Mojtaba Zarei

Languages
English
Persian
Arabic
Education
Ph.D. in ECE
Duke University
2018–2023
M.Sc. in Mechatronics
University of Tehran
2014–2017
B.Sc. in Mechanical Engineering
Isfahan University of Technology
2008–2012
Optimization skills
Gurobi
YALMIP
Machine Learning skills
scikit-learn
PyTorch
TensorFlow
Robotics and Control skills
MATLAB
Mathematica
SolidWorks/CATIA
ROS/Gazebo
DevOps skills
Docker
Fork

Career Profile

I build AI/ML systems that improve medical imaging quality and workflow efficiency. My work blends rigorous optimization and statistical methods with deep learning to deliver reliable, clinically meaningful solutions. I enjoy translating clinical questions into deployable models and collaborating across imaging science, product, and clinical teams.

Experience

CT Clinical Scientist
GE HealthCare 2023–Present
Lead validation and deployment of AI-enabled CT workflow automation (e.g., dual-energy map generation, orientation automation). Coordinate multi-site collaborations evaluating health-economic impact (reduced acquisition time, lower radiologist/CT tech load).

Technologies Used: Machine Learning, Deep Learning, Python, PyTorch, MATLAB

Research Assistant — RAI Labs (CVIT)
Duke University 2020–2023
Protocol optimization and AI harmonization for CT/CXR to reduce cross-site variability and improve downstream AI performance. Built physics-informed DNNs and automated pipelines to extract biomarkers and enhance quantitative reliability.

Technologies Used: Physics-informed DNNs, Optimization, PyTorch, MATLAB, Python

Researcher — Cyber Physical Security Lab (CPSL)
Duke University 2018–2020
Developed statistical model checking for safety and fairness of learning-enabled cyber-physical systems including medical devices and robots.

Technologies Used: Python, MATLAB, ROS, Gazebo, Webots

Researcher — Human & Robot Interaction Lab (TaarLab)
University of Tehran 2014–2018
Built obstacle-avoidance and anti-oscillation control algorithms; developed data-fusion pipelines for robust autonomous control.

Technologies Used: MATLAB, ROS, Gazebo, C++, Gurobi

Publications

A truth-based primal-dual learning approach to reconstruct CT images utilizing the virtual imaging trial platform
Mojtaba Zarei, Saman Sotoudeh-Paima, Ehsan Abadi, Ehsan Samei
Medical Imaging 2022, Physics of Medical Imaging
Optimization of imaging parameters of an investigational photon-counting CT prototype for lung lesion radiomics
Cindy McCabe, Mojtaba Zarei, W Paul Segars, Ehsan Samei, Ehsan Abadi
Medical Imaging 2022, Computer-Aided Diagnosis
Probabilistic conformance for cyber-physical systems
Yu Wang, Mojtaba Zarei, Borzoo Bonakdarpoor, Miroslav Pajic
ACM/IEEE ICCPS 2021
Multi-factorial optimization of imaging parameters for quantifying coronary stenosis in cardiac CT
Mojtaba Zarei, Ehsan Abadi, W Paul Segars, Taylor Richards, Ehsan Samei
Medical Imaging 2021, Physics of Medical Imaging
A probabilistic conditional adversarial neural network to reduce imaging variation in radiography (Best Poster Award)
Mojtaba Zarei, Ehsan Abadi, Rafael Fricks, W Paul Segars, Ehsan Samei
Medical Imaging 2021, Physics of Medical Imaging
Statistical verification of learning-based cyber-physical systems
Mojtaba Zarei, Yu Wang, Miroslav Pajic
HSCC 2020
Experimental study on shared-control of a mobile robot via a haptic device with an optimal velocity obstacle based receding horizon control approach (Featured on cover)
Mojtaba Zarei, Navid Kashi, Ahmad Kalhor, Mehdi Tale Masouleh
Journal of Intelligent & Robotic Systems
Statistical verification of hyperproperties for cyber-physical systems (Best paper finalist)
Yu Wang, Mojtaba Zarei, Borzoo Bonakdarpour, Miroslav Pajic
ACM Transactions on Embedded Computing Systems (TECS)
An experimental oscillation damping impedance control for the Novint Falcon haptic device based on the phase trajectory length function concept
Mojtaba Zarei, Ahmad Kalhor, Mehdi Tale Masouleh
Proc. IMechE Part C: Journal of Mechanical Engineering Science
Oscillation damping of nonlinear control systems based on the phase trajectory length concept: An experimental case study on a cable-driven parallel robot
Mojtaba Zarei, Ali Aflakian, Ahmad Kalhor, Mehdi Tale Masouleh
Mechanism and Machine Theory
Employing phase trajectory length concept as performance index in linear power oscillation damping controllers
Mojtaba Zarei, Ahmad Kalhor, Mohammad Rastegar
International Journal of Electrical Power & Energy Systems
Experimental dynamic identification and model feed-forward control of Novint Falcon haptic device
Nima Karbasizadeh, Mojtaba Zarei, Ali Aflakian, Mehdi Tale Masouleh, Ahmad Kalhor
Mechatronics

Volunteering

President/Vice-President/Treasurer
Graduate Student Association of Iranians at Duke 2019–2022
Organized 60+ cultural and community events; created a supportive space for Iranian students to share concerns, accomplishments, and feedback.
Co-founder/Board member
Literature and Cultural Center, NST Department, University of Tehran 2016–2017