فهرست مطالب

Journal of Medical Signals and Sensors
Volume:5 Issue: 1, Jan-Mar 2015

  • تاریخ انتشار: 1393/12/01
  • تعداد عناوین: 8
|
  • Jalil Rasekhi, Mohammad Reza Karami Mollaei, Mojtaba Bandarabadi, Cesar A. Teixeira, Antonio Dourado Pages 1-11
    Bivariate features, obtained from multichannel electroencephalogram (EEG) recordings, quantify the relation between different brain regions. Studies based on bivariate features have shown optimistic results for tackling epileptic seizure prediction problem in patients suffering from refractory epilepsy. A new bivariate approach using univariate features is proposed here. Differences and ratios of 22 linear univariate features were calculated using pairwise combination of 6 EEG channels, to create 330 differential, and 330 relative features. The feature subsets were classified using support vector machines separately, as one of the two classes of preictal and nonpreictal. Furthermore, minimum Redundancy Maximum Relevance feature reduction method is employed to improve the predictions and reduce the number of false alarms. The studies were carried out on features obtained from 10 patients. For reduced subset of 30 features and using differential approach, the seizures were on average predicted in 60.9% of the cases (28 out of 46 in 737.9 h of test data), with a low false prediction rate of 0.11 h−1. Results of bivariate approaches were compared with those achieved from original linear univariate features, extracted from 6 channels. The advantage of proposed bivariate features is the smaller number of false predictions in comparison to the original 22 univariate features. In addition, reduction in feature dimension could provide a less complex and the more cost‑effective algorithm. Results indicate that applying machine learning methods on a multidimensional feature space resulting from relative/differential pairwise combination of 22 univariate features could predict seizure onsets with high performance.
  • Zahra Assarzadeh, Ahmad Reza Naghsh Nilchi Pages 12-20
    In this paper, a chaotic particle swarm optimization with mutation-based classifier particle swarm optimization is proposed to classifypatterns of different classes in the feature space. The introduced mutation operators and chaotic sequences allows us to overcomethe problem of early convergence into a local minima associated with particle swarm optimization algorithms. That is, the mutationoperator sharpens the convergence and it tunes the best possible solution. Furthermore, to remove the irrelevant data and reduce thedimensionality of medical datasets, a feature selection approach using binary version of the proposed particle swarm optimization isintroduced. In order to demonstrate the effectiveness of our proposed classifier, mutation-based classifier particle swarm optimization,it is checked out with three sets of data classifications namely, Wisconsin diagnostic breast cancer, Wisconsin breast cancer and heartstatlog,with different feature vector dimensions. The proposed algorithm is compared with different classifier algorithms includingk-nearest neighbor, as a conventional classifier, particle swarm-classifier, genetic algorithm, and Imperialist competitive algorithmclassifier,as more sophisticated ones. The performance of each classifier was evaluated by calculating the accuracy, sensitivity,specificity and Matthews’s correlation coefficient. The experimental results show that the mutation-based classifier particle swarmptimization unequivocally performs better than all the compared algorithms.
  • Mehri Owjimehr, Habibollah Danyali, Mohammad Sadegh Helfroush Pages 21-29
    Ultrasound imaging is a popular and noninvasive tool frequently used in the diagnoses of liver diseases. A system to characterize normal,fatty and heterogeneous liver, using textural analysis of liver Ultrasound images, is proposed in this paper. The proposed approach isable to select the optimum regions of interest of the liver images. These optimum regions of interests are analyzed by two level waveletpacket transform to extract some statistical features, namely, median, standard deviation, and interquartile range. Discriminationbetween heterogeneous, fatty and normal livers is performed in a hierarchical approach in the classification stage. This stage, first,classifies focal and diffused livers and then distinguishes between fatty and normal ones. Support vector machine and k‑nearestneighbor classifiers have been used to classify the images into three groups, and their performance is compared. The Support vectormachine classifier outperformed the compared classifier, attaining an overall accuracy of 97.9%, with a sensitivity of 100%, 100%and 95.1% for the heterogeneous, fatty and normal class, respectively. The Acc obtained by the proposed computer‑aided diagnosticsystem is quite promising and suggests that the proposed system can be used in a clinical environment to support radiologists andexperts in liver diseases interpretation.
  • Hamidreza Abbaspour, Seyyed Mohammad Razavi, Nasser Mehrshad Pages 30-39
    Over the years, the feasibility of using Electrocardiogram (ECG) signal for human identification issue has been investigated, andsome methods have been suggested. In this research, a new effective intelligent feature selection method from ECG signals hasbeen proposed. This method is developed in such a way that it is able to select important features that are necessary for identificationusing analysis of the ECG signals. For this purpose, after ECG signal preprocessing, its characterizing features were extracted andthen compressed using the cosine transform. The more effective features in the identification, among the characterizing features, areselected using a combination of the genetic algorithm and artificial neural networks. The proposed method was tested on three publicECG databases, namely, MIT‑BIH Arrhythmias Database, MITBIH Normal Sinus Rhythm Database and The European ST‑T Database,in order to evaluate the proposed subject identification method on normal ECG signals as well as ECG signals with arrhythmias.Identification rates of 99.89% and 99.84% and 99.99% are obtained for these databases respectively. The proposed algorithm exhibitsremarkable identification accuracies not only with normal ECG signals, but also in the presence of various arrhythmias. Simulationresults showed that the proposed method despite the low number of selected features has a high performance in identification task.
  • Seyed Hossein Rasta, Mahsa Eisazadeh Partovi, Hadi Seyedarabi, Alireza Javadzadeh Pages 40-48
    To investigate the effect of preprocessing techniques including contrast enhancement and illumination correction on retinal imagequality, a comparative study was carried out. We studied and implemented a few illumination correction and contrast enhancementtechniques on color retinal images to find out the best technique for optimum image enhancement. To compare and choose thebest illumination correction technique we analyzed the corrected red and green components of color retinal images statistically andvisually. The two contrast enhancement techniques were analyzed using a vessel segmentation algorithm by calculating the sensitivityand specificity. The statistical evaluation of the illumination correction techniques were carried out by calculating the coefficients ofvariation. The dividing method using the median filter to estimate background illumination showed the lowest Coefficients of variationsin the red component. The quotient and homomorphic filtering methods after the dividing method presented good results basedon their low Coefficients of variations. The contrast limited adaptive histogram equalization increased the sensitivity of the vesselsegmentation algorithm up to 5% in the same amount of accuracy. The contrast limited adaptive histogram equalization techniquehas a higher sensitivity than the polynomial transformation operator as a contrast enhancement technique for vessel segmentation.Three techniques including the dividing method using the median filter to estimate background, quotient based and homomorphicfiltering were found as the effective illumination correction techniques based on a statistical evaluation. Applying the local contrastnhancement technique, such as CLAHE, for fundus images presented good potentials in enhancing the vasculature segmentation.
  • Morteza Moradi Amin, Saeed Kermani, Ardeshir Talebi Pages 49-57
    Acute lymphoblastic leukemia is the most common form of pediatric cancer which is categorized into three L1, L2, and L3 and could bedetected through screening of blood and bone marrow smears by pathologists. Due to being time‑consuming and tediousness of theprocedure, a computer‑based system is acquired for convenient detection of Acute lymphoblastic leukemia. Microscopic images areacquired from blood and bone marrow smears of patients with Acute lymphoblastic leukemia and normal cases. After applying imagepreprocessing, cells nuclei are segmented by k‑means algorithm. Then geometric and statistical features are extracted from nuclei andfinally these cells are classified to cancerous and noncancerous cells by means of support vector machine classifier with 10‑fold crossvalidation. These cells are also classified into their sub‑types by multi‑Support vector machine classifier. Classifier is evaluated by theseparameters: Sensitivity, specificity, and accuracy which values for cancerous and noncancerous cells 98%, 95%, and 97%, respectively.These parameters are also used for evaluation of cell sub‑types which values in mean 84.3%, 97.3%, and 95.6%, respectively. Theresults show that proposed algorithm could achieve an acceptable performance for the diagnosis of Acute lymphoblastic leukemia ands sub‑types and can be used as an assistant diagnostic tool for pathologists.
  • Fatemeh Shahsavari Alavijeh, Homayoun Mahdavi, Nasab Pages 59-67
    Chest radiography is a common diagnostic imaging test, which contains an enormous amount of information about a patient. However,its interpretation is highly challenging. The accuracy of the diagnostic process is greatly influenced by image processing algorithms;hence enhancement of the images is indispensable in order to improve visibility of the details. This paper aims at improving radiographparameters such as contrast, sharpness, noise level, and brightness to enhance chest radiographs, making use of a triangulation method.Here, contrast limited adaptive histogram equalization technique and noise suppression are simultaneously performed in waveletdomain in a new scheme, followed by morphological top‑hat and bottom‑hat filtering. A unique implementation of morphological filtersallows for adjustment of the image brightness and significant enhancement of the contrast. The proposed method is tested on chestradiographs from Japanese Society of Radiological Technology database. The results are compared with conventional enhancementtechniques such as histogram equalization, contrast limited adaptive histogram equalization, Retinex, and some recently proposedmethods to show its strengths. The experimental results reveal that the proposed method can remarkably improve the image contrastwhile keeping the sensitive chest tissue information so that radiologists might have a more precise interpretation.
  • Masoud Moslehi, Ahmad Shanei, Seyyed Mohammad Reza Hakimian, Milad Baradaran, Ghahfarokhi, Golshan Mahmoudi Pages 69-73
    Sentinel lymph node is the first regional lymph node that drains the lymph from the primary tumor. It is potentially the first nodeto receive the seeding of lymph‑borne metastatic cells. This study aimed to discuss lymphoscintigraphy procedural guidelines fordetection of sentinel node using Tc‑Phytate in Isfahan, Iran. Moreover, the preliminary results of the first year’s clinical experience oflymphoscintigraphy in Isfahan, Iran are also presented. A total of 36 consecutive sentinel node procedures were performed followingour protocol in March 2013 to March 2014. For all 36 patients, after intradermal injection of 0.5–1 mCi of 99mTc‑Phytate, 5, 30 and120 min with hands up lymphoscintigraphy was performed. All procedures were performed in a 1‑day setting with Tc‑Phytate injectionin intradermal volume of about 0.1 cc. At 5, 30 and 120 min after injection, anterior and lateral images (4 min), were acquired usinggamma‑camera (energy 140 keV, window 15–20% and LEHR collimator). For all patients, at least one axillary sentinel lymph nodewas detected. For three patients, 2 SNs were seen. The images 5 min after injection showed at least one axillary sentinel node in 18 of36 patients. However for the remaining patients, more delayed images (after 30 and 120 min) were needed. Although, no changes wereseen in 120 min images compared to 30 min images. Considering the used protocol, from the evaluated data it can be concluded thatlymphoscintigraphy after 30 min periareolar injection of about 0.5–1 mCi Tc‑Phytate in an intradermal volume of about 0.1 cc yieldsan axillary sentinel node in all the patients. Imaging 120 min after injection is of no additional value and can be omitted.99m