Xiaofeng Liu is an Assistant Professor at Yale University School of Medicine in the Departments of Radiology & Biomedical Imaging and Biomedical Informatics & Data Science. He is also an Associate Member at the Broad Institute of MIT and Harvard. Previously, he held faculty positions at Harvard Medical School and research roles at Massachusetts General Hospital and Beth Israel Deaconess Medical Center. PhD in Mechatronics from University of Chinese Academy of Sciences Dual Bachelor's degrees in Automation (Wang-Daheng Elite Class) and Communication from University of Science and Technology of China His research integrates trustworthy AI, medical imaging, and data science to improve diagnosis, prognosis, and treatment monitoring for neurological disorders, cancer, and cardiovascular diseases. Key focus areas include domain adaptation techniques, diffusion models, and interpretable AI systems. Led special issues in IEEE Transactions on Pattern Analysis and Medical Image Analysis Developed novel frameworks like Ordinal UDA and Memory-Consistent Adaptation Scientific accolades include the Trailblazer R21 Award (NIBIB), OpenAI Research Award, and National Artificial Intelligence Research Resource Pilot Award. He serves as Associate Editor for IEEE Transactions on Neural Networks and Learning Systems and actively contributes to MICCAI and NIH review panels. His lab at Yale (XLiu Lab) investigates neural basis of intelligence to inspire AI development, with applications in brain tumor segmentation, cardiac imaging, and cross-modal medical diagnostics.
Sina Sareh is a robotics researcher at the Royal College of Art (RCA), where he leads the RCA Robotics Laboratory within the School of Design. He has established himself as an expert in soft robotics and multimodal sensing, developing innovative solutions for human safety and access problems in industrial operations. Dr. Sareh's educational background includes: PhD in Robotics from the University of Bristol, where he worked on monolithic design of flexible actuators for operation in confined liquid environments MSc in Control Systems from the University of Sheffield BSc in Electrical Engineering from Amirkabir University of Technology, Tehran Dr. Sareh's research focuses on soft robotics, multi-modal mobility, manipulation and attachment, and multimodal sensing. His work bridges the gap between robotics engineering and practical applications, particularly in medical and industrial settings. He has developed novel approaches to robotic attachment inspired by octopus biology, created haptic interfaces that mimic the feeling of touching human internal organs, and designed soft robotic technologies to help articulate pain symptoms. His research consistently demonstrates innovation in creating adaptable robotic systems that can operate effectively in complex, unstructured environments where traditional rigid robots face limitations. His publication record demonstrates a strong trajectory in robotics research, with emphasis on soft robotics, medical applications, and novel sensing techniques. The research shows progression from fundamental soft actuator design to practical applications in surgery, industrial operations, and human-robot interaction, with a consistent focus on solving real-world problems through biologically inspired approaches. Dr. Sareh has successfully secured multiple research grants, including EPSRC funding for 'Getting a Grip' and 'Multi-vendor Interoperability in Robotics,' as well as InnoHK funding for 'Intelligent Medicine Warehousing.' He has also served as an impact assessor for the Research Excellence Framework (REF) 2021 in Engineering and is a member of the editorial board at IET Cyber-physical Systems and Robotics Journal. Currently, Dr. Sareh advises research students including Filippo Sanzeni, and maintains active collaborations with industry and academic partners through the RCA Robotics Laboratory, which serves as a hub for interdisciplinary robotics research at the intersection of design, engineering, and human-centered applications. His work on projects like 'Topographies of Pain' and 'Reminisys' demonstrates a commitment to applying robotics technology to improve healthcare outcomes and quality of life.
Ismail Ben Ayed is an Associate Professor at École de technologie supérieure (ETS) in Montreal, Canada, holding the ETS Research Chair on Artificial Intelligence in Medical Imaging. His research bridges computer vision, optimization, and medical image analysis to develop advanced algorithms for clinical applications, with particular focus on cardiac and neurological imaging. His research program centers on medical image segmentation using novel optimization techniques, graph-based methods, and deep learning models. He pioneers approaches for handling volumetric bias, shape compactness, and distribution matching in MRI and cardiac imaging, directly addressing clinical challenges in spine labeling, ventricle segmentation, and tumor detection. His work emphasizes mathematical rigor combined with practical medical relevance. Analysis of his 15 most recent publications (2014-2017) reveals dominant themes in medical image segmentation (80% of works), particularly for cardiac MRI (35%) and neurological applications (25%). Key methodological contributions include distributed optimization frameworks (20%), advanced graph cut techniques (30%), and deep learning architectures (25%), published consistently in top-tier venues including CVPR, MICCAI, and TPAMI. His scientific recognition includes: MICCAI travel award (2017) Outstanding Reviewer Award at CVPR (2015) GE innovation award (2010) He actively mentors researchers as evidenced by his recruitment of PhD students and postdocs, with research supported by the ETS Research Chair and multiple patents. His service includes chairing MICCAI 2017/2015 and IPTA 2017, plus continuous program committee roles at CVPR, ICCV, and MICCAI since 2011. Leading the ETS Research Chair on AI in Medical Imaging, he directs a collaborative team working on clinical translation of computer vision techniques. Current projects focus on cardiac motion analysis, brain tumor segmentation, and spine labeling systems with direct applications in radiology workflows.
Ken Wong is an Associate Professor in the Department of Computing Science at the University of Alberta's Faculty of Science. He also serves as Associate Chair within the same department. Holding a PhD in Computer Science from the University of Victoria (1999), his research focuses on software engineering challenges such as reverse engineering, program understanding, and software visualization. He emphasizes improving software evolution through tools like architecture recovery and root cause analysis, with applications in web/mobile platforms and diverse system understanding. Teaching highlights include developing Massive Open Online Courses (MOOCs) via Coursera, including the 'Software Product Management Specialization' and courses on Agile practices, client needs analysis, and software metrics. His recent publications (2023–2025) span AI-driven healthcare innovations (e.g., medical imaging, photoacoustic tomography) and advanced computer vision techniques (e.g., diffusion models, video inpainting). Notable collaborations include EVAREST studies on heart failure management and lung transplantation outcomes. His work bridges software engineering theory and practical applications in healthcare technology, with contributions to federated learning frameworks (e.g., FedLPPA) and AI-augmented clinical decision support systems. Research also extends to autonomous driving (DriveGPT4-V2) and 3D human avatar generation (DreamAvatar), showcasing interdisciplinary impact.
Dr. Brian Y. Chen is an Associate Professor and Doctoral Program Director in the Department of Computer Science & Engineering at Lehigh University. His research focuses on bioinformatics, structural biology, and machine learning applications in computational biology. He holds a Ph.D. in Computer Science from Rice University and B.A. degrees in Mathematics and Computer Science from Rutgers University. Dr. Chen's work emphasizes developing algorithms to analyze protein structures, protein-protein interactions, and ligand binding mechanisms. He has contributed to tools like DeepVASP-S and MechPPI, which explain molecular interactions and predict binding specificity. His recent projects include Alzheimer’s disease diagnosis using multimodal data and containerization frameworks for bioinformatics software. He previously served as a postdoctoral researcher in Barry Honig's Lab at Columbia University, where he contributed to the Center for Computational Biology and Bioinformatics. His research spans structural bioinformatics, computational methods for protein function prediction, and interdisciplinary applications in medicine and materials science. Key achievements include a nomination for Outstanding Mentorship (2017) and collaborative projects funded by the Army Research Lab and Lehigh University. His lab explores cutting-edge AI techniques for biomedical problems, including interpretable machine learning models and scalable bioinformatics pipelines.
Maarten De Vos is a Professor at the Department of Electrical Engineering (ESAT) , KU Leuven , with dual appointments in the Faculty of Medicine and Faculty of Engineering Science . He leads interdisciplinary research at the intersection of artificial intelligence and biomedical signal processing.
Paul A. Yushkevich is a Professor of Radiology at the Perelman School of Medicine, University of Pennsylvania , with affiliations in the Bioengineering Graduate Group . He leads the Penn Image Computing and Science Laboratory (PICSL) , focusing on advanced biomedical image analysis techniques. Developed first-of-its-kind computational atlas of the hippocampal formation Led NIH R01-funded research on MRI-derived biomarkers for Alzheimer's disease Created open-source software tools: ITK-SNAP and Convert3D Expert in statistical shape modeling and histology-MRI co-registration Research Focus: Specializes in hippocampal segmentation using high-resolution MRI, with applications in Alzheimer's disease research and cardiac imaging . His work combines differential equations and machine learning for accurate image analysis. Scientific Achievements: First-place MICCAI segmentation challenges (2012, 2013) Over 169 PubMed publications in neuroimaging and computational anatomy Developed DTI-TK toolkit for diffusion MRI analysis Collaborations: Works with Alzheimer's Disease Neuroimaging Initiative (ADNI) and multiple international institutions. Supervises graduate students in biomedical image analysis.
Zachi Attia, Ph.D., M.B.A., is an Associate Professor at the Mayo Clinic College of Medicine and Science, Rochester, Minnesota. His research focuses on applying artificial intelligence (AI) and machine learning to cardiac biosignals, particularly for early disease detection and prediction. He holds primary and joint appointments as Consultant in AI within the Department of Cardiovascular Medicine, collaborating with the Center for Digital Health and the Robert D. and Patricia E. Kern Center for the Science of Health Care Delivery. Education: Ph.D. in Electrical Engineering from the University of Minnesota, Rochester; BSc and MSc in Electrical Engineering from Ben Gurion University, Israel. Dr. Attia's work centers on developing AI models that analyze multimodal cardiac data (ECGs, echocardiograms, angiograms) to detect silent diseases. His research includes pragmatic clinical trials to validate AI's impact on patient outcomes, explainable AI for biological insights, and integrating AI dashboards into medical records for clinical usability. Recent publications highlight AI applications in detecting atrial fibrillation, hypertrophic cardiomyopathy, and pulmonary hypertension via ECG analysis. Scientific Awards: No explicit awards mentioned in the text. Email: attia.itzhak@mayo.edu
Karima Addetia serves as an Associate Professor in the Department of Medicine-Cardiology at the University of Chicago. Her academic career has been dedicated to advancing echocardiographic techniques and their clinical applications, particularly in the assessment of right heart function, cardiac amyloidosis, and tricuspid valve pathology. She has established herself as a leading researcher in cardiac imaging through extensive collaborations with the World Alliance of Societies of Echocardiography (WASE) and frequent co-authorship with Dr. Roberto M. Lang, a prominent figure in cardiovascular imaging. Dr. Addetia's research interests span multiple critical areas in cardiovascular medicine. She has pioneered work in right heart assessment, establishing normative values for right ventricular size and function through large-scale multicenter studies. Her investigations into cardiac amyloidosis have significantly advanced the understanding of echocardiographic patterns associated with this condition, particularly regarding apical sparing and strain patterns. She has also made substantial contributions to tricuspid valve assessment, examining both normal anatomy and pathological conditions including device-related complications. More recently, her work has incorporated artificial intelligence applications in echocardiography, exploring how machine learning can improve diagnostic accuracy and workflow efficiency. The trajectory of Dr. Addetia's research publications reveals a consistent focus on quantitative cardiac imaging with increasing sophistication over time. Her early work established foundational knowledge about right ventricular morphology and function, while more recent publications integrate advanced technologies like AI and focus on specific disease states like cardiac amyloidosis. A notable pattern is her participation in large, collaborative studies that establish normative values across diverse populations, addressing important gaps in understanding how cardiac measurements vary by age, sex, and ethnicity. Her work consistently bridges technical echocardiographic advancements with direct clinical applications. Dr. Addetia's collaborative approach is evident through her extensive involvement with the WASE study group and numerous multicenter investigations. Her research methodology typically combines rigorous quantitative analysis with clinical correlation, producing findings that directly impact diagnostic criteria and clinical practice guidelines. While specific grant information isn't detailed in the available publications, her leadership in major collaborative studies suggests significant research funding support for her work in cardiac imaging innovation.
Professor Mauricio Villarroel is an Associate Professor of Biomedical Engineering at the University of Oxford's Institute of Biomedical Engineering and a Fellow of Magdalen College. He leads the Laboratory for Computational Medicine and Technology (LCMT), which focuses on improving clinical decision-making through digital health innovations for both high-income and low- or middle-income countries. Villarroel was born in Bolivia where he completed his undergraduate engineering degree before obtaining his doctoral degree in Engineering Science from the University of Oxford. He previously worked as a research scientist at the Health Sciences and Technology department at MIT and Harvard University, collaborating with multidisciplinary teams from academia, hospitals, and industry to develop advanced monitoring algorithms for intensive care. He returned to Oxford as a post-doctoral research assistant in Data Fusion & Telehealth and later served as a Senior Researcher in Next Generation of Digital Health. His research focuses on developing non-contact video-based physiological monitoring technologies to create personalized biomarkers of health. He has founded the spinout company OxeHealth based on his early work. Currently, his laboratory develops AI models to identify meaningful physiological changes using multimodal sensing technologies including video cameras, wearable devices, wireless technologies, smartphones, and body-worn sensors. His primary research areas include cardiovascular disease and neurodegenerative diseases, spanning from early detection of chronic conditions to in-hospital monitoring and remote management in community settings. He is also the first academic appointment of The Podium Institute for Sports Medicine and Technology, where he develops technologies to monitor factors leading to sports injuries in young athletes aged 11-18 years. Analysis of his recent publications reveals a strong focus on non-contact physiological monitoring, particularly using photoplethysmography and video-based technologies. His work spans cardiovascular monitoring (blood pressure estimation, circadian rhythms), neurological applications (movement disorders), respiratory monitoring (particularly in infants), and sports medicine (athlete screening). A consistent theme across his research is the development of AI-driven, multimodal approaches to extract meaningful clinical information from non-invasive or contactless monitoring systems. Villarroel has received significant recognition for his work, with multiple publications referenced in patents and clinical guidelines. His research has been picked up by news outlets and widely shared on social media platforms, indicating substantial impact in both academic and practical domains. His work on non-contact monitoring has particularly gained attention for its potential applications in resource-limited settings. As a research leader, Villarroel collaborates extensively with clinicians, engineers, and industry partners. His laboratory offers DPhil opportunities at the intersection of medicine, engineering, and technology. His research has led to practical applications including technologies for monitoring post-operative patients, detecting apnea in infants, and screening athletes for cardiac conditions that could lead to sudden death. The Laboratory for Computational Medicine and Technology maintains strong connections with Oxford's Medical Sciences campus, adjacent to the Churchill Hospital, facilitating direct translation of engineering innovations into clinical practice. The lab's work bridges multiple domains including computer vision, signal processing, AI, and clinical medicine to address significant healthcare challenges.
Professor Maria Eriksdotter is a leading academic in geriatrics and dementia research at the Karolinska Institutet , holding the Department of Neurobiology, Care Sciences and Society . She also serves as a Senior Consultant in Themes Inflammation and Ageing at Karolinska University Hospital Huddinge and previously as Dean of KI South (2019–2023). Her work spans translational research, clinical trials, and national registry development, with a focus on Alzheimer's disease, cholinergic therapies, and aging. Her research group pioneered NGF cell therapy for Alzheimer's patients, demonstrating safety and cognitive stabilization in clinical trials. She chairs the SveDem registry , tracking over 100,000 dementia patients to refine diagnostics and care. Studies from SveDem revealed mortality reduction with cholinesterase inhibitors and highlighted pandemic-era diagnostic delays. Recent publications analyze dementia subtypes , comorbidities , and precision medicine in neurodegeneration. Her work intersects neuroimaging , epidemiology , and public health policy , addressing ageism and improving geriatric care systems. Collaborations span Karolinska University Hospital , NSGene Inc , and international institutions.
Professor Jinman Kim is a Professor in the School of Computer Science at the University of Sydney and Director of the Biomedical Data Analysis and Visualisation (BDAV) Lab. He also serves as Research Director of the Telehealth and Technology Centre at Nepean Hospital. His research focuses on machine learning applications in biomedical image analysis, visualization, and multi-modal data processing. Kim holds a PhD in Computer Science from the University of Sydney (2006) and has held roles including Senior Lecturer (2013), Associate Professor (2016), and Professor (2022). He is an Area Editor for Computer Methods and Programs in Biomedicine and actively contributes to AI-driven healthcare initiatives. His academic journey includes a Marie Curie Fellowship at the University of Geneva (2010) and leadership roles in projects like the ARC Training Centre in Innovative Biomedical Engineering. He co-leads the Digital Health Imaging initiative under the Faculty of Engineering’s Digital Science Initiative. Kim has developed teaching programs such as the Master of Digital Health and Data Science, co-taught with the Faculty of Medicine and Health. Research interests span AI in medical imaging, telehealth systems, and interdisciplinary biomedical engineering. His work includes advancements in PET/CT fusion, tumor segmentation, and medical visual analytics. Kim’s lab explores applications like AI in dental education, cutaneous lymphoma detection, and fair AI models for healthcare. Notable collaborations include the Telehealth Remote Monitoring System for chronic patients and contributions to datasets like the HRDC Challenge for hypertension classification. His labs prioritize translating AI innovations into clinical tools for improved healthcare accessibility and precision.
**FENG Mengling** is an Associate Professor at the National University of Singapore (NUS) and holds primary affiliation with the Saw Swee Hock School of Public Health. She serves as the Domain Leader for the Biostatistics, Modelling, AI and Data Analytics (B.MAD) Domain and Director of the AI for Public Health (AI4PH) Program. Her academic credentials include a Senior Post-doc from Harvard-MIT Health Science Technology Division, a PhD from Nanyang Technological University (2009), and a Bachelor's degree (2003) from NTU. Research & Teaching: Her research focuses on causal inference for evidence-based medicine, generative models for medical time-series analysis, and healthcare data analytics. She teaches courses on big data technologies for healthcare problems and healthcare data analytics. Professional Roles & Awards: She has led the Biomedical and Healthcare Analytics Lab at the Institute for Infocomm Research (2014–2015) and currently serves as an Affiliate Scientist at Harvard-MIT. Notable accolades include the MIT Teaching & Learning Laboratory Kaufman Teaching Certificate and recognition as a finalist in MIT’s 2013 Innovation Showcase. Her work has been featured in prominent media outlets like The Straits Times and Channel NewsAsia, highlighting breakthroughs such as AI nurses and Singlish-speaking healthcare assistants. Publications & Impact: Over 50 peer-reviewed publications span AI-driven clinical decision support, medical imaging analysis, and predictive modeling in critical care. Key contributions include frameworks like MedDreamer (reinforcement learning for EHR analysis) and DivScore (LLM-generated text detection). Her research bridges causal inference, generative AI, and scalable healthcare solutions. Labs & Initiatives: As a leader in NUS’s Public Health AI Innovation Center (launching early 2025), she drives initiatives like FxMammo (AI for breast cancer screening) and the Biomedical and Healthcare Analytics Lab. Her work emphasizes ethical AI deployment and cross-disciplinary collaboration in healthcare.
Bjoern Menze is a Professor and Rudolf Mößbauer Tenure Track Chair at the Technical University of Munich (TUM), leading the Image-based Biomedical Modeling Group within the Munich School of Bioengineering. His research focuses on medical image computing, tumor growth modeling, and computational physiology, with applications in clinical neuroimaging and personalized radiotherapy design. He holds a Ph.D. in Computer Science from Heidelberg University and has held positions at ETH Zurich, INRIA Sophia Antipolis, MIT, and Harvard Medical School. His academic journey includes a postdoc at MIT’s CSAIL and Harvard Medical School, followed by roles at ETH Zurich and INRIA. His work bridges biomedical imaging with machine learning, emphasizing model-driven analysis of physiological processes. He has been a visiting professor at Maastricht University and contributes to initiatives like the Center for Translational Cancer Research at TUM. Key research areas include tumor growth modeling, quantitative imaging biomarkers, and integrating mathematical models with clinical data. His awards include the MICCAI Young Scientist Award (2014), Leopoldina Fellowship (2009), and DFG Research Fellowship (2008). He advises on medical AI, leads interdisciplinary projects, and publishes extensively in top journals like Nature Neuroscience and IEEE Transactions on Medical Imaging. His lab’s work spans applications such as glioblastoma radiotherapy optimization, whole-body bone lesion detection, and neural connectivity imaging. Collaborations include institutions like Harvard, MIT, and ETH Zurich. He emphasizes translating computational methods into clinical practice for personalized healthcare solutions.
Professor Danilo Mandic is a leading academic in Machine Intelligence and Signal Processing at Imperial College London's Department of Electrical and Electronic Engineering. He holds roles including President of the International Neural Network Society and Distinguished Lecturer for IEEE Computational Intelligence and Signal Processing Societies. His research spans Statistical Learning, Wearable Sensing (Hearables), Financial Signal Processing, and Tensor Networks for Big Data. Key contributions include pioneering in-ear physiological sensing and developing quaternion-based adaptive filters. He has authored over 600 publications, including seminal monographs on neural networks and complex-valued signal processing. Education: PhD in Nonlinear Adaptive Signal Processing from Imperial College (1999). Professional accolades include the 2019 Dennis Gabor Award and multiple IEEE Best Paper Awards. His labs include the Financial Signal Processing & Machine Learning Lab and collaborations with the Centre for Neurotechnology. He advises numerous students and leads projects on AI ethics, graph signal processing, and biomedical applications. His work emphasizes translating research into educational curricula via participatory sensor-based learning.
