Introduction and Background

Can you provide a brief overview of your academic background and career journey?

I hold a B.Sc. and M.Sc. in Nuclear Engineering from Ben-Gurion University of the Negev and a Ph.D. in Biomedical Engineering from Tel Aviv University. My doctoral work focused on the development of complementary technologies for radiation therapy, and it shaped my long-term interest in medical imaging, quantitative analysis, and clinically meaningful engineering solutions.
I began my academic career at Afeka Academic College of Engineering in 2011, while completing my Ph.D. and developing my teaching and research activity. After completing my Ph.D. in 2018, I was appointed as a lecturer, later promoted to senior lecturer, and in 2024 appointed Head of the School of Electrical Engineering at Afeka. My academic work focuses on the integration of artificial intelligence, thermal imaging, and ultrasound for non-invasive diagnosis and monitoring of diseases. 

Current Research and Projects

What inspired you to conduct this research? (paper in this issue)

The research was inspired by a clinical need: to develop fast, accessible, and non-invasive tools that can support medical decision-making in real-world clinical settings. In the context of acute pharyngitis, for example, physicians often need to distinguish between bacterial and viral infections, yet unnecessary antibiotic treatment remains a significant challenge.
This motivated me to explore whether machine learning, combined with clinical information and thermal imaging, could help identify meaningful physiological patterns and support more accurate diagnosis. The broader motivation behind this work is to bridge engineering and medicine by transforming measurable signals - such as thermal patterns or image-based features - into practical tools that may improve early diagnosis, reduce unnecessary treatment, and support clinicians.

Can you discuss your other current research projects?

My current research activity is centered on AI-based non-invasive medical imaging and on translating engineering methods into clinically useful systems. Ongoing and recent projects include AI-based thermal imaging for early detection and monitoring of oral cancer; portable thermal imaging and deep learning for detection and staging of non-alcoholic fatty liver disease; AI and ultrasound for detection of ovarian tumors and classification of complex ovarian cysts; fetal ultrasound analysis for predicting preterm birth risk; automated detection of Crohn's disease and rectal cancer using ultrasound and deep learning; thermal imaging for arthritis monitoring, wound assessment, vascular/perfusion evaluation, and treatment follow-up; and AI-based systems for differentiating bacterial and viral pharyngitis.
In parallel, I am expanding my research into industrial applications, particularly AI-based non-destructive testing for defect detection in metal components, in collaboration with Israel Aerospace Industries and researchers at Afeka.

How do you see your work contributing to advancements in your field?

I see my work as contributing in three main ways. First, it advances non-invasive diagnostic technologies by showing that physiological and image-based data can be analyzed automatically and objectively using AI. Second, it supports the development of portable and accessible diagnostic tools that may be used outside highly specialized hospital environments. Third, it demonstrates the value of interdisciplinary engineering research in healthcare, where algorithms, sensors, and clinical insight are combined to improve diagnosis, monitoring, and treatment evaluation.
Beyond specific applications, my goal is to help move AI in medical imaging from research prototypes toward reliable, explainable, and clinically relevant systems.

Collaborations

Do you have any collaborations with researchers in other institutions or in other engineering schools in Afeka?

Yes. My research is highly collaborative. I work with clinicians and researchers from leading medical institutions, including Sheba Medical Center, Meir Medical Center, Tel Aviv Sourasky Medical Center, Clalit Health Services, and other clinical partners. These collaborations support research in gastrointestinal imaging, gynecological ultrasound, cardiovascular imaging, inflammatory diseases, wound assessment, pharyngitis diagnosis, and oncology.
Within Afeka, I collaborate with researchers from engineering fields such as signal processing, artificial intelligence, ultrasound, hardware development, and non-destructive testing. I also collaborate with industry partners, including Israel Aerospace Industries, particularly in AI-based NDT for defect detection in metal components.


How do you approach interdisciplinary collaboration, and what benefits do you see in this approach?
I approach interdisciplinary collaboration with mutual respect for each partner's expertise. In medical engineering projects, clinicians understand the real clinical problem, engineers understand sensing, modeling, and system design, and data scientists can transform complex data into useful decision-support tools. A successful collaboration begins with a clearly defined clinical or engineering need, followed by careful data collection, rigorous analysis, and continuous feedback from all partners.
The benefit of this approach is that the final solution is not only technologically innovative but also relevant, practical, and more likely to be adopted in real settings. Interdisciplinary work also enriches students' training by exposing them to real-world problems that require both technical depth and communication skills.

Innovation and Problem-Solving

What is your problem-solving approach?

My problem-solving approach starts with understanding the real-world need before selecting the technology. I first define the clinical or engineering question, then examine the available data, limitations, and constraints. From there, I develop a structured methodology: preprocessing, feature extraction or deep learning, model development, validation, and interpretation. I place strong emphasis on data quality, reproducibility, and avoiding methodological errors such as data leakage.
I also believe that problem-solving in engineering requires iteration. An initial model or system is rarely the final one. The process involves testing assumptions, identifying weaknesses, improving the experimental design, and communicating results clearly to both technical and clinical partners.
Can you share a specific instance where you encountered a challenging problem and the steps you took to find a solution?
One example is the development of machine-learning tools for medical diagnosis using thermal imaging. Thermal images are sensitive to acquisition conditions, patient positioning, environmental temperature, and biological variability. This creates a challenge: the algorithm must identify meaningful physiological patterns rather than artifacts.
To address this, we developed structured imaging protocols, defined regions of interest, performed careful preprocessing, and evaluated multiple feature extraction and machine-learning approaches. We also worked closely with clinicians to interpret whether the thermal patterns were biologically meaningful. This iterative process allowed us to transform complex thermal data into diagnostic models for applications such as COVID-19 detection, fatty liver disease, pharyngitis, arthritis, and treatment monitoring.
Emerging Technologies
What emerging technologies or trends in your field do you find particularly exciting or promising?
I am particularly excited by the convergence of AI, portable sensors, multimodal imaging, and edge computing. These technologies can enable diagnostic tools that are faster, more accessible, and more personalized. In medical imaging, I see great promise in combining thermal imaging, ultrasound, clinical data, and advanced AI models to provide more robust diagnostic information than any single modality alone.
I am also interested in explainable AI, radiomics, radiogenomics, and privacy-preserving AI. These fields are important because future medical AI systems must not only be accurate, but also transparent, reliable, and suitable for integration into clinical workflows.
How do you stay updated on the latest developments in your field?
I stay updated by reading leading journals, reviewing manuscripts, participating in conferences, collaborating with clinicians and engineers, and following developments in AI, computer vision, biomedical engineering, and medical imaging. My role as an Editorial Board Member of Scientific Reports also exposes me to current research directions and standards in peer review.
In addition, I encourage my students to read recent papers, compare methodologies, and present new developments. This creates a research environment in which learning is continuous and shared.
Career Advice

For aspiring engineers and scientists, what advice do you have in terms of education, skill development, and navigating a successful career in engineering science?

My advice is to build a strong foundation in mathematics, physics, programming, signal processing, and data analysis, while also developing curiosity and the ability to learn independently. Modern engineering increasingly requires the ability to connect theory with real applications, so students should seek projects that expose them to real data, real constraints, and interdisciplinary teamwork.
I also recommend developing communication skills. A good engineer or scientist must be able to explain complex ideas clearly to colleagues from other disciplines. Finally, persistence is essential: research often involves uncertainty, failed attempts, and revision. The ability to continue improving the work is one of the most important professional skills.

Are there specific experiences or lessons from your career that you believe would benefit early-career professionals?

Many of my research achievements were made possible through collaboration with clinicians, researchers, students, and industry partners. Early-career professionals should not be afraid to ask questions, seek mentors, and participate in challenging projects. These experiences build both confidence and expertise.

Challenges in Engineering

What do you see as some of the significant challenges currently facing the field of engineering, and how do you think they can be addressed?

One major challenge is ensuring that advanced technologies, especially AI systems, are reliable, transparent, and ethically implemented. In healthcare, algorithms must be validated carefully, tested on diverse populations, and integrated responsibly into clinical workflows. Another challenge is the gap between academic prototypes and practical implementation. Many systems show promise in research but require additional work in usability, regulation, data quality, and workflow integration before they can be widely adopted.
These challenges can be addressed through interdisciplinary collaboration, rigorous validation, education in responsible AI, and stronger connections between academia, industry, and clinical partners. Engineering education must also adapt by giving students experience with real-world problems, not only theoretical exercises.


Mentorship and Leadership


Have you had mentors who significantly influenced your career? How important is mentorship in the field of engineering science?

In engineering science, mentorship is especially important because students and early-career researchers often work on complex, multidisciplinary problems. They need support not only in technical issues but also in research design, communication, publication, collaboration, and career planning. Throughout my career, I have benefited from the guidance and support of senior faculty members at Afeka Academic College, as well as from my supervisors during my advanced academic degrees. Their mentorship has shaped my development as a researcher, educator, and academic leader, and has taught me the importance of professionalism, academic excellence, responsibility, and long-term vision.

How do you approach leadership in your role, and what qualities do you think are crucial for effective leadership in engineering?

In my role as Head of the School of Electrical Engineering, I view leadership as a combination of vision, responsibility, listening, and empowerment. My goal is to create an environment that encourages academic excellence, innovation, collaboration, and student success.
Effective leadership in engineering requires the ability to identify future needs, support faculty and students, promote interdisciplinary initiatives, and make decisions that balance academic quality with practical relevance.

Future of Engineering Science

Looking ahead, what do you envision as the future of engineering science, and how do you think it will impact society?

I believe the future of engineering science will be shaped by intelligent, data-driven, and human-centered technologies. Engineering will play a central role in healthcare, sustainability, energy, communication, transportation, and advanced manufacturing. In medicine, AI-based imaging and sensing technologies will make diagnosis more accessible, personalized, and preventive.
The impact on society can be profound: earlier disease detection, better monitoring of chronic conditions, safer industrial systems, more efficient infrastructure, and improved quality of life. However, this future also requires responsible development, ethical awareness, and engineers who understand both technology and society.


Are there specific areas or industries where you believe engineering science will play a particularly transformative role?

I believe engineering science will be particularly transformative in healthcare, energy, advanced industry, smart sensing, communication systems, automation, and AI-driven decision support. Electrical engineering plays a central role in this transformation because it provides the technological foundation for hardware development, sensors, signal and image processing, embedded systems, power electronics, communication networks, and intelligent systems.
In healthcare, engineering technologies can support portable and AI-enhanced diagnostic tools that improve early diagnosis and clinical decision-making. In advanced industry, smart sensing, automation, and AI-based monitoring can improve efficiency, reliability, and system performance. In the energy sector, electrical engineering is essential for developing smarter power grids, renewable energy integration, efficient power conversion, and advanced energy storage solutions.

More broadly, the integration of sensors, AI, advanced hardware, communication technologies, and energy systems will transform how we detect problems, make decisions, design systems, and manage infrastructure. Engineers, and especially electrical engineers, will be central to ensuring that these technologies are accurate, reliable, efficient, sustainable, safe, and beneficial to society.