Amirhossein Sanaat - University of Geneva  - PhD Student

Amirhossein Sanaat

University of Geneva

PhD Student

Geneva, Geneva | Switzerland

Main Specialties: Neuroradiology, Nuclear Medicine, Nuclear Radiology

ORCID logohttps://orcid.org/0000-0001-8437-2060

Amirhossein Sanaat - University of Geneva  - PhD Student

Amirhossein Sanaat

Introduction

Experienced Researcher with a demonstrated history of working in the medical image device industry. Skilled in Machine/Deep Learning, Quantitative Imaging, C++ and Python programming, and Monte Carlo simulation with GEANT4 and GATE. Strong background in physics with a bachelor's degree in nuclear physics and a good research professional with a master’s degree focused in nuclear medical technology/ medical radiation.

Primary Affiliation: University of Geneva - Geneva, Geneva , Switzerland

Specialties:

Education

Apr 2019
University of Geneva
PhD Student

Publications

5Publications

Reads

13Profile Views

Novel preclinical PET geometrical concept using a monolithic scintillator crystal offering concurrent enhancement in spatial resolution and detection sensitivity: a simulation study.

Phys Med Biol 2020 02 13;65(4):045013. Epub 2020 Feb 13.

Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva CH-1211, Switzerland.

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1088/1361-6560/ab63efDOI Listing
February 2020
2.761 Impact Factor

Projection-space implementation of deep learning-guided low-dose brain PET imaging improves performance over implementation in image-space.

J Nucl Med 2020 Jan 10. Epub 2020 Jan 10.

Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Switzerland.

View Article

Download full-text PDF

Source
http://dx.doi.org/10.2967/jnumed.119.239327DOI Listing
January 2020
6.160 Impact Factor

Altering paths of optical photons passing through a scintillator

US Patent

A method for altering paths of optical photons that pass through a scintillator. The scintillator includes a plurality of vertical sides. The method includes forming a reflective belt inside the scintillator by creating a portion of the reflective belt inside the scintillator on a vertical plane parallel with a vertical side of the plurality of vertical sides. Creating the portion of the reflective belt includes generating a plurality of defects on the vertical plane.

View Article
June 2019

Design and performance evaluation of high resolution small animal PET scanner based on monolithic crystal: a simulation study

A. Sanaat et al 2019 JINST 14 P01005

Journal of Instrumentation

Dedicated small-animal PET scanners functionality can be optimized by improving the sensitivity and spatial resolution of the scanner. Approximately most of the developed and commercially available small-animal PET scanners are equipped with pixelated scintillators; therefore, their spatial resolution is limited to the crystal pixel size. Complex fabrication, low-sensitivity, and disability in depth of interaction calculation (DOI) are the major disadvantages of pixelated crystals. However, monolithic scintillator crystals are known as one of the most commonly used substitutions, as they have higher sensitivity, DOI recognition, and lower cost. We already designed and implemented a dedicated small-animal PET scanner based on pixelated scintillator crystals and silicon photomultiplier (SiPM). In this study, we plan to present a new optimized design based on the monolithic crystal, with similar performance by the previous

View Article
January 2019

A novel convolutional neural network for predicting full dose from low dose PET scans

https://ieeexplore.ieee.org/abstract/document/9059962

The use of radiolabeled tracers in PET imaging raises concerns owing to potential risks from radiation exposure. Therefore, to reduce this potential risk in diagnostic PET imaging, efforts have been made to decrease the amount of radiotracer administered to the patient. However, decreasing the injected activity reduces the signal-to-noise Ratio (SNR) and deteriorates image quality, thus adversely impacting clinical diagnosis. Previously proposed techniques are complicated and slow, yet they yield satisfactory results at significantly low dose. In this work, we propose a deep learning algorithm to reconstruct full-dose (FD) from low-dose (LD) PET images using a fully convolutional encoder-decoder deep neural network model. The goal is to train a model to learn to reconstruct from images with only 5% of the counts to produce images corresponding to 100% of the dose. Brain PET/CT images of 140 patients acquired …

View Article
November -0001

Top co-authors

Habib Zaidi
Habib Zaidi

Geneva University Hospital

2
Hossein Arabi
Hossein Arabi

Geneva University Hospital

2
Mohammad Reza Ay
Mohammad Reza Ay

Tehran University of Medical Sciences

1
Valentina Garibotto
Valentina Garibotto

Geneva University Hospital

1
Ismini Mainta
Ismini Mainta

Hôpitaux Universitaires de Genève

1