AKAhmad Keshtkar

Ahmad Keshtkar

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Ahmad Keshtkar has a total of 9 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Classification of mastoid air cells by CT scan images using deep learning method

    by Mohammad Khosravi, Yalda Jabbari Moghaddam, Mahdad Esmaeili, Ahmad Keshtkar, Javad Jalili, Hamid Tayefi Nasrabadi

    Purpose: Mastoid abnormalities show different types of ear illnesses, however inadequacy of experts and low accuracy of diagnostic demand a new approach to detect these abnormalities and reduce human mistakes. The manual analysis of mastoid CT scans is time-consuming and labor-intensive. In this paper the first and robust deep learning-based approaches is introduced to diagnose mastoid abnormalities using a large database of CT images obtained in the clinical center with remarkable accuracy.Methods: In this paper, mastoid abnormalities are classified using the Xception based Convolutional Neural Network (CNN) model, with optimizer Adamax into five categories (Complete pneumatized, Opacification in pneumatization, Partial pneumatization, Opacification in partial pneumatization, None pneumatized). For this reason, a total of 24,800 slides of 152 patients were selected that include the mastoid from most upper to the lowest part of the middle ear cavity to complete the construction of the proposed deep neural network model.Results: The proposed model had the best accuracy of 87.80% (based on grader 1) and 88.44% (based on grader 2) on the 20th epoch and 87.70% (based on grader 1) and 87.56% (based on grader 2) on average and also significantly faster than other types of implemented architectures in terms of the computer running time (in seconds). The 99% confidence interval of the average accuracy was 0.012 which means that the true accuracy is 87.80% and 87.56% ± 1.2% that indicates the power of the model.Conclusions: The manual analysis of ear cavity CT scans is often time-consuming and prone to errors due to various inter- or intra operator variability studies. The proposed method can be used to automatically analyze the middle ear cavity to classify mastoid abnormalities, which is markedly faster than most types of models with the highest accuracy.


  • A Robust Machine learning based method to classify normal and abnormal CT scan images of mastoid air cells

    by Mohammad Khosravi, Mahdad Esmaeili, Yalda Jabbari Moghaddam, Ahmad Keshtkar, Javad Jalili, Hamid Tayefi Nasrabadi


  • Comparison of radiation dose to patient and staff for two interventional cardiology units: a phantom study

    by Asghar Mesbahi, Parinaz Mehnati, Ahmad Keshtkar, Naser Aslanabadi

    The purpose of this investigation was to measure the patient and staff dose during routine interventional cardiology procedures for an image intensifier-based and a flat detector system using a water phantom. The Integris BH3000 image intensifier-based (Philips) and the Axiom Artis flat detector-based (Siemens) angiography units were used in this study. The accuracy of tubes potential and irradiation timers and also internal dosimeters were verified and confirmed. A water phantom with a thickness of 18 cm was used for patient and staff dose measurements. For the Philips system, phantom entrance dose rates were 2.77 and 38.97 µGym2 s−1 during fluoroscopy and cineangiography. The respective dose rates for the Siemens were 1.98 and 13.46 µGym2 s−1. Phantom entrance dose rate was 28.5 and 65% higher for the Philips system during fluoroscopy and cineangiography, respectively. Comparing the scattered dose rates at the operator location showed that the flat detector-based Siemens system delivers five times lower dose to the operator in comparison with the image intensifier-based Philips unit. The results suggest that the decrease in received dose of the patient and staff is achievable using the flat detector system. In addition, application of lead curtain and glass is recommended to lower the cardiologist dose especially for the image intensifier-based Philips system.


  • Surface fluids effects on the bladder tissue characterisation using electrical impedance spectroscopy

    by Ahmad Keshtkar, Asghar Mesbahi, Parinaz Mehnati, Asghar Keshtkar

    The electrical impedance of the human urinary bladder in both benign and malignant areas can be measured using an electrical impedance spectroscopy system (EIS). Glycine is usually used in the bladder surgery in the theatre to make an insulation medium for electro-surgery and the extension of the mucosa. In addition, a saline solution is usually used to wash the inside of the bladder after bladder surgery and it is used to extend the bladder tissue mucosa. Therefore, the effect of glycine and the saline solution that fills the bladder is important, because it was expected that the application of common surface fluids (air, saline solution and glycine solution) in the bladder epithelium would affect the measured electrical impedance of the urothelium, to differentiate the malignant area from the normal bladder tissue. In this study, bladders were removed from the patients' bodies and then were moved from theatre to the histopathology department immediately after excision. These bladder samples were then opened and pinned to a corkboard to take the impedance readings, using the impedance spectroscopy system. Following this, the bladder and corkboard were completely submerged in a saline solution and readings were taken at about 1cm from the sutures. Subsequently, this procedure was repeated with the bladder submerged in glycine and then air, respectively. According to the statistical work, these fluids were found to have a significant effect on the measured impedance of the bladder tissue in benign and malignant areas. Furthermore, the best fluid between air, glycine and saline, to measure the impedance of the urinary bladder, is air (P<0.0001).