فهرست مطالب
Journal of Medical Signals and Sensors
Volume:10 Issue: 2, Apr-Jun 2020
- تاریخ انتشار: 1399/02/16
- تعداد عناوین: 8
-
-
Pages 69-75Background
Pulmonary movements during radiation therapy can cause damage to healthy tissues. It is necessary to adapt treatment planning based on tumor motion to avoid damage to healthy tissues. A range of approaches has been proposed to monitor the issue. A treatment planning based on fourdimensional computed tomography (4D CT) images can be addressed as one of the most achievable options. Although several methods proposed to predict pulmonary movements based on mathematical algorithms, the use of deep artificial neural networks has recently been considered.
MethodsIn the current study, convolutional long shortterm memory networks are applied to predict and generate images throughout the breathing cycle. A total of 3295 CT images of six patients in three different views was considered as reference images. The proposed method was evaluated in six experiments based on a leaveonepatientout method similar to crossvalidation.
ResultsThe weighted average results of the experiments in terms of the rootmeansquared error and structural similarity index measure are 9 × 10^−3 and 0.943, respectively.
ConclusionUtilizing the proposed method, because of its generative nature, which results in the generation of CT images during the breathing cycle, improves the radiotherapy treatment planning in the lack of access to 4D CT images.
Keywords: Convolutional long short‑term memory, deep neural network, lung motion, radiotherapy, respiratory motion prediction -
Forming Optimal Projection Images from Intra-Retinal Layers Using Curvelet-Based Image Fusion MethodPages 76-85Background
Image fusion is the process of combining the information of several input images into one image. Projection images obtained from three‑dimensional (3D) optical coherence tomography (OCT) can show inlier retinal pathology and abnormalities that are not visible in conventional fundus images. In recent years, the projection image is often made by an average on all retina that causes to lose many intraretinal details.
MethodsIn this study, we focus on the formation of optimum projection images from retinal layers using Curvelet‑based image fusion. The latter consists of three main steps. In the earlier studies, macular spectral 3D data using diffusion map‑based OCT were segmented into 12 different boundaries identifying 11 retinal layers in three dimensions. In the second step, projection images are attained using conducting some statistical methods on the space between each pair of boundaries. In the next step, retinal layers are merged using Curvelet transform to make the final projection images.
ResultsThese images contain integrated retinal depth information as well as an ideal opportunity to better extract retinal features such as vessels and the macula region. Finally, qualitative and quantitative evaluations show the superiority of this method to the average‑based and wavelet‑based fusion methods. Overall, our method obtains the best results for image fusion in all terms such as entropy (6.7744) and AG (9.5491).
ConclusionCreating an image with more and detailed information made by the Curvelet-based image fusion has significantly higher contrast. There are also many thin veins in Curvelet-based fused image, which are absent in average-based and wavelet-based fused images
Keywords: Curvelet transform, image fusion, optical coherence tomography, projection image, retina -
Pages 86-93Background
In this paper, a novel approach is proposed for the recognition of Persian phonemes in the Persian consonant‑vowel combination (PCVC) speech dataset. Nowadays, deep neural networks (NNs) play a crucial role in classification tasks. However, the best results in speech recognition are not yet as perfect as human recognition rate. Deep learning techniques show outstanding performance over many other classification tasks, such as image classification and document classification. Furthermore, the performance is sometimes better than a human. The reason why automatic speech recognition systems are not as qualified as the human speech recognition system, mostly depends on features of data which are fed to deep NNs.
MethodsIn this research, first, the sound samples are cut for the exact extraction of phoneme sounds in 50 ms samples. Then, phonemes are divided into 30 groups, containing 23 consonants, 6 vowels, and a silence phoneme.
ResultsThe short‑time Fourier transform is conducted on them, and the results are given to PPNet (a new deep convolutional NN architecture) classifier and a total average of 75.87% accuracy is reached which is the best result ever compared to other algorithms on separated Persian phonemes (like in PCVC speech dataset).
ConclusionThis method not only can be used for recognizing mono‑phonemes but it can also be adopted as an input to the selection of the best words in speech transcription
Keywords: Persian consonant‑vowel combination, Persian, PPNet, speech recognition, short‑timeFourier transform -
Pages 94-104Background
How to explore the dynamics of transition probabilities between phases of budding yeast cell cycle (BYCC) network based on the dynamics of protein activities that control this network? How to identify the robust structure of protein interactions of BYCC Boolean network (BN)? Budding yeast allows scientists to put experiments into effect in order to discover the intracellular cell cycle regulating structures which are well simulated by mathematical modeling.
MethodsWe extended an available deterministic BN of proteins responsible for the cell cycle to a Markov chain model containing apoptosis besides G1, S, G2, M, and stationary G1. Using genetic algorithm (GA), we estimated the kinetic parameters of the extended BN model so that the subsequent transition probabilities derived using Markov chain model of cell states as normal cell cycle becomes the maximum while the structure of chemical interactions of extended BN of cell cycle becomes more stable.
ResultsUsing kinetic parameters optimized by GA, the probability of the subsequent transitions between cell cycle phases is maximized. The relative basin size of stationary G1 increased from 86% to 96.48% while the number of attractors decreased from 7 in the original model to 5 in the extended one. Hence, an increase in the robustness of the system has been achieved.
ConclusionThe structure of interacting proteins in cell cycle network affects its robustness and probabilities of transitions between different cell cycle phases. Markov chain and BN are good approaches to study the stability and dynamics of the cell cycle network.
Keywords: Boolean network, budding yeast cell cycle, genetic algorithm, Markov chain model -
Pages 105-112Background
For a new biomaterial which is going to be applied in bone tissue regeneration, bioactivity (bone bonding ability) and desirable mechanical properties are very essential parameters to take into consideration. In the present study, the gehlenite's mechanical properties and bioactivity are assessed and compared with hydroxyapatite (HA) for bone tissue regeneration.
MethodGehlenite and HA nanoparticles are synthesized through sol–gel method and coprecipitation technique, respectively, and their physical and chemical properties are characterized through X‑ray diffraction, Fourier transform infrared spectroscopy, and transmission electron microscopy.
ResultsThe results prove that the gehlenite and HA phases without any undesirable phase are obtained, and the particles of both compounds are in the nanometer range with spherical morphology. The compressive strength of both compounds are assessed, and the values for gehlenite and HA disks are 144 ± 5 and 150 ± 4.8 MPa, respectively. Next, their bioactivity potential is assessed into simulated body fluid (SBF) up to 21 days, and the results show that after 14 days, gehlenite disk’s surface is completely covered with newly formed Ca‑P particles. However, some sporadic precipitations after 21 days soaking into SBF are formed onto the HA disk’s surface.
ConclusionThis comparative study shows that nanostructured gehlenite disk with desirable mechanical properties and faster bioactivity kinetic than HA can be considered as a promising bioceramic for bone tissue regeneration.
Keywords: Bioactivity, gehlenite, hydroxyapatite, mechanical properties -
Pages 113-118Background
Nowadays, the use of radiopharmaceuticals in medicine is unavoidable. Depending on the distribution of the radiopharmaceutical in the cells, the nucleus absorbed dose changes by the variations in their geometry size. Therefore, this study aims to investigate the S‑value by the variation of nucleus size using Geant4 toolkit.
MethodsTwo spherical cells with a variety of nucleus size have been considered as the cancerous cell. Monoenergetic electrons ranging from 5 to 300 keV are distributed uniformly. The S‑value for four target‑source components (including Nucleus←Cytoplasm, Nucleus←Cell surface, Nucleus←Nucleus, and Nucleus←Nucleus surface) is computed and plotted. Then, the obtained data are compared with analytical Medical Internal Radiation Dose (MIRD) data.
ResultsIn Nucleus←Cytoplasm compartment for electrons below 10 keV, obtained S‑values show a slight decrease for the nucleus in the radii of around half of the cell radius and then S‑values increase with the increase in the nucleus radii. In the S‑value of Nucleus←Cell surface, for all electron energy levels, a slight decrease observed with the increase of nucleus radii. For Nucleus←Nucleus and Nucleus←Nucleus surface cases, with an increase in the size of the cell nucleus, a sharp reduction in the S‑values is detected.
ConclusionIt can be concluded that for the beta emitters with low‑energy radiation (<40 keV), the S‑value is heavily dependent on the nucleus size which may affect the treatment of small tumors. While for the beta emitters with higher‑energy radiation (>100 keV), the size of the nucleus is not very noticeable in the induced S‑value
Keywords: Beta‑emitting radiopharmaceutical, Geant4‑DNA, nuclear medicine, S‑value -
Pages 119-124Background
In diffuse optical tomography, determining the optimal angle between the source and detector is an effective method to reduce the number of projections while maintaining the quality of the reconstructed images. In this study, a new parameter is introduced to evaluate the source‑detector geometries.
MethodsA two‑dimensional mesh with the radius of 20 mm and 7987 nodes were built. In each reconstruction, 0.5 mm heterogeneity with the absorption coefficient of 0.06 mm−1 and the dispersion coefficient of 0.6 mm−1 was added in different parts of the sample randomly. The relationship between the mean square error (MSE), sensitivity Laplacian ratio (SLR), and sensitivity standard deviation ratio (SSR) was evaluated based on their correlation coefficients. The quality of the images achieved using the optimized projections were compared with that of the full projections for the same depths.
ResultsMSE decreases by increasing the SLR magnitudes which indicate that the parameter could be used to evaluate the scanning geometries. There was a negative correlation coefficient (R = −0.76) with the inverse relationship between the SLR and MSE indices. SSR does not have a significant relationship with the quality of the reconstructed images. For each scanning depth, the comparison of the images obtained using the full and optimized‑selective projections did not show any considerable difference despite the decrease of the projection numbers in scanning geometry with the optimized‑selective projections.
ConclusionThe unnecessary projections could be eliminated by placing the detectors at the specific angles, which were determined using the SLR. Thus, a proper compromise between the quality of the reconstructed images and reconstruction time might establish.
Keywords: Diffuse optical tomography, geometry optimization, sensitivity Laplacian ratio, sensitivity standard deviation ratio, source‑detector angle -
Pages 125-133Background
Bioimpedance spectroscopy (BIS) is a device used to measure electrical impedance at frequencies from 0 Hz to 1 MHz. Many clinical diagnosis and fundamental researches, especially in the field of physiology and pathology, rely on this device. The device can be used to estimate human body composition, through the information of total body water, extracellular fluid and intracellular fluid, fat-free mass, and fat mass from its impedance. BIS analysis can provide physiological statuses such as ischemia, pulmonary edema, skin cancer, and intramuscular tumors. BIS is expected to be used even more widely, both for hospital or home-based use, particularly because BIS handy, compact, inexpensive, and less power-consuming with adequately accurate real-time. In previous research, the BIS design was based on the magnitude-ratio and phase-difference detection using the AD8302 gain-phase detector method which resulted in an operating range between 20 kHz and 1 MHz. However, the impedance was obtained from the logarithmic ratio magnitude which caused the device to have limited accuracy at frequencies <20 kHz.
MethodsIn this research, we conduct design and development of a low-cost arduino-based electrical bioimpedance spectrometer.
ResultsThe low-cost bioimpedance spectrometry was successfully developed using AD9850 as the programmable function generator, OPA2134 as the OpAm of voltage-controlled current source, AD620A as the instrument amplifier and AD536A as the alternating current to direct current converter which could work accurately from 0 Hz to 100 kHz.
ConclusionThe multi-frequency bioimpedance device developed in this research has the capability to safely measure the impedance of the human body due to its relatively stable electric current, which is equal to (0.370 ± 0.003) mA with frequencies ranging from 5 to 200 kHz and has an accuracy of over 90% in the frequency range of 10 Hz to 100 kHz.
Keywords: Arduino based, electrical bioimpedance, low‑cost, spectrometer