My research focuses on medical imaging at the intersection of Electrical Engineering, Computer Science, and Radiology. We develop signal processing, image processing, and machine learning methods to improve image quality, facilitate information extraction, and enable more accurate and robust medical image analysis.

Selected Publications

Journal Articles

• Se-In Jang, Yassir Najmaoui, Yanis Chemli, Samira Vafay Eslahi, Nicolas Guehl, Maeva Dhaynaut, Georges El Fakhri, Chao Ma, Jinsong Ouyang, and Thibault Marin " Deep learning enables quantitative kinetic modeling from low-dose dynamic [18F]-MK6240 Tau PET ," Scientific Reports .
• Samira Vafay Eslahi, Jian Tao, and Jim Ji. " An evolutionary neural architecture search for magnetic resonance image reconstructions ," International Journal of Computer Assisted Radiology and Surgery (2026): 1–9.
• Liu, Xiaofeng, Thibault Marin, Samira Vafay Eslahi, Amal Tiss, Yanis Chemli, Yassir Najmaoui, Se-In Jang, Georges El Fakhri, and Jinsong Ouyang. " Scan-wise generalized PET denoising with contrastive adversarial learning ," Physics in Medicine and Biology (2026).
• Lee, Wonil, Paul Kyu Han, Thibault Marin, Ismaël BG Mounime, Samira Vafay Eslahi, Yanis Djebra, Didi Chi et al. " Free‐breathing 3D cardiac extracellular volume (ECV) mapping using a linear tangent space alignment (LTSA) model ," Magnetic Resonance in Medicine 93, no. 2 (2025): 536–549.
• Liu, Xiaofeng, Samira Vafay Eslahi, Thibault Marin, Amal Tiss, Yanis Chemli, Yongsong Huang, Keith A. Johnson, Georges El Fakhri, and Jinsong Ouyang. " Cross noise level PET denoising with continuous adversarial domain generalization ," Physics in Medicine & Biology 69, no. 8 (2024): 085001.
• Samira Vafay Eslahi, and Jim Ji. " Accelerated positive contrast MRI of interventional devices using parallel compressed sensing imaging ," Magnetic Resonance Imaging 60 (2019): 130–136.

Conference Proceedings

• Liu, Xiaofeng, Yongsong Huang, Thibault Marin, Yanis Chemli, Samira Vafay Eslahi, Amal Tiss, Keith A. Johnson, Georges El Fakhri, and Jinsong Ouyang. " Dual Prompting for Diverse Count-Level PET Denoising ," 2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI), pp. 1–5. IEEE, 2025.
• Mounime, Ismaël BG, Wonil Lee, Thibault Marin, Paul K. Han, Yanis Djebra, Samira Vafay Eslahi, Pietro Gori, Elsa Angelini, Georges El Fakhri, and Chao Ma. " Sparsity constrained linear tangent space alignment model (LTSA) for 3D cardiac extracellular volume mapping ," 2024 IEEE International Symposium on Biomedical Imaging (ISBI), pp. 1–5. IEEE, 2024.
• Liu, Xiaofeng, Yongsong Huang, Thibault Marin, Yanis Chemli, Samira Vafay Eslahi, Amal Tiss, Keith A. Johnson, Georges El Fakhri, and Jinsong Ouyang. " Subject-aware PET Denoising with Contrastive Adversarial Domain Generalization ," 2024 IEEE Nuclear Science Symposium (NSS), Medical Imaging Conference (MIC) and RTSD.
• Samira Vafay Eslahi, Caiyun Shi, Haifeng Wang, Yifeng Ye, Hanwei Chen, Guoxi Xie, and Jim Ji. "Accelerated imaging for visualizing interventional devices using parallel acquisition and compressed sensing reconstruction." Proc. Intl. Soc. Mag. Reson. Med, vol. 26, p. 1477, 2018.
• Samira Vafay Eslahi, Pranav Vaidik Dhulipala, Caiyun Shi, Guoxi Xie, and Jim X. Ji. "Parallel compressive sensing in a hybrid space: application in interventional MRI." 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 3260-3263. IEEE, 2017.

EEL 4829/5820 - Digital Image Processing (Graduate and Undergraduate), UNF, Fall 2026

• This course covers image acquisition, sampling, quantization, intensity transformations, spatial and frequency-domain filtering, fundamentals of color image processing, essential segmentation methods, image compression, morphological processing, and advanced topics such as machine learning-based image processing.

EEE 3380 - Microelectronics I (Undergraduate), UNF, Fall 2026

• This course covers semiconductor materials, diode circuits, bipolar junction transistors (BJTs), field-effect transistors (FETs), and basic BJT and FET amplifiers.

ECE 578 – Digital Image Processing II (Graduate), SIUC, Spring 2026

• This course covered advanced image processing techniques, including image reconstruction, segmentation, registration, compression, restoration, denoising, and machine learning.

ECE 558 – Digital Image Processing I (Graduate), SIUC, Fall 2025

• This course covered fundamental concepts and techniques for analyzing, enhancing, and extracting information from digital images using computational methods. Topics included image filtering, segmentation, feature extraction, and image transformations. It also included hands-on programming projects using MATLAB and Python to reinforce theoretical concepts through practical implementation.

BME 536 – Biomedical Signal Analysis (Graduate), SIUC, Spring 2025

• This course covered methods for analyzing and processing physiological signals using Fourier transforms, time-frequency analysis, feature extraction, and machine learning techniques. The course also covered the applications of these methods to real-world biomedical data, including electrocardiogram (ECG) and electroencephalogram (EEG) signals.

BME 533 – Speech and Natural Language Processing (Graduate), SIUC, Spring 2025

• This course covered core concepts in speech processing, including speech production, perception, auditory modeling, signal coding, and acoustic feature extraction. It also covered fundamental topics in natural language processing (NLP), including text classification, language modeling, and sentiment analysis. In addition, the course explored advanced machine learning techniques for NLP, including neural networks, transformers, and large language models (LLMs).

ENGR 222 – Computational Methods for Engineers and Technologists (Undergraduate), SIUC, Spring 2025

• This course introduced C++ fundamentals and programming with an emphasis on engineering problem-solving. It covered language fundamentals, control flow, functions, memory management, data structures, object-oriented programming, and the C++ Standard Library. It also included hands-on programming assignments and projects to develop practical computational skills and apply programming concepts to engineering applications.

ECEN 248 – Digital Systems Design Laboratory (Undergraduate), TA at Texas A&M University, 2021

• This laboratory was led independently, assisting students with the design, simulation, implementation, and debugging of digital circuits using VHDL, as well as guiding laboratory experiments using Xilinx Vivado and Field-Programmable Gate Arrays (FPGAs). I also served as the lead teaching assistant for this course, responsible for coordinating all sections, including schedules, instructional materials, and laboratory work.

ECEN 215 – Principles in Electrical Engineering Laboratory (Undergraduate), TA at Texas A&M University, 2018

• This laboratory was led independently, assisting students with circuit design and analysis, breadboard-based circuit construction, hardware troubleshooting, code debugging, and circuit simulation using NI Multisim. I also guided students in applying fundamental electrical engineering concepts through laboratory experiments and programming exercises.

I am looking for multiple highly motivated graduate students in Master of Science in Electrical Engineering (MSEE), Master of Computer and Information Science (MS-CIS), or Ph.D. in Computing to join my research group at the University of North Florida, with start dates in Spring 2027 or Fall 2027.

Research areas include medical imaging, image processing, signal processing, and machine learning.

Qualifications:

MSEE: Background in signals and systems, signal processing, image processing, machine learning, programming, and familiarity with high-performance computing systems. For more information about the admission requirements, please refer to the University and MSEE Program Admissions Requirements.

MS-CIS: Background in machine learning, data science, programming, and familiarity with high-performance computing systems. For more information about the admission requirements, please refer to the University and MS-CIS Program Admissions Requirements.

Ph.D. in Computing: Background in machine learning, data science, programming, and familiarity with high-performance computing systems. For more information about the admission requirements, please refer to the University and Ph.D. in Computing Program Admissions Requirements.

Contact:

If you are interested, please email me your CV and a brief description of your research interests.

To help me respond more quickly, please use the following subject line for your email:

Subject: Prospective Student – Semester Year

Example: Prospective Student – Spring 2027