Deep learning-guided attenuation correction in the image domain for myocardial perfusion SPECT imaging

Mostafapour Samaneh,Gholamiankhah Faeze,Maroufpour Sirwan,Momennezhad Mehdi,Asadinezhad Mohsen,Zakavi Seyed Rasoul,Arabi Hossein,Zaidi Habib 한국CDE학회 2022 Journal of computational design and engineering Vol.9 No.2

We investigate the accuracy of direct attenuation correction (AC) in the image domain for myocardial perfusion SPECT (single-photon emission computed tomography) imaging (MPI-SPECT) using residual (ResNet) and UNet deep convolutional neural networks. MPI-SPECT 99mTc-sestamibi images of 99 patients were retrospectively included. UNet and ResNet networks were trained using non-attenuation-corrected SPECT images as input, whereas CT-based attenuation-corrected (CT-AC) SPECT images served as reference. Chang’s calculated AC approach considering a uniform attenuation coefficient within the body contour was also implemented. Clinical and quantitative evaluations of the proposed methods were performed considering SPECT CT-AC images of 19 subjects (external validation set) as reference. Image-derived metrics, including the voxel-wise mean error (ME), mean absolute error, relative error, structural similarity index (SSI), and peak signal-to-noise ratio, as well as clinical relevant indices, such as total perfusion deficit (TPD), were utilized. Overall, AC SPECT images generated using the deep learning networks exhibited good agreement with SPECT CT-AC images, substantially outperforming Chang’s method. The ResNet and UNet models resulted in an ME of −6.99 ± 16.72 and −4.41 ± 11.8 and an SSI of 0.99 ± 0.04 and 0.98 ± 0.05, respectively. Chang’s approach led to ME and SSI of 25.52 ± 33.98 and 0.93 ± 0.09, respectively. Similarly, the clinical evaluation revealed a mean TPD of 12.78 ± 9.22% and 12.57 ± 8.93% for ResNet and UNet models, respectively, compared to 12.84 ± 8.63% obtained from SPECT CT-AC images. Conversely, Chang’s approach led to a mean TPD of 16.68 ± 11.24%. The deep learning AC methods have the potential to achieve reliable AC in MPI-SPECT imaging.

Providing a Model of Effective Factors to Successful Acceptance of Social CRM in Banks of Iran

Mojtaba Mostafapour,Seyed Abdolah Heydariyeh 대한산업공학회 2018 Industrial Engineeering & Management Systems Vol.17 No.4

Social Customer Relationship Management (SCRM) in social media is considered as a new generation of CustomerRelationship Management (CRM) in organizations, in such a way that organizations are trying to make infrastructureto use this strategy as a new means of interaction with customers. In this study, several conceptual models proposedby researchers were examined in the field of technology acceptance and with regards to theories like TAM and TRAin this field, a localized model in SCRM technology acceptance in banks of Iran was provided. In this regard, two exogenousfactors of WEB2.0 and endogenous factors were examined as the factors influencing adoption of this technologyin 30 Iranian banks using filed studies and questionnaires. The questionnaires were filled in marketing andinformation technology departments of the banks by 128 chief administrates of these departments. In order to test themodel, we used of structural equation model by using SMART PLS and SPSS software. Confirming the model in theform of a measurement and structural model with GOF =. 421 fitted at the desire level. The results of the study provideda model suitable for SCRM technology acceptance in banking industry in Iran.

Adsorption of Bisphenol A Using Dried Rice Husk: Equilibrium, Kinetic and Thermodynamic Studies

Balarak, Davoud,Mostafapour, Ferdos Kord,Lee, Seung Mok,Jeon, Choong The Korean Society of Industrial and Engineering C 2019 공업화학 Vol.30 No.3

The adsorption of bisphenol A from an aqueous solution onto dried rice husk was investigated. Batch adsorption experiments were performed as a function of the pH, contact time, bisphenol A concentration, adsorbent dose and temperature. The concentration of Bisphenol A was measured by HPLC. The results showed that bisphenol A removal was highest at a solution pH value of 3, adsorbent dose of 4 g/L, and contact time of 75 min. The bisphenol A removal percentage decreased from 99.1 to 66.7%, when the bisphenol A concentration increased from 10 to 200 mg/L. The Langmuir isotherm and pseudo-second order kinetics provided the best fit for the experimental data. Thermodynamic parameters such as ${\Delta}G^0$, ${\Delta}H^0$ and ${\Delta}S^0$ were also evaluated and it was found that the sorption process was feasible, spontaneous and exothermic in nature. Overall, the studied absorbent can be used as an effective and low cost material to treat the industrial wastewater and aqueous solution containing phenolic compounds.

Channel Fading Effect Analysis on Diffusion Cooperation Strategies over Adaptive Networks

( Jie Yang ),( Ehsan Mostafapour ),( Amir Aminfar ),( Jie Wang ),( Hao Huang ),( Afsaneh Akhbari ),( C. Ghobadi ),( Guan Gui ) 한국인터넷정보학회 2019 KSII Transactions on Internet and Information Syst Vol.13 No.1

In this paper, we investigate the performance of the diffusion adaptation strategies for parameter estimation in wireless adaptive networks, where the nodes exchange information over noisy and fading wireless channels. This paper shows the differences between the effect of Rayleigh and Rician fading over wireless adaptive networks and proves that the Rician fading is a more practical model in such kinds of networks. Simulation results imply that the effect of Rayleigh fading is more degrading for the estimation process than Rician fading. Also, the simulation results show the performance of adapt then combine (ATC) diffusion algorithm is better than the combine then adapt (CTA) algorithm by merely considering noise in wireless channels. While the performance of CTA prevails ATC over the wireless adaptive network in the presence of noise plus channel fading.

Adsorption of Bisphenol A Using Dried Rice Husk: Equilibrium, Kinetic and Thermodynamic Studies

( Davoud Balarak ),( Ferdos Kord Mostafapour ),( Seung Mok Lee ),( Choong Jeon ) 한국공업화학회 2019 공업화학 Vol.30 No.3

The adsorption of bisphenol A from an aqueous solution onto dried rice husk was investigated. Batch adsorption experiments were performed as a function of the pH, contact time, bisphenol A concentration, adsorbent dose and temperature. The concentration of Bisphenol A was measured by HPLC. The results showed that bisphenol A removal was highest at a solution pH value of 3, adsorbent dose of 4 g/L, and contact time of 75 min. The bisphenol A removal percentage decreased from 99.1 to 66.7%, when the bisphenol A concentration increased from 10 to 200 mg/L. The Langmuir isotherm and pseudo-second order kinetics provided the best fit for the experimental data. Thermodynamic parameters such as △G⁰, △H⁰ and △S⁰ were also evaluated and it was found that the sorption process was feasible, spontaneous and exothermic in nature. Overall, the studied absorbent can be used as an effective and low cost material to treat the industrial wastewater and aqueous solution containing phenolic compounds.

Effect of heat treatment and number of passes on the microstructure and mechanical properties of friction stir processed AZ91C magnesium alloy

M. Dadashpour,R. Yeşildal,A. Mostafapour,V. Rezazade 대한기계학회 2016 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.30 No.2

In this paper, the effect of heat treatment and number of passes on microstructure and mechanical properties of friction stir processed AZ91C magnesium alloy samples were investigated. From six samples of as-cast AZ91C magnesium alloy, three plates were pre-heated at temperature of 375°C for 3 hours, and then were treated at temperature of 415 °C for 18 hours and finally were cooled down in air. Three plates were relinquished without heat treatment. 8 mm thick as-cast AZ91C magnesium alloy plates were friction stir processed at constant traverse speed of 40 mm/min and tool rotation speed of 1250 rpm. After process, microstructural characterization of samples was analyzed using optical microscopy and tensile and Vickers hardness tests were performed. It was found that heat treated samples had finer grains, higher hardness, improved tensile strength and elongation relative to non-heat treated ones. As the number of passes increased, higher UTS and TE were achieved due to finer grains and more dissolution of β phase (Mg 17 Al 12 ). The micro-hardness characteristics and tensile improvement of the friction stir processed samples depend significantly on grain size, removal of voids and porosities and dissolution of β phase in the stir zone.

Antiproliferative Evaluation and Apoptosis Induction in MCF-7 Cells by Ziziphus spina christi Leaf Extracts

Farmani, Fatemeh,Moein, Mahmoodreza,Amanzadeh, Amir,Kandelous, Hirsa Mostafapour,Ehsanpour, Zahra,Salimi, Mona Asian Pacific Journal of Cancer Prevention 2016 Asian Pacific journal of cancer prevention Vol.17 No.1

Background: Herbal medicine has becoming a potential source of treatment for different types of cancer including breast cancer. It has been shown that plants from the family Rhamnaceae possess anticancer activity. Objective: In this study, we determined the antiproliferative influence of Ziziphus spina christi- a species from this family- on the MCF-7 (human breast adenocarcinoma) cell line. Materials and Methods: The cytotoxicity of the total extract, ethanol, ethanol-aqueous (1:1) as well as aqueous fractions of Ziziphus spina christi leaves was evaluated through MTT assay against MCF-7 cell line. Cell cycle inhibition and apoptosis induction were assessed by flowcytometry cycle RNase/PI analysis and Annexin V-FLUOS, respectively. Apoptosis was also analyzed by immunoblotting assay. Results: Our results indicated that the ethanolic fraction had the lowest $IC_{50}$ value (0.02 mg/ml), induced cell cycle arrest at the G1/S phase as well as apoptosis after a 48h of treatment. Conclusions: This is the first report on anticancer effect of Ziziphus spina christi ethanolic fraction on breast cancer cells, providing a scientific basis for its utility in traditional medicine. However, further in-depth studies are needed to confirm the precise mechanisms.

Non-stationary Sparse Fading Channel Estimation for Next Generation Mobile Systems

( Saadat Dehgan ),( Changiz Ghobadi ),( Javad Nourinia ),( Jie Yang ),( Guan Gui ),( Ehsan Mostafapour ) 한국인터넷정보학회 2018 KSII Transactions on Internet and Information Syst Vol.12 No.3

In this paper the problem of massive multiple input multiple output (MIMO) channel estimation with sparsity aware adaptive algorithms for 5^th generation mobile systems is investigated. These channels are shown to be non-stationary along with being sparse. Non-stationarity is a feature that implies channel taps change with time. Up until now most of the adaptive algorithms that have been presented for channel estimation, have only considered sparsity and very few of them have been tested in non-stationary conditions. Therefore we investigate the performance of several newly proposed sparsity aware algorithms in these conditions and finally propose an enhanced version of RZA-LMS/F algorithm with variable threshold namely VT-RZA-LMS/F. The results show that this algorithm has better performance than all other algorithms for the next generation channel estimation problems, especially when the non-stationarity gets high. Overall, in this paper for the first time, we estimate a non-stationary Rayleigh fading channel with sparsity aware algorithms and show that by increasing non-stationarity, the estimation performance declines.