gu does not form a spatially connected district with Seocho-Gu and Gangnam-Gu.

Soil and Climate Characterization to Define Environments for Summer Crops in Senegal

Investigating soil and climate variability is critical to defining environments for field crops, understanding yield-limiting factors, and contributing to the sustainability and resilience of agro-ecosystems. Following this rationale, the aim of this study was to develop a soil–climate characterization to describe environmental constraints in the Senegal summer-crops region. For the soil database, 825 soil samples were collected characterizing pH, electrical conductivity (EC), phosphorus (P), potassium (K), cation exchange capacity (CEC), and total carbon (C) and nitrogen (N). For the climate, monthly temperature, precipitation, and evapotranspiration layers were retrieved from WorldClim 2.1, CHIRPS and TERRACLIMATE. The same analysis was applied individually to both databases. Briefly, a principal component analysis (PCA) was executed to summarize the spatial variability. The outcomes from the PCA were subjected to a spatial fuzzy c-means algorithm, delineating five soil and three climate homogeneous areas, accounting for 73% of the soil and 88% of the climate variation. To our knowledge, no previous studies were done with large soil databases since availability field data is often limited. The use of soil and climate data allowed the characterization of different areas and their main drivers. The use of this classification will assist in developing strategic planning for future land use and capability classifications.

A Fuzzy clustering based MRI brain image segmentation using back propagation neural networks

The paper focuses on how a brain image is being segmented to diagnose the brain tumor by using spatial fuzzy clustering algorithm. The segmentation process may cause error while diagonizing MR images due to the artifacts and noises exist in it. This may leads to misclassify the normal tissue as abnormal tissue. The proposed method is to segment normal tissues such as White Matter, Gray Matter, Cerebrospinal fluid and abnormal tissue like tumor part from MR images automatically. It comprises of pre-processing step, using wrapping based curvelet transform to remove noise and modified spatial fuzzy C-Means algorithm (Liu et al. in Tsinghua Sci Technol 19(6):578–595, 2014; Kwak and Choi in IEEE Trans Neural Netw 13(1):143–159, 2014) segments normal tissues by considering spatial information. The neighboring pixels are highly correlated and construct initial membership matrix randomly. The process is also intended to segment the tumor cells as well as the removal of background noises for smoothening the region, results in presenting segmented tissues and parameter evaluation to produce the algorithm efficiency.

Dental X-ray Image Segmentation using Gaussian Kernel-Based in Conditional Spatial Fuzzy C-means

Dental X-ray image segmentation is a difficult task because of intensity inhomogeneities among various regions, low image quality due to noise and low contrast errors of data scanning. In this paper, we proposed a new conditional spatial fuzzy C-means algorithm with Gaussian kernel function to facilitate dental X-ray image segmentation. The Gaussian kernel function is used as an objective function of conditional spatial fuzzy C-means algorithm to substitute the Euclidian distance. Performance evaluation of the proposed algorithm was carried on dental X-ray from different teeth of some panoramic radiographs. The average of false negative fraction (FNF) and false positive fraction (TPF) values using proposed algorithm better than conditional spatial fuzzy C-means algorithm but vise versa for true positive volume fraction (FPF) value. The segmentation result of the proposed algorithm effectively recognizes tooth region as main part of the dental X-ray image.

Automatic Abdominal Aortic Aneurysm segmentation in MR images

Abdominal Aortic Aneurism is a disease related to a weakening in the aortic wall that can cause a break in the aorta and the death. The detection of an unusual dilatation of a section of the aorta is an indicative of this disease. However, it is difficult to diagnose because it is necessary image diagnosis using computed tomography or magnetic resonance. An automatic diagnosis system would allow to analyze abdominal magnetic resonance images and to warn doctors if any anomaly is detected. We focus our research in magnetic resonance images because of the absence of ionizing radiation. Although there are proposals to identify this disease in magnetic resonance images, they need an intervention from clinicians to be precise and some of them are computationally hard. In this paper we develop a novel approach to analyze magnetic resonance abdominal images and detect the lumen and the aortic wall. The method combines different algorithms in two stages to improve the detection and the segmentation so it can be applied to similar problems with other type of images or structures. In a first stage, we use a spatial fuzzy C-means algorithm with morphological image analysis to detect and segment the lumen; and subsequently, in a second stage, we apply a graph cut algorithm to segment the aortic wall. The obtained results in the analyzed images are pretty successful obtaining an average of 79% of overlapping between the automatic segmentation provided by our method and the aortic wall identified by a medical specialist. The main impact of the proposed method is that it works in a completely automatic way with a low computational cost, which is of great significance for any expert and intelligent system.

Identification of Contour Lines from Average-Quality Scanned Topographic Maps

Contour line is the main linear feature on topographic maps. Extraction of contour lines is tedious and time-consuming process, but is still an interesting problem. This paper presents a novel method for extracting contour lines from average-quality scanned topographic maps. First, it uses spatial fuzzyc-means algorithm (sFCM) to solve color aliasing and false color problems by taking into consideration both color and spatial information of topographic maps during color segmentation. In order to improve the categorizing rate, upper and lower cut-sets are introduced into sFCM. Second, to deal with the problem of thick lines, node segments are removed before gaps are repaired. Third, different methods are used to repair contour lines gaps according to the causes, which improves the break points matching accuracy. The performance of the method is tested on several topographic maps comparing with other methods, and the results show that the method can avoid misleading results caused by distortion and wrong branches at intersecting regions when using thinning algorithms and have more accurate and higher quality extraction results.

Multi-parametric (ADC/PWI/T2-w) image fusion approach for accurate semi-automatic segmentation of tumorous regions in glioblastoma multiforme

Glioblastoma multiforme (GBM) brain tumor is heterogeneous in nature, so its quantification depends on how to accurately segment different parts of the tumor, i.e. viable tumor, edema and necrosis. This procedure becomes more effective when metabolic and functional information, provided by physiological magnetic resonance (MR) imaging modalities, like diffusion-weighted-imaging (DWI) and perfusion-weighted-imaging (PWI), is incorporated with the anatomical magnetic resonance imaging (MRI). In this preliminary tumor quantification work, the idea is to characterize different regions of GBM tumors in an MRI-based semi-automatic multi-parametric approach to achieve more accurate characterization of pathogenic regions. For this purpose, three MR sequences, namely T2-weighted imaging (anatomical MR imaging), PWI and DWI of thirteen GBM patients, were acquired. To enhance the delineation of the boundaries of each pathogenic region (peri-tumoral edema, viable tumor and necrosis), the spatial fuzzy C-means algorithm is combined with the region growing method. The results show that exploiting the multi-parametric approach along with the proposed semi-automatic segmentation method can differentiate various tumorous regions with over 80% sensitivity, specificity and dice score. The proposed MRI-based multi-parametric segmentation approach has the potential to accurately segment tumorous regions, leading to an efficient design of the pre-surgical treatment planning.

Spatial fuzzy c-means algorithm with adaptive fuzzy exponent selection for robust vermilion border detection in healthy and diseased lower lips

IntroductionAccurate lip contour identification is demanding since variations in color, form and surface texture, even in normal lips, introduce artifacts in non-adapted segmentation algorithms. Herein, a method for vermilion border detection and quantification in healthy and diseased lower lips is presented. AimTo quantify the morphological irregularities of lower lip border, to validate its discriminative power in solar cheilosis diagnosis and to provide supportive tools toward, cost effective, non invasive, disease monitoring. MaterialsSegmentation algorithm for lower lip border was based on spatial fuzzy c-means clustering algorithm with adaptive selection of fuzzy exponent m. Lip features measuring morphological lip border deviations were estimated. The method of lip border extraction and quantitative description was evaluated in a gold standard set of 25 young volunteers without onset of lip diseases. Quantitative descriptors were evaluated in terms of correct classification rates in differentiating 30 healthy control cases from 41 patients with solar cheilosis and were further applied to quantify the therapeutic outcome after immunocryosurgery in eight patients with solar cheilosis. ResultsAdaptive estimation of fuzzy exponent m substantially boosted the segmentation quality in gold standard cases yielding quite smooth lip contours and uniformly low values of lip irregularity features. Discriminant analysis highlighted the distance between the extracted and modeled vermilion border as a feature with excellent diagnostic accuracy (sensitivity and specificity 98% and 93% respectively). Results on patients with solar cheilosis followed up after treatment with immunocryosurgery showed that proposed quantitative lip marker was able to trace the improvement of disease after treatment. ConclusionCorrect lip border recognition is the prerequisite for extracting essential morphological descriptors from lips with epithelial diseases like solar cheilosis. In this paper we presented an efficient method for the automatic identification and quantitative description of lower lip vermilion border morphology in health and disease using digital photography and image analysis techniques.

Hybrid Methods of Spatial Credibilistic Clustering and Particle Swarm Optimization in High Noise Image Segmentation

information from the original image as compared with crisp or hard segmentation methods. In practice, noisy images (even high noise images) are very co mmon. It's very essential and critical to deal with such images to process real-image segmentation and pattern recognition. In this paper, differences of credibilistic clustering algorithm (CCA) and fuzzy c-means algorithm (FCM) in dealing with noisy images are studied and the research shows that in most cases, CCA performs better than FCM in high noise image segmentation. Based on that, a new kind of fuzzy clustering methods is presented. It combines spatial credibilistic clustering algorithm (SCCA) with particle swarm optimization (PSO) and takes full advantages of them. The advantages that come from CCA in noise image segmentation also help in SCCA, and the imposition of spatial information enlarges the advantage. The addition of PSO helps to improve global search performance; thereby the novel methods overcome the drawback of single clustering methods - local optimal solutions. Computational experiments show that the proposed methods give the best segmentation results when compared with FCM, CCA, spatial fuzzy c-means algorithm (SFCM), SCCA and the PSO incorporated versions of FCM, CCA, and SFCM.