1
„Personalized Medicine“ –
Challenges & Chances forImaging
Konstantin Nikolaou
Abteilung für Diagnostische und Interventionelle Radiologie
Increase in Workload + Costs of Imaging „Value-based Healthcare“
Imaging Biomarker Quantatitive Imaging
Radiomics „Big Data“ + Artificial Intelligence
Potential & Innovations in Magnetic Resonance Imaging
Personalized Medicine at the University Hospital Tuebingen
„Personalized Medicine“Challenges & Chances for Imaging
2
Transforming Radiology:Large (functional) information in relation to „Big Data“
Imaging Business
Information Business
Decisionmaking
business
1895.........................................1997.................................2025
Personal Communication
PACS
WEB 2.0/CLOUD
Courtesy of Maximilian Reiser, LMU Munich
Department of Radiology, UKT
Diagnostic CT
McDonald, Acad Radiol 2015
15000
16000
17000
18000
19000
20000
21000
22000
23000
24000
2008 2009 2010 2011 2012 2013 2014 2015 20167600
7800
8000
8200
8400
8600
8800
9000
9200
2008 2009 2010 2011 2012 2013 2014 2015 2016
Diagnostic MRT
3
Radiology, 2010Kashani, Perspective for Managers Newsletter, 2010
„Value-based healthcare“
Modified from: Jakka and Rossbach, The HUGO Journal, 2013
Radiology
Surrogate Imaging, Imaging Biomarker and Radiomics as an Integral Part in Precision Medicine
4
Imaging Biomarkers
Courtesy of G. Krestin, Rotterdam
• can reliably be used to test medical hypotheses, cross the first gap• becoming useful ‘medical research tools’
• Any new biomarker has to cross the gaps of technical validation, biological/clinical validation, and cost effectiveness
then it becomes a ‘clinical decision-making tool’
To generate QUANTITATIVE Imaging Biomarkers….
• …medical images have to be within describable limits of bias and variance.
• …imaging protocols have to be standardized across imaging centers.
• …acquisition and reconstruction standards have to be defined.
NATURE REVIEWS | CLINICAL ONCOLOGY, 2016
Inter- and intratumoral tumor heterogeneityDo we have to biopsy every lesion?
“Intratumor heterogeneity can lead to underestimation of the tumor genomics landscape and may present major challenges to personalized-medicine and
biomarker development.”New England Journal of Medicine 366;10 nejm.org march 8, 2012
Radiology, 2016
“Multiscale HCC”, eMed BMBF project, University Hospital Tuebingen
5
(Advanced) Imaging Big data Artificial intelligence
Scan Images Features Prediction Biomarkers
Radiomics
Courtesy of F. Nensa, University of Essen
Adap+ng to ar+ficial intelligence
• Radiologists and pathologists need to adapt
• Artificial Intelligence will (partly) perform the information extraction from imaging data
• Radiologists/pathologists will transform to…
Information Specialists:
information processing
putting it into clinical context
communication
Artificial Intelligence
6
Why Tübingen?
Why MRI?
OK!, but….
Tübingen: Center for Personalized Medicine(ZPM)
7
Patient management
(SAP)
Clinical CancerRegistryGTDS
HL7
WebInterface
BiobankingPathology
BiobankingUniversity
gynecologicalhospital
BiobankingNeuropathology
by MPI
XML
by MPI XML
XML
Clinical Study center
XML
CentraXXBiobank / Study Mgt. / Research
data integration solutionResearch data
Identified an validated User(pseudonymized web‐view)
Courtesy of N. Malek, Chairman, ZPM & Med. Dpt., University Hospital Tuebingen
1972 1975 1980 1983 1990 2000 2003 2005 2010 2015
Milestones of MRI development
0,5 Tesla
Clinical MR Systems4
1,5 Tesla 3 Tesla 7 Tesla
Lauterbur & Mansfield
1
Basics for modern MRI
First MR images in humans3
First experimentalMR Systems
2
PET-MR6
MR Fingerprinting7
Hyperpolarized MRI8
Noble Price forLauterbur und Mansfield
5
Innovations in MRI
8
MotivationMotion Artifacts
Motion Blur
Aliasing• respiratory motion• cardiac movement• patient and organmovement
with motion w/o motion
Need for adaptation and motion correction strategiesCourtesy of Th. KüstnerDpt. Radiology, UKT
Personalized Medicine:Role of (standardized) Imaging, Quantification & Reporting
Res-
ponse
Res-
ponse
Therapy
Relevance
Therapy
Relevance
Quantitative / Structured Data
Quantitative / Structured Data
Reading / AnalysisReading / Analysis
Image AcquisitionImage Acquisition
PatientPatient
9
Role of imaging in personalized medicine
27.02.2017
Acquire, identify, structure and curate data• Radiologist as an INFORMATION SPECIALIST
Multidisciplinary research• clinical partners, IT, Statisticians, data scientists
Apply classifications to new data Provide decision support
Where do we see the MAGNETOM VIDA?
Modified from: Jakka and Rossbach, 2013
Test
Thank you!
