Markus Hagenbuchner is an Associate Professor at the University of Wollongong's School of Computing and Information Technology, leading research in artificial intelligence and data science. His work advances machine learning methodologies for healthcare and engineering applications. Research focuses on developing robust deep learning architectures, including recursive convolutional networks and transformers for medical image analysis. Key applications include radiotherapy dose prediction, freezing of gait detection, and long-tailed classification challenges. Recent publications demonstrate innovations in model interpretability, computational efficiency, and handling of imbalanced datasets. Recurring technical themes include architectural optimizations for convolutional networks and generative adversarial networks. As principal investigator on NHMRC-funded projects, Hagenbuchner develops machine learning solutions for adaptive radiotherapy and medical diagnostics. His research bridges theoretical AI advancements with clinical healthcare applications.
Associate Professor Chelsea Dobbins holds a faculty position at the University of Queensland (UQ), leading the School of Electrical Engineering and Computer Science as Director of Teaching and Learning. Previously, she served as a Senior Lecturer at Liverpool John Moores University (UK). Her expertise spans Software Engineering, Digital Signal Processing, and Human-Computer Interaction with a focus on emotion detection via wearable sensors and lifelogging technologies. Education: Bachelor (Honours) of Science (Advanced) from Liverpool John Moores University Doctor of Philosophy (PhD) from Liverpool John Moores University Research Interests: Dr. Dobbins’ work integrates affective computing, digital health, and pervasive computing. Core areas include emotion detection through mobile/wearable sensors, lifelogging for memory augmentation, physiological computing, and applications in healthcare. Her research has been supported by the UK’s EPSRC, notably for developing mobile platforms to detect negative emotions during driving. Key Contributions: She pioneered studies on neuroadaptive gaming for pain distraction, smartwatch battery utilization analysis, and machine learning frameworks for fatigue detection. Her 2016 ACM award-winning work addressed multivariate mobile data mining. Impact: Featured in New Scientist and Times Higher Education Case study highlighted on Shimmer’s platform Active in interdisciplinary collaborations, bridging engineering, healthcare, and cognitive science Future Directions: Current projects explore wearable devices in cystic fibrosis management and immersive VR presence measurement. She advocates for health professional education via FHIR-based platforms and continues advancing human-centered computing solutions.
Dr. Michael I. Miga is the Harvie Branscomb Professor and Chair of Biomedical Engineering at Vanderbilt University's School of Engineering. He holds joint appointments in Radiology, Neurological Surgery, Otolaryngology, and Computer Science. As Director of the Vanderbilt Institute for Surgery and Engineering (VISE) and the Biomedical Modeling Laboratory (BML), he leads interdisciplinary research in image-guided surgery, computational modeling for therapeutic applications, and soft-tissue biomechanics. Affiliations : Vanderbilt University School of Engineering, VISE, BML. Education : Ph.D. in Biomedical Engineering from Dartmouth College (2001). Research : Focuses on enhancing surgical guidance through advanced modeling, including digital twins, augmented reality, and biomechanical simulations. His work spans liver, brain, breast, and kidney surgeries. His lab develops translational technologies, such as the first FDA-cleared image-guided liver surgery system. He directs an NIH-funded T32 training program in surgery-engineering collaboration. Awards : AIMBE Fellow, SPIE Fellow; NIH Study Sections (BMIT-B, BTSS). Grants : Multiple NIH grants for image-guided interventions, tumor response modeling, and surgical training. Current projects include computational forecasting for neoadjuvant therapy, vagus nerve stimulation modeling, and mixed-reality surgical navigation systems.
Dr. Ellen Donovan is a Visiting Professor at the University of Surrey's School of Biosciences, affiliated with the Centre for Vision, Speech and Signal Processing (CVSSP). She also serves as a Research Adviser for the Research Design Service South East region since 2017. Her research focuses on advancing radiotherapy techniques for breast cancer patients, particularly leveraging medical imaging data to improve treatment outcomes and quantify radiomics features. Donovan has a PhD from the Institute of Cancer Research, University of London, and prior degrees from the University of Cambridge and the University of Aberdeen. Education: BA (Hons) Natural Sciences, University of Cambridge (1987) MSc Medical Physics, University of Aberdeen (1992) PhD, Institute of Cancer Research, University of London (2005) Her research interests include optimizing radiotherapy delivery, reducing treatment duration, and minimizing secondary cancer risks. She explores quantitative imaging data (radiomics) to correlate with treatment efficacy and patient outcomes. Donovan is a principal investigator in landmark trials like the FAST and IMPORT series, which evaluate hypofractionated radiotherapy and partial-breast irradiation. Her publications highlight advancements in adaptive radiotherapy, heart-sparing techniques, and breath-hold methods to minimize cardiac exposure. Recent work focuses on reproducibility in radiomics and clinical trial outcomes for breast cancer treatments. Awards: National Institute of Health Research (NIHR) Mentor for Clinical Academics Donovan supervises PhD and MSc students in radiomics and radiotherapy tool development. She teaches radiotherapy physics and clinical academic career development at institutions like the Princes Teaching Trust and British Institute of Radiology. Her lab, CVSSP, integrates interdisciplinary approaches to enhance medical imaging and signal processing in oncology. Future work emphasizes precision radiotherapy and AI-driven radiomics for personalized treatment planning.
Professor Richard Wilson serves as Professor of Gastrointestinal Oncology at the Institute of Clinical Sciences, University of Glasgow, and is an Honorary Consultant in Medical Oncology at the Beatson West of Scotland Cancer Centre. Previously, he was a Senior Lecturer at Queen's University Belfast and Consultant Oncologist at Belfast City Hospital. Graduated from Queen's University Belfast in 1984 Completed clinical oncology training followed by post-CCT Fellowship at the National Cancer Institute in the USA Appointed Senior Lecturer at Queen's University Belfast in 2001 Joined University of Glasgow in 2019 as Professor in Gastrointestinal Oncology Professor Wilson's research spans gastrointestinal cancer (particularly colorectal, small bowel, and anal cancer), drug development, biomarkers, personalized medicine, and early/late phase clinical trials. His work integrates cancer biology, translational research, and clinical applications to advance cancer treatment. He has established significant research programs including the first early phase cancer clinical trials program on the island of Ireland and the International Rare Cancer Initiative Small Bowel Adenocarcinoma Working Group. His publication record reveals consistent contributions to colorectal cancer research with focus areas including molecular subtyping, targeted therapies, immunotherapy approaches, and clinical trial design. Recent work emphasizes personalized medicine approaches and biomarker-driven treatment strategies. Chair of Colorectal Cancer Clinical Studies Group (2014-2017) Co-Chair of International Rare Cancer Initiative Small Bowel Adenocarcinoma Working Group Member of Medical Advisory Board for Bowel Cancer UK (since 2013) First Clinical Director of the N. Ireland Cancer Trials Network Professor Wilson leads the Glasgow Clinical Academic Training component of the TRACC programme, which provides PhD positions for postgraduate trainees and intercalating medical and dental students. He has secured multiple substantial research grants including projects investigating BRAF V600E mutated colorectal cancer, BRAF-driven systemic neutrophilia, and the BALLAD global study for small bowel adenocarcinoma. His leadership extends to major clinical trial initiatives including the FOCUS4 trial program for metastatic colorectal cancer. He directs research teams focused on gastrointestinal oncology, with particular expertise in colorectal cancer biology, clinical trial design, and translational research. His laboratory work spans from basic cancer biology to clinical implementation, maintaining strong connections between discovery science and clinical practice.
David Pekker is an Associate Professor in the Department of Physics & Astronomy at the University of Pittsburgh, affiliated with the Dietrich School. His research focuses on quantum many-body systems, including dynamics of ultracold atoms and condensed matter physics. Key interests include alternatives to thermalization, topology, and non-Abelian excitations for quantum computing applications. Education: BA in Mathematics and BS in Physics from Rice University (2002), PhD in Physics from University of Illinois at Urbana-Champaign (advised by Paul Goldbart). Postdoctoral training at Harvard University and Caltech, focusing on ultracold atom physics and topological systems. Research emphasizes quantum interference devices, superconducting nanowires, and many-body localization. Notable contributions include work on Majorana fermions in cold atom systems and the 'Higgs' amplitude mode in superfluid transitions. Current advisees include Chenxu Liu and Binbin Tian. Collaborates on nanoscale superconducting devices and quantum information technologies.
Katsuto Shinohara is a faculty member at the University of California San Francisco (UCSF), affiliated with the School of Medicine and the Department of Urology. He specializes in urologic cancers, particularly prostate cancer, with expertise in innovative biopsy techniques and image-guided minimally invasive treatments. His clinical and research work emphasizes the application of ultrasound and MRI in cancer diagnosis and therapy. Education: MD in Medicine, Yokohama City University, Yokohama City, Japan Residency in General Surgery, Mitsui Memorial Hospital, Tokyo, Japan Residency in Urology, Kitasato University Hospital, Sagamihara, Japan Fellowship in Urologic Oncology, Baylor College of Medicine, Houston, Texas Dr. Shinohara's research focuses on advancing prostate cancer management through active surveillance , focal therapy , and image-guided interventions . His work integrates multiparametric MRI, ultrasound, and metabolic imaging to improve detection, reduce overdiagnosis, and personalize treatment. He is deeply involved in clinical trials evaluating novel ablation techniques and patient-centered outcomes. The recent publications highlight a strong emphasis on refining risk stratification (e.g., Gleason Grade Groups, CAPRA score), optimizing surveillance protocols, and evaluating emerging therapies like whole-gland and focal ablation. Collaborative studies explore mobile health tools and exercise interventions to enhance patient care. The integration of advanced imaging and biomarkers is a recurring theme across his research. Professional Memberships: Japanese Urological Association Japan Society of Ultrasonics in Medicine American Institute of Ultrasound in Medicine American Urological Association Engineering & Urology Society Dr. Shinohara has lectured widely and published extensively in top-tier urology and oncology journals. His collaborative research includes major multi-institutional trials and consensus guidelines. He contributes to advancing clinical practice through evidence-based studies on biopsy strategies, treatment timing, and innovative imaging. While no formal advising or grant information is provided, his role in numerous studies suggests mentorship and research leadership. He is actively involved in the UCSF urology research ecosystem, contributing to technical developments in imaging and therapy. His work supports the broader mission of precision oncology in urology, aiming to improve outcomes while minimizing treatment burden.
Olivier Morin, PhD , is a Professor in the Department of Radiation Oncology at the University of California, San Francisco (UCSF) School of Medicine. His research focuses on developing multi-omics prediction models for personalized cancer diagnosis and treatment through the MEDomics Consortium . Key research areas include quantitative imaging , natural language processing , and prognostic machine learning models applied to radiation oncology and cancer informatics. Morin's work leverages artificial intelligence and machine learning to create point-of-care tools for clinical decision-making. His group develops novel algorithms for interpretable multi-criteria analysis in cancer treatment planning and outcome prediction. Publications highlight collaborations across institutions in radiomics , radiation therapy optimization , and medical imaging . Education: PhD in Bioengineering (UCSF & UC Berkeley) Certification: Management of New Technologies (UC Berkeley) His recent articles demonstrate expertise in GBM recurrence prediction , adverse radiation effects , and multi-institutional imaging datasets . Despite extensive publication history, no explicit scientific awards are mentioned in the provided materials.
Nicola Dilillo is a PhD Student in Computer and Systems Engineering (38th cycle, 2022-2025) at the Department of Control and Computer Science (DAUIN) of Politecnico di Torino. He also serves as an External Collaborator for Internationalization, Cooperation, Alliances and Mobility (INCAM) and as an External lecturer and/or teaching assistant at DAUIN. His educational background includes: Bachelor's degree in Computer Engineering (specializing in Embedded Systems) from Politecnico di Torino Master's degree in Computer Engineering (specializing in Embedded Systems) from Politecnico di Torino His research focuses on Smart Agriculture, integrating advanced technologies to address agri-food sector challenges. He develops AI and computer vision solutions for soil moisture prediction using recurrent neural networks (RNN, GRU, LSTM), multispectral imaging for crop health assessment, and deep learning for weed detection. His work aims to optimize resource use, increase yields, and reduce environmental impact through precision farming. His recent publications (2024-2025) demonstrate a strong trend in applying artificial intelligence to agricultural problems, particularly in soil moisture modeling, crop classification via spectral analysis, and sustainable practices using biofertilizers. The research spans computer vision, machine learning, and environmental science, highlighting interdisciplinary approaches for sustainable farming. No information on student advising or research grants was provided in the available text. He is an active member of the CAD - Electronic CAD & Reliability Group at DAUIN, contributing to research in electronic design and reliability.
Hesham Elhalawani, MD, MSc is an Attending Physician in the Department of Radiation Oncology and Instructor in Radiation Oncology at Harvard Medical School. He is affiliated with Dana-Farber/Boston Children's Cancer and Blood Disorders Center, where he specializes in treating pediatric cancer patients with radiation therapy. His educational background includes: Medical School: Ain Shams University, Faculty of Medicine (2011, Cairo, Egypt) Internship: Internal Medicine, Ain Shams University (2012) Residency: Clinical Oncology/Nuclear Medicine, Ain Shams University (2015) Fellowship: Radiation Oncology, University of Texas MD Anderson Cancer Center (2019) Fellowship: Radiation Oncology, Cleveland Clinic Taussig Cancer Institute (2020) Fellowship: CNS Radiation Oncology, Brigham and Women's Hospital (2022) Dr. Elhalawani's clinical focus centers on pediatric cancers, particularly brain tumors, bone tumors, Hodgkin lymphoma, and neuroblastoma. His research interests bridge radiation oncology with cutting-edge computational approaches, with a strong emphasis on leveraging machine learning and imaging informatics to personalize cancer care. He has developed expertise in integrating multi-parametric magnetic resonance imaging (mpMRI) and quantitative imaging analytics to advance image-guided cancer treatment and surveillance. His work has significantly contributed to the development of clinical applications of radiomics analytics in radiation oncology. Analysis of his recent publications (2023-2025) reveals a strong research focus on applying artificial intelligence and machine learning techniques to radiation oncology, particularly for pediatric brain tumors and metastases. His work spans from developing deep learning algorithms for tumor segmentation to creating predictive models for treatment outcomes and recurrence risk. A notable trend is his integration of radiomics with genomic data to create more precise treatment approaches, as seen in his work on molecular subtyping of pediatric gliomas and genomic scores for predicting treatment response. Dr. Elhalawani has been actively involved in several major challenges and collaborative efforts in medical imaging AI, including the Brain Tumor Segmentation (BraTS) Challenge and the HECKTOR challenge for head and neck tumor analysis. His research demonstrates a consistent pattern of bridging clinical radiation oncology with computational innovation to improve pediatric cancer outcomes. While specific advising relationships aren't detailed in the provided information, his position as an Instructor at Harvard Medical School suggests involvement in training medical students, residents, and fellows in radiation oncology. His research program likely involves collaboration with data scientists, medical physicists, and other oncology specialists working at the intersection of AI and cancer treatment. Dr. Elhalawani's work is primarily conducted within the Dana-Farber/Boston Children's Cancer and Blood Disorders Center, which provides comprehensive care for children with cancer and blood disorders. His research appears to be part of larger collaborative teams focused on developing innovative approaches to pediatric radiation oncology, with particular emphasis on computational methods to enhance treatment precision and personalization.
Sachin Kheterpal, MD, MBA is a Professor of Anesthesiology at the University of Michigan Medical School , where he serves as the Chair of the Department of Anesthesiology and holds the Robert B Sweet Endowed Professorship . He leads the Multicenter Perioperative Outcomes Group (MPOG) , a consortium of over 60 health systems advancing observational research, pragmatic trials, and quality improvement in perioperative care. Education MD - University of Michigan Medical School (1999) MBA - University of Michigan Business School (2004) BS - University of Michigan College of Literature, Science and the Arts (1996) Kheterpal’s research focuses on applying information technology , electronic health records , and machine learning to solve critical challenges in anesthesia, including: Transfusion risk prediction Neuromuscular blockade optimization Acute kidney injury prevention Difficult airway assessment Cardiac surgery outcomes Clinical practice variation analysis His recent publications demonstrate expertise in perioperative data science , with applications spanning predictive analytics , pediatric anesthesiology , and critical care . Kheterpal received the 2024 ASA Excellence in Research Award for his transformative work in multicenter collaborations. He maintains active roles in national organizations including: Elected member - National Academy of Medicine Member - NIH Novel and Exceptional Technology and Research Advisory Committee (NExTRAC) Center member - Institute for Healthcare Policy and Innovation , Weil Critical Care Research , Samuel and Jean Frankel Cardiovascular Center , and Precision Health Initiative A dedicated mentor, Kheterpal contributes to grant-funded research programs and drives institutional innovation in anesthesiology.
Dr. Atılım Güneş Baydin is an Assistant Professor in Machine Learning at the University of Oxford , where he leads the Oxford AI for Science Lab . He holds dual appointments in the Department of Computer Science and Department of Engineering Science , and is affiliated with Jesus College , Kellogg College , and the European Lab for Learning and Intelligent Systems (ELLIS) . Academic Roles : Departmental Lecturer (Assistant Professor) in Machine Learning, Senior Researcher in Engineering Science Research Groups : Torr Vision Group, Oxford Applied and Theoretical Machine Learning Group (OATML) His research focuses on probabilistic programming , differentiable programming , and generative modeling , with applications in scientific discovery and space missions. He develops methods for large-scale simulator inference and deep learning for space weather , collaborating with NASA , ESA , and Lawrence Berkeley National Lab . Notable Contributions : Co-organized 7+ NeurIPS workshops on ML for Physical Sciences Led the development of PyProb and DiffSharp probabilistic programming frameworks Served on editorial board of ACM Transactions on AI for Science
Amit Pai is a Professor and Chair of Clinical Pharmacy at the University of Michigan's College of Pharmacy. He also serves as Co-Director of the Pharmacokinetics Core Laboratory and Associate Director of Pharmacomorphomics for the Morphomics Analysis Group. Education: Pharm.D. from University of Texas at Austin and Health Sciences Center in San Antonio Pharmacy Practice Residency at Bassett Healthcare, Cooperstown Infectious Diseases/Pharmacokinetics Fellowship at University of Illinois at Chicago Research Focus: Dr. Pai specializes in optimal drug dose selection for specific populations , particularly obesity-related pharmacokinetic alterations. His work spans antimicrobial dosing , pharmacomorphomics , and therapeutic drug monitoring , integrating CT imaging and radiomics for body composition analysis. Publication Trends: Recent studies emphasize antibiotic pharmacokinetics in obesity , GLP-1 receptor agonist interactions , and radiomic biomarkers for drug dosing. Collaborative works address pediatric antibiotic regimens and precision oncology . Awards & Recognition: 2023 Russell R. Miller Award (ACCP) 2020 ACCP Excellence in Achievement 2019 SIDP Paper of the Year US FDA Regulatory Science Excellence Award Students & Labs: Mentored researchers like Trey Putnam and Indhumathy Subramaniyan . Leads the Pai Laboratory and collaborates with the Morphomics Analysis Group on body composition studies.
Dr. Sanjay Aneja is an Assistant Professor within the Department of Therapeutic Radiology at Yale School of Medicine, with a secondary appointment in Biomedical Informatics & Data Science. He serves as Director of Clinical Informatics and Director of Medical School Clerkship in Therapeutic Radiology, and is Assistant Cancer Center Director for Bioinformatics at Yale Cancer Center. Dr. Aneja's educational background includes: MD from Yale School of Medicine (2013) BA in Applied Mathematics from Columbia University (2009) Residency in Radiation Oncology at Yale-New Haven Hospital Medicine Internship at Memorial Sloan Kettering Cancer Center Postdoctoral Research Fellowship in Machine Learning at the Center for Outcomes Research and Evaluation (CORE) Research Fellowship at the Department of Health and Human Services Dr. Aneja is a physician-scientist whose research focuses on applying machine learning techniques to clinical oncology. His laboratory develops AI-driven solutions that leverage high-dimensional healthcare data to improve patient outcomes. The Aneja Lab's work spans multiple domains from "calculation to clinic," including machine learning algorithm development (metric learning, generalization theory, interpretability techniques, uncertainty quantification) and clinical applications (outcome prediction, disease classification, clinical workflow automation). His research group has established a national consortium of 7 institutions for developing imaging-based biomarkers of cancer outcomes. Analysis of Dr. Aneja's recent publications reveals a strong focus on applying deep learning to medical imaging, particularly for cancer diagnosis and treatment planning. His work addresses critical challenges in medical AI including model robustness against adversarial attacks, interpretability of deep learning models, and generalization across heterogeneous healthcare data. His research spans multiple cancer types including brain metastases, lung cancer, and breast cancer, with growing interest in patient-reported outcomes and clinical trial matching. Dr. Aneja has received significant research funding and recognition including: NIH Career Development Award NSF Research Grant American Cancer Society Research Award Radiation Society of North America (RSNA) Funding SWOG Hope Grant IBM Computing Research Grant As a mentor, Dr. Aneja leads the Aneja Lab, which includes clinicians, computer scientists, mathematicians, and data scientists working collaboratively on interdisciplinary projects. His lab has established collaborations with Amazon for developing AI-driven patient-reported outcome collection and with SWOG for clinical trial matching research. The lab actively seeks postdoctoral associates and students with quantitative backgrounds to contribute to their innovative research at the intersection of machine learning and clinical medicine. The Aneja Lab maintains active research programs in deep learning for imaging-based biomarkers, interpretability methods for deep learning models, metric learning for "digital twins," generalization of deep learning models across healthcare data streams, physician and patient perception of AI, deep learning methods for patient-reported outcome capture, and natural language processing for clinical trial matching. The lab's GitHub repository hosts several open-source projects related to adversarial imaging, capsule networks, and 3D/2D segmentation techniques.
Peter van der Voort is a Full Professor at TIAS School for Business and Society and University of Groningen , focusing on Health Care Management . He serves as Academic Director of the Executive Master Health Administration (MHA) program and leads research within the TIAS Health cluster. His background as a physician and internist-intensivist at AMC and OLVG informs his expertise in Intensive Care Medicine and clinical leadership. Medical Degree, VU Medical Center Master in Epidemiology, 2006 His research bridges clinical practice with organizational strategy, emphasizing quality management in healthcare systems. Recent work explores: Metabolic factors in respiratory failure (leptin, obesity) Antimicrobial resistance and decolonization Telemedicine and digital transformation Precision dosing in ICU pharmacology Organizational governance in critical care He has co-authored 15+ peer-reviewed articles (2020-2023) on topics spanning: COVID-19 pathophysiology Glucose prediction models Respiratory therapy guidelines Advanced practice provider roles Antibiotic stewardship Healthcare network governance Peter's leadership extends to: Former Head of Adult Intensive Care, University Medical Center Groningen (UMCG) Founding director of Stichting Venticare (telemedicine initiatives) Former Senator for D66, shaping healthcare policy Quality improvement committee leadership
