oalib

OALib Journal期刊

ISSN: 2333-9721

费用:99美元

投稿

时间不限

2017 ( 228 )

2016 ( 268 )

2015 ( 5695 )

2014 ( 7111 )

自定义范围…

匹配条件: “H Soltanian-Zadeh” ,找到相关结果约149711条。
列表显示的所有文章,均可免费获取
第1页/共149711条
每页显示
Computer- Aided diagnosis system for the evaluation of chronic obstructive pulmonary disease on CT Images
Parsa Hosseini M,Soltanian-Zadeh H,Akhlaghpoor Sh
Tehran University Medical Journal , 2011,
Abstract: "n Normal 0 false false false EN-US X-NONE AR-SA MicrosoftInternetExplorer4 /* Style Definitions */ table.MsoNormalTable {mso-style-name:"Table Normal"; mso-tstyle-rowband-size:0; mso-tstyle-colband-size:0; mso-style-noshow:yes; mso-style-priority:99; mso-style-qformat:yes; mso-style-parent:""; mso-padding-alt:0cm 5.4pt 0cm 5.4pt; mso-para-margin:0cm; mso-para-margin-bottom:.0001pt; mso-pagination:widow-orphan; font-size:11.0pt; font-family:"Calibri","sans-serif"; mso-ascii-font-family:Calibri; mso-ascii-theme-font:minor-latin; mso-fareast-font-family:"Times New Roman"; mso-fareast-theme-font:minor-fareast; mso-hansi-font-family:Calibri; mso-hansi-theme-font:minor-latin; mso-bidi-font-family:Arial; mso-bidi-theme-font:minor-bidi;} Background: Chronic Obstructive Pulmonary Disease (COPD) is one of the most prevalent pulmonary diseases. Use of an automatic system for the detection and diagnosis of the disease will be beneficial to the patients' treatment decision-making process. In this paper, we propose a new approach for the Computer Aided Diagnosis (CAD) of the disease and determination of its severity axial CT scan images."n"nMethods: In this study, 24 lung CT scans in full inspiratory and expiratory states were performed. Variations in the normalized pattern of the lungs' external parenchyma were exploited as a feature for COPD diagnosis. Subsequently, a Bayesian classifier was used to classify variations into two normal and abnormal patterns for the discrimination of patients and healthy individuals. Finally, the accuracy of the classification was assessed statistically. "n"nResults: With the proposed method, the lungs parenchymal elasticity and air-trapping were determined quantitatively. The more this feature tended to zero, the more severe air-trapping and obstructive pulmonary disease is. By analyzing CT images in the healthy and patient groups, we calculated the hard threshold for the diagnosis of the disease. Clinical results tested by the mentioned method, suggested the effectiveness of this approach."n"nConclusion: In regard to the challenges of COPD diagnosis, we propose a new computer-aided design which may be helpful to physicians for a more accurate diagnosis of the disease. Moreover, this severity scoring algorithm may be useful for targeted disease management and risk-adjustment.
Designing A New CAD System for Pulmonary Nodule Detection in High Resolution Computed Tomography (HRCT) Images
M Parsa Hosseini,H Soltanian-Zadeh,SH Akhlaghpoor,A Jalali
Tehran University Medical Journal , 2012,
Abstract: Background: Lung diseases and lung cancer are among the most dangerous diseases with high mortality in both men and women. Lung nodules are abnormal pulmonary masses and are among major lung symptoms. A Computer Aided Diagnosis (CAD) system may play an important role in accurate and early detection of lung nodules. This article presents a new CAD system for lung nodule detection from chest computed tomography (CT) images.Methods: Twenty-five adult patients with lung nodules in their CT scan images presented to the National Research Institute of Tuberculosis and Lung Disease, Masih Daneshvari Hospital, Tehran, Iran in 2011-2012 were enrolled in the study. The patients were randomly assigned into two experimental (9 female, 6 male, mean age 43±5.63 yrs) and control (6 female, 4 male, mean age 39±4.91 yrs) groups. A fully-automatic method was developed for detecting lung nodules by employing medical image processing and analysis and statistical pattern recognition algorithms.esults: Using segmentation methods, the lung parenchyma was extracted from 2-D CT images. Then, candidate regions were labeled in pseudo-color images. In the next step, some features of lung nodules were extracted. Finally, an artificial feed forward neural network was used for classification of nodules.Conclusion: Considering the complexity and different shapes of lung nodules and large number of CT images to evaluate, finding lung nodules are difficult and time consuming for physicians and include human error. Experimental results showed the accuracy of the proposed method to be appropriate (P<0.05) for lung nodule detection.
Optimization of Liver Iron Load Assessment by Pixel-Based T2* MRI in Thalassemic Patients  [PDF]
Neda Gholizadeh, Shahram Akhlaghpoor, Hamid Soltanian-Zadeh, Emad Fatemizadeh, Amin Shams Akhtari, Mohammad Nourizadeh, Mohammad Reza Alinaghizadeh
Open Journal of Radiology (OJRad) , 2012, DOI: 10.4236/ojrad.2012.22008
Abstract: Purpose: To improve liver iron load assessment by investigating the precision of different approaches of T2* Measurement. Background: Iron overload is a major problem in the treatment of thalassemic patients. Liver iron concentration (LIC) is an important index toward the management of body iron load. The accuracy of iron load estimation may suffer from the methodology of T2* measurement and there is no complete agreement upon the best approach of T2* calculation. Methods: 32 β-thallasemic patients (18 male) with the mean age of 20.0 ± 6.5 years were involved in this study. A multi-echo fast gradient-echo technique on a 1.5 T MRI system was used to measure liver iron overload and the T2* map of liver was reconstructed on a pixel-by-pixel basis. The T2* map and MRI images were utilized to deter- mine accurate location of ROI (region of interest). The mean of T2* were computed from the ROIs. The reproducibility of calculated T2* values in two methods were obtained. Moreover, the mean of the pixel’s T2* was calculated in the entire liver parenchyma of one slice. The T2* value of the entire slice was compared with the ROI approach. Results: In the ROI based method, the CoV for the intra-observer reproducibility was 8.5% and for the inter-observer was 9.78%. In the pixel based method, the CoVs for intra-observer and inter-observer reproducibility were 2.79% and 3.91%. There was an acceptable correlation (r = 0.96) between the T2* values calculated by the ROI and the entire slice. Conclusions: The pixel-based approach is more precise to determine the appropriate placement of the ROI. The assessment of T2* in the entire slice reduces the user-based errors significantly.
Information Theoretic Hierarchical Clustering
Mehdi Aghagolzadeh,Hamid Soltanian-Zadeh,Babak Nadjar Araabi
Entropy , 2011, DOI: 10.3390/e13020450
Abstract: Hierarchical clustering has been extensively used in practice, where clusters can be assigned and analyzed simultaneously, especially when estimating the number of clusters is challenging. However, due to the conventional proximity measures recruited in these algorithms, they are only capable of detecting mass-shape clusters and encounter problems in identifying complex data structures. Here, we introduce two bottom-up hierarchical approaches that exploit an information theoretic proximity measure to explore the nonlinear boundaries between clusters and extract data structures further than the second order statistics. Experimental results on both artificial and real datasets demonstrate the superiority of the proposed algorithm compared to conventional and information theoretic clustering algorithms reported in the literature, especially in detecting the true number of clusters.
Detection and Severity Scoring of Chronic Obstructive Pulmonary Disease Using Volumetric Analysis of Lung CT Images
Mohammad Parsa Hosseini,Hamid Soltanian-Zadeh,Shahram Akhlaghpoor
Iranian Journal of Radiology , 2012,
Abstract: Background: Chronic obstructive pulmonary disease (COPD) is a devastating disease. While there is no cure for COPD and the lung damage associated with this disease cannot be reversed, it is still very important to diagnose it as early as possible.Objectives: In this paper, we propose a novel method based on the measurement of air trapping in the lungs from CT images to detect COPD and to evaluate its severity.Patients and Methods: Twenty-five patients and twelve normal adults were included in this study. The proposed method found volumetric changes of the lungs from inspiration to expiration. To this end, trachea CT images at full inspiration and expiration were compared and changes in the areas and volumes of the lungs between inspiration and expiration were used to define quantitative measures (features). Using these features, the subjects were classified into two groups of normal and COPD patients using a Bayesian classifier. In addition, t-tests were applied to evaluate discrimination powers of the features for this classification.Results: For the cases studied, the proposed method estimated air trapping in the lungs from CT images without human intervention. Based on the results, a mathematical model was developed to relate variations of lung volumes to the severity of the disease.Conclusions: As a computer aided diagnosis (CAD) system, the proposed method may assist radiologists in the detection of COPD. It quantifies air trapping in the lungs and thus may assist them with the scoring of the disease by quantifying the severity of the disease.
Robust Iris Verification Based on Local and Global Variations
Tajbakhsh Nima,Araabi BabakNadjar,Soltanian-Zadeh Hamid
EURASIP Journal on Advances in Signal Processing , 2010,
Abstract: This work addresses the increasing demand for a sensitive and user-friendly iris based authentication system. We aim at reducing False Rejection Rate (FRR). The primary source of high FRR is the presence of degradation factors in iris texture. To reduce FRR, we propose a feature extraction method robust against such adverse factors. Founded on local and global variations of the texture, this method is designed to particularly cope with blurred and unfocused iris images. Global variations extract a general presentation of texture, while local yet soft variations encode texture details that are minimally reliant on the image quality. Discrete Cosine Transform and wavelet decomposition are used to capture the local and global variations. In the matching phase, a support vector machine fuses similarity values obtained from global and local features. The verification performance of the proposed method is examined and compared on CASIA Ver.1 and UBIRIS databases. Efficiency of the method contending with degraded images of the UBIRIS is corroborated by experimental results where a significant decrease in FRR is observed in comparison with other algorithms. The experiments on CASIA show that despite neglecting detailed texture information, our method still provides results comparable to those of recent methods.
Robust Iris Verification Based on Local and Global Variations
Nima Tajbakhsh,Babak Nadjar Araabi,Hamid Soltanian-Zadeh
EURASIP Journal on Advances in Signal Processing , 2010, DOI: 10.1155/2010/979058
Abstract: This work addresses the increasing demand for a sensitive and user-friendly iris based authentication system. We aim at reducing False Rejection Rate (FRR). The primary source of high FRR is the presence of degradation factors in iris texture. To reduce FRR, we propose a feature extraction method robust against such adverse factors. Founded on local and global variations of the texture, this method is designed to particularly cope with blurred and unfocused iris images. Global variations extract a general presentation of texture, while local yet soft variations encode texture details that are minimally reliant on the image quality. Discrete Cosine Transform and wavelet decomposition are used to capture the local and global variations. In the matching phase, a support vector machine fuses similarity values obtained from global and local features. The verification performance of the proposed method is examined and compared on CASIA Ver.1 and UBIRIS databases. Efficiency of the method contending with degraded images of the UBIRIS is corroborated by experimental results where a significant decrease in FRR is observed in comparison with other algorithms. The experiments on CASIA show that despite neglecting detailed texture information, our method still provides results comparable to those of recent methods.
Pigment Melanin: Pattern for Iris Recognition
Mahdi S. Hosseini,Babak N. Araabi,Hamid Soltanian-Zadeh
Computer Science , 2009,
Abstract: Recognition of iris based on Visible Light (VL) imaging is a difficult problem because of the light reflection from the cornea. Nonetheless, pigment melanin provides a rich feature source in VL, unavailable in Near-Infrared (NIR) imaging. This is due to biological spectroscopy of eumelanin, a chemical not stimulated in NIR. In this case, a plausible solution to observe such patterns may be provided by an adaptive procedure using a variational technique on the image histogram. To describe the patterns, a shape analysis method is used to derive feature-code for each subject. An important question is how much the melanin patterns, extracted from VL, are independent of iris texture in NIR. With this question in mind, the present investigation proposes fusion of features extracted from NIR and VL to boost the recognition performance. We have collected our own database (UTIRIS) consisting of both NIR and VL images of 158 eyes of 79 individuals. This investigation demonstrates that the proposed algorithm is highly sensitive to the patterns of cromophores and improves the iris recognition rate.
Neuronal Spike Train Analysis in Likelihood Space
Yousef Salimpour, Hamid Soltanian-Zadeh, Sina Salehi, Nazli Emadi, Mehdi Abouzari
PLOS ONE , 2011, DOI: 10.1371/journal.pone.0021256
Abstract: Background Conventional methods for spike train analysis are predominantly based on the rate function. Additionally, many experiments have utilized a temporal coding mechanism. Several techniques have been used for analyzing these two sources of information separately, but using both sources in a single framework remains a challenging problem. Here, an innovative technique is proposed for spike train analysis that considers both rate and temporal information. Methodology/Principal Findings Point process modeling approach is used to estimate the stimulus conditional distribution, based on observation of repeated trials. The extended Kalman filter is applied for estimation of the parameters in a parametric model. The marked point process strategy is used in order to extend this model from a single neuron to an entire neuronal population. Each spike train is transformed into a binary vector and then projected from the observation space onto the likelihood space. This projection generates a newly structured space that integrates temporal and rate information, thus improving performance of distribution-based classifiers. In this space, the stimulus-specific information is used as a distance metric between two stimuli. To illustrate the advantages of the proposed technique, spiking activity of inferior temporal cortex neurons in the macaque monkey are analyzed in both the observation and likelihood spaces. Based on goodness-of-fit, performance of the estimation method is demonstrated and the results are subsequently compared with the firing rate-based framework. Conclusions/Significance From both rate and temporal information integration and improvement in the neural discrimination of stimuli, it may be concluded that the likelihood space generates a more accurate representation of stimulus space. Further, an understanding of the neuronal mechanism devoted to visual object categorization may be addressed in this framework as well.
Effects of Ferumoxides – Protamine Sulfate Labeling on Immunomodulatory Characteristics of Macrophage-like THP-1 Cells
Branislava Janic, A. S. M. Iskander, Ali M. Rad, Hamid Soltanian-Zadeh, Ali S. Arbab
PLOS ONE , 2008, DOI: 10.1371/journal.pone.0002499
Abstract: Superparamagnetic Iron Oxide (SPIO) complexed with cationic transfection agent is used to label various mammalian cells. Labeled cells can then be utilized as an in vivo magnetic resonance imaging (MRI) probes. However, certain number of in vivo administered labeled cells may be cleared from tissues by the host's macrophages. For successful translation to routine clinical application of SPIO labeling method it is important that this mode of in vivo clearance of iron does not elicit any diverse immunological effects. The purpose of this study was to demonstrate that SPIO agent ferumoxides-protamine sulfate (FePro) incorporation into macrophages does not alter immunological properties of these cells with regard to differentiation, chemotaxis, and ability to respond to the activation stimuli and to modulate T cell response. We used THP-1 cell line as a model for studying macrophage cell type. THP-1 cells were magnetically labeled with FePro, differentiated with 100 nM of phorbol ester, 12-Myristate-13-acetate (TPA) and stimulated with 100 ng/ml of LPS. The results showed 1) FePro labeling had no effect on the changes in morphology and expression of cell surface proteins associated with TPA induced differentiation; 2) FePro labeled cells responded to LPS with slightly higher levels of NFκB pathway activation, as shown by immunobloting; TNF-α secretion and cell surface expression levels of CD54 and CD83 activation markers, under these conditions, were still comparable to the levels observed in non-labeled cells; 3) FePro labeling exhibited differential, chemokine dependent, effect on THP-1 chemotaxis with a decrease in cell directional migration to MCP-1; 4) FePro labeling did not affect the ability of THP-1 cells to down-regulate T cell expression of CD4 and CD8 and to induce T cell proliferation. Our study demonstrated that intracellular incorporation of FePro complexes does not alter overall immunological properties of THP-1 cells. The described experiments provide the model for studying the effects of in vivo clearance of iron particles via incorporation into the host's macrophages that may follow after in vivo application of any type of magnetically labeled mammalian cells. To better mimic the complex in vivo scenario, this model may be further exploited by introducing additional cellular and biological, immunologically relevant, components.
第1页/共149711条
每页显示


Home
Copyright © 2008-2017 Open Access Library. All rights reserved.