BIMCV, Banco de Imagen Medica de la Comunidad Valenciana. María de la Iglesia

BIMCV: The Perfect "Big Data" Storm.
Collision of Peta Bytes of Population Image Data, Millions of Hardware
Devices and Thousands of Software Tools.
e-Infraestructuras
Nacionales
Maria de la Iglesia, PhD. http://ceib.san.gva.es

OVERVIEW
• Big Data
• Strategic Vision of Big Data in EU
• Strategic Vision of Big Data in US
• Big Data in Neuroimaging
• Population Imaging
• BIMCV – EuroBioimaging - Valencia Node
• Neuroimaging: the landscapes of the mind
• Relevant facts

Big data techniques and
technologies
• Techniques for analyzing big data
– A/B testing.
• Association rule learning.
• Classification.
• Cluster analysis.
• Crowdsourcing.
• Data fusion and data integration.
– Signal processing
– natural language processing
• Data mining.

technologies
– Ensemble learning
– Genetic algorithms
– Machine learning
– Natural language processing (NLP)
– Neural Networks
• Pattern recognition
– Network analysis

technologies
– Optimization
• Pattern recognition
• Predictive modeling.
• Regression.
• Signal processing
– time series analysis
– data fusion
• Spatial analysis.
• Statistics.

technologies
• Big DataTechnologies
– Big Table. (Proprietary distributed database system
built on the Google File System. Inspiration for
Hbase)
– Business intelligence (BI). BI tools are often used to
read data that have been previously stored in a data
warehouse or data mart
– Cassandra. An open source (free) database
management system designed to handle huge
amounts of data on a distributed system. This system
was originally developed at Facebook and is now
managed as a project of the Apache Software
foundation

technologies
– Cloud computing.
– Data mart.
– Data warehouse. using ETL (extract, transform, and load)
– Distributed system.
– Dynamo
– ETL
– Google File System.
– Hadoop
– HBase.
– MapReduce.
– Mashup

technologies
– Non-relational database.
– R.
– Relational database.
– Semi-structured data.
– SQL.
– Stream processing.
– Structured data.
– Unstructured data.
– Visualization.

technologies
– VISUALIZATION
• Tag cloud
• Clustergram
• History flow
• Spatial information flow

VISUALIZATION: Spatial
information flow

Strategic Vision of Big Data in EU

How Is the Europe Union Responding?
In Big Data

Panel: Personalized Medicine in the
Era of Big Data
EHTEL Symposium
Tapani Piha
• Head of Unit for eHealth and Technology
Assessment
European Commission
DG Health and Consumers
Health Systems and Products

How does Big Data link to the
Personalized Medicine?
•Big Data refers to a collection of data sets so
large and complex, it’s impossible to process
them with the usual databases and tools
•The data is gathered (most of the time) by
people just living their lives (e.g. using mobile
phones, the internet, driving cars, paying with
banking cards)
•Big data is used in the private sector (e.g.
Google), and in the public sector (e.g. NSA)

Big Data use in public health &
health care?
•Research: "In the last five years, more scientific
data has been generated than in the entire history
of mankind”1
•Health care: more evidence about personalized
treatment, better selection of right provider, better
equipped health care providers (e.g. IBM's Watson)
•Public health: better personalized life-style info
for citizens, earlier detection of epidemics, more
and quicker access to epidemiological
information
12012 Winston Hide, The Promise of Big Data, Harvard Public Health

Staff Working Document on –omics
•the potential for, and issues with, the use of '-
omics' technologies in personalised medicine,
and the related EU research funding,
•recent developments in EU legislation for
placing medicinal products and devices on the
market.
•factors affecting the uptake of personalised
medicine in health care systems.

Commission action on Big Data
•BIG-project: multi-sectorial initiative started in
2011 to promote adoption of earlier waves of big
data technology and contribute to EU
competitiveness;
•Green paper on mHealth: to assess market and
further clarify what is needed in the legal
framework concerning mHealth
•Study in health program: to assess the usages
and adoption of big data programs for (public)
health systems within the EU.

Strategic Vision of Big Data in US

How Is U.S. Responding?
National Institute of Standards an
Technology (NIST)
NIST is an agency of the U.S. Department of Commerce.
To search federal science and technology web sites, including online databases see:
science.org
NIST program questions:
Public Inquiries Unit: (301) 975-NIST (6478), Federal Relay Service (800) 877-8339 (TTY).
NIST, 100 Bureau Drive, Stop 1070, Gaithersburg, MD 20899-1070
Technical website questions: DO-webmaster@nist.gov

NIST Big Data Public Working Group
Big Data PWG Overview Presentation
September 30, 2013
Wo Chang, NIST
Robert Marcus, ET-Strategies
Chaitanya Baru, UC San Diego

Agenda
• Why Big Data? Why NIST?
• NBD-PWG Charter
• Overall Workplan
• Subgroups Charter and Deliverables
– Use Case and Requirements SG
– Definitions and Taxonomies SG
– Reference Architecture SG
– Security and Privacy SG
– Technology Roadmap SG
• Next Steps
9/30/13 NBD-PWG Overview
28

Why Big Data? Why NIST?
• Why Big Data? There is a broad agreement among commercial, academic, and government
leaders about the remarkable potential of “Big Data” to spark innovation, fuel commerce,
and drive progress.
• Why NIST? (a) Recommendation from January 15 -- 17, 2013 Cloud/Big Data Forum and (b)
A lack of consensus on some important, fundamental questions is confusing potential users
and holding back progress. Questions such as:
– What are the attributes that define Big Data solutions?
– How is Big Data different from the traditional data environments and related
applications that we have encountered thus far?
– What are the essential characteristics of Big Data environments?
– How do these environments integrate with currently deployed architectures?
– What are the central scientific, technological, and standardization challenges that
need to be addressed to accelerate the deployment of robust Big Data solutions?
NBD-PWG is being launched to address these questions and is charged to develop
consensus definitions, taxonomies, secure reference architecture, and technology roadmap
for Big Data that can be embraced by all sectors.
29

NBD-PWG Deliverables
Working Drafts version 1.0 for
1. Big Data Definitions
2. Big Data Taxonomies
3. Big Data Requirements
4. Big Data Security and Privacy Requirements
5. Big Data Architectures White Paper Survey
6. Big Data Reference Architectures
7. Big Data Security and Privacy Reference Architectures
8. Big Data Technology Roadmap
30

NBD-PWG Workplan
31

Big Data Ecosystem in One Sentence
• Use Clouds running Data Analytics
Collaboratively processing Big Data to solve
problems in X-Informatics ( or e-X)
• X = Astronomy, Biology, Biomedicine, Business, Chemistry, Climate,
Crisis, Earth Science, Energy, Environment, Finance, Health, Intelligence,
Lifestyle, Marketing, Medicine, Pathology, Policy, Radar, Security,
Sensor, Social, Sustainability, Wealth and Wellness with more fields
(physics) defined implicitly
• Spans Industry and Science (research)
• Education: Data Science see recent New York Times articles
• http://datascience101.wordpress.com/2013/04/13/new-york-times-data-
science-articles/
32

Social Informatics
Visual&Decision
Informatics
33

Big Data Definition
• More consensus on Data Science definition than that of Big Data
• Big Data refers to digital data volume, velocity and/or variety
that:
– Enable novel approaches to frontier questions previously inaccessible or
impractical using current or conventional methods; and/or
– Exceed the storage capacity or analysis capability of current or
conventional methods and systems; and
– Differentiates by storing and analyzing population data and not sample
sizes.
– Needs management requiring scalability across coupled horizontal
resources
34

Vendor-neutral and Technology-agnostic Proposals
Data Processing Flow
M0039
Data Transformation Flow
M0017
IT Stack
M0047
35

M0039
M0017
IT Stack
M0047
36

M0039
IT Stack
M0047
M0017
37

Vendor-neutral and Technology-agnostic
Proposals
M0017
IT Stack
M0047
M0039
38

Electronic Medical Record (EMR) Data I
• Application: Large national initiatives around health data are emerging, and
include developing a digital learning health care system to support
increasingly evidence-based clinical decisions with timely accurate and up-to-
date patient-centered clinical information; using electronic observational
clinical data to efficiently and rapidly translate scientific discoveries into
effective clinical treatments; and electronically sharing integrated health
data to improve healthcare process efficiency and outcomes. These key
initiatives all rely on high-quality, large-scale, standardized and aggregate
health data. One needs advanced methods for normalizing patient,
provider, facility and clinical concept identification within and among
separate health care organizations to enhance models for defining and
extracting clinical phenotypes from non-standard discrete and free-text
clinical data using feature selection, information retrieval and machine
learning decision-models. One must leverage clinical phenotype data to
support cohort selection, clinical outcomes research, and clinical decision
support.
39
PP, Fusion, S/Q, Index Parallelism Streaming over EMR (a set per person), viewers

Electronic Medical Record (EMR) Data II
• Current Approach: Clinical data from more than 1,100 discrete logical,
operational healthcare sources in the Indiana Network for Patient Care
(INPC) the nation's largest and longest-running health information
exchange. This describes more than 12 million patients, more than 4
billion discrete clinical observations. > 20 TB raw data. Between
500,000 and 1.5 million new real-time clinical transactions added per
day.
• Futures: Teradata, PostgreSQL and MongoDB supporting information
retrieval methods to identify relevant clinical features (tf-idf, latent
semantic analysis, mutual information). Natural Language Processing
techniques to extract relevant clinical features. Validated features will
be used to parameterize clinical phenotype decision models based on
maximum likelihood estimators and Bayesian networks. Decision
models will be used to identify a variety of clinical phenotypes such as
diabetes, congestive heart failure, and pancreatic cancer.
40

Pathology Imaging/ Digital Pathology I
• Application: Digital pathology imaging is an emerging field where examination of high
resolution images of tissue specimens enables novel and more effective ways for
disease diagnosis. Pathology image analysis segments massive (millions per image)
spatial objects such as nuclei and blood vessels, represented with their boundaries,
along with many extracted image features from these objects. The derived information
is used for many complex queries and analytics to support biomedical research and
clinical diagnosis.
41
MR, MRIter, PP, Classification Streaming Parallelism over Images

Pathology Imaging/ Digital Pathology II
• Current Approach: 1GB raw image data + 1.5GB analytical results per 2D image. MPI for
image analysis; MapReduce + Hive with spatial extension on supercomputers and
clouds. GPU’s used effectively. Figure 3 of section 2.12 shows the architecture of
Hadoop-GIS, a spatial data warehousing system over MapReduce to support spatial
analytics for analytical pathology imaging.
42
• Futures: Recently, 3D pathology imaging
is made possible through 3D laser
technologies or serially sectioning
hundreds of tissue sections onto slides
and scanning them into digital images.
Segmenting 3D microanatomic objects
from registered serial images could
produce tens of millions of 3D objects
from a single image. This provides a
deep “map” of human tissues for next
generation diagnosis. 1TB raw image
data + 1TB analytical results per 3D
image and 1PB data per moderated
hospital per year.
Architecture of Hadoop-GIS, a spatial data warehousing system over MapReduce
to support spatial analytics for analytical pathology imaging

Computational Bioimaging
• Application: Data delivered from bioimaging is increasingly automated, higher
resolution, and multi-modal. This has created a data analysis bottleneck that, if
resolved, can advance the biosciences discovery through Big Data techniques.
• Current Approach: The current piecemeal analysis approach does not scale to
situation where a single scan on emerging machines is 32TB and medical
diagnostic imaging is annually around 70 PB even excluding cardiology. One
needs a web-based one-stop-shop for high performance, high throughput
image processing for producers and consumers of models built on bio-imaging
data.
• Futures: Goal is to solve that bottleneck with extreme scale computing with
community-focused science gateways to support the application of massive
data analysis toward massive imaging data sets. Workflow components include
data acquisition, storage, enhancement, minimizing noise, segmentation of
regions of interest, crowd-based selection and extraction of features, and
object classification, and organization, and search. Use ImageJ, OMERO,
VolRover, advanced segmentation and feature detection software.
43
MR, MRIter?, PP, Classification Streaming Parallelism over Images

22: Statistical Relational Artificial Intelligence for Health Care
• Application: The goal of the project is to analyze large, multi-modal medical data
including different data types such as imaging, EHR, genetic and natural language. This
approach employs the relational probabilistic models that have the capability of
handling rich relational data and modeling uncertainty using probability theory. The
software learns models from multiple data types and can possibly integrate the
information and reason about complex queries. Users can provide a set of descriptions
– say for instance, MRI images and demographic data about a particular subject. They
can then query for the onset of a particular disease (say Alzheimer’s) and the system
will then provide a probability distribution over the possible occurrence of this disease.
• Current Approach: A single server can handle a test cohort of a few hundred patients
with associated data of 100’s of GB.
• Futures: A cohort of millions of patient can involve petabyte datasets. Issues include
availability of too much data (as images, genetic sequences etc) that complicate
analysis. A major challenge lies in aligning the data and merging from multiple sources
in a form that can be made useful for a combined analysis. Another issue is that
sometimes, large amount of data is available about a single subject but the number of
subjects themselves is not very high (i.e., data imbalance). This can result in learning
algorithms picking up random correlations between the multiple data types as
important features in analysis.
MRIter, EGO Streaming Parallelism over People and their EMR 44

El paradigma P4 de la Medicina
PREDICTIVO PREVENTIVO PERSONALIZADO PARTICIPATIVO

El paradigma V4 en Big Data
Medicina
V-OLUME V-ARIETY V-ELOCITY V-ALUE

human neuroimaging is now, officially, a
“big data” science
• Among the examples of “big data” featured at
the meeting was – no surprise - human
neuroimaging
• The Brain Research through Advancing
Innovative Neurotechnologies (BRAIN) Initiative
• Initiatives surrounding large-scale brain mapping
are also underway in Europe
http://www.humanbrainproject.eu
• Organization for Human Brain Mapping (OHBM;
http://www.humanbrainmapping.org)

How Big is “Big”?
• While size is a relative term when it comes to data,
medical imaging applied to the brain comes in a variety of
forms which each generating differing types and amounts
of information about neural structure and/or function.
• NeuroImage, indicates that since 1995 the amount of
data collected has doubled approximately every 26
months. At this rate, by 2015 the amount of acquired
neuroimaging data alone, discounting header information
and before more files are generated during data
processing and statistical analysis, may exceed an average
of 20GB per published research study

Growth of Neuroimaging
Study Size
20000
15000
10000
5000
0
1990 1995 2000 2005 2010 2015 2020
MegaBytes
Year
Expected
Observed
Predicted
Van Horn and Toga (in press) Brain Imaging and Behavior

Kryder’s law: Exponential Growth of
Data
VOLUME OF DATA
MB = MEGABYTE = 106, GB = GIGABYTE = 109
TB = TERABYTE = 1012, PB = PETABYTE = 1015
COMPUTE
POWER
CPU TRANSISTOR
COUNTS
MOORE’S LAW
YEARS
SINGLE CRYO BRAIN VOLUME
1600 CM2
NEUROIMAGING
(ANNUALLY)
GENOMICS
(BP/YR)
Voxel Resolution Gray Scale Color 200 GB 10 MB 1x105 1985-1989
Size Count 8bits 16bits 24bits 1 TB 100 MB 1x106 1990-1994
1cm 12x15x9 1620 3000 4860 50 TB 10 GB 5x106 1995-1999
1mm
120x
150x90
1.62
MB
3.24 MB 4.86 MB 250 TB 1TB 1x107 2000-2004
100 μm
1200x
1500x900
1.62
GB
3.24 GB 4.86 GB 1 PB 30TB 8x106 2005-2009
10 μm
12000x
15000x
9000
1.62
TB
3.24 TB 4.86 TB 5 PB 1 PB 1x109 2010-2014
1 μm
120000x
150000x
90000
1.62
PB
3.24 PB 4.86 PB 10+ PB 20+ PB 1x1011 2015-2019
(estimated)
Kryder's law, Chip Walter - Scientific American, 2005 - nature.com

Big Neuroimaging + Big Genetics =
REALLY Big Data
• With the ability to obtain genome-wide sets of single
nucleotide polymorphism (SNP) information becoming
routine and the costs of full genomic sequencing rapidly
becoming affordable.
• Next Generation Sequencing (NGS) methods, for major
brain imaging studies such as the Alzheimer’s Disease
Neuroimaging Initiative (ADNI) (Weiner, Veitch et al.
2012), with its initially available sample of 832 subjects.
• As the bond between neuroimaging and genomics grows
tighter, with both areas growing at incredible rates, disk
storage, unique data compression techniques

Multisite Consortia and
Data Sharing
• Examples of multisite neuroimaging efforts can be found
in the ubiquitous application of neuroimaging in health
but also in devestating illnesses such as:
• Parkinson’s (Evangelou, Maraganore et al. 2009)
• psychiatric disorders (Schumann, Loth et al. 2010)
• the mapping of human brain connectivity (Toga, Clark et
al. 2012
• databases of aging and aging-related diseases, largescale
Autism Research (NDAR; Hall,Huerta et al. 2012) and the
Federal InteracgencyTraumatic Brain Injury Research
(FITBIR; Bushnik and Gordon 2012)

Multisite Consortia and Data Sharing
• The various “grass roots” collections of resting-state
fMRI data maintained as part of the
“1000 Functional Connectomes” project
http://fcon_1000.projects.nitrc.org/
(see Biswal, Mennes et al. 2010)
• Task-based OpenfMRI http://www.openfmri.org
(Poldrack, Barch et al. 2013) are other notable
examples.

The Role of Cyberinfrastructure
• Individual desktop computers are now no longer
suitable for analyzing potentially petabytes
worth of brain and genomics data at a time.
• While the National Science Foundation (NSF)
has made major investments in the computer
architecture needed for physics, weather, and
geological data.
• Eg. XSEDE, https://www.xsede.org/ , and Open
Science Grid, https://www.opensciencegrid.org

The Role of Cyberinfrastructure
• The Neuroimaging Informatics Tools and
Resources Clearinghouse
(NITRC; http://www.nitrc.org )
• The International Neuroinformatics Coordinating
Facility (INCF; http://incf.org )
Have begun to deploy local clusters with Amazon
EC2 server technology toward this goal but a larger
effort will be required involving dedicated
processing centers or distributed grids of linked
compute centers.

Conclusions
• Neuroimaging research, by its very nature, is data intensive,
multimodal, and collaborative factors which have been
instrumental in its success and growth.
• Yet the infrastructure needed for supporting this advancing form
of brain research where data is king is still maturing.
• The next steps for the development of resources supporting “big
data” brain imaging at the Exabyte scale will require the further
creation of new tools and services for data discovery, integration,
analysis, and visualization.
• For the “big data” science of human brain imaging, now is the
time to begin.

Many 1,000’s of Software Tools
• Acquisition, processing, storage/DB, service, migration, mining, analysis,
visualization, annotation, … “(data-driven) process understanding”
• Biomedical Imaging
– There are 100’s of different types of image
processing algorithms and filters
– For each type of process there may be dozens
of
concrete software products (instance implementations)
• (Example) Neuroimaging
– NITRC lists > 500 openly shared software tools
– For each openly shared tool there may be
dozens of
proprietary or less commonly used analogues

Millions of Dispersed Hardware Devices
• Cisco: "By the end of 2012, the number of mobile-connected devices will
exceed the number of people on Earth”
• There will be over 10 billion mobile-connected devices in 2016; i.e., there
will be 1.3 mobile devices per capita
– These include phones, tablets, laptops, handheld gaming consoles, e-readers,
in-car entertainment systems, digital cameras, and “machine-to-machine
modules”
• DBs, Clients, Servers, Compute-Nodes, Web-Services, Interfaces, …
• Solution …
Dinov et al., BMC 2011

Image
spatial
alignment
Slice
timing
adjustment
Van Horn et al., Nature Neuro, 2004
Statistical
modeling
(e.g. GLM)
Functional –
structural
co-registration
Raw fMRI
time series
High-resolution
anatomical
image
Standardized
brain atlas
template
Image
smoothing
Gaussian
spatial
filtering
Experimental
design matrix
Study Meta Data
Scanner protocols
Subject demographics
Stimulus timing
etc.
Spatial
normalization
to atlas space
Statistical
results maps
Graphical
overlays
Table of
statistically
significant
voxels in atlas
space coordinates

Pipeline Version 5.9.1 Features
Graphical Programming Environment
8/29/2014 63

Perfect Neuroimaging-Computation Storm?
• Single Subject Studies (N=1)
– Genetics:
• Depending on Coverage(X)
• Whole Genome Seq Data > 320GB (>80X)
• Require 2+ TB RAM, and 100+ hrs CPU
– Imaging:
• Depending on protocols
• 40-512 gradient directions Diffusion imaging data
• Raw (multimodal) Neuroimaging Data > 10 GB
• Derived Data > 100 GB
• Require 100GB RAM and 70+ hrs CPU
• Large Subject Studies
– Cohort studies (N>10, Typically N~100’s)
– Multi-Institutional Population-wide Studies (N>1,000)
– Longitudinal (neuroimaging) studies …

From Biomedical Challenges to Modeling,
Computation, Tools and Curricular
Training
• Quantitative Volumetric and Surface based Stats Analyses
– Interactome: Challenge↔Models↔Data Analysis↔Computation↔Education
– Statistics Online Computational Resource Che, et al., JSS (2009) No effect
Marginal
Significant

Grid & Cloud Computing
• UCLA Grids
Cerebro Medulla
 1,200 cores
 1.4TB RAM
 12,000 jobs/day
 700 users
• Amazon Cloud
 4,300 cores
 9.6 TB RAM
 (new)
– EC2 (Elastic Cloud Computing)
– S3 (Simple Storage Service)
• UC Grid
• Globus GridFTP
• INI Cluster @ USC
– 3328 cores, 128GB RAM per 16 cores, 26tb aggregate
memory space. Connectivity is 5Gbit per 16 cores,
roughly 4terabit aggregate on comp and another 4.3Tbit
on the storage. 2.43PB of online storage with over 50TB
of SSD accelerating it currently.

Neuroimaging Applications: 56-ROI Global
Shape Analysis (NC vs. IBS/Pain) Group
Effects
Data Workflow Protocol Results
Structural T1 data
NC IBS
221 107
Mean-Curvature between-group
differences in:
L_cuneus
R_angular_gyrus
Left View
Right View

Neuroimaging Applications: Stat Mapping
of Cortical GM Thickness (Group Effects)
Results
Left
Anterior
Insula
Data
Workflow Protocol
Structural T1 data
Cortical Models
1.0
P-value
0.0

Big Data y el sector de la Salud en
Imagen Poblacional
• Según Bonnies Feldman “el potencial de Big Data en medicina
reside en la posibilidad de combinar los datos tradicionales con
otras nuevas formas de datos, tanto a nivel individual como
Poblacional”
• El potencial del Big Data indica que se pueden producir ahorros en
el sector sanitario a través de varias vías:
– Transformación de datos en información.
– Apoyo al autocuidado de las personas.
– Aumento del conocimiento.
– Concienciación del estado de salud.
• El Big Data es una metodología de acceso abierto para integrar
diferentes tipos de datos en imagen poblacional, cuantificación de
imagen y extracción de características.

Tipos de Estudios
• Individual
• Longitudinal
0 1 2 M
• Transversal

Estudios Poblacionales
• Estudios Poblacionales
– Si no se forman grupos en la población, se calcula la media
del parámetro o parámetros.
– Si se forman grupos (control y Patológicos) se debe realizar
un contraste de hipótesis.
• Modelado Poblacional
– Modelar la degeneración volumétrica de sustancia gris y
sustancia blanca
– Establecer parámetros de degeneración
– Contrastar el estado de un individuo con respecto a dicho
modelo.

Aplicación a Casos Reales
Resultados de parámetros globales

Resultados de grosor y volumen por estructura,
junto con los valores de referencia

• Representación de la diferencia del volumen en comparación
con la población

¿Porqué no podemos combinar
BELLEZA Y CIENCIA?

Objetivos BIMCV
• Desarrollar e implementar estrategias para
prevenir o tratar efectivamente las
enfermedades mediante una infraestructura de
investigación en imagen asociada a grandes
estudios poblacionales de imagen.
– Concepto de “Population Imaging”.
• Proporcionar datos,
herramientas y recursos de
proceso para realizar estudios
avanzados en imagen.

Nodo Valenciano
Euro-BioImaging
Infraestructura Europea para la Investigación en
Tecnologías de Imagen Biomédica e Imagen
Biológica.
Un proyecto sobre la hoja de ruta de las ESFRI en infraestructuras
de investigación
www.eurobioimaging.eu

EIBIR key facts and daily work
In the service of research,
EIBIR offers to its Network Members:
- Multidisciplinary networking
- Project Management
- Research communication
- Research Training
- Meeting organisation
EIBIR Office
• Established in 2006
• Staff: 4.5, incl. 3 Project Managers, 1 assistant
• Provision of services to Network Members + EIBIR bodies
• Monitoring European Affairs + research funding opportunities
• Project management and coordination
• Information activities and media work
• Promotion of Network Membership
• Website and data base updates
• Congress activities
• Scientific Advisory Board

Cronología & Financiación
83
2013 - 2017
Fase de
Construcción
• Evaluación &
selección de nodos.
• Construccion de los
nodes.
Financiado por los Estados
Miembros (¿MINECO?)
2010 - 2013
Fase Preparatoria
• Framework
• Definición de los
criterios de
elegibilidad para los
nodos
• Llamada a los
Nodos, Abierta.
Financiado por CE
………
2017 - ….
Fase Operacional
• Acceso y formación
• Tecnología y evaluación
para mejorar el servicio
Financiado por los Estados Miembros
& EC

MULTIMODAL
TECHNOLOGY
NODE
Imaging Infrastructure with open user access
European life scientists as users
FLAGSHIP NODE
FLAGSHIP NODE
FLAGSHIP NODE
FLAGSHIP NODE
USER TRAINING
STAFF TRAINING
Web-access portal
Data storage and analysis infrastructure
User returns with results for publication
NODES HUB
MULTIMODAL
TECHNOLOGY
NODE

1st Open Call
Euro-BioImaging Nodes – Expression of Interest
The 1st Open Call: 1 February – 30 April 2013
• Multi-Modal Molecular Imaging
• Phase contrast Imaging
• High-field MRI
• MR-PET
• Population Imaging
• Data Infrastructure: Challenges Framework
• The biological imaging community will call for EoIs in 6 technologies

Resultados 1ª Convocatoria
Biological Imaging
Biomedical Imaging
9 NODOS ESPAÑOLES
– 18 Instituciones –

Evaluation summary and Final ranking
• The node develops and provides access to a large database of
imaging data and the associated clinical data records.
• Big Data repository from hospitals in the Valencia region (5 million
inhabitants living over an area of 23.255 Km2. average number of
5.3 million clinical cases per year, from 210 different imaging
modalities).
• The access to such data and tools will be an efficient way of
advancing population imaging studies and research.
• The node has ability to incorporate data from other facilities

Services offered by the node
• BIMCV facility provides a multi-level and multi-ology storage
service (Vendor Neutral Archive).
• CEIB-CS node integrates access to high-performance
computational services from local and European
infrastructures (Principe Felipe Research Centre & UPV-I3M
Infrastructure).
• Open access methodology to integrate different data types for
population imaging, quantitative resources and feature
extraction.
• Comprehensive user training

Single Technology Flagship Node – Population Imaging: Valencia
Evaluation summary and Final ranking:
• Requires minor improvements (training plan, actually corrected).
• The node develops and provides access to a large database of imaging data
and the associated clinical data records.
• Big Data repository from hospitals in the Valencia region (5 million inhabitants
living over an area of 23.255 Km2. average number of 5.3 million clinical cases
per year, from 210 different imaging modalities).
• The access to such data and tools will be an efficient way of advancing
population imaging studies and research.
• The node has ability to incorporate data from other facilities.
Other facilities
MEDICAL IMAGING DATA BANK (BIMCV)
BIG DATA DIASEASE SIGNATURES
Services offered by the node:
• BIMCV facility provides a multi-level and multi-ology
storage service (Vendor Neutral Archive).
• CEIB-AVS node integrates access to high-performance
computational services from local and European
infrastructures (Principe Felipe Research Centre & UPV-I3M
Infrastructure).
• Open access methodology to integrate different data
types for population imaging, quantitative resources and
feature extraction.
• Comprehensive user training.

Nodo Valenciano, BIMCV
Centro de Excelencia en Imagen Biomédica de la Conselleria de
Sanitat
Sede CEIB clínica Sede CEIB computo

Neuroimaging. The landscapes' of the mind

Human Neuroimaging as a
“Big Data” Science
The mind landscapes
http://prezi.com/sseievn7ujcf/?utm_campaign=share&utm_medium=copy

Estudio de la estructura
Morfometría

Estudio de la estructura
Tractografía

10 K Structural Modeling in
Neuroimage of Valencia Region
• Dos becas de la Subdirección General de Sistemas para la
Salud de la CS. Ingenieros Informáticos o Ingenieros de
Telecomunicaciones (DOGV 9-07-2014).
• Se van a medir las estructuras principales del cerebro.
• En colaboración con LABMAN (http://www.labman.org)
• En colaboración con Brain Dynamics
• La universidad del Sur de California (Jack Van Horn)
• En colaboración con IBIME

Demo:
Prototipo de realidad Virtual Aumentada de:
Gonzalo Rojas Costas

BIMCV, Banco de Imagen Medica de la Comunidad Valenciana. María de la Iglesia

Recomendados

Recomendados

Mais conteúdo relacionado

Mais procurados

Mais procurados (20)

Destaque

Destaque (20)

Semelhante a BIMCV, Banco de Imagen Medica de la Comunidad Valenciana. María de la Iglesia

Semelhante a BIMCV, Banco de Imagen Medica de la Comunidad Valenciana. María de la Iglesia (20)

Último

Último (20)

BIMCV, Banco de Imagen Medica de la Comunidad Valenciana. María de la Iglesia