Search published articles


Showing 7 results for Computer
Computer- Aided diagnosis system for the evaluation of chronic obstructive pulmonary disease on CT Images
Parsa Hosseini M, Soltanian-Zadeh H, Akhlaghpoor Sh,
Volume 68, Issue 12 (3-2011)
Abstract
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.
Methods: 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.
Results: 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.
Conclusion: 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.


Investigation of the molecular relationship between breast cancer and obesity by candidate gene prioritization methods
Saba Garshasbi , Dariush Salimi , Abbas Doosti ,
Volume 73, Issue 7 (10-2015)
Abstract

Background: Cancer and obesity are two major public health concerns. More than 12 million cases of cancer are reported annually. Many reports confirmed obesity as a risk factor for cancer. The molecular relationship between obesity and breast cancer has not been clear yet. The purpose of this study was to investigate priorities of effective genes in the molecular relationship between obesity and breast cancer. Methods: In this study, computer simulation method was used for prioritizing the genes that involved in the molecular links between obesity and breast cancer in laboratory of systems biology and bioinformatics (LBB), Tehran University, Tehran, Iran, from March to July 2014. In this study, ENDEAVOUR software was used for prioritizing the genes and integrating multiple data sources was used for data analysis. Training genes were selected from effective genes in obesity and/or breast cancer. Two groups of candidate genes were selected. The first group was included the existential genes in 5 common region chromosomes (between obesity and breast cancer) and the second group was included the results of genes microarray data analysis of research Creighton, et al (In 2012 on patients with breast cancer). The microarray data were analyzed with GER2 software (R online software on GEO website). Finally, both training and candidate genes were entered in ENDEAVOUR software package. Results: The candidate genes were prioritized to four style and five genes in ten of the first priorities were repeated twice. In other word, the outcome of prioritizing of 72 genes (Product of microarray data analysis) and genes of 5 common chromosome regions (Between obesity and breast cancer) showed, 5 genes (TNFRSF10B, F2, IGFALS, NTRK3 and HSP90B1) were the priorities in the molecular connection between obesity and breast cancer. Conclusion: There are some common genes between breast cancer and obesity. So, molecular relationship is confirmed. In this study the possible effect of gene F2 polymorphism in making breast cancer associated with obesity risk factor was confirmed, the fact that past studies have not been reported.


Effective feature selection of clinical and genetic to predict warfarin dose using artificial neural network
Mohammad Karim Sohrabi , Alireza Tajik ,
Volume 73, Issue 12 (3-2016)
Abstract

Background: Warfarin is one of the most common oral anticoagulant, which role is to prevent the clots. The dose of this medicine is very important because changes can be dangerous for patients. Diagnosis is difficult for physicians because increase and decrease in use of warfarin is so dangerous for patients. Identifying the clinical and genetic features involved in determining dose could be useful to predict using data mining techniques. The aim of this paper is to provide a convenient way to select the clinical and genetic features to determine the dose of warfarin using artificial neural networks (ANN) and evaluate it in order to predict the dose patients.

Methods: This experimental study, was investigate from April to May 2014 on 552 patients in Tehran Heart Center Hospital (THC) candidates for warfarin anticoagulant therapy within the international normalized ratio (INR) therapeutic target. Factors affecting the dose include clinical characteristics and genetic extracted, and different methods of feature selection based on genetic algorithm and particle swarm optimization (PSO) and evaluation function neural networks in MATLAB (MathWorks, MA, USA), were performed.

Results: Between algorithms used, particle swarm optimization algorithm accuracy was more appropriate, for the mean square error (MSE), root mean square error (RMSE) and mean absolute error (MAE) were 0.0262, 0.1621 and 0.1164, respectively.

Conclusion: In this article, the most important characteristics were identified using methods of feature selection and the stable dose had been predicted based on artificial neural networks. The output is acceptable and with less features, it is possible to achieve the prediction warfarin dose accurately. Since the prescribed dose for the patients is important, the output of the obtained model can be used as a decision support system.


A patient-specific study of blood flow in a cerebral aneurysm using medical images
Reza Abdollahi , Bahman Vahidi , Mohammad Karimi ,
Volume 77, Issue 9 (12-2019)
Abstract
Background: Cerebral aneurysm disease causes intracranial hemorrhage by rupturing, which can eventually, lead to organ failure or death. For this reason, it is important to anticipate the reasons for rupturing of a cerebral aneurysm from biomechanical point of view. Investigating this disease may even help the physicians to find treatments and predict the patient’s situation. This research was conducted to understand risks of development and rupture of a patient-specific cerebral aneurysm.
Methods: In a computational simulation, fluid-structure interaction method has been used for a patient-specific case. Also, considering the speed of the systole as the initial condition of the problem, the blood fluid domain has been solved in three types of fluid mathematical models (Newtonian, non-Newtonian Carreau, and non-Newtonian power-law). Then, the pressure results on the wall have been transmitted to ANSYS software, version 15.0 (ANSYS Inc., Canonsburg, PA, USA) and the structure has been solved based on three material models (linear elastic, hyperplastic Neo-Hookean and hyperplastic Mooney-Rivlin, with 5 parameters). The study was done in University of Tehran, Iran, from October 2016 to September 2018.
Results: Shear stress, pressure, flow velocity, wall displacement and von-Mises stress have been extracted from the simulations. The average wall displacement of the aneurysm was 1.8 mm. Also, no significant difference was found in the amount of arterial wall displacement, with constant wall material model and different blood models. However, a significant difference has been observed in the case of considering constant blood model and different wall material models in the value of displacement.
Conclusion: With regard to the amount of displacement of the aneurysm wall in this particular patient, with the geometry and location of the specific aneurysm, the brain nerves 3 and 6 were under stress and exposed to damage. The minimum shear stress was in the aneurysm neck, which stimulates the endothelial cells in the area of aneurysm. In addition, the blood model didn’t had a significant effect on the displacement calculations, while the wall material model played a more decisive role.

Non-melanoma skin cancer diagnosis with a convolutional neural network
Ali Ameri,
Volume 78, Issue 4 (7-2020)
Abstract
Background: The most common types of non-melanoma skin cancer are basal cell carcinoma (BCC), and squamous cell carcinoma (SCC). AKIEC -Actinic keratoses (Solar keratoses) and intraepithelial carcinoma (Bowen’s disease)- are common non-invasive precursors of SCC, which may progress to invasive SCC, if left untreated. Due to the importance of early detection in cancer treatment, this study aimed to propose a computer-based model for identification non-melanoma malignancies.
Methods: In this analytic study, 327 AKIEC, 513 BCC, and 840 benign keratosis images from human against machine with 10000 training dermoscopy images (HAM10000) were extracted. From each of these three types, 90% of the images were designated as the training set and the remaining images were considered as the test set. A deep learning convolutional neural network (CNN) was developed for skin cancer detection by using AlexNet (Krizhevsky, et al., 2012) as a pretrained network. First, the model was trained on the training images to discriminate between benign and malignant lesions. In comparison with conventional methods, the main advantage of the proposed approach is that it does not need cumbersome and time-consuming procedures of lesion segmentation and feature extraction. This is because CNNs have the capability of learning useful features from the raw images. Once the system was trained, it was validated with test data to assess the performance. Study was carried out at Shahid Beheshti University of Medical Sciences, Tehran, Iran, in January and February, 2020.
Results: The proposed deep learning network achieved an AUC (area under the ROC curve) of 0.97. Using a confidence score threshold of 0.5, a classification accuracy of 90% was attained in the classification of images into malignant and benign lesions. Moreover, a sensitivity of 94% and specificity of 86% were obtained. It should be noted that the user can change the threshold to adjust the model performance based on preference. For example, reducing the threshold increase sensitivity while decreasing specificity.
Conclusion: The results highlight the efficacy of deep learning models in detecting non-melanoma skin cancer. This approach can be employed in computer-aided detection systems to assist dermatologists in identification of malignant lesions.
 

Comparison of disability score estimation in multiple sclerosis patients with artificial neural network and decision tree models
Mansour Rezaei , Daryush Afshari, Negin Fakhri, Nazanin Razazian,
Volume 79, Issue 4 (7-2021)
Abstract
Background: Multiple Sclerosis (MS) is one of the most debilitating disease among young adults. Understanding the disability score (Expanded Disability Status Scale (EDSS)) of these patients is helpful in choosing their treatment process. Calculating EDSS takes a lot of time for Neurologists, so having a way to estimate EDSS can be helpful. This study aimed to estimate the EDSS score of MS patients using statistical models including Artificial Neural Network (ANN) and Decision Tree (DT) models.
Methods: This cross-sectional study was performed on MS registry study data of Kermanshah province from April 2017 to November 2018. From the total data available in the registry system, The 12 variables including demographic information, information about MS disease and their EDSS score were extracted. EDSS scores were also estimated using ANN and DT models. The performance of the models was compared in terms of estimation error, correlation and mean of an estimated score. Data were analyzed using Weka software version 3.9.2 and SPSS software version 25 with a significance level of 0.05.
Results: In this study, 353 people were studied. The mean age of the patients was 36.47±9.1 years, the mean age of onset was 9.2±30.34 years, the mean duration of the disease was 6.20±5.7 years and the mean EDSS score was 2.46±1.8. Estimation errors in the DT model were lower than in the ANN model. The real EDSS score was significantly correlated with scores estimated by DT (r=0.571) and ANN (r=0.623). The mean EDSS estimated by the DT model (2.46±1.1) was not significantly different from the real EDSS mean (P=0.621) but the mean EDSS estimated by the ANN model (2.87±1.3) was significantly higher than the real EDSS mean. (P<0.05).
Conclusion: The DT model could better estimate the EDSS score of MS patients than the ANN model and made predictions that were closer to the actual EDSS scores. Therefore, the DT model can accurately estimate the EDSS score of MS patients.

Deep learning approach for motor imagery EEG signal classification
Faezeh Moghadas, Zahra Amini, Rahele Kafieh,
Volume 80, Issue 10 (1-2023)
Abstract
Background: Brain-computer interface systems provide the possibility of communicating with the outside world without using physiological mediators for people with physical disabilities through brain signals. A popular type of BCIs is the motor imagery-based systems and one of the most important parts in the design of these systems is the classification of brain signals into different motor imagery classes in order to transform them into control commands. In this paper, a new method of brain signal classifying based on deep learning methods is presented.
Methods: This cross-sectional study was conducted at Isfahan University of Medical Sciences, School of Advanced Technologies in Medicine, from February 2020 to June 2022. In the pre-processing block, segmentation of brain signals, selection of suitable channels and filtering by Butterworth filter have been done; then data has transformed to the time-frequency domain by three different kinds of mother wavelets including Cmor, Mexicanhat, and Cgaus. In the classification step, two types of convolutional neural networks (one-dimensional and two-dimensional) were applied whereas each one of them was utilized in two different architectures. Finally, the performance of the networks has been investigated by each one of these three types of input data.
Results: Three channels were selected as the best ones for nine subjects. To separate 8-30 Hz, a 5th degree Butterworth filter was used. After finding the optimal parameters in the proposed networks, wavelet transform with Cgauss mother wavelet has the highest percentage in the both proposed architectures. Two-dimensional convolutional neural network has higher convergence speed, higher accuracy and more complexity of calculations. In terms of accuracy, precision, sensitivity and F1-score, two-dimensional convolutional neural network has performed better than one-dimensional convolutional neural network. The accuracy of 92.53%, which is obtained from the second architecture, as the best result, is reported.
Conclusion: The results obtained from the proposed network indicate that suitable, and well-designed deep learning networks can be utilized as an accurate tool for data classification in application of motion perception.

Page 1 from 1     

© 2024 , Tehran University of Medical Sciences, CC BY-NC 4.0

Designed & Developed by : Yektaweb