Keynote Speakers of MICAD2023

 

Prof. Marcel Van Herk

Chair in Radiotherapy Physics, University of Manchester, UK






Physicist Marcel van Herk is responsible for a programme of international leading cancer research and innovation, closely interfaced with clinical practice. The group’s focus is on improving accuracy of radiation therapy including target volume definition, treatment planning, image guidance and imaging-based treatment follow-up generating real-world evidence from very large cohorts of patients.
His multidisciplinary group is part of the division of cancer sciences. It includes 2 senior lecturers (one honorary), 5 research associates, 24 PhD students, 14 masters’ students and 6 clinical scientist (HSST) students who cover physics, clinical oncology, clinical physics, radiography, and radiology. All research is directly aimed at improving the clinical practice of cancer treatment in the Christie, UK, and the world. A key element is the direct collaboration with academic clinicians, of which there are few. His work led to new standards of care in cancer treatment delivery and is recognised internationally as practice changing. Marcel has (co-) authored 300 papers in peer reviewed journals.
Speech Title: Image Guided Radiotherapy - from Bench to Bedside
Abstract: Radiotherapy entails treating cancer with radiation. The most common form is external beam treatment with a linear accelerator. In the last decades this technology has evolved tremendously, and all treatments are now prepared in a meticulous way to maximise dose delivered to the tumour and avoid delivering unnecessary dose to healthy organs close to the tumour. The actual delivery of the treatment requires precisely aligning the target with the treatment beams, and this has been the focus of the first part of my career. I have developed 2D, 3D and 4D imaging solutions integrated with the radiotherapy machine that have been clinically implemented on a very large scale. To enable clinical implementation, the associated software must be straightforward to use and understand. When developing such software, it is important to always keep the clinical requirements in mind, and focus on algorithm stability and acquiring the correct user input. For instance, a simple but important factor is the definition of the region of interest in (rigid) image registration applications. This conveys important clinical information (the most important anatomy), greatly improves algorithm stability by limiting deformations, and provides guidance for algorithm validation. I would therefore argue that design of the user interface, image visualisation and awareness of clinical requirements are as important as the applied algorithms - a fact that is sometimes overlooked by researchers in the medical image computing field. For this reason, collaboration with clinicians and allied healthcare professionals is essential. Another issue that is often forgotten is that clinicians themselves have uncertainty and variability and that there is no such thing as a ground truth to train algorithms. We have been working to improve this situation by training and protocol development, and more recently by big data analysis. For instance, by correlating dose distributions of thousands of patients with clinical outcomes, we have been able to detect that dose to the base of the heart is most predictive of outcomes and this has led to the definition of a new organ at risk, that is currently being tested in a clinical trial.

Prof. Dr. Nassir Navab

Professor and Director of the Laboratories for Computer Aided Medical Procedures at Technical University of Munich (TUM)
Adjunct Professor, Johns Hopkins University
Director of Medical Augmented Reality Summer School Series at Balgrist Hospital, Zurich



Nassir Navab is a full professor and director of the Laboratories for Computer Aided Medical Procedures (CAMP: http://campar.in.tum.de) at Technical University of Munich (TUM) and an Adjunct Professor at Johns Hopkins University (http://camp.lcsr.jhu.edu/). He is also the director of Medical Augmented Reality (http://medicalaugmentedreality.org/) summer school series at Balgrist Hospital in Zurich. In 2001, while acting as distinguished member of technical staff at Siemens Corporate Research (SCR) in Princeton, he received the prestigious Siemens Inventor of the Year Award for the body of his work in interventional imaging. He also received the SMIT Technology Award in 2010 and IEEE ISMAR 10 Years Lasting Impact Award in 2015. He had received his PhD from INRIA and University of Paris XI in France and enjoyed two years of postdoctoral fellowship at MIT Media Laboratory before joining SCR in 1994. He is Fellow of the MICCAI Society and acted on its board of directors from 2007 to 2012 and from 2014 to 2017. He has been one of the founders of and is serving on the Steering Committee of the IEEE Symposium on Mixed and Augmented Reality since 2001. He is the author of hundreds of peer reviewed scientific papers and 51 granted US and over 80 international patents. He served as General Chair for MICCAI 2015, ISMAR 2001, 2005 and 2014. He is a founding board member of IPCAI 2010-2021 and Area Chair for ICCV 2022 and ECCV 2020. He is on the editorial board and advisory board of many international journals including IEEE TMI and MedIA. He is proud of his PhD students, who have received over 50 prestigious awards including MICCAI young investigator awards in 2007, 2009, 2010, 2012, 2015, 2016, 2017 and 2018 and best paper awards at IEEE ISMAR 2005 and 2017, MICCAI MedIA 2016 MICCAI IJCARS 2016 and 2019, IBM best paper award at VOEC-ICCV 2009, IPMI Erbsmann award in 2007 and best poster in 2019, and IPCAI best paper awards in 2014 and 2020. As of September 21, 2021, his papers have received over 44700 citations and enjoy an h-index of 95.
Speech Title: Particularity and Challenges of Machine Learning for Intra-operative Imaging (MLMI2): Towards precision and Intelligence in high intensity, dynamic environments
Abstract: Over the past decade, the rapid advancements in machine learning have revolutionized various fields, significantly impacting our lives. In this talk, we will delve into the realm of medical applications and explore the challenges and opportunities associated with integrating these cutting-edge technologies into computer-assisted interventions. Our primary focus will be on fostering acceptance and trust in machine learning and robotic solutions within the medical domain, which often necessitates the path through Intelligence Amplification (IA). Augmented Reality allows us to leverage IA to augment human intelligence and expertise, ultimately paving the way for the seamless integration of Artificial Intelligence (AI) and robotics into clinical solutions.
Drawing from some groundbreaking research conducted at the Chair of Computer-Aided Medical Procedures at both TU Munich and Johns Hopkins Universities, I will present a series of novel techniques developed to address the unique demands of medical applications. Specifically, we will explore their practical implementations in diverse areas, including Robotic Ultrasound Imaging, Multimodal Data Analysis, and Semantic Scene Graphs for Holistic Modeling of Surgical Domain. Furthermore, I will showcase compelling examples of how Augmented Reality solutions can serve as catalysts for embracing AI in computer-assisted surgery. By harnessing the power of intelligence amplification, we can unlock the full potential of AI technologies, bolstering acceptance and driving the future of computer-assisted interventions. Join me on this enlightening journey as we navigate the intricate intersection of machine learning, medical advancements, and the path from intelligence amplification to artificial intelligence in healthcare.

Prof. Kenji Suzuki

Professor of Biomedical Artificial Intelligence, Founding Director of BMAI
Vice Chair of Department of Information and Communications Engineering BioMedical Artificial Intelligence Research Unit (BMAI)
Institute of Innovative Research at Tokyo Institute of Technology



Kenji Suzuki, Ph.D. (Nagoya University) worked at Hitachi Medical Corp, Aichi Prefectural University, Japan, as a faculty member, in Department of Radiology, University of Chicago, as Assistant Professor, and Medical Imaging Research Center, Illinois Institute of Technology, as Associate Professor (Tenured). He is currently a Professor (Tenured) & Founding Director of Biomedical Artificial Intelligence Research Unit, Institute of Innovative Research, Tokyo Institute of Technology, Japan. He published more than 390 papers (including 120 peer-reviewed journal papers). He has been actively researching on deep learning in medical imaging and AI-aided diagnosis in the past 25 years, especially his early deep-learning model was proposed in 1994. His papers were cited more than 15,000 times, and his h-index is 59. He is inventor on 37 patents (including ones of earliest deep-learning patents), which were licensed to several companies and commercialized. He published 15 books and edited 16 journal special issues. He has been awarded numerous grants including NIH, NEDO, and JST grants, totaling $17M. He serves as Editors of 34 leading international journals including Pattern Recognition. He chaired 120 international conferences. He received 23 awards, including 3 Best Paper Awards in leading journals.
Speech Title: Small-data AI and Its Applications to Diagnostic Aid and Virtual AI Imaging
Abstract: Deep leaning becomes one of the most active areas of research in medical imaging. My group has been actively studying on deep learning in medical imaging in the past 25 years, including ones of the earliest deep-learning models for medical image processing, semantic segmentation of lesions and organs, lesion/organ enhancement, and classification of lesions in medical imaging. In this talk, small-data AI that can be trained with a small number of cases is introduced. Our small-data AI was applied to develop AI-aided diagnostic systems (“AI doctor”) and deep-learning-based imaging for diagnosis (“virtual AI imaging”), including 1) AI systems for cancer detection and diagnosis with medical images, and 2) virtual AI imaging systems for separation of bones from soft tissue in chest radiographs and those for radiation dose reduction in CT and mammography. Some of them have been commercialized via FDA approval in the U.S., including the first FDA-approved deep-learning product.
Research Interests: Artificial intelligence, Deep learning, Machine learning, AI-aided system, Computer-aid diagnosis, Medical image analysis

Prof. Greg Slabaugh

Director of the Digital Environment Research Institute (DERI)
Professor of Computer Vision and AI at Queen Mary University of London, UK





Greg Slabaugh is Professor of Computer Vision and AI and Director of the Digital Environment Research Institute (DERI) at Queen Mary. His primary research interests include computer vision and deep learning, with applications to computational photography and medical image computing. Prior to joining Queen Mary University of London in 2020, he was Chief Scientist in Computer Vision (EU) for Huawei Technologies R&D where he led a team of research scientists working in computational photography, studying the camera image signal processor (ISP) pipeline including denoising, demosaicing, automatic white balance, super-resolution, and colour enhancement for high quality photographs and video. Earlier industrial appointments include Medicsight, where he led a team of research scientists in detection of pre-cancerous lesions in the colon and lung, imaged with computed tomography; with the company's ColonCAD product receiving FDA clearance and CE marking. He also was an employee of Siemens, where he performed research in medical image computing and 3D shape modelling. He holds 36 granted patents and has roughly 200 publications. He earned a PhD in Electrical Engineering from Georgia Institute of Technology in Atlanta, USA where his thesis focused on reconstruction of 3D shapes from 2D photographs. For six years he was an academic at City, University of London where he taught modules in computer vision, graphics, computer games technology, and programming in addition to leading research grants funded by the European Commission, EPSRC and Innovate UK. He was awarded a university-wide Research Student Supervision Award in 2017, and a Teaching in the Schools award for the School of Mathematics, Computer Science, and Engineering in 2016.
Speech Title: Seeing Triple: Working Across Modalities, Anatomies or Tasks for Medical Imaging and Computer-Aided Diagnosis
Abstract: A patient’s journey in the healthcare system often results in multiple data streams including medical images, but also other non-imaging modalities. And even for a single modality, we may want to leverage it for multiple purposes. Starting from a simplified abstraction of the field of medical image computing, this talk will present short vignettes of our recent research, touching on multi-modal, multi-task, and multi-anatomy deep learning applied to medical images.

Prof. Gitta Kutyniok

Professor at Ludwig Maximilian University of Munich, Germany






Gitta Kutyniok completed her Diploma in Mathematics and Computer Science in 1996 at the Universitat Paderborn in Germany. She was then employed as a Scientific Assistant and in 2000 received her Ph.D. degree in the area of time-frequency analysis from the same university. In 2001, she spent one term as a Visiting Assistant Professor at the Georgia Institute of Technology. After having returned to Germany, she accepted a position as a Scientific Assistant at the Justus-Liebig-Universitat Giessen. In 2004, she was awarded a Research Fellowship by the DFG-German Research Foundation, with which she spend one year at Washington University in St. Louis and at the Georgia Institute of Technology. She then returned to Germany, completed her Habilitation in Mathematics in 2006 and received her venia legendi. In 2007 and 2008, being awarded one of the highly competitive "Heisenberg Fellowships” by the DFG-German Research Foundation, she spent half a year at each, Princeton University, Stanford University, and Yale University. After returning to Germany in October 2008, she became a full professor for Applied Analysis at the Universitat Osnabrück Gitta Kutyniok was awarded various prizes for both her teaching and research, among which were the "Weierstrass Prize for outstanding teaching of the Universitat Paderborn” in 1998, the "Research Prize of the Universitat Paderborn” in 2003 as well as the "Prize of the University Gießen” in 2006. Just recently, in 2007, she received the prestigious "von Kaven Prize” awarded annually by the DFG-German Research Foundation. Since 2007, she is an Associate Editor for the Journal of Wavelet Theory and Applications, and since 2009, she is a Corresponding Editor for Acta Applicandae Mathematicae. She was a panelist for the NSF in 2008 and serves as a reviewer for the NSF, GIF, NWO, WWTF as well as for over 30 journals. Her research interests include the areas of applied harmonic analysis, numerical analysis, and approximation theory, in particular, sparse approximations, compressed sensing, geometric multiscale analysis, sampling theory, time-frequency analysis, and frame theory with applications in signal and image processing.

Speech Title: Reliable AI in Medical Imaging: Successes, Challenges, and Limitations

Abstract: Deep neural networks as the current work horse of artificial intelligence have already been tremendously successful in real-world applications, ranging from science to public life. The area of (medical) imaging sciences has been particularly impacted by deep learning-based approaches, which sometimes by far outperform classical approaches for particular problem classes. However, one current major drawback is the lack of reliability of such methodologies. In this lecture we will first provide an introduction into this vibrant research area. We will then present some recent advances, in particular, concerning optimal combinations of traditional model-based methods with deep learning-based approaches in the sense of true hybrid algorithms. Due to the importance of explainability for reliability, we will also touch upon this area by highlighting an approach which is itself reliable due to its mathematical foundation. Finally, we will discuss fundamental limitations of deep neural networks and related approaches in terms of computability, and how these can be circumvented in the future, which brings us in the world of novel computing hardware such as neuromorphic computing.