Find Academic Supervisors

• Computer Vision
• Machine Learning
• Medical Imaging
• +3 more

Stella Yu is a Professor specializing in computer vision, machine learning, and AI applications across medical imaging, robotics, and wildlife recognition. She emphasizes adaptive advising tailored to individual student strengths, with regular one-on-one and group meetings to discuss research progress and paper presentations. Yu's research group focuses on unsupervised learning, deep learning workflows, and interdisciplinary applications such as MRI reconstruction, meibography analysis, and aerial wildlife monitoring. Her work bridges theoretical advancements with practical tools like DeepInPy for inverse problems. She strongly advocates for teaching experience through GSI roles and ensures students have conference funding to present findings at top venues. Education Expectations: Regular literature review, lab presence for junior students, and clear authorship protocols. Key Research Themes: Feature learning, medical AI, computational optics, and wildlife population surveys. Her lab promotes a collaborative environment with structured feedback loops, emphasizing both technical rigor and creative problem-solving. Current projects include BatVision for 3D spatial navigation using audio signals, and AI-driven solutions for dry eye diagnosis and building information modeling.

Raphael SznitmanView profile

Professor

• Computer Vision
• Probabilistic Methods
• Statistical Learning
• +2 more

Prof. Dr. Raphael Sznitman serves as Director of the ARTORG Center for Biomedical Engineering Research and Head of the Artificial Intelligence in Medical Imaging group at the University of Bern, Switzerland, holding a Full Professor position in AI for Medical Imaging since 2015. Education: PhD in Computer Science, Johns Hopkins University (2011) MSc in Computer Science, Johns Hopkins University (2009) BSc in Cognitive Systems, University of British Columbia (2007) Research Interests: Sznitman's work centers on computational vision , probabilistic methods , and statistical learning applied to medical imaging challenges. His group develops AI algorithms for ophthalmic diagnostics, surgical robotics, and medical image analysis, with emphasis on OCT, surgical phase recognition, and domain adaptation techniques. Key application areas include retinal disease detection and cataract surgery automation. Publication Trends: His 2021-2025 publications reveal concentrated efforts in deep learning for medical imaging , particularly in ophthalmology (OCT analysis) and surgical video understanding. Emerging themes include LLM applications for clinical monitoring, unsupervised out-of-distribution detection for surgical safety, and physics-informed AI for multimodal medical data fusion. Research Leadership: As ARTORG Center Director, Sznitman oversees interdisciplinary research bridging computer science and clinical medicine. His group collaborates extensively with Bern University Hospital clinicians on translational projects, securing funding for AI-driven diagnostic tools and surgical assistance systems. Current initiatives focus on real-time intraoperative guidance and spaceflight ophthalmology applications. Laboratory: The Artificial Intelligence in Medical Imaging group operates within ARTORG's dedicated facilities, maintaining partnerships with surgical robotics labs and ophthalmology departments for clinical validation of AI systems. Their work integrates multimodal data streams including OCT, VR perimetry, and surgical video feeds.

Miroslav PajicView profile

Professor

• Cyber-Physical Systems
• Embedded Systems
• Artificial Intelligence
• +6 more

Miroslav Pajic serves as a Professor in the Department of Electrical and Computer Engineering at Duke University's Pratt School of Engineering. He also holds joint appointments as Associate Professor in the Thomas Lord Department of Mechanical Engineering and Materials Science and Associate Professor of Computer Science. As Director of Master's Studies, he oversees the graduate program in Electrical and Computer Engineering and teaches numerous courses spanning embedded systems, cyber-physical systems design, and robotics. Education: Ph.D. in Electrical and Computer Engineering from University of Pennsylvania (2012) Miroslav Pajic's research focuses on the design and analysis of cyber-physical systems (CPS) with varying levels of autonomy and human interaction. His work spans the intersection of embedded systems, artificial intelligence, machine learning, control theory, formal methods, and robotics. He specializes in developing high-assurance autonomous systems with applications in robotics, automotive systems, and medical devices, with particular emphasis on CPS security and resilient autonomy. His research addresses fundamental challenges in creating systems that can operate reliably in uncertain environments while maintaining security against potential cyber attacks. Analysis of Pajic's recent publications reveals a strong interdisciplinary research program bridging theoretical foundations with practical applications. His work spans secure sensor fusion for distributed autonomy, medical applications of CPS (particularly deep brain stimulation for neurological disorders), and innovative sensing technologies for autonomous vehicles. A significant portion of his research addresses security challenges in cyber-physical systems, including stealthy GPS attacks on UAVs and methods for attack-resilient state estimation. His publications increasingly integrate machine learning techniques with traditional control theory to create more adaptive and robust autonomous systems. Pajic actively mentors graduate students and leads research groups focused on cyber-physical systems security and high-assurance autonomy. His research is supported by multiple grants, including the NSF AI Institute for Edge Computing (Athena), which he co-leads. He has received funding from various sources to support his work on secure and resilient cyber-physical systems, medical device security, and autonomous vehicle technologies. Pajic collaborates extensively with medical researchers on applications of cyber-physical systems in healthcare, particularly in deep brain stimulation for neurological disorders. His work bridges the gap between theoretical control systems and practical implementations in safety-critical domains, with a growing emphasis on translating research into real-world applications that improve system security and reliability.

Ehsan AzimiView profile

Assistant Professor

• Human-AI Interaction
• Extended Reality
• Robotics
• +7 more

Ehsan Azimi is an Assistant Professor in the Department of Electrical and Computer Engineering and the Department of Computer Science at the University of Arizona, where he is also a member of the Graduate Faculty. His research bridges human-AI interactive systems, extended reality, robotics, and human-centered design, with a strong focus on medical applications. His research interests lie in creating synergistic human-AI systems that enhance medical procedures through advanced technologies. Key areas include extended reality for surgical navigation , robotics in minimally invasive surgery , and intelligent user interfaces . His work has led to innovations in smart glasses calibration, intraocular robotic snakes, needle steering, and digital twins for surgical training, all aimed at improving precision, safety, and learning in medicine. The recent articles highlight a consistent trend in medical robotics , augmented reality in surgery , and human-robot collaboration . These works span from hardware development to AI-driven interfaces, emphasizing real-time interaction, user experience, and clinical applicability across disciplines like ophthalmology, otology, and surgical education. Scientific Awards: Siebel Scholar Provost Postdoctoral Fellowship Link Fellowship Ehsan actively mentors students and scholars in research projects, indicating a strong commitment to academic advising. While specific grant details are not listed, his patented technologies and publication record suggest successful funding and translational research outcomes. His work has been featured in Engineering Magazine and other media, reflecting its impact and innovation. His research is conducted within an interdisciplinary lab environment focused on human-centered AI and medical robotics, integrating expertise from computer science, engineering, and clinical medicine to develop next-generation surgical and training systems.

• Medical Genetics
• Nephrology
• Genomics
• +3 more

Dr. Ian Wilson is a researcher at Newcastle University with a focus on medical genetics, nephrology, and genomic analysis. His work spans genetic determinants of kidney diseases, mitochondrial disorders, and biomarker development. Notable contributions include studies on uromodulin genetics in African populations, copy-number variations in rare diseases, and kidney ciliopathies. He has collaborated extensively on projects involving genome sequencing, mitochondrial replacement therapy, and muscular dystrophy biomarkers. Wilson's research integrates computational tools like machine learning for predictive modeling in urolithiasis and employs advanced imaging techniques for disease progression monitoring. Key areas: Genetic epidemiology, renal genomics, mitochondrial DNA analysis Focus on translational applications: Biomarker development for kidney stones and muscular dystrophies Interdisciplinary collaborations in ophthalmology and orthopedics His publications reflect a commitment to advancing diagnostic accuracy and understanding complex genetic disorders through multi-omics approaches.

Pengtao XieView profile

Associate Professor

• Machine Learning
• Natural Language Processing
• Machine Learning for Healthcare
• +4 more

Pengtao Xie is an Associate Professor (tenured) in the Department of Electrical and Computer Engineering at UC San Diego, with cross-appointments in the Division of Biomedical Informatics and affiliations across multiple schools and institutes including the Halıcıoğlu Data Science Institute, School of Biological Sciences, and Skaggs School of Pharmacy. His research bridges human-inspired machine learning and healthcare applications. Education: PhD in Machine Learning, Carnegie Mellon University (2018) MS from Tsinghua University BS from Sichuan University Research Interests: His work focuses on machine learning inspired by human learning strategies , including learning by testing, interleaving, self-explanation, and teaching. These techniques are applied to large language models , foundation models , healthcare , and biomedicine . Recent efforts emphasize generative AI for medical image segmentation and protein function prediction. Scientific Awards: NIH MIRA Award (2025) NSF Career Award (2024) Best Graduate Teacher Award, ECE UCSD (2023) ICLR Notable-Top-5% Paper (2023) Global Top-100 Chinese Young Scholars in AI (2022) Tencent Faculty Award (2021) AMIA Doctoral Dissertation Award Finalist (2020) Siebel Scholarship (2014) Teaching & Mentorship: He has developed and taught courses such as Deep Generative Models , Probabilistic Graphical Models , and Linear Algebra and Applications . He actively mentors PhD, master's, and undergraduate students, with alumni now at CMU, Stanford, Mila, and industry roles. Labs & Teams: He leads a research group within the Center for Machine-Intelligence, Computing and Security and collaborates with the Institute for Genomic Medicine and Institute of Engineering in Medicine at UC San Diego.

Tan Viet Tuyen NguyenView profile

Lecturer

• Human-centered Artificial Intelligence
• Social Human-Robot Interaction
• Multimodal Perception and Interaction
• +5 more

Dr. Tan Viet Tuyen Nguyen is a New Frontiers Fellow (Lecturer) in AI at the University of Southampton, specializing in Human-Centered Artificial Intelligence and Social Human-Robot Interaction. His research focuses on multimodal learning for robots to adapt their behavior to human social needs, with applications in healthcare, education, and service environments. Prior to this role, he was a Research Associate at King’s College London and a Research Assistant on the EU-funded CARESSES project, developing culturally-aware assistive robots for elderly support. Education: PhD in Information Science (Robotics) from Japan Advanced Institute of Science and Technology. He has organized conferences such as the IEEE RO-MAN 2022 special session on nonverbal communication and served as a reviewer for top-tier robotics and AI conferences. Research Interests include: Human-Robot Collaboration, Multimodal Perception, Generative AI for Social Interaction, and Context-Aware Robot Behavior Generation. His work has been recognized with awards including the Best Paper Award at ROMAN 2022 and the Prospective Research Award at ICServ 2023. Teaching Responsibilities include courses on Biologically Inspired Robotics, High-Level Programming, and MSc/Undergraduate project supervision. He currently oversees two PhD students and collaborates on projects like 'Exploring the impact of AI-driven writing of engagement in climate change' and 'Bridging Generations and Cultures through Generative AI.' Labs/Teams: Member of the Agents, Interaction and Complexity Centre and the Centre for Robotics Research at Southampton.

• Machine Learning
• Computer Vision
• Medical Image Analysis
• +7 more

Professor Arcot Sowmya is a distinguished academic at the University of New South Wales, serving as Professor in the School of Computer Science and Engineering. With a strong background in both computer science and mathematics, she has established herself as a leading researcher in machine learning and computer vision applications, particularly in medical imaging and diagnostics. Dr. Sowmya earned her PhD in Computer Science from the Indian Institute of Technology, Bombay, along with an MTech in Computer Science, MSc in Mathematics, and BSc in Mathematics from the same institution. Her academic journey has positioned her at the intersection of theoretical computer science and practical medical applications. Her research interests span multiple domains with a primary focus on Machine Learning for Computer Vision . She has made significant contributions to learning object models, feature extraction, segmentation, and recognition techniques. Her work extends into medical image analysis, computer-aided diagnostics, high-resolution remote sensing, and biomedical informatics. More recently, she has applied similar techniques to social sciences domains, developing improved forecasting models for genocide and politicide. Her earlier work also includes contributions to real-time, concurrent, and embedded systems. Analyzing her recent publications reveals a strong trend toward medical applications of computer vision and deep learning. Her work spans from OCT-based glaucoma diagnosis to tumor segmentation, lung disease detection, and breast cancer prognosis. She has successfully bridged computer science with clinical medicine, developing practical tools for disease diagnosis and prediction that incorporate explainable AI approaches. Professor Sowmya's collaborative approach is evident in her extensive publication record across multiple journals and conferences. She has worked with researchers from diverse fields including ophthalmology, oncology, neurology, and public health, demonstrating the interdisciplinary nature of her research. Her laboratory work focuses on developing robust deep learning architectures for medical image analysis, with particular attention to segmentation networks, transformer models, and multimodal data fusion techniques. Her team has developed specialized networks for lung segmentation, tumor detection, and disease classification that address specific challenges in medical imaging.

Eung-Joo LeeView profile

Assistant Professor

• Computer Vision
• Medical Image Analysis
• Artificial Intelligence
• +7 more

Eung-Joo Lee is an Assistant Professor in the Department of Electrical and Computer Engineering at the University of Arizona, where he also holds affiliations with the Department of Ophthalmology and Vision Science, the BIO5 Institute, and the UA Cancer Center. He serves as an adjunct professor at the University of Nebraska–Lincoln and is a member of the Graduate Faculty. Dr. Lee leads the Vision Systems and Intelligence (VSI) Laboratory and contributes to interdisciplinary research bridging engineering and medicine. Education: PhD in Electrical and Computer Engineering, University of Maryland, College Park, 2021 MS in Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea, 2015 BS in Electrical Engineering, University of Texas at Dallas, 2013 Dr. Lee's research centers on developing computationally efficient and interpretable deep learning models for real-time, low-resource environments, particularly in computer vision and medical imaging. His work addresses perception and decision-making challenges in autonomous and medical systems. He applies cross-disciplinary expertise in engineering and medicine to create lightweight AI solutions. Although no specific publications are listed in the provided text, his research direction suggests strong engagement in areas such as embedded AI, medical image analysis, and real-time computer vision systems, likely published in top-tier venues in machine learning and biomedical engineering. Scientific Service and Recognition: Associate Editor, Journal of Signal Processing Systems (Springer) Editorial Board Member, Scientific Reports (Nature Portfolio) Reviewer for IEEE Transactions on Pattern Analysis and Machine Intelligence, Medical Image Analysis, Nature Machine Intelligence, and others Active participant in major conferences including NeurIPS, CVPR, MICCAI, AAAI, and SPIE Dr. Lee advises research through the VSI Laboratory and contributes to academic leadership via service on the Scientific Advisory Committee for the Body and Imaging Center at the University of Arizona. He has served on numerous program committees, organized workshops, and chaired sessions at international conferences, demonstrating growing leadership in the academic community. He is actively involved in interdisciplinary research collaborations, including past work with Children’s National Hospital and the U.S. Army Research Laboratory, and continues to bridge gaps between engineering and clinical applications.

James TungView profile

Associate Professor

• Assistive Technology
• Rehabilitation Engineering
• Biomedical Engineering
• +5 more

James Tung is an Associate Professor at the University of Waterloo’s Faculty of Engineering, Department of Mechanical and Mechatronics Engineering. His research focuses on assistive technology, rehabilitation engineering, and mobility solutions for individuals with disabilities. He leads the Neural and Rehabilitation Engineering (NRE) Lab, which develops wearable sensors, robotics, and machine learning tools to enhance mobility and monitor motor rehabilitation. He teaches courses including BME 355 (Physiological Systems Modelling), BME 540 (Neural and Rehabilitation Engineering), and ME/MTE engineering modules. The lab collaborates with clinical and industry partners to translate research into practical solutions, addressing real-world mobility challenges and aging demographics. His research spans real-world gait analysis, fall risk assessment, and prosthetic design, with a focus on pediatric neurodevelopmental disorders and elderly mobility. The NRE Lab emphasizes interdisciplinary work, combining biomechanics, robotics, and data science to improve healthcare outcomes. Lab Alumni: Includes researchers like Robin Murdock (Myant Inc.), Andrew Hart, and Raj Senthilkumar, contributing to prosthetics and gait analysis. Partnerships: Engages clinical and industry stakeholders for knowledge translation and commercialization. Current projects include developing smart rollators, biofeedback prosthetics, and sensor-based assessment tools to address mobility limitations in aging populations and individuals with disabilities.

Xenophon PapademetrisView profile

Professor

• Medical Image Analysis
• Machine Learning
• Biomedical Software Development
• +7 more

Xenophon Papademetris is a Professor of Biomedical Informatics & Data Science and Radiology & Biomedical Imaging at Yale School of Medicine. He serves as Associate Director of Biomedical Imaging Data Sciences at Yale Biomedical Imaging Institute and directs the Medical Software and Medical Artificial Intelligence Certificate Program. PhD in Electrical and Information Sciences from Yale University (2000) BA from Cambridge University (1994) Postdoctoral Fellowship at Yale University (2002) His research focuses on medical image analysis, machine learning, and biomedical software development. He has developed tools like BioImage Suite Web and contributed to standards committees at the Association for the Advancement of Medical Instrumentation (AAMI). His work spans modalities including MRI, CT, PET, and optical imaging. Recent publications emphasize neuroimaging analysis, explainable AI in healthcare, and multimodal data integration across species. He leads NIH-funded research under the BRAIN Initiative (R24 MH114805) and has authored a textbook on Medical Software published by Cambridge University Press. IEEE Senior Member Yale Brown-Coxe Postdoctoral Fellowship Harding Bliss Prize for Excellence in Engineering He directs the BioImage Suite Project, creating web-based image analysis tools using JavaScript and WebAssembly. His teaching includes both academic courses and a Coursera program on Medical Software with over 14,000 enrollments.

• Biomedical Engineering
• Control Systems
• Brain-Computer Interfaces
• +7 more

Andrzej Majkowski is an Associate Professor at the Institute of the Theory of Electrical Engineering, Measurement and Information Systems, Faculty of Electrical Engineering, Warsaw University of Technology. His career spans over two decades of research in biomedical engineering, focusing on brain-computer interfaces, signal processing, and emotion recognition. Active in both teaching and research, he contributes to advancing methodologies in electrophysiological signal analysis. Warsaw University of Technology Institute of the Theory of Electrical Engineering, Measurement and Information Systems Faculty of Electrical Engineering Specializing in biomedical engineering , Majkowski's research bridges control systems and information technologies with neuroscience applications. His work explores brain-computer interfaces , EEG/EMG signal processing , and emotion recognition using multimodal physiological data. Recent studies focus on deep learning architectures for artifact removal and classification tasks. Recent publications highlight trends in CNN-LSTM hybrid models for signal denoising, convolutional networks for seizure detection, and machine learning applications in visual evoked potential analysis. His work spans both clinical applications (epilepsy monitoring) and human-computer interaction (emotion recognition, sign language detection). With over 98 documented publications and significant bibliometric indicators (h-index 13 in Scopus), Majkowski has supervised 95 promoted theses. His research includes one funded project and collaborations in biomedical instrumentation, though specific award details remain unspecified in available records.

Athina E MarkakiView profile

Professor

• Tissue Engineering
• Biomaterials
• Regenerative Medicine
• +3 more

Professor Athina E Markaki serves as Professor of Materials & Biomedical Engineering in the Department of Engineering at the University of Cambridge, leading research in advanced biomaterials and tissue engineering solutions for regenerative medicine with emphasis on vascularization and tubular scaffold development for human conduit replacement. Her academic credentials include a Diploma in Metallurgical Engineering (8.6/10) from the National Technical University of Athens and a PhD in Materials Science from the University of Cambridge. Markaki's research program centers on vascularisation techniques for clinically relevant tissue dimensions and tubular scaffolds to replace diseased or damaged human conduits, integrating biomaterials science with regenerative medicine principles. Key applications span liver tissue engineering, neural crest-derived stem cell differentiation, and vascular graft development, with strong translational focus on orthopaedic and cardiovascular medical devices. Analysis of her recent publications reveals dominant trends in biomimetic scaffold design, particularly collagen-based tubular structures and hydrogel systems for vascularized tissue constructs. Her work demonstrates interdisciplinary convergence of AI-driven retinal assessment, glioblastoma modeling, and self-healing cementitious materials, with consistent emphasis on clinically applicable regenerative solutions for liver, bone, and neural tissues. Her distinguished scientific contributions are recognized by major awards: Rosetrees Trust 2017 Interdisciplinary Award European Research Council (ERC) Starting Grant (2010) Advanced EPSRC Fellowship (2005) De Montfort Award at SET for Britain National Event (2004) Young Scientist Prize 2003 (5th Euromech Solid Mechanics Conference) Multiple academic excellence awards from Greek foundations Markaki directs a well-funded research program including ERC and EPSRC grants, mentoring graduate students in tissue engineering while teaching core engineering curricula covering plastic deformation, fracture mechanics, and medical materials design. Her group maintains strong industry and clinical partnerships to advance regenerative technologies. Her laboratory, accessible via http://www-memti.eng.cam.ac.uk/, specializes in vascularized tissue constructs and tubular scaffolds using laser-based manufacturing, biomimetic design, and hydrogel engineering to address critical challenges in tissue replacement and disease modeling.

Gunnar BlohmView profile

Assistant Professor

• Sensorimotor Neuroscience
• Clinical Medicine
• Neurology
• +3 more

Gunnar Blohm is an Assistant Professor in the Department of Biomedical and Molecular Sciences at Queen's University, affiliated with the School of Medicine and Faculty of Health Sciences. His research focuses on sensorimotor neuroscience, particularly 3D sensorimotor control, eye-hand coordination, and computational modeling of neural processes. He holds a Ph.D. from Université Catholique de Louvain and has held postdoctoral positions at York University and his alma mater. Cross-appointed to the School of Computing, Department of Psychology, and Department of Mathematics and Statistics, he is also Vice-Director of the Connected Minds initiative. His research integrates behavioral experiments, brain imaging (MEG/EEG), and patient studies to understand how sensory information is transformed into goal-directed actions. Key areas include visuomotor transformations, multisensory integration, and Bayesian processes in neural computations. Blohm leads the Computational Sensorimotor Neuroscience Lab, emphasizing collaborative projects like Neuromatch Academy and contributions to open science initiatives. Affiliated with Queen's Centre for Neuroscience Studies and Ingenuity Labs, his work bridges computational approaches with clinical applications, aiming to develop frameworks for understanding brain dysfunction and clinical tools. His recent articles explore topics like saccade dynamics, pupil responses, and generative adversarial collaborations in scientific discourse.

Ghassan AlRegibView profile

Professor

• Machine Learning
• Image and Video Processing
• Computer Vision
• +7 more

Ghassan AlRegib is the John and Marilu McCarty Chair Professor in the School of Electrical and Computer Engineering at Georgia Institute of Technology. He directs the Omni Lab for Intelligent Visual Engineering and Science (OLIVES), the Center for Energy and Geo Processing (CeGP), and previously led Georgia Tech's MENA initiatives (2015-2018). His research spans machine learning, image processing, and seismic interpretation with real-world applications in autonomous vehicles, medical imaging, and subsurface analysis. His research focuses on trustworthy AI systems through three pillars: enhancing interpretability, improving robustness/generalizability, and tackling domain-specific challenges. Key interests include human-in-the-loop frameworks, uncertainty quantification, explainable AI, and physics-driven learning. The OLIVES lab pioneered modern machine learning applications in seismic interpretation and developed open-source datasets for geological fault analysis. Dr. AlRegib's scientific contributions include over 270 publications, multiple U.S. patents, and leadership roles as Technical Program co-Chair for ICIP 2020/2024. His work demonstrates significant impact through awards like the IEEE Fellow designation (2022) and multiple best paper awards at premier conferences. IEEE Fellow (2022) 2023 EURASIP Best Paper Award 2019 ICIP Best Paper Award 2017 Denning Faculty Award for Global Engagement CSIP Research & Service Awards (2003) He has advised numerous PhD students including Dr. Ashraf Alattar (now Auburn professor) and Dr. Zhiling Long (Kennesaw State faculty). His lab structure emphasizes collaborative teams comprising postdocs, senior/junior PhD students, and undergraduates working on high-impact problems from autonomous systems to medical diagnostics. Current research thrusts include trustworthy neural networks, human-in-the-loop frameworks, and deployment of machine learning in seismic interpretation and ophthalmology.