Amin Gharipour

Segmentation of cell nuclei in fluorescence microscopy images: An integrated framework using level set segmentation and touching-cell splitting

Abstract Accurate segmentation of cells in fluorescence microscopy images plays a key role in high-throughput applications such as quantification of protein expression and the study of cell function. In this paper, an integrated framework consisting of a new level sets based segmentation algorithm and a touching-cell splitting method is proposed. For cell nuclei segmentation, a new region-based active contour model in a variational level set formulation is developed where our new level set energy functional minimizes the Bayesian classification risk. For touching-cell splitting, the touching cells are first distinguished from non-touching cells, and then a strategy based on the splitting area identification is proposed to obtain splitting point-pairs. To form the appropriate splitting line, the image properties from different information channels are used to define the surface manifold of the image patch around the selected splitting point-pairs and geodesic distance is used to measure the length of the shortest path on the manifold connecting the two splitting points. The performance of the proposed framework is evaluated using a large number of fluorescence microscopy images from four datasets with different cell types. A quantitative comparison is also performed with several existing segmentation approaches.

Feature Selection Using Parallel Genetic Algorithm for the Prediction of Geometric Mean Diameter of Soil Aggregates by Machine Learning Methods

Aggregate stability is a useful soil physical dynamic index of soil resistivity to surface wind and water erosion in all ecosystems, especially, in arid and semi-arid regions. Two machine learning techniques including support vector machines (SVMs) and artificial neural networks (ANNs) were used to develop predictive models for the estimation of geometric mean diameter (GMD) of soil aggregates. An empirical multiple linear regression (MLR) model was also constructed as the benchmark to compare their performances. Furthermore, the influence of feature space dimension reduction using parallel genetic algorithm (PGA) on the prediction accuracy of all investigated techniques was evaluated. The ANN model achieved greater accuracy in GMD prediction as compared to the MLR and SVM models. The obtained ERROR% value in GMD prediction using the ANN model was 6.9%, while it was 15.7 and 10.6% for the MLR and SVM models, respectively. Feature selection using PGA improved the prediction accuracy of all investigated techniques. The coefficient of determination (R2) values between the measured and the predicted GMD values using PGA-based MLR, SVM, and ANN models increased by 20.0, 12.2, and 8.8% in comparison with the proposed MLR, SVM, and ANN models. In conclusion, it appears that the PGA-based ANN model could be considered as an alternative to conventional regression models for the GMD prediction.

Prediction of soil physical properties by optimized support vector machines

Prediction of soil physical properties by optimized support vector machines The potential use of optimized support vector machines with simulated annealing algorithm in developing prediction functions for estimating soil aggregate stability and soil shear strength was evaluated. The predictive capabilities of support vector machines in comparison with traditional regression prediction functions were also studied. In results, the support vector machines achieved greater accuracy in predicting both soil shear strength and soil aggregate stability properties comparing to traditional multiple-linear regression. The coefficient of correlation (R) between the measured and predicted soil shear strength values using the support vector machine model was 0.98 while it was 0.52 using the multiple-linear regression model. Furthermore, a lower mean square error value of 0.06 obtained using the support vector machine model in prediction of soil shear strength as compared to the multiple-linear regression model. The ERROR% value for soil aggregate stability prediction using the multiple-linear regression model was 14.59% while a lower ERROR% value of 4.29% was observed for the support vector machine model. The mean square error values for soil aggregate stability prediction using the multiple-linear regression and support vector machine models were 0.001 and 0.012, respectively. It appears that utilization of optimized support vector machine approach with simulated annealing algorithm in developing soil property prediction functions could be a suitable alternative to commonly used regression methods.

Fuzzy clustering using local and global region information for cell image segmentation

In high-throughput applications, accurate segmentation of biomedical images can be considered as an important step for recognizing cells that have the phenotype of interest. In this paper, while conventional fuzzy clustering is not able to implement the local and global spatial information, a novel spatial fuzzy clustering cell image segmentation algorithm is proposed. The segmentation procedure is divided into two stages: the first stage involves processing the local and global spatial information of the given cell image and a final segmentation stage which is based on the idea of conventional fuzzy clustering. Our idea can be considered as a sequential integration of region based methods and fuzzy clustering for cell image segmentation. Experimental results show that the proposed model yields significantly better performance in comparison with several existing methods.

An integration strategy based on fuzzy clustering and level set method for cell image segmentation

In this study a new image segmentation framework which combines the Fuzzy c means clustering and the level set method is presented. Using this framework, the well-known Chan and Veses level set technique and classical Bayes classifier are employed to obtain a prior membership value for each pixel based on region information. Next, a novel clustering model based on fuzzy c-mean clustering assisted by prior membership values is used to obtain the final segmentation. Experiments performed on high-throughput fluorescence microscopy colon cancer cell images, which are commonly utilized for the study of many normal and neoplastic procedures, indicate a significant improvement in accuracy when compared to several existing techniques.

Colon cell image segmentation based on level set and kernel-based fuzzy clustering

This paper presents an integration framework for image segmentation. The proposed method is based on Fuzzy c-means clustering (FCM) and level set method. In this framework, firstly Chan and Veses level set method (CV) and Bayes classifier based on mixture of density models are utilized to find a prior membership value for each pixel. Then, a supervised kernel based fuzzy c-means clustering (SKFCM) algorithm assisted by prior membership values is developed for final segmentation. The performance of our approach has been evaluated using high-throughput fluorescence microscopy colon cancer cell images, which are commonly used for the study of many normal and neoplastic procedures. The experimental results show the superiority of the proposed clustering algorithm in comparison with several existing techniques.

Association of expression of selenoprotein P in mRNA and protein levels with metabolic syndrome in subjects with cardiovascular disease: Results of the Selenegene study

Selenoprotein P (SeP) is involved in transporting selenium from the liver to target tissues. Because SeP confers protection against disease by reducing chronic oxidative stress, the present study aimed to assess the level of SeP in the serum of patients with metabolic syndrome (MetS) with a history of cardiovascular disease (CVD).

Effects of selenium supplementation on expression of SEPP1 in mRNA and protein levels in subjects with and without metabolic syndrome suffering from coronary artery disease: Selenegene study a double-blind randomized controlled trial

Selenoprotein P (SePP) is involved in the protection against diseases. The present study is the first investigation of the effect of selenium supplementation on plasma selenium and expression of SEPP1 in mRNA and protein levels based on metabolic syndrome (MetS), in individuals suffering from coronary artery diseases. In this clinical trial, 160 patients with angiographically documented stenosis of more than 75% in each vessel were enrolled. Patients received either 200‐mg selenium yeast tablets or placebo tablets orally after a meal, once daily for 60 days. The mRNA and protein levels of the selenium and SePP1 products were determined before and after the study. From the initial 160 participants, 145 subjects (71 MetS‐affected individuals, 74 MetS‐unaffected individuals) enrolled in this study. Comparing the selenium and placebo groups, no significant percentage changes of plasma selenium, △Ct SEPP1, or SePP were shown (P > 0.05). Moreover, beyond a significant difference for the expression of SePP in the selenium group compared to its baseline level (P < 0.05), no other significant differences were revealed for plasma selenium and △Ct SEPP1 after the intervention in either group (P > 0.05). Selenium supplementation did not affect plasma selenium or the mRNA or protein level of SePP in either groups after a 2‐months intervention beyond a significant increase of SePP in the MetS group. This trial suggests that further studies should investigate the long‐term use of selenium supplementation and the effect of a SePP increase on MetS as a potential therapeutic effect.

Bio-Cell Image Segmentation Using Bayes Graph-Cut Model

The accurate segmentation of biomedical images has become increasingly important for recognizing cells that have the phenotype of interest in biomedical applications. In order to improve the conventional deterministic segmentation models, this paper proposes a novel graph-cut cell image segmentation algorithm based on Bayes theorem. There are two segmentation phases in this method. The first phase is an interactive process to specify a preliminary set of regional pixels and the background based on the interactive graph-cut model. In the second phase, final segmentation is calculated based on the idea of Bayes theorem, combining prior information with data. Our idea can be considered an integration of graph-cut methods and Bayes theorem for cell image segmentation. Experimental results show that the proposed model performs better in comparison with several existing methods.

Level Set Based Segmentation of Cell Nucleus in Fluorescence Microscopy Images Using Correntropy-Based K-Means Clustering

Fluorescence microscopy image segmentation is a challenging task in fluorescence microscopy image analysis and high-throughput applications such as protein expression quantification and cell function investigation. In this paper, a novel local level set segmentation algorithm in a variational level set formulation via a correntropy-based k-means clustering (LLCK) is introduced for fluorescence microscopy cell image segmentation. The performance of the proposed method is evaluated using a large number of fluorescence microscopy images. A quantitative comparison is also performed with some state-of-the-art segmentation approaches.