Bioautomation

Volume 20, Issue 4
Bioinformatics
Snake Model Based on Improved Genetic Algorithm in Fingerprint Image Segmentation	431-440
Mingying Zhang [ +/- abstract ][ full text ]
Automatic fingerprint identification technology is a quite mature research field in biometric identification technology. As the preprocessing step in fingerprint identification, fingerprint segmentation can improve the accuracy of fingerprint feature extraction, and also reduce the time of fingerprint preprocessing, which has a great significance in improving the performance of the whole system. Based on the analysis of the commonly used methods of fingerprint segmentation, the existing segmentation algorithm is improved in this paper. The snake model is used to segment the fingerprint image. Additionally, it is improved by using the global optimization of the improved genetic algorithm. Experimental results show that the algorithm has obvious advantages both in the speed of image segmentation and in the segmentation effect.
2D- and 3D-QSAR Study of Acyl Homoserine Lactone Derivatives as Potent Inhibitors of Quorum Sensor, SdiA in Salmonella typhimurium	441-456
Gnanendra Shanmugam, Syed Mohamed, Jeyakumar Natarajan [ +/- abstract ][ full text ]
A series of Acyl homoserine lactone derivatives against quorum sensing (QS) enhanced transcriptional regulator SdiA of S. typhimurium were used to establish the physicochemical and structural requirements for the inhibition of QS using 2D- and 3D-QSAR methods. The QSAR model was developed by employing 35 compounds as a training set and the predictive ability was assessed by a test set of 12 compounds. The best 2D-QSAR model for the prediction of SdiA, quorum sensor inhibitory activity has been developed using Multiple Linear Regression method (giving r²=0.8012 and q²=0.657), Principal Component Regression method (giving r²=0.8104 and q²=0.625), and Partial Least Squares Regression method (giving r²=0.8023 and q²=0.648). The best model for 3D-QSAR has been obtained using Comparative Molecular Field Analysis (CoMFA) method, giving r²=0.896 and q²=0.772. The 2D-QSAR results revealed that the most important descriptors for predicting the anti-quorum sensing activity were alignment-independent descriptors and the topology index descriptors. The 3D-QSAR results of CoMFA contour maps impart some important structural features-like electronegative substituent (Br, Cl, F) on lactone ring favors the strong inhibitory activity. These results will be further useful for development of new quorum sensing inhibitors with structural diversity.
Total Variation-based Denoising Model for Bioinformatics Images	457-470
Zhenhua Zhou [ +/- abstract ][ full text ]
The total variation-based denoising model enhancement method for bioinformatics images is introduced at the beginning of this paper, and this model morphologically reconstructs and constrains the regularization items. The model is smoothed with variance in different areas by adding the smooth coefficient, and accordingly the image denoising effect is enhanced. Compared with the traditional image filtration model, the optimized total variation-based model is more distinctive in the field of higher items and lower items. As the simulation experiment shows, the optimized total variation-based model has the better effect in denoising. Lastly, by applying the marked-based watershed segmentation algorithm and the optimized total variation-based image denoising model, the bioinformatics image is segmented.
Blood Cell Segmentation Based on Improved Pulse Coupled Neural Network and Fuzzy Entropy	471-482
Zhanbo Liu, Fang Wang, Shi Yan, Rui Huang [ +/- abstract ][ full text ]
In the field of biomedical image processing, because of the low intensity and brightness of the cell image, and the complex structure of the cell image, the segmentation of cell images is very difficult. A large number of studies have shown that the Pulse Coupled Neural Networks (PCNN) is suitable for image segmentation. However, the traditional PCNN must set a large number of parameters in image segmentation, and the optimal number of iterations cannot be automatically determined. In this paper, a new improved PCNN model is proposed. The work of improved PCNN includes the acceptance portion of the PCNN model being simplified and the connection portion of PCNN being improved. In addition, the maximum fuzzy entropy is used as the criterion to determine the optimal number of iterations. Experimental results on blood cell image segmentation show that this proposed method can automatically determine the number of loop iterations and automatically select the best threshold. It also has the characteristics of fast convergence, high accuracy and good segmentation effect in blood cell image segmentation processing.
Cuckoo Search Algorithm for Model Parameter Identification	483-492
Olympia Roeva, Vassia Atanassova [ +/- abstract ][ full text ]
In this paper, the metaheuristics algorithm Cuckoo Search (CS), is adapted and applied for a model parameter identification of an E. coli fed-batch cultivation process. The dynamics of bacteria growth and substrate (glucose) utilization is described by a system of ordinary nonlinear differential equations. Using real experimental data set from an E. coli MC4110 fed-batch cultivation process a parameter optimization is performed. The simulation results indicate that the applied algorithm is effective and efficient. As a result, a model with high degree of accuracy is obtained applying the CS. The simulation results and comparison with genetic algorithm and ant colony optimization algorithm confirm the effectiveness of the applied CS algorithm in solving a cultivation model parameter identification problem.
Biomedical systems
The Application of Genetic Algorithms in the Biological Medical Diagnostic Research	493-504
Xi Wang [ +/- abstract ][ full text ]
In this paper, a genetic algorithm is used to determine the Mean Corpuscular Volume (MCV) as the optimal decision-making criterion for anemia caused by iron deficiency based on the diagnostic test of patients with such anemia. On the premise of attaining maximum sensitivity and specificity for the cost, this paper studies the impact of the cost ratio of the optimal decision-making criteria and compares the mathematical derivation and binominal model method, so as to discuss the application of the optimal diagnostic criteria in the genetic algorithm and provide a practical study method for the diagnostic test.
Ant Colony Clustering Algorithm and Improved Markov Random Fusion Algorithm in Image Segmentation of Brain Images	505-514
Guohua Zou [ +/- abstract ][ full text ]
New medical imaging technology, such as Computed Tomography and Magnetic Resonance Imaging (MRI), has been widely used in all aspects of medical diagnosis. The purpose of these imaging techniques is to obtain various qualitative and quantitative data of the patient comprehensively and accurately, and provide correct digital information for diagnosis, treatment planning and evaluation after surgery. MR has a good imaging diagnostic advantage for brain diseases. However, as the requirements of the brain image definition and quantitative analysis are always increasing, it is necessary to have better segmentation of MR brain images. The FCM (Fuzzy C-means) algorithm is widely applied in image segmentation, but it has some shortcomings, such as long computation time and poor anti-noise capability. In this paper, firstly, the Ant Colony algorithm is used to determine the cluster centers and the number of FCM algorithm so as to improve its running speed. Then an improved Markov random field model is used to improve the algorithm, so that its antinoise ability can be improved. Experimental results show that the algorithm put forward in this paper has obvious advantages in image segmentation speed and segmentation effect.
Influence Factors of in vitro Culture of Goat Spermatogonial Stem Cells	515-528
Bin Li, Hui Zhang [ +/- abstract ][ full text ]
This study aims to determine the condition factors influencing the in vitro proliferation culture of spermatogonial stem cells (SSCs) through isolation and culture of SSCs. With mouse embryonic fibroblast (MEF) cells, SIM-6-thiogunanie-oualiain (STO) cells and Hela cells used as the feeder layers, we compared the numbers of cell clones treated with mitomycin C as well as the proliferation conditions with and without the treatment with trypsin. In the culture solution, we respectively added serum and vitamin C (of different concentrations, VC) to culture goat SSCs; furthermore, we tested their pro-proliferation effect on goat SSCs and its mechanism. We determined that one-month-old goats were the most suitable for the in vitro culture; 1.5 h, 2.5 h and 2.5 h were respectively the most suitable treatment times in the feeder layers of MEF cells, STO cells and Hela cells; 2.5% was the optimal serum concentration; VC (30 μg/mL) had a promoting effect on the in vitro culture of goat SSCs. We conclude that the age of goats, different feeding layers and their preparation conditions, serum concentrations and VC concentrations are the condition factors influencing the in vitro culture and proliferation of SSCs.
A Short Report. Radiotherapy Treats a Greater Volume than Surgery Using an Axillary Sentinel Node Model	529-534
Timothy Wong, April Wong, Raef Awad, Lauren Haydu, Nicole Dougheney, Gerald Fogarty [ +/- abstract ][ full text ]
Radiotherapy and surgery are local treatments and can be compared in randomized trails. Recent examples have compared axillary radiotherapy to completion lymphadectomy surgery for sentinel lymph node positive breast cancer and have shown radiotherapy was non-inferior in terms of regional control, but was also significantly less morbid. A superficial reading of these studies may miss an important consideration, the volume of the axilla actually being treated by the different modalities. We conducted this study to compare the difference in planned axillary treatment volumes undergoing axillary lymph node dissection as compared to axillary radiotherapy.