Marriott Marquis Houston
Houston, Texas, United States
15 - 20 February 2020
Plenary Events
Awards and Plenary Session
Date: Monday 17 February 2020
Time: 4:00 PM - 5:15 PM
Location: Salon F

4:00 pm - Welcome and new SPIE Fellows Acknowledgements

4:15 pm - Best Student Paper Awards Announcements

The first place winner and runner up of the Robert F. Wagner All-Conference Student Paper Award will be announced.

4:20 pm - SPIE Harrison H. Barrett Award in Medical Imaging

This award will be presented in recognition of outstanding accomplishments in medical imaging.

4:30 pm - Plenary Presentation


Are today's Mixed Reality experience pillars and hardware architectures well aligned with the specific needs of medical imaging and surgical guidance?


Bernard Kress
Principal Optical Architect, HoloLens team
Microsoft Corp. (United States)


Abstract: Mixed Reality (MR) headsets have the potential to revolutionize the way we work, learn, communicate, and get entertained. The main pillars for MR development are wearable, visual and social comfort, as well as immersion experience. Do these pillars intersect the specific needs of medical imaging and surgical guidance applications? We will review the various challenges to implement MR hardware specifically adapted to such tasks with today’s start of the art MR headset technology.

Biography: Bernard Kress has been involved in AR,VR and MR technology for the past decade, specifically focussing on hardware issues such as optics, optical architectures and related technologies as well as sensors (depth mapping, head and eye tracking, gesture sensing). Bernard published various books and book chapters and authored more than 100 papers on this topics and holds 50+ international patents on related technologies.
He has been involved in the Google Glass project at Google X Labs since its infancy in 2010, as the principal optical architect, and later joined the HoloLens Team at Microsoft in 2015 as the Partner Optical Architect. He is in charge of shaping the next generation mixed reality optical hardware architectures at HoloLens. He is also a board member and fellow of the SPIE, and conference chair for various SPIE and OSA conferences related to AR,VR and MR.
Imaging Informatics for Healthcare, Research, and Applications Conference Keynote Presentation Sunday
Date: Sunday 16 February 2020
Time: 3:30 PM - 4:30 PM
Location: River Oaks
Imaging Informatics for Healthcare, Research, and Applications
Cybersecurity in healthcare: is our patients' health now at risk?


Dr. Jim Whitfill, HonorHealth and Society for Imaging Informatics (United States)

Abstract: The cybersecurity landscape continues to rapidly evolve across all industries including healthcare. Unique to healthcare, however, is the fact that patients lives can be impacted by simply altering or withholding information. This is session we will look at the evolution of attacks on personal information, to personal health information to personal heath. In addition potential methods to balance sharing of data with protecting patients' identities will be explored to better understand concepts around federated databases and other anonymization techniques.

Biography: As Chief Transformation Officer, Jim Whitfill, MD, brings leadership expertise in healthcare, organizational culture, and information technology to promote a customer-centric experience and offer new ways to deliver more complete, coordinated and accessible care. He brings together data, technology and marketing to advance technical innovations, such as call center technology, CRM systems, apps and digital tools, to give both the customer and caregivers an enhanced approach to care.

By focusing the efforts of these business areas and finding the right digital tools, Dr. Whitfill aims to improve the customer journey so that it becomes more seamless and focused on the needs of the individual. The goal is to transform the organization into a more patient focused and provider friendly health system which better serves the surrounding community.

Before joining HonorHealth, Dr. Whitfill served as chief medical officer for Innovation Care Partners, a clinically integrated network in Phoenix. He also serves as a clinical associate professor in the departments of Internal Medicine and Biomedical Informatics at the University of Arizona College of Medicine-Phoenix.

Dr. Whitfill previously held or holds advisory board responsibilities at GE Healthcare, Philips Healthcare, IDX and KLAS. In July 2018, he began his term as the board chair of the Society of Imaging Informatics in Medicine and is a regular faculty member for the Radiology Society of North America and the American College of Radiology. He is a founding member of the HIMSS-SIIM community for Enterprise Imaging.

Dr. Whitfill received his BA from Princeton University and his MD from the University of Pennsylvania. He trained in internal medicine at the Hospital of the University of Pennsylvania, where he also completed a fellowship in medical informatics.
Imaging Informatics for Healthcare, Research, and Applications Conference Keynote Presentation Monday
Date: Monday 17 February 2020
Time: 8:00 AM - 8:40 AM
Location: River Oaks
Imaging Informatics for Healthcare, Research, and Applications
Shining light into the machine learning "black box": the state of explainable AI


William Hsu, Univ. of California, Los Angeles (United States)

Abstract: The rapid advancement of artificial intelligence (AI) and machine learning (ML) techniques has yielded models whose sensitivity and specificity rival those of trained human experts. However, as these models transition from proofs-of-concept to decision support tools that are used clinically, model developers and the end-users who interact with them should have a clear appreciation of how and what these models are “learning”. Future users of these models should not see them as a “black box” but demand greater transparency from model developers in conveying the rationale behind the chosen representation, how the model was trained, and the explanation associated with a model’s prediction.

In this talk, I will review current and late-breaking research on the development of explainable machine and deep learning algorithms, particularly in the areas of computer-aided detection and diagnosis. I will present a taxonomy of different types of explanations and highlight techniques that interrogate the model based on internal structure or the model’s response to perturbations in the input. I will discuss experiences in applying and interpreting the results of these techniques drawn from my work in lung and breast cancer screening and other published research. Finally, I will assess the limitations and opportunities of current work in interpretable AI/ML, emphasizing the need for visualizations that aid clinical end-users with understanding model outputs and tools for ensuring the validity of model predictions over time.

Biography: William Hsu is Associate Professor at University of California, Los Angeles in the Departments of Radiological Sciences, Bioinformatics, and Bioengineering and a core faculty member with the Medical & Imaging Informatics group. He directs the Integrated Diagnostics Shared Resource, an interdepartmental program that catalyzes research and development of computational tools to improve early detection, diagnosis, and treatment of cancer through the integration and curation of multi-scale data. His research lab focuses on adapting and validating novel AI/ML algorithms, towards assisting physicians with formulating timely, accurate, and personalized management strategies for individual patients. He is a Deputy Editor for the Radiology: Artificial Intelligence journal, a co-editor for the Sensor, Signal, and Imaging Informatics section of the IMIA Yearbook of Medical Informatics, and a working group leader for the American Medical Informatics Association.
Physics of Medical Imaging Conference Keynote Presentation
Date: Monday 17 February 2020
Time: 10:10 AM - 10:50 AM
Location: Salon A
Physics of Medical Imaging (Conference 11312)
Innovations and translation in molecular PET/MR and PET/CT


Georges El Fakhri, Massachusetts General Hospital and Harvard Medical School (United States)

Abstract: In this talk, recent developments in Positron Emission Tomography (PET) and Magnetic Resonance Imaging (MRI) are explored and the challenges of simultaneous imaging in PET/MR and PET/CT as well as the opportunities afforded by two modalities are discussed. The unique sensitivity of PET (picomolar) and its quantitative capabilities can be associated with the superb spatial and temporal resolution of MR as well as its excellent soft tissue contrast to provide an ideal imaging modality for many cancers as well as cardiac and brain explorations. Improvements in image quality and diagnostic accuracy are illustrated in specific patient studies in PET/MR and PET/CT, and synergies between PET and MR spectroscopy are discussed in the context of guiding radiotherapy. Beyond oncology, applications in cardiac (viability, perfusion) and brain imaging (neurodegenerative disease, traumatic brain injury) are presented including very early imaging of prodromal AD and normal aging, mapping of mitochondrial membrane potential and simultaneous PET/fMRI for mapping dopaminergic and serotoninergic neurotransmission.

Biography: Dr El Fakhri is the Nathaniel & Diana Alpert Professor of Radiology at Harvard Medical School (HMS) and the founding Director of the Gordon Center for Medical Imaging at Massachusetts General Hospital and HMS with over 150 members. He is also co-Director of the Division of Nuclear Medicine and Molecular Imaging. Dr El Fakhri is an internationally recognized expert in quantitative molecular imaging (SPECT, PET-CT, and PET-MR) for in vivo assessment of patho-physiology in brain, cardiac and oncologic diseases. Current areas of research include high resolution PET & MR imaging in a range of diseases including neurodegenerative disease and traumatic brain injury (amyloid and neurofibrillary tangles), cardiac arrhythmia and heart failure (mitochondrial membrane potential), as well as guiding radiotherapy planning (PET/MRS). He has authored or co-authored over 300 papers and mentored over 100 students, post-docs and faculty. Dr El Fakhri received many awards and honors, including the Mark Tetalman Award from the Society of Nuclear Medicine, the Dana Foundation Brain and Immuno-Imaging Award, the Howard Hughes Medical Institutes Training Innovation Award and the Edward J. Hoffman Award from the Society of Nuclear Medicine and Molecular Imaging. He was elected Fellow to the SNMMI, AAPM and IEEE for “contributions to biological imaging”.
Computer-Aided Diagnosis Conference Keynote Presentation
Date: Tuesday 18 February 2020
Time: 1:20 PM - 2:20 PM
Location: Salon B
Computer-Aided Diagnosis
Title TBA

(headshot)
TBA, (Affiliation) (Country)

Abstract:

Biography:
Image-Guided Procedures, Robotic Interventions, and Modeling Conference Keynote Presentation
Date: Monday 17 February 2020
Time: 1:20 PM - 2:20 PM
Location: Hunter's Creek
Image-Guided Procedures, Robotic Interventions and Modeling
Healthcare in need of innovation: (exponential) technology and biomedical entrepreneurship as solution providers


Michael Friebe, IDTM GmbH, Otto-von-Guericke Univ. Magdeburg (Germany)

Abstract: There are significant challenges in global healthcare delivery. Some countries have abundant services, but are stuck with a rather nimble and expensive system that focuses on incremental innovations. Other geographies are still in need of basic tools and infrastructure and require completely different, inexpensive, and with that more disruptive solutions.

Healthcare 4.0 with a focus on prevention / early detection and pro-active therapy will employ exponential technologies (AI, Big Data, Sensor Technology, Synthetic Biology, Robotics, 3D Printing, ...) that will surely lead to significant changes in the way we experience and deliver healthcare, where an empowered patient will play a more and more important role.

Innovation in that segment can only lead to meaningful solutions if these actually solve a problem and if these problems have been properly studied and understood including the future economics and delivery changes. Which leads to the question on whether we actually teach our biomedical engineers the right skills considering these developments.

We should introduce a "MEDTEC DESIGN FOR FUTURE HEALTHCARE" type program that embraces technological developments, understands the needs of a future healthcare, teaches entrepreneurial basics and exponential thinking in an interdisciplinary setting.

Biography: Michael is a German citizen with expertise in diagnostic imaging + image guided therapies, as founder/innovator/CEO/investor, and research scientist.

After a BSc. in electrical engineering he spend 5 years in San Francisco as R&D Engineer at a MRI and Ultrasound device manufacturer. In that time he graduated with a MSc. in Technology Management from Golden Gate University, San Francisco and back in Germany obtained his PhD in Medical Physics from the University of Witten.

Dr. Friebe currently is a research fellow of TUM in Munich, an adjunct professor at the Queensland University of Technology in Brisbane, and a professor of Image Guided Therapies at Otto-von-Guericke-University in Magdeburg, Germany.

He is a listed inventor of almost 100 patents, author of >250 scientific contributions, has started well over 20 medical technology start-ups, is a board member of four medical technology startup companies, and an investment partner of a MedTec investment-fund.

He is an SPIE, and IEEE Senior Member and was from 2016-2018 Distinguished Lecturer of the IEEE EMBS teaching innovation generation and future oriented MedTec translation/entrepreneurship from bench to bedside especially in combination with exponential technologies and by employing interdisciplinary approaches within an ethical and patient-benefit centered environment with the ultimate goal to help democratize healthcare.
Ultrasonic Imaging and Tomography Conference Keynote Presentation
Date: Monday 17 February 2020
Time: 2:40 PM - 3:40 PM
Location: Salon C
Ultrasonic Imaging and Tomography
Quantitative ultrasound successes: past, present, and future


Michael Oelze, Beckman Institute, Univ. of Illinois (United States)

Abstract: Diagnostic ultrasound is ubiquitous in clinical practice because it is safe, portable, inexpensive, has high spatial resolution and is real time. Therefore, improving the capabilities of diagnostic ultrasound is a highly significant clinically. In this talk we will discuss different applications of quantitative ultrasound (QUS) imaging and how QUS approaches have evolved over time. Specifically, we will discuss the use of spectral-based approaches to estimate the backscatter coefficient (BSC) and attenuation slope and the use of envelope statistics to describe underlying tissue microstructure. These QUS approaches have been successful at classifying tissue state, monitoring focused ultrasound therapy, detecting early response of breast cancer to neoadjuvant chemotherapy and the automatic detection of nerves in the imaging field. We will demonstrate how QUS approaches can be incorporated on breast tomography machines, which allow an expansion of the tradeoff between spatial resolution and the variance of QUS estimates. One of the ongoing issues with QUS is the inability to properly account for losses in tissues that affect the estimates of the backscatter coefficient. We will demonstrate new calibration procedures that can improve the ability to account for tissue losses. Finally, we will discuss how machine learning approaches can further improve QUS techniques by eliminating the need for models and in some cases eliminating the need for a reference scan.

Biography: Professor Oelze earned a B.S. in Physics and Mathematics (1994, Harding University) and Ph.D. in Physics (2000, University of Mississippi). Dr. Oelze joined the faculty of ECE at UIUC in 2005 and serves as a professor and Associate Head. His research interests involve biomedical ultrasound including: quantitative ultrasound, tomography, therapy and beamforming. Dr. Oelze is a fellow of the AIUM and a senior member of IEEE. He is a member of the Technical Program Committee of the IEEE Ultrasonics Symposium and serves as an associate editor-in-chief of IEEE TUFFC, associate editor of Ultrasonic Imaging and associate editor for IEEE TBME.
Biomedical Applications in Molecular, Structural, and Functional Imaging Conference Keynote Presentation
Date: Tuesday 18 February 2020
Time: 10:10 AM - 11:10 AM
Location: River Oaks
Biomedical Applications in Molecular, Structural, and Functional Imaging
Label-free molecular imaging with spins: a path to high resolution through learned subspaces


Zhi-Pei Liang, Univ. of Illinois (United States)

Abstract: Since its invention in the early 1970s, magnetic resonance imaging (MRI) has become a premier tool for structural imaging and functional imaging using water proton spin signals. MR spectroscopic imaging (MRSI) has also long been recognized as a potentially powerful tool for non-invasive, label-free molecular imaging by exploiting the spin signals from other molecules. However, state-of-the-art MRSI methods, after more than four decades of development, still fall far short of providing adequate spatial resolution, speed, and signal-to-noise ratio (SNR) useful for label-free molecular imaging applications.

The talk will discuss our recent “breakthroughs” in overcoming the long-standing technical barriers of MRSI-based label-free molecular imaging using a new technology known as SPICE (SPectroscopic Imaging by exploiting spatiospectral CorrElation). SPICE uses a subspace mathematical framework to effectively integrate rapid scanning, sparse sampling, constrained image reconstruction, quantum simulation, and machine learning. Preliminary results show an unprecedented capability for simultaneous mapping of brain structures, function and metabolism using intrinsic spin signals from multiple molecules. In this talk, I’ll will give an overview of SPICE and also show some “SPICY” experimental results we have obtained.

Biography: Zhi-Pei Liang is currently the Franklin W. Woeltge Professor of Electrical and Computer Engineering at the University of Illinois at Urbana-Champaign (UIUC). His research is in the general area of magnetic resonance imaging and spectroscopy, ranging from spin physics, signal processing, machine learning, to biomedical applications. His work has been recognized by a number of awards, including the Sylvia Sorkin Greenfield Award (Medical Physics, 1990), Whitaker Biomedical Engineering Research Award (1991), NSF CAREER Award (1995), Henry Magnuski Scholar Award (UIUC, 1999), University Scholar Award (UIUC, 2001), the Otto Schmitt Award (IFMBE, 2012), and the Technical Achievement Award (IEEE-EMBS, 2014). Dr. Liang is a Fellow of the IEEE, ISMRM and AIMBE. He was elected to the International Academy of Medical and Biological Engineering in 2012. Dr. Liang served as President of the IEEE-EMBS from 2011-2012 and received its Distinguished Service Award in 2015.
Image Perception, Observer Performance, and Technology Assessment Conference Keynote Presentation
Date: Wednesday 19 February 2020
Time: 8:00 AM - 9:00 AM
Location: Briargrove
Image Perception, Observer Performance, and Technology Assessment
Towards understanding perception in the latest era of AI in medical imaging


Maryellen Giger, Univ. of Chicago, (United States)

Abstract: The study of human perception is as old as medical imaging. Understanding perception has yielded the rules of engagement for radiologists as they tackle the “Where’s Waldo?” situations, the satisfaction of search problem, distractions, fatigue, the varying subtlties of disease states and normal, their prior training and experience, and the somewhat endless non-image-interpretation tasks associated with a radiology practice. The understanding of artificial intelligence (AI) on a radiologist’s interpretation can be likened to considering the suggestions from a first-year resident to incorporating insights from a seasoned expert. Kundel’s eye gaze experiments which demonstrated the search patterns of radiologists and laymen continue to be used today to understand the added influence of AI in the end user’s performance. Multi-disciplinary perception research has evolved from understanding human performance in the interpretation of medical images, to the understanding of computer-aided diagnosis (CAD), and to now the understanding of AI -- either as an aid to radiologists as a second reader, a concurrent reader, or a primary reader, or as a complete replacement. This lecture will take the audience through history to appreciate the role and necessity of perception (and its associated metrics of performance) in the development, validation, and ultimate future implementation of AI in the clinical radiology workflow.

Biography: Maryellen Giger, Ph.D. is the A.N. Pritzker Professor of Radiology / Medical Physics at the University of Chicago. She has been working, for multiple decades, on computer-aided diagnosis /machine learning/deep learning in medical imaging and cancer diagnosis / management. Her AI research in breast cancer for risk assessment, diagnosis, prognosis, and therapeutic response has yielded various translated components, and she is using these “virtual biopsies” in imaging-genomics association studies. Giger is a former president of AAPM and of SPIE; and is the Editor-in-Chief of the Journal of Medical Imaging. She is a member of the NAE; Fellow of AAPM, AIMBE, SPIE, SBMR, IEEE, IAMBE; and was cofounder, equity holder, and scientific advisor of Quantitative Insights [now Qlarity Imaging], which produces QuantX, the first FDA-cleared, machine-learning driven CADx system.
Image Processing Conference Keynote Presentation
Date: Wednesday 19 February 2020
Time: 10:10 AM - 11:10 AM
Location: Salon C
Image Processing Conference Keynote Presentation (Conference [volume number]}
Bringing machine learning to the clinic: opportunities and challenges


Tim Leiner, Univ. Medical Ctr. Utrecht (Netherlands)

Abstract: Machine learning and especially deep learning hold great promise to improve patient care. In several domains, algorithms perform as good as or better than fellowship trained radiologists for identification of abnormalities in clinically acquired images. However, there are much broader applications beyond image analysis such as patient selection and examination scheduling, image acquisition and reconstruction, using image data for prognostic purposes, and combing image data with information from electronic health records, laboratory and genetic data. Furthermore, in order for algorithms to be broadly accepted, there are many scenarios where it is important for the clinician that results are explainable. In addition, clinical deployment and workflow should be taken into consideration when designing the algorithm and bringing it to clinical practice. In my lecture I will focus on these aspects from a cardiovascular imaging perspective.

Biography: Dr. Tim Leiner is tenured Professor of Radiology and holds the Chair in Cardiovascular Imaging at Utrecht University Medical Center, Utrecht, The Netherlands. His research interests center around the development and implementation of new MR and CT techniques with a focus on cardiovascular imaging and machine learning. Dr. Leiner is Associate Editor of the Journal of Magnetic Resonance Imaging (JMRI), the Journal of Cardiovascular Magnetic Resonance (JCMR), and Radiology – Cardiothoracic. He is the author of over 300 original papers, review articles and book chapters as well as editor of several electronic radiology textbooks. He is currently Vice-President of the ISMRM.
Digital Pathology Conference Keynote Presentation
Date: Wednesday 19 February 2020
Time: 1:20 PM - 2:20 PM
Location: Salon A
Digital Pathology
Petascale computational pathology for precision medicine


Nasir Rajpoot, Univ. of Warwick (United Kingdom)

Abstract: Modern day slide scanners are capable of generating large microscopic resolution images of conventional tissue slides, spurring a revolution in the practice of cellular pathology as a discipline. This development comes at a time when computing capacity and machine learning technologies are peaking, offering a remarkable opportunity to reveal complex cellular patterns in a data-driven manner. With an increasing number of NHS pathology labs being digitised in the UK, there is an explosion in the amount of pathology image data with linked clinical outcomes. This data is a potential goldmine of invaluable information, ripe for deep mining of novel digital histological biomarkers of the ‘state of play’ of complex diseases such as cancer. How can we facilitate the discovery of digital histology biomarkers to further our understanding of cancer, stratify patients into different risk groups and predict the progression and survival of cancer?

Biography: Nasir Rajpoot is Professor of Computational Pathology at the Computer Science department of the University of Warwick, where he started his academic career as a Lecturer (Assistant Professor) in 2001. He also holds an Honorary Scientist position at the Department of Pathology, University Hospitals Coventry & Warwickshire NHS Trust since 2016.

Prof Rajpoot is the founding Head of Tissue Image Analytics laboratory (TIA lab) at Warwick since 2012. In Autumn 2017, he was awarded the Wolfson Fellowship by the UK Royal Society and the Turing Fellowship by the Alan Turing Institute, the UK’s national institute for data science and artificial intelligence.

Current focus of research in Prof Rajpoot’s lab is on developing algorithms for the analysis of digitised pathology images, with applications to computer-assisted grading of cancer and image-based markers for prediction of cancer progression and survival. He has been active in the digital pathology community for almost a decade now, having co-chaired several meetings in the histology image analysis (HIMA) series since 2008 and served as a founding PC member of the SPIE Digital Pathology meeting since 2012.

Prof Rajpoot served as the President of the European Congress on Digital Pathology (ECDP), which was held at Warwick in April 2019. Since Jan 2019, he acts as Co-Director of the £15m PathLAKE national centre of excellence on AI in pathology, leading the computational arm of the centre.
Back to Top