Town and Country Resort & Convention Center
San Diego, California, United States
16 - 21 February 2019
Plenary Events
Awards and Plenary Session
Date: Monday 18 February 2019
Time: 4:10 PM - 5:30 PM
Location: Town & Country

4:10 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 - Inaugural Presentation

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

4:30 pm - Plenary Presentation


Clinical-grade artificial intelligence: hype or hope for pathology
Paper Number 10956-200

Thomas J. Fuchs
Director of Computational Pathology, Dept. of Pathology
Memorial Sloan Kettering Cancer Ctr. (United States)
Weill Cornell Medicine (United States)

Biography: Thomas Fuchs heads the Computational Pathology and Medical Machine Learning Lab at Memorial Sloan Kettering Cancer Center and teaches biomedical machine learning as associate professor at Weill-Cornell in New York City. He is director of The Warren Alpert Center for Digital and Computational Pathology. His passion for the tremendous potential of artificial intelligence in medicine resulted in more than 90 publications spanning a range of topics from novel deep learning and Bayesian approaches for quantification to real-world applications in the clinic. Previously, Thomas was a rocket scientist at NASA's Jet Propulsion Laboratory, where he developed autonomous computer vision systems for space exploration. He completed his Postdoc at the California Institute of Technology after receiving his Dr.Sc. in machine learning from ETH Zurich.
Imaging Informatics for Healthcare, Research, and Applications Conference Keynote Presentation
Date: Sunday 17 February 2019
Time: 1:20 PM - 2:00 PM
Location: San Diego
Imaging Informatics for Healthcare, Research, and Applications (Conference 10954)
AI research and applications in radiology: experience in China
Paper Number 10954-12


Shiyuan Liu, Changzheng Hospital (China)

Abstract: Artificial Intelligence (AI) is growing rapidly almost everywhere and entering the fields of healthcare and medicine. Compared to in developed countries, AI may play a distinct role, face different challenges, yet represents a greater opportunity in less-developed countries, where quality medical services and resources are in general limited. The speaker, Dr. Shiyuan Liu, President-Elect of the Chinese Society of Radiology, will talk about the status, experience, and challenges regarding AI research, applications, and regulatory in the clinical/radiology workflow specifically in hospitals in China. He will also share his thoughts and insights in leading the national efforts of AI innovation by synergizing the academic, industry, and clinical strengths.

Biography: Dr. Shiyuan Liu, Professor and Chairman of the Department of Radiology in the ChangZheng Hospital in Shanghai, China. He is the President-Elect of the Chinese Society of Radiology and of the Asian Society of Chest Radiology. Dr. Liu serves as the President of the Chinese Medical Imaging AI Innovation Alliance and leads the national efforts of AI research and applications in radiology. Dr. Liu received approximately $6 million research grants from Chinese National Science Foundation, Ministry of Science and Technology, and Shanghai Local Research Foundation. Dr. Liu is the Editor-in-Chief of the Oncoradiology journal. He has published more than 321 journal papers and authored 9 books. Dr. Liu is specialized in chest radiology especially in lung cancer screening and clinical imaging diagnosis with more than 30 years of experience.
Physics of Medical Imaging Conference Keynote Presentation
Date: Monday 18 February 2019
Time: 10:10 AM - 10:50 AM
Location: Town & Country
Physics of Medical Imaging (Conference 10948)
World’s deepest-penetration and fastest optical cameras: photoacoustic tomography and compressed ultrafast photography
Paper Number 10948-28


Lihong Wang, Caltech (United States)

Abstract: We developed photoacoustic tomography to peer deep into biological tissue. Photoacoustic tomography (PAT) provides in vivo omniscale functional, metabolic, molecular, and histologic imaging across the scales of organelles through organisms. We also developed compressed ultrafast photography (CUP) to record 10 trillion frames per second, 10 orders of magnitude faster than commercially available camera technologies. CUP can tape the fastest phenomenon in the universe, namely, light propagation, and can be slowed down for slower phenomena such as combustion.

PAT physically combines optical and ultrasonic waves. Conventional high-resolution optical imaging of scattering tissue is restricted to depths within the optical diffusion limit (~1 mm in the skin). Taking advantage of the fact that ultrasonic scattering is orders of magnitude weaker than optical scattering per unit path length, PAT beats this limit and provides deep penetration at high ultrasonic resolution and high optical contrast by sensing molecules. Broad applications include early-cancer detection and brain imaging. The annual conference on PAT has become the largest in SPIE’s 20,000-attendee Photonics West since 2010.

CUP can image in 2D non-repeatable time-evolving events. CUP has a prominent advantage of measuring an x, y, t (x, y, spatial coordinates; t, time) scene with a single exposure, thereby allowing observation of transient events occurring on a time scale down to 100 femtoseconds, such as propagation of a light pulse. Further, akin to traditional photography, CUP is receive-only—avoiding specialized active illumination required by other single-shot ultrafast imagers. CUP can be coupled with front optics ranging from microscopes to telescopes for widespread applications in both fundamental and applied sciences.

Biography: Lihong Wang is Bren Professor of Medical and Electrical Engineering at Caltech. Published 495 journal articles (h-index = 122, citations = 61,000). Delivered 500 keynote/plenary/invited talks. Published the first functional photoacoustic CT, 3D photoacoustic microscopy, and compressed ultrafast photography (world’s fastest camera). Served as Editor-in-Chief of the Journal of Biomedical Optics. Received the Goodman Book Award, NIH Director’s Pioneer Award, OSA Mees Medal, IEEE Technical Achievement and Biomedical Engineering Awards, SPIE Chance Biomedical Optics Award, IPPA Senior Prize, OSA Feld Biophotonics Award, and an honorary doctorate from Lund University, Sweden. Inducted into the National Academy of Engineering.
Ultrasonic Imaging and Tomography Conference Keynote Presentation
Date: Monday 18 February 2019
Time: 1:20 PM - 2:20 PM
Location: Pacific Salon 2
Ultrasonic Imaging and Tomography (Conference 10955)
Seismo-medical tomography
Paper Number 10955-34


Andreas Fichtner, ETH Zurich (Switzerland)

Abstract: The wave equation is linear, and it scales in time and space. As a consequence, wave phenomena that occur during fractions of a millisecond in human tissue often have a close correspondence in waves travelling for hours through the interior of the Earth. The scale invariance of the wave equation is the foundation for collaboration and technology transfer between medical ultrasound and seismic imaging - the promotion of which is the main goal of this contribution.

In the first part of our presentation, we review the current state of the art in seismic imaging, with a focus on regional to global scales. Special emphasis will be on (1) high-performance modelling of seismic wave propagation through a heterogeneous, attenuating and anisotropic Earth, (2) the nature of seismic data and the resulting characteristics of the inverse problem, (3) recent images of 3D deep-Earth structure, and (4) future challenges in the field.

In the second part, we highlight efforts to translate techniques from seismic imaging to medical ultrasound. This includes optimal design to position transducers, finite-frequency travel time tomography to image out of plane, reverse-time migration, and 3D multi-parameter full-waveform inversion.

Finally, we discuss several non-mathematical challenges that still impede technology transfer, and that remain to be addressed. These include the acceptable time to solution, and the ability of well-trained radiologists and seismic interpreters to handle entirely new types of images (and artifacts).

Biography: Andreas Fichtner is Professor of Seismology and Wave Physics in the Department of Earth Sciences at ETH Zurich. His research is focused on the development of waveform inversion techniques, including a diverse range of aspects, such as numerical wave propagation through complex media, high-performance computing, large-scale data analysis, Bayesian inference and Monte Carlo methods, as well as effective medium theory. Though most applications are in seismic imaging for deep Earth structure, his group actively engages in technology transfer to medical imaging and material testing. Andreas Fichtner is the author of 3 books on applied mathematics and geophysics, and of around 70 research papers in various international journals. He received early career awards from the American Geophysical Union and from the International Union of Geodesy and Geophysics. In addition to ETH Zurich, he has been affiliated with LMU Munich, Utrecht University, Stanford University and the Australian National University.
Image-Guided Procedures, Robotic Interventions, and Modeling Conference Keynote Presentation
Date: Tuesday 19 February 2019
Time: 8:40 AM - 9:40 AM
Location: California
Image-Guided Procedures, Robotic Interventions and Modeling (Conference 10951)
Bringing transcranial MR-guided focused ultrasound into focus
Paper Number 10951-43


Kim Butts-Pauly, Stanford Univ. (United States)

Abstract: Focused Ultrasound can target tissue within the skull with grain-of-rice accuracy. It is being studied for movement disorders, blood-brain barrier opening for cancer therapy, and for non-invasive deep brain neuromodulation. Although at various points in the translation process, each of these exciting applications require image-guided transcranial focusing, focal spot imaging, and treatment evaluation.

Biography: Kim Butts Pauly is Professor at Stanford in the Departments of Radiology, Bioengineering, and Electrical Engineering. She is Division Chief of the Radiological Sciences Laboratory in the Department of Radiology. She is Secretary General of the International Society for Therapeutic Ultrasound. She is a fellow of the ISMRM, Distinguished Investigator of the Academy of Radiology Research, and a member of the American Institute for Medical and Biological Engineering (AIMBE)'s College of Fellows.
Biomedical Applications in Molecular, Structural, and Functional Imaging Conference Keynote Presentation
Date: Tuesday 19 February 2019
Time: 10:10 AM - 11:10 AM
Location: Pacific Salon 2
Biomedical Applications in Molecular, Structural, and Functional Imaging (Conference 10953)
The dawning of AI in radiology: a brave new world
Paper Number 10953-6


Christopher Filippi, North Shore-Long Island Jewish Health System (United States), Columbia Univ. (United States)

Abstract: In this lecture, there will be a brief review of machine learning and deep learning techniques in artificial intelligence (AI) in diagnostic radiology. The focus will be on the translation of AI in diagnostic radiology from clinical workflow to its implementation in routine clinical practice to inform diagnosis, treatment management, and prognostication. Specific, ongoing work in the automated detection of hemorrhage on non-contrast head CT, prediction of genetic variability of brain tumors, detection of breast cancer and risk factors for breast cancer, and detection of knee ligament injury will be profiled among other clinical applications. In addition, work on improving the speed of MR acquisition with partial k-space reconstruction with deep learning techniques will be mentioned. Both machine learning and deep learning techniques will transform how radiologists make intelligent decisions from the quantitative data that is embedded in all the pixels/voxels per CT and MR image, which will necessitate that we radiologists become data scientists and data managers in the future, which is far from being superfluous. Potential barriers to the development and implementation of this technology to routine radiology practice will be addressed.

Biography: Dr. Christopher G. Filippi, “Risto”, is a Professor of Radiology and Vice Chairman of Biomedical Imaging and Translational Science at the Donald and Barbara Zucker School of Medicine of Hofstra/Northwell and an attending physician at Lenox Hill Hospital and Greenwich Village Healthplex. He is a graduate of Cornell University Medical College and completed training in diagnostic radiology at New York Hospital-Cornell and a 2-year neuroradiology fellowship at Yale University School of Medicine. Past President of the American Society of Functional Neuroradiology (ASFNR) and Eastern Neuroradiology Society (ENRS) and formerly the Director of MRI Research at the University of Vermont and Division Chief of Neuroradiology at Columbia University, his research interests include Artificial Intelligence (AI), DTI applications in pediatric neuroradiology, novel MR techniques (T1 rho), and translational MR in pediatric and adult demyelinating disease and glioma. He has had extramural funding annually for the past 17 years, and he has more than 85 peer-reviewed publications and 125 presented/published abstracts at national and international meetings. Currently, he is the Deputy Editor of Artificial Intelligence for the American Journal of Neuroradiology (AJNR), Chairman of the ASNR Task Force on Artificial Intelligence, and member of the AI Working Group of the ASFNR.
Computer-Aided Diagnosis Conference Keynote Presentation
Date: Tuesday 19 February 2019
Time: 1:20 PM - 2:20 PM
Location: Golden West
Computer-Aided Diagnosis (Conference 10950)
The U-net and its impact to medical imaging
Paper Number 10950-52


Bernardino Romera-Paredes, Google DeepMind (United Kingdom)

Abstract: The U-net has become the predominant choice when facing any medical image segmentation task. This is due to its high performance in many different medical domains. In this talk, I will introduce the U-net, and I will present three projects from DeepMind Health Research that use the U-net to address different challenges. The first project, a collaboration with University College London Hospital, deals with the challenging task of the precise segmentation of radiosensitive head and neck anatomy in CT scans, an essential input for radiotherapy planning. The second project, together with Moorfields Eye Hospital, developed a system that analyses 3D OCT (optical coherence tomography) eye scans to provide referral decisions for patients. The performance was on par with world experts with over 20 years experience. Finally, I will focus on the third project, which deals with the segmentation of ambiguous images. This is of particular relevance in medical imaging where ambiguities can often not be resolved from the image context alone. We propose a combination of a U-net with a conditional variational autoencoder that is capable of efficiently producing an unlimited number of plausible segmentation map hypotheses for a given ambiguous image. We show that each hypothesis provides a globally consistent segmentation, and that the probabilities of these hypotheses are well calibrated.

Biography: Bernardino Romera-Paredes is a research scientist at DeepMind. He was a postdoctoral research fellow in the Torr Vision Group at the University of Oxford. Previously, he received his Ph.D. degree from University College London in 2014, supervised by Prof. Massimiliano Pontil and Prof. Nadia Berthouze, and also did an internship at Microsoft Research. He has published in top-tier machine-learning conferences such as in Conference on Neural Information Processing Systems (NIPS), International Conference on Machine Learning (ICML), and International Conference on Computer Vision (ICCV), as well as in journals, such as the Journal of Machine Learning Research (JMLR). His research focuses on structure prediction in computer vision, such as semantic and instance segmentation, and its application to the medical domain.
Image Perception, Observer Performance, and Technology Assessment Conference Keynote Presentation
Date: Wednesday 20 February 2019
Time: 8:00 AM - 9:00 AM
Location: Royal Palm 1
Image Perception, Observer Performance, and Technology Assessment (Conference 10952)
Visual adaptation and the perception of radiological images
Paper Number 10952-1


Michael A. Webster, Univ. of Nevada, Reno (United States)

Abstract: The interpretation of medical images relies heavily on visual inspection by human observers. Many studies have explored how sensory and cognitive factors in visual processing influence how medical images are perceived and evaluated. But how do these images influence visual processing itself? The visual system is highly adaptable and constantly adjusting to changes in the visual environment. These adjustments recalibrate and optimize visual coding not only for simple properties of the world like the average light level, but also for complex features like the average blur or texture in a scene. Adaptation thus affects everything we see. The unique visual characteristics of radiological images suggest that they may hold the radiologist in unique states of adaptation. I will illustrate how this adaptation influences contrast sensitivity and the appearance of medical images. One proposed function of adaptation is to highlight novel information by “filtering out” the expected characteristics of scenes, and I will illustrate the implications of this by considering how adaptation may affect visual search for novel or suspicious features in medical images.

Biography: Michael Webster is Foundation Professor of Psychology at the University of Nevada, Reno. He received his PhD in 1988 from UC Berkeley and was a postdoctoral fellow at Cambridge University before joining the UNR faculty in 1994. His research is focused on color and form perception in human vision and how visual processing adapts to changes in the environment or the observer. He is the Director of UNR’s Center for Integrative Neuroscience (an NIH COBRE grant), and co-directs both the BS and PhD degree programs in Neuroscience.
Image Processing Conference Keynote Presentation
Date: Wednesday 20 February 2019
Time: 10:10 AM - 11:10 AM
Location: San Diego
Image Processing (Conference 10949)
Deep learning for inverse imaging problems: some recent approaches
Paper Number 10949-26


Carola-Bibiane Schönlieb, Univ. of Cambridge (United Kingdom)

Abstract: In this talk we discuss the idea of data-driven regularisers for inverse imaging problems. We are in particular interested in the combination of model-based and purely data-driven image processing approaches. In this context we will make a journey from “shallow” learning for computing optimal parameters for variational regularisation models by bilevel optimization to the investigation of different approaches that use deep neural networks for solving inverse imaging problems. Alongside all approaches that are being discussed, their numerical solution and available solution guarantees will be stated.

Biography: Carola-Bibiane Schönlieb is Professor in Applied Mathematics at the Department of Applied Mathematics and Theoretical Physics (DAMTP), University of Cambridge. There, she is head of the Cambridge Image Analysis group, Director of the Cantab Capital Institute for Mathematics of Information, Co-Director of the EPSRC Centre for Mathematical and Statistical Analysis of Multimodal Clinical Imaging, and since 2011 a fellow of Jesus College Cambridge. Her current research interests focus on variational methods and partial differential equations for image analysis, image processing and inverse imaging problems. Her research has been acknowledged by scientific prizes, among them the LMS Whitehead Prize 2016, and by invitations to give plenary lectures at several renowned applied mathematics conference, among them the SIAM conference on Imaging Science in 2014, the SIAM conference on Partial Differential Equations in 2015, the IMA Conference on Challenges of Big Data in 2016, the SIAM annual meeting in 2017 and the Applied Inverse Problems Conference in 2019.

In her research Carola is interested in the interaction of mathematical sciences and imaging. She studies non-smooth and possibly non-convex variational methods and nonlinear partial differential equations for image analysis and inverse imaging problems, among them image reconstruction and restoration, object segmentation, and dynamic image reconstruction and analysis such as fast flow imaging, object tracking and motion analysis in videos. Moreover, she works on computational methods for large-scale and high-dimensional problems appearing in, e.g. image classification and 3D and 4D imaging.
Digital Pathology Conference Keynote Presentation
Date: Wednesday 20 February 2019
Time: 1:20 PM - 2:20 PM
Location: California
Digital Pathology (Conference 10956)
Pixels to diagnosis: image analysis for digital pathology
Paper Number 10956-1


Metin Gurcan, Wake Forest Baptist Medical Ctr. (United States)

Abstract: Increased interest in medical imaging has resulted in development of a variety of image analysis systems. Many of these systems follow the ‘computer-aided diagnosis’ paradigm. In this paradigm, the main function of the image analysis system is to help medical professionals (e.g. radiologists, pathologists, dermatologists) in their decision-making, instead of making decisions on their behalf. If a system is designed to help medical professionals, its logic, development methodology and evaluation should be transparent to its users.

In this talk, we will describe how to develop an image analysis system: how to translate medical knowledge into algorithms, how to supplement this knowledge with pattern recognition methods, and how to evaluate such systems with carefully designed reader studies with the participation of medical professionals of varying levels of experience.

Biography: Dr. Metin Gurcan is Director of Center for Biomedical Informatics and Professor of Internal Medicine, Pathology and Biomedical Engineering and Director of the Clinical Image Analysis Lab (http://tsi.wakehealth.edu/CIALab/) at Wake Forest School of Medicine. Previously, he was Professor of Biomedical Informatics and Pathology, Director of Division of Clinical and Translational Informatics at the Ohio State University. Dr. Gurcan received his BSc. and Ph.D. degrees in Electrical and Electronics Engineering from Bilkent University, Turkey and his MSc. Degree in Digital Systems Engineering from the University of Manchester Institute of Science and Technology, England. From 1999 to 2001, he was a postdoctoral research fellow in the Department of Radiology at the University of Michigan, Ann Arbor. Following his postdoctoral work, he worked as a senior researcher and a product director at a high-tech company, specializing in computer-aided detection and diagnosis of cancer from radiological images.

Dr. Gurcan is the author of over 200 peer-reviewed publications, book chapters and was awarded three patents for his inventions in medical image analysis. He is the recipient of several awards including the British Foreign and Commonwealth Organization Award, NCI caBIG Embodying the Vision Award, NIH Exceptional, Unconventional Research Enabling Knowledge Acceleration (EUREKA) Award, Children’s Neuroblastoma Cancer Foundation Young Investigator Award, The OSU Cancer Center REAP Award, and Pelotonia Idea Award. As an internationally recognized researcher and educator, he is a senior of member of IEEE, SPIE, and AMIA. He currently serves on the editorial boards of Journal of Pathology Informatics and Journal of Medical Imaging; and organizes the Pathology Informatics Histopathological Image Analysis (HIMA) workshop.
Back to Top