Use of Artificial Neural Networks and PCA to Predict Results of Infertility Treatment in the ICSI Method

Background:

Intracytoplasmic sperm injection (ICSI) or microinjection is one of the most commonly used assisted reproductive technologies (ART) in the treatment of patients with infertility problems. At each stage of this treatment cycle, many dependent and independent variables may affect the results, according to which, estimating the accuracy of fertility rate for physicians will be difficult

Objective:

This study aims to evaluate the efficiency of artificial neural networks (ANN) and principal component analysis (PCA) to predict results of infertility treatment in the ICSI method

Material and Methods:

In the present research that is an analytical study, multilayer perceptron (MLP) artificial neural networks were designed and evaluated to predict results of infertility treatment using the ICSI method. In addition, the PCA method was used before the process of training the neural network for extracting information from data and improving the efficiency of generated models. The network has 11 to 17 inputs and 2 outputs.

Results:

The area under ROC curve (AUC) values were derived from modeling the results of the ICSI technique for the test data and the total data. The AUC for total data vary from 0.7670 to 0.9796 for two neurons, 0.9394 to 0.9990 for three neurons and 0.9540 to 0.9906 for four neurons in hidden layers

Conclusion:

The proposed MLP neural network can model the specialist performance in predicting treatment results with a high degree of accuracy and reliability

Computer-Aided Tinnitus Detection based on Brain Network Analysis of EEG Functional Connectivity

Background

Tinnitus known as a central nervous system disorder is correlated with specific oscillatory activities within auditory and non-auditory brain areas. Several studies in the past few years have revealed that in the most tinnitus cases, the response pattern of neurons in auditory system is changed due to auditory deafferentation, which leads to variation and disruption of the brain networks.

Objective

In this paper, we introduce an approach to automatically distinguish tinnitus individuals from healthy controls based on whole-brain functional connectivity and network analysis.

Material and Methods

The functional connectivity analysis was applied to the resting state electroencephalographic (EEG) data of both groups using Weighted Phase Lag Index (WPLI) for various frequency bands in 2-44 Hz frequency range. In this case- control study, the classification was performed on graph theoretical measures using support vector machine (SVM) as a robust classification method.

Results

Experimental results showed promising classification performance with a high accuracy, sensitivity, and specificity in all frequency bands, specifically in the beta2 frequency band.

Conclusion

The current study provides substantial evidence that tinnitus network can be successfully detected by consistent measures of the brain networks based on EEG functional connectivity.

An Efficient Framework for Accurate Arterial Input Selection in DSC-MRI of Glioma Brain Tumors

INTRODUCTION

Automatic and accurate arterial input function (AIF) selection has an essential role for quantification of cerebral perfusion hemodynamic parameters using dynamic susceptibility contrast magnetic resonance imaging (DSC-MRI). The purpose of this study is to develop an optimal automatic method for arterial input function determination in DSC-MRI of glioma brain tumors by using a new preprocessing method.

MATERIAL AND METHODS

For this study, DSC-MR images of 43 patients with glioma brain tumors were retrieved retrospectively. Our proposed AIF selection framework consisted an effcient pre-processing step, through which non-arterial curves such as tumorous, tissue, noisy and partial-volume affected curves were excluded, followed by AIF selection through agglomerative hierarchical (AH) clustering method. The performance of automatic AIF clustering was compared with manual AIF selection performed by an experienced radiologist, based on curve shape parameters, i.e. maximum peak (MP), full-width-at-half-maximum (FWHM), M (=MP/ (TTP × FWHM)) and root mean square error (RMSE).

RESULTS

Mean values of AIFs shape parameters were compared with those derived from manually selected AIFs by two-tailed paired t-test. The results showed statistically insignificant differences in MP, FWHM, and M parameters and lower RMSE, approving the resemblance of the selected AIF with the gold standard. The intraclass correlation coefficient and coefficients of variation percent showed a better agreement between manual AIF and our proposed AIF selection than previously proposed methods.

CONCLUSION

The results of current work suggest that by using efficient preprocessing steps, the accuracy of automatic AIF selection could be improved and this method appears promising for efficient and accurate clinical applications.

Heart Rate Variability Classification using Support Vector Machine and Genetic Algorithm

BACKGROUND

Electrocardiogram (ECG) is defined as an electrical signal, which represents cardiac activity. Heart rate variability (HRV) as the variation of interval between two consecutive heartbeats represents the balance between the sympathetic and parasympathetic branches of the autonomic nervous system.

OBJECTIVE

In this study, we aimed to evaluate the efficiency of discrete wavelet transform (DWT) based features extracted from HRV which were further selected by genetic algorithm (GA), and were deployed by support vector machine to HRV classification.

MATERIALS AND METHODS

In this paper, 53 ECGs including 3 different beat types (ventricular fibrillation (VF), atrial fibrillation (AF) and also normal sinus rhythm (NSR)), were selected from the MIT/BIH arrhythmia database. The approach contains 4 stages including HRV signal extraction from each ECG signal, feature extraction using DWT (entropy, mean, variance, kurtosis and spectral component β), best features selection by GA and classification of normal and abnormal ECGs using the selected features by support vector machine (SVM).

RESULTS

The performance of the classification procedure employing the combination of selected features were evaluated using several measures including accuracy, sensitivity, specificity and precision which resulted in 97.14%, 97.54%, 96.9% and 97.64%, respectively.

CONCLUSION

A comparative analysis with the related existing methods illustrates the proposed method has a higher potential in the classification of AF and VF. The attempt to classify the ECG signal has been successfully achieved. The proposed method has shown a promising sensitivity of 97.54% which indicates that this technique is an excellent model for computer-aided diagnosis of cardiac arrhythmias.

Analytical study of 226Ra activity concentration in market consuming foodstuffs of Ramsar, Iran

BACKGROUND

Ramsar, a city of Iran located on the coast of the Caspian Sea, has been considered to be enormously important due to its high natural radioactivity levels. People living in High Level Natural Radiation Areas (HLNRAs) have been exposed by several sources, one of which could be foodstuff. However, many studies have been carried out to measure the environmental radioactivity in Ramsar, but no survey has been conducted in all stapled consumed foods yet. This study was dedicated to determine ²²⁶Ra activity concentration in the daily diets of Ramsar residents as a probable exposure.

METHODS

Approximately 70 different market samples were collected during the four seasons based on the daily consumption patterns of residents which have the highest consumption and their availability in the seasons. All samples, after washing, drying and pretreatment, were analyzed for ²²⁶Ra radionuclide determination by α-spectrometry.

RESULTS

The mean radioactivity concentration of ²²⁶Ra ranged between 7 ± 1 mBq Kg^-1 wet weight in meat, and 318 ± 118 mBq Kg^-1 for tea dry leaves. The ²²⁶Ra activity concentrations in collected samples varied from below the minimum detectable activity up to 530 ± 30 mBq Kg^-1. To compare the results with United Nations Scientific Committee on Effects of Atomic Radiation (UNSCEAR) reference values, the ²²⁶Ra activity concentrations concluded from the results appear to be higher in milk, chicken and eggs and less in grain products, vegetables, fruits and fish products. These results indicate that no significant ²²⁶Ra contamination is present in market foodstuffs and provide reference values for the foodstuffs in Ramsar.

CONCLUSIONS

Of the total daily dietary ²²⁶Ra exposure from market consuming foodstuffs for adults in Ramsar, the largest percentage was from wheat. The residents consuming wheat and manufacturing wheat products such as bread, pasta, porridge, crackers, biscuits, pancakes, pies, pastries, cakes, cookies, muffins, rolls, doughnuts, breakfast cereals and so on may receive an elevated dose in the diet. In conclusion, with regards to presence of ²²⁶Ra in foodstuffs it is necessary to monitor regularly the activity of ²²⁶Ra in foodstuffs including market and local foods.

Local-Reference Patient Dose Evaluation in Conventional Radiography Examinations in Mazandaran, Iran

BACKGROUND

The most efficient application of ionizing radiation is serving medical purposes and using this radiation has caused people to learn that artificial sources of radiation exposure among these resources can be of highest exposure rate.

OBIECTIVE

The present study is aimed at initially establishing a baseline for local-reference dose level in Mazandaran, Iran in 12 projections of the most conventional x-ray examination.

METHODS

In this study, 13 public hospitals in Mazandaran province were selected for review and required data collected for ten adult patients with mean weight of 70±10kg in each projection. Then, information of each center was separately analyzed. Next, in order to measure x-ray output tube, the dosimeter RTI model Barracuda calibrated has been applied for measuring air karma within energy rage of 40-150kvp. ESAK and ESD parameters, usually used for monitoring DRL in conventional radiography, were calculated.

RESULTS

Mean ESDs in this study has been obtained to 1.47±0.98 for skull (PA/AP), 1.01±0.79 for skull (LAT), 0.67±0.38 for cervical spine (AP), 0.79±0.37 for cervical (LAT), 0.49±0.38 for chest (PA/AP), 1.06±0.44 for chest (LAT), 2.15±0.73 for thoracic spine (AP), 3±0.87 for thoracic spine (LAT), 2.81 ±0.82 for lumbar spine (AP), 4.28±0.78 for lumbar (LAT), 2.07±1.17 for abdomen and 1.90±0.99 for pelvis, respectively. The ESDs calculated for chest examination in both projections, PA and LAT are more than values recommended by the UK (2000), Brazil and Slovenia.

CONCLUSION

The present study has determined wide variations in radiation dose of x-ray examinations among hospitals in Mazandaran, Iran. In order to reduce skin dose, an optimization procedure should be considered. Application of a reference dose (DRL) could be a practical method for this purpose. The role of optimization of radiography parameters for reducing patient dose is a significant issue. Through optimizing parameters, it would be possible to preserve image quality while reduction of patient dose.

Criteria for patient release according to external dose rate and residual activity in patients treated with 131I-sodium iodide in Iran

External dose rate (ED) and residual activity (RA) of patients treated with (131)I sodium iodide are two main factors, to consider before release of patients. In this study, six nuclear medicine centres out of total seven centres in Iran were selected and measurements have been done on 330 patients. ED of patients was measured by physicists of the centres for 6 months (May-November 2009) at a 1 m distance from the thyroid of each patient on the first, second and third days after administration by a calibrated survey meter. The maximum and minimum values of ED were 21 (SD = 18) and 11 (SD = 4) µSv h(-1), respectively. Furthermore, the maximum and minimum values of RA during release of patient were 720 and 250 MBq, respectively. According to the study, we recommend a release activity limit of 500 MBq (14 mCi) or a dose rate level of 20 µSv h(-1) at 1 m from the patient to be set instead of a release activity limit of 1100 MBq (30 mCi) as it is now for the country.

Evaluation of patient dose in some mammography centres in Iran

High diagnostic sensitivity and specificity while maintaining the least dose to the patient is the ideal mammography. The objective of this work was to evaluate patient dose and image quality of mammograms to propose corrective actions. The image quality for 1242 patient in 7 mammography facilities in Tehran city was evaluated based on selected image quality criteria using a three-point scale. Clinical image quality, the entrance surface air kerma, the average glandular dose and optical density of films for standard PMMA phantom of 4.5 cm thickness were evaluated. The results showed that up to 72 % of mammograms were in good condition to be diagnosed, and only about 3.4 % of the images were unacceptable or with suboptimal quality. The entrance surface air kerma values were in the range of 3.8-10.5 mGy, average glandular dose 0.5-1.8 mGy and optical density of films 0.74-2.03. The image quality evaluation after correction actions, periodic image quality evaluation and using the correct equipment certainly will improve patient dose.

The evaluation of parameters affecting accidents in companies using industrial radioactive sources in Iran

More than 1000 radiation workers are engaged in about 70 private industrial radiography companies (IRCs) using 312 mobile gamma radiography devices (GRDs) in Iran. These companies mainly carry out radiography in open areas using 192Ir radioactive sources, ranging from 0.07 to 3 TBq (2-80 Ci). The radiation accidents that occurred in these companies led to acute radiation syndrome in 13 workers and overexposure of 36 workers since 1998. The facilities and operating procedures of the Iranian private IRCs have been investigated during the past 5 y. According to this study, in spite of the fact that most of the accidents were found to be due to the failure of critical components of GRDs, the main parameters affecting overexposures and deterministic effects were found to be incorrect or there was insufficient implementation of the monitoring programme, training and local rules in the IRCs.