Short Courses

Course Title: Radiation Detection and Measurement

Coordinator: David K. Wehe, University of Michigan, USA

Date/time/venue: Saturday, 26 October 2019 & Sunday, 27 October 2019  –  8:30-17:30  –  Hilton Hotel Deansgate 1

Description

This two-day course provides an overall review of the basic principles that underlie the operation of all major types of instruments used in the detection and spectroscopy of charged particles, gamma rays, and other forms of ionizing radiation. Examples of both established applications and recent developments are drawn from areas including particle physics, nuclear medicine, homeland security, and general radiation spectroscopy. Emphasis is on understanding the fundamental processes that govern the operation of radiation detectors, rather than on operational details that are unique to specific commercial instruments. This course does not cover radiation dosimetry nor health physics instrumentation. The level of presentation is best suited to those with some prior background in ionizing radiation interaction mechanisms.  Those with prior experience in radiation measurements would benefit from discovering concepts and applications outside their experience base. A complete set of course notes is provided to registrants, and a recent copy of Radiation Detection and Measurement by G. F. Knoll is highly recommended.

Outline

1. Fundamental Concepts in Ionizing Radiation Detection
2. Gas-Filled Detectors
3. Scintillation Detectors
4. Semiconductor Detectors
5. Analog and Digital Electronics for Radiation Measurements
6. Pulse Shape Discrimination and Multi-modality Sensing
7. Recent Detector Developments and Summary

Instructors

Sara Pozzi is a Professor of Nuclear Engineering and Radiological Sciences at University of Michigan. She previously worked at the Oak Ridge National Laboratory, and currently serves as the Director of the Consortium for Verification Technology. She and her group have developed new methods for digital pulse shape discrimination using organic scintillators read out by photomultiplier tubes and silicon photomultipliers for applications in nuclear nonproliferation and homeland security.

Robert Redus is a Member of the IEEE and is the Chief Scientist and Director of Engineering at Amptek, an Ametek company in Bedford, MA.  He has spent over thirty years designing instruments for radiation detection and measurement, for many applications and many customers.  These include X-ray spectroscopy, gamma-ray spectroscopy using compound semiconductors, scintillators, and HPGe detectors, and space radiation measurements.

Kanai Shah is the President of Radiation Monitoring Devices, Inc. His research areas of interest include novel scintillation materials for high resolution gamma-ray spectroscopy including CeBr3, LuI3:Ce and SrI2:Eu and dual mode scintillators such as Cs2LiYCl6:Ce, Cs2LiLaBr 6:Ce and Cs2LiLa(Br,Cl)6:Ce for combined detection of gamma-rays and neutrons. He has also worked in the areas of ceramic scintillators including garnets and silicates, and organic crystalline and plastic scintillators for neutron detection.

Graham Smith is a Senior Physicist at Brookhaven National Laboratory. He received a Ph.D. in Physics from Durham University, England. He has worked for the last thirty-five years at Brookhaven National Laboratory, USA, on development of advanced radiation instrumentation for experimental studies using neutrons, X-rays and charged particles, specializing in gas-filled detectors. He is an IEEE Fellow.

Lothar Strueder is the scientific director of PNSensor GmbH and professor at the University of Siegen. He earned his Ph.D. in Experimental Physics at the TU Munich in 1988. His interests include position-, energy-, and time-resolving detectors for photons and particles. He is author or co-author of more than 300 technical and scientific publications. He has been issued 13 worldwide patents in scientific instrumentation.

David Wehe is Professor of Nuclear Engineering and Radiological Sciences at University of Michigan. He worked at the Oak Ridge National Laboratory as a Wigner Fellow, and served as Director of the Michigan Phoenix Memorial Project, which included the 2-MW Ford Nuclear Reactor. His teaching and research have focused on applied radiation measurements, and is an editor for Nuclear Instruments and Methods in Physics Research.

Course Title: Integrated Circuits for Detector Signal Processing

Coordinator: Paul O’Connor, Brookhaven National Lab, USA

Date/time/venue: Saturday, 26 October 2019 –  8:00-18:00  –  Hilton Hotel Deansgate 2

Description

This one-day course is intended to introduce physicists and detector specialists to the fundamentals of integrated circuit front end design. The class begins with a discussion of low-noise signal processing and semiconductor devices and then delves into the details of implementing practical circuits in modern CMOS technology. A basic knowledge of detectors and electronics is assumed.

Outline

1. Pulse Processing Fundamentals
   • Signal formation in detectors
   • Noise and gain mechanisms
   • Pulse processing for amplitude and timing extraction
2. Semiconductor Technology for Integrated Circuit Front Ends
   • Operation and characteristics of MOS and bipolar transistors
   • Sub-micron CMOS and BICMOS technology
   • Feature size scaling
   • Radiation effects and reliability
   • Mixed-signal circuits
3. Brief introduction to design methodology, CAD tools and foundry access for research-scale projects
4. Analog circuit design
   • Elementary amplifier configurations
   • Building blocks for the analog channel: charge-sensitive and pulse-shaping amplifiers, baseline stabilizers, peak detectors, track/hold, multiplexers, output stages
   • Feature extraction: event occurrence, position, time, energy
   • Analog-to-digital and time-to-digital converters (ADC and TDC)
5. Application examples from particle physics, astrophysics, photon science, and medical imaging

Instructors

Paul O’Connor is a group leader in the Instrumentation Division at Brookhaven National Laboratory. After receiving the Ph.D. degree in solid-state physics from Brown University he worked from 1980-1990 at AT&T Bell Laboratories prior to joining BNL. His research interests are in the field of instrumentation systems for radiation detection, particularly those involving low noise front-end electronics. He is author and co-author of about 130 publications and has been an IEEE member since 1980.

Christophe de La Taille is Director of OMEGA microelectronics lab at Ecole Polytechnique and CNRS/IN2P3 (France). After receiving engineering and Ph.D. degree from Ecole Polytechnique, he joined LAL Orsay and worked on the readout of the ATLAS calorimeter at CERN/LHC and other high energy physics experiments. He was subsequently CTO of IN2P3and recently founded a design lab at Ecole Polytechnique. He is now coordinator of CMS HGCAL electronics. His research interests are in the field of detectors and mixed signal ASIC design. He is author and co-author of about 168 publications and has been an IEEE member since 2003.

Sergio Rescia is a scientist at the Instrumentation Division at Brookhaven National Laboratory. He received an engineering degree from University of Pavia, Italy and a Ph.D. degree from University of Pennsylvania, Philadephia, USA. After joining Brookhaven National Laboratory he has worked on the readout of liquid argon calorimeters (Helios-NA48, Atlas), silicon detectors, time projection chambers (MicroBoone, SBND, Dune, nEXO) and medical electronics. His research interests center in the field of instrumentation for particle and radiation detectors, particularly optimizing the detector – low noise front end interface. He is author or co-author of over 130 publications and has been an IEEE member since 2002.

Course Title: Fast timing detectors for HEP and medical applications

Coordinators: Jona Bortfeldt, LMU, Germany; Nicolo Cartiglia, INFN, Italy

Date/time/venue: Sunday, 27 October 2019 & Monday, 28 October 2019 –  8:00-18:00  –  Hilton Hotel Deansgate 2

Description

This two-day course will cover fast timing detectors and their application in high energy and medical physics. The first day focuses on high energy physics instrumentation. Different timing detectors, based on charge detection in silicon and gas, or light detection from scintillators and Cherenkov radiators are described, their working principles and characteristics are discussed. Signal analysis and reconstruction are described and the influence of analog and digital electronics is discussed in detail. The last lesson of the day focuses on the system aspects and the challenges of designing a complex ASIC, using examples from the latest ASIC currently in the R&D phase.

On the second day, the course is instead focused on the application of fast timing detectors in medical physics, namely in TOF-PET or in-beam PET systems, in prompt-gamma imaging or in beam monitoring applications. Signal generation and analysis, analytical and Monte Carlo based modeling are described, together with an in-depth review of currently available and novel commercial PET systems. The development and performance of new scintillator materials are reviewed, and suitable photo-detectors are discussed.

Outline

1. Silicon detectors for 4D tracking in High Energy Physics (Cartiglia)
   • Basics of signal formation, Ramos’ theorem
   • Signal from thin and thick Silicon detectors
   • Why thin sensors with internal gain are critical to a good time resolution
   • Radiation damage effect on the gain mechanism
   • The interplay of sensor and front-end electronics
2. Gaseous detectors for timing measurements (Bortfeldt)
   • Large area, cost-effective timing, and trigger detector
   • Functional principles, characteristics and performance of different gaseous timing detectors: Resistive Plate Chambers, Thin Gap Chambers, Fast Timing MPGD
   • Below 25ps: the Picosec Micromegas detector for particle and photon detection. Signal formation and analysis, modeling, photo-cathode robustness.
3. Readout electronics for fast timing detectors (de La Taille)
   • Electronics speed and noise impact on timing resolution
   • Preamplifier configurations for high-speed response: voltage vs. current or charge sensitive
   • Theoretical expressions for jitter due to electronics noise
   • Examples of simulated and measured responses from different configurations
   • Examples of preamplifier schematics
4. ADC-based waveform samplers for timing detectors (Gui)
   • Overview of waveform samplers for timing detectors
   • ADC-based waveform sampler design: targeting specifications and challenge
   • Circuit architectures and design techniques (Successive Approximation Register (SAR) and Pipelined SAR structures)
   • Time-interleaving approach to achieve a very high sampling rate
   • Calibration methods for intra-channel and inter-channel mismatches
   • Example ADC designs and simulation/measurement results
5. System aspects for fast timing detectors (Liu)
   • Design methodology to optimize front-end design from a system point of view
   • System power and cooling constraint and how it influences ASIC design
   • Precision clock distribution considerations: from system to detector, to chip, to pixel and to each TDC delay unit
   • Design for monitoring and calibration considerations
   • Time-frame of ASIC development: choice of “several miniASICs vs. single full ASIC”
   • Examples of ASICs developed in recent years
6. Introduction to fast timing applications in Medical Physics (Schaart)
   • Time-of-flight positron emission tomography (TOF-PET)
   • Organ-specific and in-beam PET systems
   • Prompt gamma detection in hadron therapy
   • Basic principles of fast timing scintillation detectors in Med Phys
   • Theory of scintillation detector time resolution timing properties of the scintillation signal
   • Monte Carlo modeling of time resolution
   • Analytical models of time resolution
   • Order statistics and Cramer-Rao modeling
7. Photosensors in fast timing scintillation detectors (Schaart)
   • Signal formation in common photosensors
   • Temporal properties of common photosensors
   • Factors affecting time resolution
   • Readout of fast timing photosensors
8. Exploiting timing information in particle therapy (Cerello)
   • Timing in particle therapy: where and how?
   • Beam monitoring applications
   • Range monitoring applications
   • New delivery concept(s)
   • Flash therapy
9. Development on scintillators for fast timing detectors (Auffray)
   • Scintillation mechanisms
   • Key factors and limits of the scintillators properties for fast timing detection
   • The recent development on scintillators fields to push time resolution toward 10ps
10. System review: the latest commercial TOF PET systems (Surti)
    • Detector design of PMT based TOF PET systems and their limitations.
    • Detector design of the latest digital TOF PET systems and other system design improvements.
    • TOF image reconstruction methods and their impact on clinical lesion detection and quantitative measurement performance.
    • New developments in PET system design with a focus on long axial FOV systems.

Instructors

Etiennette Auffray is a Member of the IEEE, and she has been a member of the RISC committee. She is a senior physicist at CERN, Geneva, Switzerland. She has spent over twenty-five years in the field of scintillators and their applications in particular in high energy physics and medical applications. She was actively involved in the construction of the electromagnetic calorimeter of the CMS experiment at CERN made of 75848 crystals of PWO and now in its operation. She is involved in research activities on scintillating materials for the development of PET and TOFPET through the Crystal Clear collaboration of which she is the spokesperson since 2010. In recent years she has coordinated several European projects related to scintillating materials and their applications in particular in recent years for fast timing detectors.

Jonathan Bortfeldt is Staff Scientist at the Department of Medical Physics of the Ludwig-Maximilians-Universität (LMU) Munich, Germany. He received his Ph.D. in High Energy Physics from LMU Munich in 2014, developing novel micro-pattern gaseous detectors. After post-doctoral work at LMU, he became CERN-COFUND fellow, working on the ATLAS New Small Wheel upgrade with Micromegas. In 2018, he took over the instrumentation lab at the Department of Medical Physics of LMU Munich. He is co-convener of the Picosec Micromegas collaboration, and member of the RD51 and the ATLAS collaborations. Dr. Bortfeldt’s main research interest is the development of high (spatial and temporal) resolution instrumentation for pre-clinical research and laser-accelerated beams.

Nicolò Cartiglia is a Senior Scientist at INFN-Torino. After receiving his Ph.D. from UCSC, he moved to Columbia University and then in 1998 joined INFN. His carrier focuses on the development of new instrumentation for high energy particle experiments. He worked on several experiments, specializing on Silicon sensors. Currently, he is working on the development of a Silicon-based tracking system able to measure time and position concurrently. In recent years, he has been awarded a European ERC-advanced grant and a PRIN grant from Italy.

Piergiorgio Cerello is Senior Researcher at INFN, Italy, Torino Unit. He received his Ph.D. in Nuclear Physics in 1995 and is among the founders of the ALICE experiment at the CERN LHC. In the past two decades, he focused mostly on Medical Applications, setting up a Medical Imaging group in Torino, active on both software and hardware projects. It applied artificial intelligence techniques to the search for lung nodules in chest CT, by developing an algorithm that was clinically validated. Recently, the group took part, with a major role, in the development of the INSIDE hybrid scanner for online range monitoring in particle therapy.

Ping Gui is a Full Professor of Electrical and Computer Engineering at Southern Methodist University, Dallas, TX, USA, and an IEEE senior member. Her research focuses on analog and mixed-signal IC design, including radiation-tolerant and high-speed ADCs, PLLs, and data link design. Her research group has developed 56GSps ADCs for 100/400G optical communications, 4x10Gbps laser driver and E-links for the LpGBT and the Versatile Link Plus projects (VL+), and PLL and Data Links capable of operating under cryogenic environments in the DUNE Project. Ping Gui is currently the principle investigator on a DoE awarded project to develop high-speed high-resolution ADCs and waveform samplers for high-energy physics applications.

Christophe de La Taille is director of OMEGA microelectronics lab at École Polytechnique and CNRS/IN2P3 (France). After receiving engineering and Ph.D. degree from École Polytechnique, he joined LAL Orsay and worked on the readout of the ATLAS calorimeter at CERN/LHC and other high energy physics experiments. He was subsequently CTO of IN2P3and recently founded a design lab at École Polytechnique. He is now coordinator of CMS HGCAL electronics. His research interests are in the field of detectors and mixed signal ASIC design. He is author and co-author of about 168 publications and has been an IEEE member since 2003.

Tiehui Ted Liu is a senior scientist at Fermilab. After receiving his Ph.D. in physics from Harvard in 1995 (CLEO experiment at Cornell), he worked at Princeton from 1995-1997 (on BELLE at KEK), Berkeley Lab from 1997-2000 (BABAR at SLAC), and then moved to Fermilab since year 2000 (on CDF and then CMS). He has been involved in many aspects of particle physics instrumentation, ranging from (current) CMS Endcap Timing Layer upgrade, to tracking trigger R&D for HL-LHC, various trigger systems at CDF and BABAR, Aerogel-based Cherenkov detector at Belle, and Time-of-Flight system at CLEO.

Dennis R. Schaart is head of the section Medical Physics & Technology at the Radiation Science & Technology department of Delft University of Technology (TU Delft). He started his career as an R&D physicist at Nucletron (now Elekta), where he developed new devices for radiotherapy. In his private time he wrote a Ph.D. thesis on the subject of intravascular brachytherapy, for which he obtained his doctoral degree (with highest honors) at TU Delft in 2002. He subsequently joined the university to set up a new research line on in-vivo molecular imaging technology, with special focus on ultrafast detectors for time-of-flight positron emission tomography (TOF-PET). His main research interests include novel methods and technologies for in vivo molecular imaging and for image guidance in (proton) radiotherapy. Since 2016, he coordinates the research activities of TU Delft within the R&D program of the Holland Proton Therapy Centre (HollandPTC), a joint initiative of Erasmus Medical Centre (Erasmus MC), Leiden University Medical Centre (LUMC), and TU Delft. He furthermore serves as a member of the HollandPTC R&D Program Board. Dr. Schaart is a Senior Member of the IEEE and has served on the IEEE Nuclear and Medical Imaging Sciences Council (NMISC). He has (co-)authored more than 100 peer-reviewed papers and is a frequently invited speaker.

Suleman Surti is a Research Associate Professor in the Physics and Instrumentation group in the Department of Radiology at the University of Pennsylvania. He obtained his Ph.D. in Physics at the University of Pennsylvania and continued his post-doctoral work and faculty appointment in PET imaging research at Penn. Dr. Surti has been involved in PET imaging for over twenty years focusing on system development, optimization, and evaluation of several PET scanners developed at the University of Pennsylvania as well as new commercial systems ranging from small-animal PET through application-specific PET (brain, breast, proton) to whole-body PET (Non-TOF, TOF, long axial field-of-view). His work has spanned development of scintillation detectors and electronics, their incorporation in optimized scanner geometries, evaluation of system performance and data/image correction techniques, and optimization of imaging protocols.

Course Title: Medical image reconstruction: from foundations to AI

Coordinator: Andrew Reader, Kings College London, UK

Date/time/venue: Monday, 28 October 2019 –  8:30-18:00  –  Hilton Hotel Deansgate 1

Description

Using the primary example of positron emission tomography (PET), this one-day course covers key foundational principles for fully 3D image reconstruction through to state-of-the-art methods using artificial intelligence (AI). The course will start with analytic 2D and 3D filtered back projection (FBP) methods, and then cover more advanced data modelling with iterative and statistical image reconstruction methods, including compensation for noise through Bayesian regularisation.

After covering these foundations, relatively recent reconstruction advances will be considered, including guided and synergistic PET-MR image reconstruction, fully 4D image reconstruction along with direct estimation of kinetic parametric maps from dynamic emission tomography data.

The last section of the course will provide a comprehensive introduction to the key concepts of artificial intelligence (AI), more specifically machine and deep learning, in the context of emission tomographic image reconstruction, and review some of the latest methods which exploit AI to enhance reconstructed image quality.

Outline:

1. Foundations

• Object representation, emission tomography data, linear shift-invariant (LSI) systems
• System modelling, analytic image reconstruction
• Backproject then filter (BPF), filtered backprojection (FBP), 3D FBP
• Orlov’s condition, Colsher filter

2. Iterative and statistical image reconstruction

• Maximum likelihood (ML) reconstruction
• Poisson log-likelihood, simple gradient method
• Complete data and expectation maximisation (EM)
• Factorised system models, PSF modelling
• Ordered subsets EM (OSEM), ordinary Poisson (OP)-OSEM
• Properties of ML estimates
• Maximum a posteriori (MAP) / Bayesian reconstruction
• Types of prior, simple EM algorithms
• Optimisation transfer methods
• Modelling and data corrections
• Attenuation, scatter, randoms, normalisation, motion correction

3. Recent advances

• Guided regularised image reconstruction
• MLEM, MAP and kernel EM (KEM)
• Synergistic PET-MR image reconstruction
• Joint estimation, and alternating example methods
• 4D and direct parametric image reconstruction
• Linear methods, non-linear models

4. Artificial intelligence (AI) in PET image reconstruction

• Introductory concepts, direct methods, convolutional neural networks (CNNs), post-reconstruction methods
• Introduction to unrolled reconstruction methods with deep learning
• State-of-the-art current examples of deep learning in PET image reconstruction

Instructors

Andrew Reader is a Professor of Imaging Sciences at King’s College London, United Kingdom. He is in the School of Biomedical Engineering and Imaging Sciences, and is also an adjunct Professor at McGill University. He received his Ph.D. in medical physics from the University of London in 1999 on the subject of PET image reconstruction. He was a Canada Research Chair based at the Montreal Neurological institute for 6 years, and returned to the UK in 2014 taking up his post at King’s College London. He has co-authored over 200 scientific outputs. His research interests include PET and multi-modal image reconstruction, data modelling and the application of machine learning to PET-MR imaging.

Jinyi Qi is a Professor of Biomedical Engineering at the University of California – Davis (UC Davis), USA. He received his Ph.D. in electrical engineering from the University of Southern California in 1998. He was a research scientist at the Lawrence Berkeley National Laboratory before joining the faculty of UC Davis in 2004. He has been an Associate Editor for IEEE Transactions on Medical Imaging since 2006. He is a Fellow of IEEE and AIMBE. His main research interests concern the development of advanced image formation and processing tools to push the boundary of molecular imaging using positron emission tomography (PET)/computed tomography (CT). His lab combines in silico modelling of tracer kinetics, imaging system response and human observation to create new image reconstruction algorithms and design future imaging systems that provide higher sensitivity and specificity for clinical applications.

Kris Thielemans is a Professor in Medical Imaging Physics at University College London (UCL), United Kingdom. He received his PhD degree in String Theory from KU Leuven in 1994. Prior to UCL, he worked as a Researcher at Hammersmith (London, UK) for the Medical Research Council and General Electric, and at King’s College London (KCL). His research interests encompass all aspects of quantitative PET image reconstruction with emphasis on the development of advanced reconstruction techniques for PET and SPECT including motion correction. He developed along with others an open source software for tomographic image reconstruction (STIR) which has been cited more than 250 times. More recently he leads a project in synergistic image reconstruction (the synergistic image reconstruction framework (SIRF)).

Course Title: Hybrid nuclear medicine devices: instrumentation and application

Coordinator: Georges El Fakhri, PhD, DABR

Date/time/venue: Tuesday, 29 October 2019  –  8:30-17:30  –  Hilton Hotel Deansgate 1

Description

This one-day course covers both physical aspects of SPECT/PET-CT and MR (instrumentation, requirements for integration) as well as clinical applications of hybrid nuclear medicine imaging.  Basics of PET, SPECT T and MR physics and instrumentation as they pertain to SPECT/CT, PET/CT, PET/MR are discussed in detail.  An overview of wide range of detector technologies from Anger camera to state-of-the-art PET/MR systems will be provided.

Challenges in terms of attenuation correction, geometry integration, etc are discussed and opportunities afforded by  detection of PET/SPECT and CT or MR signals (e.g., motion compensation, partial volume correction) are explored.

We will also introduce the state-of-art deep learning method for image reconstruction and quantitation for hybrid imaging system.

These discussions will culminate with detailed assessment of what clinical applications can benefit from SPECT/CT, PET/CT or PET/MR and how to leverage its use both in the animal and human research as well as in the clinical setting.

Outline

1. SPECT&PET Basic Instrumentation & Image Formation (Georges El Fakhri)
2. PET/MR & SPECT/PET/CT Instrumentation (Hamid Sabet)
3. Image Reconstruction & Quantitation (Quanzheng Li)
4. Clinical Applications(Georges El Fakhri)

Instructors

Georges El Fakhri, PhD, DABR. Dr El Fakhri is the Alpert Professor of Radiology at Harvard Medical School (HMS) and the founding Director of the Endowed Gordon Center for Medical Imaging at Massachusetts General Hospital and HMS with over 140 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) especially as it pertains to quantitative imaging, pharmacokinetic modeling and probing pathophysiology in brain, cardiac and oncologic PET/CT/MR.  He has authored or co-authored over 200 papers and mentored over 90 students, post-docs and faculty.  He has been a chartered member of many NIH study sections pertaining to Medical Imaging and Radiotherapy as well as DOD, DOE and other Foundations.  He has received many awards and honors, including the Mark Tetalman Award and the E.J. Hoffman Award from the Society of Nuclear Medicine and Molecular Imaging and the Dana Foundation Brain and Immuno-Imaging Award.  He was elected Fellow to the SNMMI, AAPM and IEEE for “contributions to biological imaging”.

Quanzheng Li, PhD. Quanzheng Li is an Associate Professor of Radiology at Massachusetts General Hospital and Harvard Medical School. Dr. Li is also Core faculty in the Gordon Center for Medical Imaging and scientific director of MGH/BWH Center for Clinical Data Science. He received his B.S degree from Zhejiang University in 1997,  M.S. degree from Tsinghua University in 2000, and his Ph.D degree in Electrical Engineering from the University of Southern California (USC) in 2005. He did his post-doctoral training at USC from 2006 to 2007, and was a Research Assistant Professor from 2008 to 2010. In 2011, he joined the Radiology Department at Massachusetts General Hospital. Dr. Li is the recipient of 2015 IEEE Nuclear and Plasma Sciences Society (NPSS) early achievement award. He is an associate editor of IEEE Transaction on Image Processing, and members of editorial boards of Theranostics and Physics in Medicine and Biology. His research interests include image reconstruction and analysis in PET, SPECT, CT and MRI, and data science in health and medicine.

Hamid Sabet, PhD. Hamid Sabet is an Assistant Professor of Radiology at Harvard Medical School, and faculty at Gordon Center for Medical Imaging and Nuclear Medicine and Molecular Imaging Division at Massachusetts General Hospital. He earned his PhD in Quantum Science and Energy Engineering from Tohoku University, Japan in 2008. After a postdoctoral training at Rush Medical Center in Chicago (2009-2010), he worked as staff scientist at RMD Inc. from 2011 to 2014. He joined MGH/Harvard as faculty in 2014 and established Radiation Physics and Instrumentation Lab in GCMI, Radiology department. The research theme of his Lab is development of novel detector technologies for nuclear medicine and x-ray imaging, and image-guided surgical applications.

Course Title: Artificial intelligence for medical image analysis and processing

Coordinator: Jorge Cardoso, King’s College London, UK

Date/time/venue: Tuesday, 29 October 2019  –  9:15-17:00  –  Hilton Hotel Deansgate 2

Description

This one-day course will cover important aspects of deep learning with a particular focus on medical imaging applications, and provide hands on experience in using and training deep learning models. The tutorial aims to provide an introduction to the basics and fundamental concepts of deep learning, practical advice for the use of deep learning for medical imaging tasks, and gives an overview of latest developments and opportunities for future research. The tutorial is targeted at all levels and for any researcher interested in deep learning. The first lectures are tailored for people new to the field (e.g., first year PhD students), while later lectures cover more advanced topics and latest developments which should be of interest to anyone already working with deep learning methods.

Outline

Introduction to deep learning

Applications of deep learning in Medical Imaging

Semantic deep learning: segmentation and regression
Architectures and optimization
Transfer Learning and Domain adaptation
Learning useful information from unlabeled data
Generative adversarial networks
Practical Hands-on Session

Instructors 

Dr Jorge Cardoso is a Senior Lecturer in Artificial Medical Intelligence at King’s College London, where he leads a research portfolio on big data analytics, quantitative radiology and value based healthcare. He is also the CTO of the new InnovateUK-funded “London Medical Imaging and AI Centre for Value Based Healthcare”, where he is developing a software platform and associated computing infrastructure to enable data aggregation, machine learning and actionable analytics at scale across the three King’s Health Partners trusts. Jorge also co-lead the development of NiftyNet, a deep-learning platform for artificial intelligence in medical imaging, and is a founder and CSO of BrainMiner, a medtech startup aiming to bring quantitative biomarkers and predictive models to neurological care.

Dr Ben Glocker is a Senior Lecturer in Machine Learning for Imaging at Imperial College London and one of three academics leading the Biomedical Image Analysis Group. He is also an  Adviser – Medical Image Analysis at HeartFlow and leading the London-based HeartFlow-Imperial Research Team. Ben works as scientific adviser for Definiens and Kheiron Medical Technologies. His research is at the intersection of medical image analysis and artificial intelligence aiming to build computational tools for improving image-based detection and diagnosis of disease.

Dr Carole Sudre is an Alzheimer’s Society Research Fellow at the School of Biomedical Engineering & Imaging Sciences at King’s College London. During her PhD at UCL, she developed algorithms to automatically segment brain lesions commonly observed in ageing populations. Her current research focuses on the development of machine learning solutions for quantification and characterisation of magnetic resonance imaging biomarkers associated with cerebrovascular damage.