فهرست مطالب

Medical Signals and Sensors - Volume:8 Issue: 4, Oct-Dec 2018

Journal of Medical Signals and Sensors
Volume:8 Issue: 4, Oct-Dec 2018

  • تاریخ انتشار: 1397/08/28
  • تعداد عناوین: 8
|
  • Seyed Vahab Shojaedini *, Sajedeh Morabbi, MohammadReza Keyvanpour Pages 205-214
    Background
    P300 signal detection is an essential problem in many fields of Brain-ComputerInterface (BCI) systems. Although deep neural networks have almost ubiquitously used in P300detection, in such networks, increasing the number of dimensions leads to growth ratio of saddlepoints to local minimums. This phenomenon results in slow convergence in deep neural network.Hyperparameter tuning is one of the approaches in deep learning, which leads to fast convergencebecause of its ability to find better local minimums. In this paper, a new adaptive hyperparametertuning method is proposed to improve training of Convolutional Neural Networks (CNNs).
    Methods
    The aim of this paper is to introduce a novel method to improve the performance of deep neuralnetworks in P300 signal detection. To reach this purpose, the proposed method transferred thenon-convex error function of CNN) into Lagranging paradigm, then, Newton and dual active settechniques are utilized for hyperparameter tuning in order to minimize error of objective function inhigh dimensional space of CNN.
    Results
    The proposed method was implemented on MATLAB 2017package and its performance was evaluated on dataset of Ecole Polytechnique Fédérale de Lausanne(EPFL) BCI group. The obtained results depicted that the proposed method detected the P300 signalswith 95.34% classification accuracy in parallel with high True Positive Rate (i.e., 92.9%) and lowFalse Positive Rate (i.e., 0.77%).
    Conclusions
    To estimate the performance of the proposed method,the achieved results were compared with the results of Naive Hyperparameter (NHP) tuning method.The comparisons depicted the superiority of the proposed method against its alternative, in such waythat the best accuracy by using the proposed method was 6.44%, better than the accuracy of thealternative method.
  • Saba Ajami, Amin Mahnam *, Samane Behtaj, Vahid Abootalebi Pages 215-224
    Background
    Brain‑computer interfaces (BCIs) based on steady‑state visual evoked potentials(SSVEPs) provide high rates of accuracy and information transfer rate, but need user’s attentionto flickering visual stimuli. This quickly leads to eye‑fatigue when the flickering frequency isin the low‑frequency range. High‑frequency flickering stimuli (>30 Hz) have been proposedwith significantly lower eye‑fatigue. However, SSVEP responses in this frequency range areremarkably weaker, leading to doubts about usability of high‑frequency stimuli to develop efficientBCI systems. The purpose of this study was to evaluate if a practical SSVEP Speller can bedeveloped with Repetitive Visual Stimuli in the high‑frequency range.
    Methods
    An asynchronoushigh‑frequency (35–40 Hz) speller for typing in Persian language was developed using five flickeringvisual stimuli. Least absolute shrinkage and selection operator algorithm with two user‑calibratedthresholds was used to detect the user’s selections. A total of 14 volunteers evaluated the system inan ordinary office environment to type 9 sentences consist of 81 characters with a multistage virtualkeyboard.
    Results
    Despite very high performance of 6.9 chars/min overall typing speed, averageaccuracy of 98.3%, and information transfer rate of 64.9 bpm for eight of the participants, the othersix participants had serious difficulty in spelling with the system and could not complete the typingexperiment.
    Conclusions
    The results of this study in accordance with some previous studies suggestthat high rate of illiteracy in high‑frequency SSVEP‑based BCI systems may be a major burden fortheir practical application.
  • Sahar Sadeghi, Ali Maleki * Pages 225-230
    Background
    The empirical mode decomposition (EMD) is a technique to analyze the steady‑statevisual evoked potential (SSVEP) which decomposes the signal into its intrinsic mode functions(IMFs). Although for the limited stimulation frequency range, choosing the effective IMF leadsto good results, but extending this range will seriously challenge the method so that even thecombination of IMFs is associated with error.
    Methods
    Stimulation frequencies ranged from 6 to16 Hz with an interval of 0.5 Hz were generated using Psychophysics toolbox of MATLAB. SSVEPsignal was recorded from six subjects. The EMD was used to extract the effective IMFs. Twofeatures, including the frequency related to the peak of spectrum and normalized local energy in thisfrequency, were extracted for each of six conditions (each IMF, the combination of two consecutiveIMFs and the combination of all three IMFs).
    Results
    The instantaneous frequency histogram andthe recognition accuracy diagram indicate that for wide stimulation frequency range, not only oneIMF, but also the combination of IMFs does not have desirable efficiency. Total recognition accuracyof the proposed method was 79.75%, while the highest results obtained from the EMD‑fast Fouriertransform (FFT) and the CCA were 72.05% and 77.31%, respectively.
    Conclusion
    The proposedmethod has improved the recognition rate more than 2.4% and 7.7% compared to the CCA andEMD‑FFT, respectively, by providing the solution for situations with wide stimulation frequencyrange.
  • Vida Kabiri Rahani, Alireza Vard *, Mostafa Najafi Pages 231-237
    Background
    Claustrophobia or fear of closed spaces is the most common of phobias that istypically categorized as an anxiety disorder. Different methods have been proposed for treatmentof phobias that one of the most recent and successful of these methods is applying virtualreality (VR) technology and simulating computer‑generated environment. In this regard, thepurpose of this research is design and development of a software game called “ClaustrophobiaGame” for treatment of claustrophobia using VR.
    Methods
    In the Claustrophobia Game project,two closed spaces, including an elevator and a magnetic resonance imaging (MRI) device,were designed and implemented in the form of a VR computer game. To design this game,environments and scenario of the game were prepared in collaboration with a psychiatrist expert.Implementation of the software game was developed in the unity three‑dimensional (3D) gameengine and the programming of it was done by the C# language. In addition, a personal computerand the Oculus Rift VR glasses were utilized for running and testing the Claustrophobia Game.
    Results
    To evaluate, we tested the game by 33 participants (14 men, 19 women, averageage 24.6 years). In this regard, the Claustrophobia Game was considered from two aspects:psychology and playability using two questionnaires. Statistical analysis of the obtained databy the Excel software showed that all playability factors were “good” performance. In addition,the mean of obvious anxiety was decreased after playing the game.
    Conclusion
    The promisingresults demonstrate that the game has an appropriate performance and can help to treat theClaustrophobia.
  • Zeinab Momeni *, Mohammad Bagher Tavakoli, Maryam Atarod Pages 238-243
    Background

    The purpose of this study was to estimate the secondary cancer risk of thyroidin standard radiotherapy methods which are commonly used for breast cancer patients.

    Methods

    A total of 64 breast cancer patients (their age range was around 50 years old) whoreferred to Seyed‑Al‑Shohada hospital (Isfahan, Iran) were included in this study. The radiotherapyof the mentioned patients was performed using 6‑MV photon beams. Dose measurements were alsodone using thermoluminescent dosimeters. Calculation of the risk of developing secondary cancer inthyroid was done using the Biological Effects of Ionizing Radiation Committee VII and recommendedquantity of the International Radiation Protection Commission, excess relative risk.

    Results

    Themean radiation dose to thyroid for the tangential beams, tangential field with supraclavicular (SC)field, and also a tangential field with SC field in modified radical mastectomy (MRM) were0.883 ± 0.472, 1.512 ± 0.365, and 1.587 ± 0.37, respectively. The risk of developing secondarythyroid cancer over a period of 5 years after breast cancer therapy in the tangential, tangential witha SC field, and also tangential beam with SC field in MRM were 9.974 ± 4.318, 17.891 ± 0.365,and 18.783 ± 4.384, respectively. The mean of the measured thyroid doses in patients treated withtangent fields was significantly lower than the patients under the irradiation of the tangent fields withSC field (P < 0.001).

    Conclusions

    Using radiation protection equipment is suggested for breastcancer patients who treated with the studied radiotherapy methods.

  • Mansour Zabihzadeh *, Mohammad Momen Gharibvand, Azim Motamedfar, Morteza Tahmasebi, Amir Hossein Sina, Kavous Bahrami, Mozafar Naserpour Pages 244-252
    Background
    Noninvasive quantification of liver fat by gradient echo (GRE) technique is aninteresting issue in quantitative magnetic resonance imaging. In this study, the fat content in patientswith nonalcoholic fatty liver disease (NAFLD) was quantified with GRE sequences with differentT1 and T2* weighting.
    Methods
    This prospective, cross‑sectional study was performed on thirtyNAFLD patients. Sixteen GRE sequences with different T1 weighting were performed with four echotimes. In each sequence, repetition time (TR) or flip angle was changed and other parameters werefixed. Forty‑eight fat indexes (FIs) from 16 sequences were calculated based on three methods. Todetermine the relationship between FIs and histological findings, Pearson’s correlation coefficientwas used at the level of 1% significance.
    Results
    Mean FIs which obtained from Eq. 3 have themaximum values in comparison to other FIs. The maximum FI was 23.58%, which related to heavilyT1 weighted sequence obtained with method 3. The minimum FI was −2.49%, which related to theminimal T1 weighted obtained with method 2. FIs increase with a flip angle, especially at low flipangles. Increase the TR parameter decrease the FIs gradually. Calculated FIs with methods 1 and 3stronger correlated with histological findings relative to calculated FIs with method 2.
    Conclusion
    For fat quantification, T1 relaxation effects probably more critical than T2*. Flip angle parametercould be a major factor causing the overestimation of liver fat content. Sequences with low flipangle are more suitable for fat quantification with methods 1 and 3. In fat quantification with GREtechniques, it is possible that the third and fourth echoes are unnecessary.
  • Mohammad Javad Keikhai Farzaneh *, Shahrokh Nasseri, Mehdi Momennezhad, Roham Salek Pages 253-262
    Background
    Deep inspiration breath‑hold (DIBH) is known as a radiotherapy method for thetreatment of patients with left‑sided breast cancer. In this method, patient is under exposureonly while he/she is at the end of a deep inspiration cycle and holds his/her breath. In thissituation, the volume of the lung tissue is enhanced and the heart tissue is pushed away from thetreating breast. Therefore, heart dose of these patients, using DIBH, experiences a considerabledecline compared to free breathing treatment. There are a few commercialized systems forimplementation of DIBH in invasive or noninvasive manners.
    Methods
    We present a novelconstructed noninvasive DIBH device relied on a manufacturing near‑field laser distance meter.This in‑house constructed system is composed of a CD22‑100AM122 laser sensor combinedwith a data acquisition system for monitoring the breathing curve. Qt Creator (a cross‑platformJavaScript, QML, and C++‑integrated development environment that is part of the SDK fordevelopment of the Qt Graphical User Interface application framework) and Keil MDK‑ARM (aprogramming software where users can write in C and C++ and assemble for ARM‑basedmicrocontrollers) are used for composing computer and microcontroller programs, respectively.
    Results
    This system could be mounted in treatment or computed tomography (CT) roomat suitable cost; it is also easy to use and needs a little training for personnel and patients.The system can assess the location of chest wall or abdomen in real time with high precisionand frequency. The performance of CD22‑100AM122 demonstrates promise for respiratorymonitoring for its fast sampling rate as well as high precision. It can also deliver reasonablespatial and temporal accuracy. The patient observes his/her breathing waveform through a 7”1024 × 600 liquid crystal display and gets some instructions during treatment and CT sessionsby an exploited algorithm called “interaction scenario” in this study. The system is alsononinvasive and well sustainable for patients.
    Conclusions
    The constructed system has truereal‑time operation and is rapid enough for delivering clear contiguous monitoring. In addition,in this system, we have provided an interaction scenario option between patient and CT or Linacoperator. In addition, the constructed system has the capability of sending triggers for turningon and off CT or Linac facilities. In this concern, the system has the superiority of combining aplenty of characteristics.
  • Maryam Samieinasab *, Zahra Amini Pages 263-264
    The Annual Congress in the School ofAdvanced Technologies in Medicine (ATiM)is the main event of the department thattakes place during wintertime each year.This congress offers a unique opportunityfor presenting research and finding outwhat colleagues are doing in the fields ofBiomedical Engineering. In addition, thiscongress provides a friendly and sociablecontext to meet colleagues from otherdepartments and to formulate joint researchprojects. Participants included universityprofessors, industrialists, students, andresearchers in this field.