SlideShare a Scribd company logo
1
The project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 825111.The project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 825111.
BDV ppp virtual workshop: How to exchange
and grant access to heath data in a secure
way: approaches and recommendations
Monica Caballero (Project Manager) - monica.caballero.galeote@everis.com
Jon Ander Gómez (Technical Manager) - jon@upv.es
May 14th 2020
Deep-Learning and HPC to Boost Biomedical Applications for Health
4
The project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 825111.
About DeepHealth
Aim & Goals
• Put HPC computing power at the service of biomedical applications with DL needs and apply DL
techniques on large and complex image biomedical datasets to support new and more efficient ways
of diagnosis, monitoring and treatment of diseases.
• Facilitate the daily work and increase the productivity of medical personnel and IT professionals in
terms of image processing and the use and training of predictive models without the need of
combining numerous tools.
• Offer a unified framework adapted to exploit underlying heterogeneous HPC and Cloud
architectures supporting state-of-the-art and next-generation Deep Learning (AI) and Computer
Vision algorithms to enhance European-based medical software platforms.
Duration: 36 months
Starting date: Jan 2019
Budget 14.642.366 €
EU funding 12.774.824 €
22 partners from 9 countries:
Research centers, Health organizations,
large industries and SMEs
Research Organisations Health Organisations Large Industries SMEs
Key facts
5
The project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 825111.
Developments &
Expected Results
• The DeepHealth toolkit
• Free and open-source software: 2 libraries + front-end.
• EDDLL: The European Distributed Deep Learning Library
• ECVL: the European Computer Vision Library
• Ready to run algorithms on Hybrid HPC + Cloud architectures with heterogeneous hardware
(Distributed versions of the training algorithms)
• Ready to be integrated into end-user software platforms or applications
• HPC infrastructure for an efficient execution of the training algorithms which are computational
intensive by making use of heterogeneous hardware in a transparent way
• Seven enhanced biomedical and AI software platforms provided by EVERIS, PHILIPS, THALES,
UNITO, WINGS, CRS4 and CEA that integrate the DeepHealth libraries to improve their potential
• Proposal for a structure for anonymised and pseudonymised data lakes
• Validation in 14 use cases (Neurological diseases, Tumor detection and early cancer prediction, Digital
pathology and automated image annotation).
EU libraries
6
The project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 825111.
The Concept
SOFTWARE
PLATFORM
BIOMEDICAL
APPLICATION
Medical image
(CT , MRI , X-Ray,…)
Health professionals
(Doctors & Medical staff)
ICT Expert users
New
image to be analysed
Prediction
Score and/or
highlighted RoI
returned to the doctor Load trained predictive models to the platform
Use toolkit to train
predictive models
Data used to
train models
Platform uses
the toolkit to
train models
(optional)
Images labelled by doctors
Add
validated
images
Production environment Training environment
Using loaded/trained
predictive models
(Optional) Train predictive models using the platform and the toolkit
Samples to be pre-processed and validated
Images pending to
be pre-processed
and validated
HPC infrastructure
TOOLKIT
7
The project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 825111.
Current status at May 2020 (M1–M16)
• Design & specification of libraries APIs, HPC system and use-cases finished.
• Definition of the structure for anonymised and pseudonymised data lakes in progress
• DeepHealth Toolkit:
• EDDL & ECVL:
• First stable versions publicly available in GitHub (non-distributed):
https://github.com/deephealthproject/eddl / | https://github.com/deephealthproject/ecvl
• Work in progress: improving non-distributed version, Python wrapper, distributed version
using COMPSs from BSC to run on hybrid HPC + Cloud architectures, also using FPGAs
kernels
• Front-end:
• GUI mostly finished
• Supporting back-end to load and transform images on the fly during training ready
8
The project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 825111.
Current status at May 2020 (M1–M16)
• HPC Infrastructure Adaptation – in progress:
• Development of heterogeneous support for the DeepHealth libraries
• Communication and Synchronisation optimizations to make training and inference algorithms
efficient
• HPC runtime support and custom hardware support for both libraries
• Design an hybrid cloud computing solution to support DeepHealth libraries
• Integration of libraries and use cases in application platforms— in progress:
• Adaptation of application platforms to use cases specifics
• Design of the “how to” integrate libraries into the platforms finished. Iterative integration in
progress
• Testing and pilots:
• About to start 1st technical validation setting complete pipelines
• Example: https://github.com/deephealthproject/use_case_pipeline
• Use-cases preparing data-sets for pilots (acquiring, labelling, curation, etc.)
9
The project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 825111.
Challenges/difficulties identified
1. Data sharing among project’s partners is not
always possible
2. Data is not curated enough
10
The project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 825111.
Challenge 1: Data sharing among project’s partners is not always possible
• Even under signed NDAs
• Different legal advisors do different interpretations of the same Law
• GDPR and other data protection rules of EU member states
• Health data is very sensitive data that may include patient’s information —so involved people (doctors, IT staff,
researchers, industry, etc.) must guarantee no patient’s information is disclosed
• Validated/certified anonymization/pseudonymization and de-identification techniques not easy to achieve
• No scientific progress without risks
• Proposal for addressing this challenge in the Health sector:
• Privacy and security by design in the standard protocols to collect and annotate data —protocols to be defined
• Legal-technical-ethical committees must be created to issue data-sharing authorisations in order to avoid the
responsibility falling on individual doctors or medical teams
• Federated and split learning under software restrictions where only training algorithms have access to data
11
The project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 825111.
Challenge 2: Data is not curated enough
• Data is partially labelled/annotated
• Non-standard protocols were followed to collect datasets for the same diseases
• Relevant differences depending on the source/origin (hospital across Europe)
• In particular regarding metadata that affects how labels and/or annotations are stored
• Proposal for addressing this challenge in the Health sector:
• Standard ontologies must be a priority
• Standard protocols to collect and store for sharing FAIR data in Europe must be a
priority
• Make medical personnel more involved in technical projects —difficult to explain
12
The project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 825111.The project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 825111.
Questions?
@DeepHealthEU
https://deephealth-project.eu
Project Coordinator: Mónica Caballero
monica.caballero.galeote@everis.com
Technical Manager: Jon Ander Gómez
jon@upv.es

More Related Content

Similar to Deep-Learning and HPC to Boost Biomedical applications for health

Virtual BenchLearning - DeepHealth - Needs & Requirements for Benchmarking
Virtual BenchLearning - DeepHealth - Needs & Requirements for BenchmarkingVirtual BenchLearning - DeepHealth - Needs & Requirements for Benchmarking
Virtual BenchLearning - DeepHealth - Needs & Requirements for Benchmarking
Big Data Value Association
 
Heterogeneous HPC Computing in the DeepHealth Project
Heterogeneous HPC Computing in the DeepHealth ProjectHeterogeneous HPC Computing in the DeepHealth Project
Heterogeneous HPC Computing in the DeepHealth Project
Big Data Value Association
 
Gergely Sipos (EGI): Exploiting scientific data in the international context ...
Gergely Sipos (EGI): Exploiting scientific data in the international context ...Gergely Sipos (EGI): Exploiting scientific data in the international context ...
Gergely Sipos (EGI): Exploiting scientific data in the international context ...
Gergely Sipos
 
EOSC-hub in EOSC context
EOSC-hub in EOSC contextEOSC-hub in EOSC context
EOSC-hub in EOSC context
EOSC-hub project
 
Elixir Training: Professional skills for managing and exploiting data
Elixir Training: Professional skills for managing and exploiting dataElixir Training: Professional skills for managing and exploiting data
Elixir Training: Professional skills for managing and exploiting data
EUDAT
 
NordForsk Open Access Reykjavik 14-15/8-2014: H2020
NordForsk Open Access Reykjavik 14-15/8-2014: H2020NordForsk Open Access Reykjavik 14-15/8-2014: H2020
NordForsk Open Access Reykjavik 14-15/8-2014: H2020
NordForsk
 
Linked Data with hybrid services in Agriculture
Linked Data with hybrid services in AgricultureLinked Data with hybrid services in Agriculture
Linked Data with hybrid services in Agriculture
Raul Palma
 
EGI Engage: Impact & Results
EGI Engage: Impact & ResultsEGI Engage: Impact & Results
EGI Engage: Impact & Results
EGI Federation
 
Sshoc kick off meeting - 1.2.1 How to Connect to EOSC? - Tiziana Ferrari - EGI
Sshoc kick off meeting - 1.2.1 How to Connect to EOSC? - Tiziana Ferrari - EGISshoc kick off meeting - 1.2.1 How to Connect to EOSC? - Tiziana Ferrari - EGI
Sshoc kick off meeting - 1.2.1 How to Connect to EOSC? - Tiziana Ferrari - EGI
SSHOC
 
DEX Innovation Centre at a glance
DEX Innovation Centre at a glanceDEX Innovation Centre at a glance
DEX Innovation Centre at a glance
Jan Šašek
 
Exposing EO Linked (meta-)Data from OpenSearch Catalogue
Exposing EO Linked (meta-)Data from OpenSearch CatalogueExposing EO Linked (meta-)Data from OpenSearch Catalogue
Exposing EO Linked (meta-)Data from OpenSearch Catalogue
Raul Palma
 
HZ Health IT Cluster Collaborative Project Update
HZ Health IT Cluster Collaborative Project UpdateHZ Health IT Cluster Collaborative Project Update
HZ Health IT Cluster Collaborative Project Update
Health Informatics New Zealand
 
About IRT Nanoelec
About IRT NanoelecAbout IRT Nanoelec
About IRT Nanoelec
IRTNanoelec
 
WEBINAR: "How to manage your data to make them open and fair"
WEBINAR:  "How to manage your data to make them open and fair"  WEBINAR:  "How to manage your data to make them open and fair"
WEBINAR: "How to manage your data to make them open and fair"
OpenAIRE
 
PaNOSC and Research Data Management / Battery2030+ Initiative Workshop / 12 M...
PaNOSC and Research Data Management / Battery2030+ Initiative Workshop / 12 M...PaNOSC and Research Data Management / Battery2030+ Initiative Workshop / 12 M...
PaNOSC and Research Data Management / Battery2030+ Initiative Workshop / 12 M...
PaNOSC
 
High-Performance Computing Research in Europe
High-Performance Computing Research in EuropeHigh-Performance Computing Research in Europe
High-Performance Computing Research in Europe
Govnet Events
 
Furore devdays 2017- continua implementing fhir
Furore devdays 2017- continua implementing fhirFurore devdays 2017- continua implementing fhir
Furore devdays 2017- continua implementing fhir
DevDays
 
Mohammad-Reza (Saied) Tazari gfke 2014
Mohammad-Reza (Saied) Tazari gfke 2014Mohammad-Reza (Saied) Tazari gfke 2014
Mohammad-Reza (Saied) Tazari gfke 2014
innovationoecd
 
Overview of the data pilot and OpenAIRE tools, Elly Dijk and Marjan Grootveld...
Overview of the data pilot and OpenAIRE tools, Elly Dijk and Marjan Grootveld...Overview of the data pilot and OpenAIRE tools, Elly Dijk and Marjan Grootveld...
Overview of the data pilot and OpenAIRE tools, Elly Dijk and Marjan Grootveld...
OpenAIRE
 
The EOSC Compute Platform with the EGI-ACE project
The EOSC Compute Platform with the EGI-ACE project The EOSC Compute Platform with the EGI-ACE project
The EOSC Compute Platform with the EGI-ACE project
EGI Federation
 

Similar to Deep-Learning and HPC to Boost Biomedical applications for health (20)

Virtual BenchLearning - DeepHealth - Needs & Requirements for Benchmarking
Virtual BenchLearning - DeepHealth - Needs & Requirements for BenchmarkingVirtual BenchLearning - DeepHealth - Needs & Requirements for Benchmarking
Virtual BenchLearning - DeepHealth - Needs & Requirements for Benchmarking
 
Heterogeneous HPC Computing in the DeepHealth Project
Heterogeneous HPC Computing in the DeepHealth ProjectHeterogeneous HPC Computing in the DeepHealth Project
Heterogeneous HPC Computing in the DeepHealth Project
 
Gergely Sipos (EGI): Exploiting scientific data in the international context ...
Gergely Sipos (EGI): Exploiting scientific data in the international context ...Gergely Sipos (EGI): Exploiting scientific data in the international context ...
Gergely Sipos (EGI): Exploiting scientific data in the international context ...
 
EOSC-hub in EOSC context
EOSC-hub in EOSC contextEOSC-hub in EOSC context
EOSC-hub in EOSC context
 
Elixir Training: Professional skills for managing and exploiting data
Elixir Training: Professional skills for managing and exploiting dataElixir Training: Professional skills for managing and exploiting data
Elixir Training: Professional skills for managing and exploiting data
 
NordForsk Open Access Reykjavik 14-15/8-2014: H2020
NordForsk Open Access Reykjavik 14-15/8-2014: H2020NordForsk Open Access Reykjavik 14-15/8-2014: H2020
NordForsk Open Access Reykjavik 14-15/8-2014: H2020
 
Linked Data with hybrid services in Agriculture
Linked Data with hybrid services in AgricultureLinked Data with hybrid services in Agriculture
Linked Data with hybrid services in Agriculture
 
EGI Engage: Impact & Results
EGI Engage: Impact & ResultsEGI Engage: Impact & Results
EGI Engage: Impact & Results
 
Sshoc kick off meeting - 1.2.1 How to Connect to EOSC? - Tiziana Ferrari - EGI
Sshoc kick off meeting - 1.2.1 How to Connect to EOSC? - Tiziana Ferrari - EGISshoc kick off meeting - 1.2.1 How to Connect to EOSC? - Tiziana Ferrari - EGI
Sshoc kick off meeting - 1.2.1 How to Connect to EOSC? - Tiziana Ferrari - EGI
 
DEX Innovation Centre at a glance
DEX Innovation Centre at a glanceDEX Innovation Centre at a glance
DEX Innovation Centre at a glance
 
Exposing EO Linked (meta-)Data from OpenSearch Catalogue
Exposing EO Linked (meta-)Data from OpenSearch CatalogueExposing EO Linked (meta-)Data from OpenSearch Catalogue
Exposing EO Linked (meta-)Data from OpenSearch Catalogue
 
HZ Health IT Cluster Collaborative Project Update
HZ Health IT Cluster Collaborative Project UpdateHZ Health IT Cluster Collaborative Project Update
HZ Health IT Cluster Collaborative Project Update
 
About IRT Nanoelec
About IRT NanoelecAbout IRT Nanoelec
About IRT Nanoelec
 
WEBINAR: "How to manage your data to make them open and fair"
WEBINAR:  "How to manage your data to make them open and fair"  WEBINAR:  "How to manage your data to make them open and fair"
WEBINAR: "How to manage your data to make them open and fair"
 
PaNOSC and Research Data Management / Battery2030+ Initiative Workshop / 12 M...
PaNOSC and Research Data Management / Battery2030+ Initiative Workshop / 12 M...PaNOSC and Research Data Management / Battery2030+ Initiative Workshop / 12 M...
PaNOSC and Research Data Management / Battery2030+ Initiative Workshop / 12 M...
 
High-Performance Computing Research in Europe
High-Performance Computing Research in EuropeHigh-Performance Computing Research in Europe
High-Performance Computing Research in Europe
 
Furore devdays 2017- continua implementing fhir
Furore devdays 2017- continua implementing fhirFurore devdays 2017- continua implementing fhir
Furore devdays 2017- continua implementing fhir
 
Mohammad-Reza (Saied) Tazari gfke 2014
Mohammad-Reza (Saied) Tazari gfke 2014Mohammad-Reza (Saied) Tazari gfke 2014
Mohammad-Reza (Saied) Tazari gfke 2014
 
Overview of the data pilot and OpenAIRE tools, Elly Dijk and Marjan Grootveld...
Overview of the data pilot and OpenAIRE tools, Elly Dijk and Marjan Grootveld...Overview of the data pilot and OpenAIRE tools, Elly Dijk and Marjan Grootveld...
Overview of the data pilot and OpenAIRE tools, Elly Dijk and Marjan Grootveld...
 
The EOSC Compute Platform with the EGI-ACE project
The EOSC Compute Platform with the EGI-ACE project The EOSC Compute Platform with the EGI-ACE project
The EOSC Compute Platform with the EGI-ACE project
 

More from Big Data Value Association

Data Privacy, Security in personal data sharing
Data Privacy, Security in personal data sharingData Privacy, Security in personal data sharing
Data Privacy, Security in personal data sharing
Big Data Value Association
 
Key Modules for a trsuted and privacy preserving personal data marketplace
Key Modules for a trsuted and privacy preserving personal data marketplaceKey Modules for a trsuted and privacy preserving personal data marketplace
Key Modules for a trsuted and privacy preserving personal data marketplace
Big Data Value Association
 
GDPR and Data Ethics considerations in personal data sharing
GDPR and Data Ethics considerations in personal data sharingGDPR and Data Ethics considerations in personal data sharing
GDPR and Data Ethics considerations in personal data sharing
Big Data Value Association
 
Intro - Three pillars for building a Smart Data Ecosystem: Trust, Security an...
Intro - Three pillars for building a Smart Data Ecosystem: Trust, Security an...Intro - Three pillars for building a Smart Data Ecosystem: Trust, Security an...
Intro - Three pillars for building a Smart Data Ecosystem: Trust, Security an...
Big Data Value Association
 
Three pillars for building a Smart Data Ecosystem: Trust, Security and Privacy
Three pillars for building a Smart Data Ecosystem: Trust, Security and PrivacyThree pillars for building a Smart Data Ecosystem: Trust, Security and Privacy
Three pillars for building a Smart Data Ecosystem: Trust, Security and Privacy
Big Data Value Association
 
Market into context - Three pillars for building a Smart Data Ecosystem: Trus...
Market into context - Three pillars for building a Smart Data Ecosystem: Trus...Market into context - Three pillars for building a Smart Data Ecosystem: Trus...
Market into context - Three pillars for building a Smart Data Ecosystem: Trus...
Big Data Value Association
 
BDV Skills Accreditation - Future of digital skills in Europe reskilling and ...
BDV Skills Accreditation - Future of digital skills in Europe reskilling and ...BDV Skills Accreditation - Future of digital skills in Europe reskilling and ...
BDV Skills Accreditation - Future of digital skills in Europe reskilling and ...
Big Data Value Association
 
BDV Skills Accreditation - Big Data skilling in Emilia-Romagna
BDV Skills Accreditation - Big Data skilling in Emilia-Romagna BDV Skills Accreditation - Big Data skilling in Emilia-Romagna
BDV Skills Accreditation - Big Data skilling in Emilia-Romagna
Big Data Value Association
 
BDV Skills Accreditation - EIT labels for professionals
BDV Skills Accreditation - EIT labels for professionalsBDV Skills Accreditation - EIT labels for professionals
BDV Skills Accreditation - EIT labels for professionals
Big Data Value Association
 
BDV Skills Accreditation - Recognizing Data Science Skills with BDV Data Scie...
BDV Skills Accreditation - Recognizing Data Science Skills with BDV Data Scie...BDV Skills Accreditation - Recognizing Data Science Skills with BDV Data Scie...
BDV Skills Accreditation - Recognizing Data Science Skills with BDV Data Scie...
Big Data Value Association
 
BDV Skills Accreditation - Objectives of the workshop
BDV Skills Accreditation - Objectives of the workshopBDV Skills Accreditation - Objectives of the workshop
BDV Skills Accreditation - Objectives of the workshop
Big Data Value Association
 
BDV Skills Accreditation - Welcome introduction to the workshop
BDV Skills Accreditation - Welcome introduction to the workshopBDV Skills Accreditation - Welcome introduction to the workshop
BDV Skills Accreditation - Welcome introduction to the workshop
Big Data Value Association
 
BDV Skills Accreditation - Definition and ensuring of digital roles and compe...
BDV Skills Accreditation - Definition and ensuring of digital roles and compe...BDV Skills Accreditation - Definition and ensuring of digital roles and compe...
BDV Skills Accreditation - Definition and ensuring of digital roles and compe...
Big Data Value Association
 
BigDataPilotDemoDays - I BiDaaS Application to the Manufacturing Sector Webinar
BigDataPilotDemoDays - I BiDaaS Application to the Manufacturing Sector WebinarBigDataPilotDemoDays - I BiDaaS Application to the Manufacturing Sector Webinar
BigDataPilotDemoDays - I BiDaaS Application to the Manufacturing Sector Webinar
Big Data Value Association
 
BigDataPilotDemoDays - I-BiDaaS Application to the Financial Sector Webinar
BigDataPilotDemoDays - I-BiDaaS Application to the Financial Sector WebinarBigDataPilotDemoDays - I-BiDaaS Application to the Financial Sector Webinar
BigDataPilotDemoDays - I-BiDaaS Application to the Financial Sector Webinar
Big Data Value Association
 
Virtual BenchLearning - Data Bench Framework
Virtual BenchLearning - Data Bench FrameworkVirtual BenchLearning - Data Bench Framework
Virtual BenchLearning - Data Bench Framework
Big Data Value Association
 
Virtual BenchLearning - I-BiDaaS - Industrial-Driven Big Data as a Self-Servi...
Virtual BenchLearning - I-BiDaaS - Industrial-Driven Big Data as a Self-Servi...Virtual BenchLearning - I-BiDaaS - Industrial-Driven Big Data as a Self-Servi...
Virtual BenchLearning - I-BiDaaS - Industrial-Driven Big Data as a Self-Servi...
Big Data Value Association
 
Policy Cloud Data Driven Policies against Radicalisation - Technical Overview
Policy Cloud Data Driven Policies against Radicalisation - Technical OverviewPolicy Cloud Data Driven Policies against Radicalisation - Technical Overview
Policy Cloud Data Driven Policies against Radicalisation - Technical Overview
Big Data Value Association
 
Policy Cloud Data Driven Policies against Radicalisation - Participatory poli...
Policy Cloud Data Driven Policies against Radicalisation - Participatory poli...Policy Cloud Data Driven Policies against Radicalisation - Participatory poli...
Policy Cloud Data Driven Policies against Radicalisation - Participatory poli...
Big Data Value Association
 
Policy Cloud Data Driven Policies against Radicalisation
Policy Cloud Data Driven Policies against RadicalisationPolicy Cloud Data Driven Policies against Radicalisation
Policy Cloud Data Driven Policies against Radicalisation
Big Data Value Association
 

More from Big Data Value Association (20)

Data Privacy, Security in personal data sharing
Data Privacy, Security in personal data sharingData Privacy, Security in personal data sharing
Data Privacy, Security in personal data sharing
 
Key Modules for a trsuted and privacy preserving personal data marketplace
Key Modules for a trsuted and privacy preserving personal data marketplaceKey Modules for a trsuted and privacy preserving personal data marketplace
Key Modules for a trsuted and privacy preserving personal data marketplace
 
GDPR and Data Ethics considerations in personal data sharing
GDPR and Data Ethics considerations in personal data sharingGDPR and Data Ethics considerations in personal data sharing
GDPR and Data Ethics considerations in personal data sharing
 
Intro - Three pillars for building a Smart Data Ecosystem: Trust, Security an...
Intro - Three pillars for building a Smart Data Ecosystem: Trust, Security an...Intro - Three pillars for building a Smart Data Ecosystem: Trust, Security an...
Intro - Three pillars for building a Smart Data Ecosystem: Trust, Security an...
 
Three pillars for building a Smart Data Ecosystem: Trust, Security and Privacy
Three pillars for building a Smart Data Ecosystem: Trust, Security and PrivacyThree pillars for building a Smart Data Ecosystem: Trust, Security and Privacy
Three pillars for building a Smart Data Ecosystem: Trust, Security and Privacy
 
Market into context - Three pillars for building a Smart Data Ecosystem: Trus...
Market into context - Three pillars for building a Smart Data Ecosystem: Trus...Market into context - Three pillars for building a Smart Data Ecosystem: Trus...
Market into context - Three pillars for building a Smart Data Ecosystem: Trus...
 
BDV Skills Accreditation - Future of digital skills in Europe reskilling and ...
BDV Skills Accreditation - Future of digital skills in Europe reskilling and ...BDV Skills Accreditation - Future of digital skills in Europe reskilling and ...
BDV Skills Accreditation - Future of digital skills in Europe reskilling and ...
 
BDV Skills Accreditation - Big Data skilling in Emilia-Romagna
BDV Skills Accreditation - Big Data skilling in Emilia-Romagna BDV Skills Accreditation - Big Data skilling in Emilia-Romagna
BDV Skills Accreditation - Big Data skilling in Emilia-Romagna
 
BDV Skills Accreditation - EIT labels for professionals
BDV Skills Accreditation - EIT labels for professionalsBDV Skills Accreditation - EIT labels for professionals
BDV Skills Accreditation - EIT labels for professionals
 
BDV Skills Accreditation - Recognizing Data Science Skills with BDV Data Scie...
BDV Skills Accreditation - Recognizing Data Science Skills with BDV Data Scie...BDV Skills Accreditation - Recognizing Data Science Skills with BDV Data Scie...
BDV Skills Accreditation - Recognizing Data Science Skills with BDV Data Scie...
 
BDV Skills Accreditation - Objectives of the workshop
BDV Skills Accreditation - Objectives of the workshopBDV Skills Accreditation - Objectives of the workshop
BDV Skills Accreditation - Objectives of the workshop
 
BDV Skills Accreditation - Welcome introduction to the workshop
BDV Skills Accreditation - Welcome introduction to the workshopBDV Skills Accreditation - Welcome introduction to the workshop
BDV Skills Accreditation - Welcome introduction to the workshop
 
BDV Skills Accreditation - Definition and ensuring of digital roles and compe...
BDV Skills Accreditation - Definition and ensuring of digital roles and compe...BDV Skills Accreditation - Definition and ensuring of digital roles and compe...
BDV Skills Accreditation - Definition and ensuring of digital roles and compe...
 
BigDataPilotDemoDays - I BiDaaS Application to the Manufacturing Sector Webinar
BigDataPilotDemoDays - I BiDaaS Application to the Manufacturing Sector WebinarBigDataPilotDemoDays - I BiDaaS Application to the Manufacturing Sector Webinar
BigDataPilotDemoDays - I BiDaaS Application to the Manufacturing Sector Webinar
 
BigDataPilotDemoDays - I-BiDaaS Application to the Financial Sector Webinar
BigDataPilotDemoDays - I-BiDaaS Application to the Financial Sector WebinarBigDataPilotDemoDays - I-BiDaaS Application to the Financial Sector Webinar
BigDataPilotDemoDays - I-BiDaaS Application to the Financial Sector Webinar
 
Virtual BenchLearning - Data Bench Framework
Virtual BenchLearning - Data Bench FrameworkVirtual BenchLearning - Data Bench Framework
Virtual BenchLearning - Data Bench Framework
 
Virtual BenchLearning - I-BiDaaS - Industrial-Driven Big Data as a Self-Servi...
Virtual BenchLearning - I-BiDaaS - Industrial-Driven Big Data as a Self-Servi...Virtual BenchLearning - I-BiDaaS - Industrial-Driven Big Data as a Self-Servi...
Virtual BenchLearning - I-BiDaaS - Industrial-Driven Big Data as a Self-Servi...
 
Policy Cloud Data Driven Policies against Radicalisation - Technical Overview
Policy Cloud Data Driven Policies against Radicalisation - Technical OverviewPolicy Cloud Data Driven Policies against Radicalisation - Technical Overview
Policy Cloud Data Driven Policies against Radicalisation - Technical Overview
 
Policy Cloud Data Driven Policies against Radicalisation - Participatory poli...
Policy Cloud Data Driven Policies against Radicalisation - Participatory poli...Policy Cloud Data Driven Policies against Radicalisation - Participatory poli...
Policy Cloud Data Driven Policies against Radicalisation - Participatory poli...
 
Policy Cloud Data Driven Policies against Radicalisation
Policy Cloud Data Driven Policies against RadicalisationPolicy Cloud Data Driven Policies against Radicalisation
Policy Cloud Data Driven Policies against Radicalisation
 

Recently uploaded

Fueling AI with Great Data with Airbyte Webinar
Fueling AI with Great Data with Airbyte WebinarFueling AI with Great Data with Airbyte Webinar
Fueling AI with Great Data with Airbyte Webinar
Zilliz
 
“How Axelera AI Uses Digital Compute-in-memory to Deliver Fast and Energy-eff...
“How Axelera AI Uses Digital Compute-in-memory to Deliver Fast and Energy-eff...“How Axelera AI Uses Digital Compute-in-memory to Deliver Fast and Energy-eff...
“How Axelera AI Uses Digital Compute-in-memory to Deliver Fast and Energy-eff...
Edge AI and Vision Alliance
 
Digital Banking in the Cloud: How Citizens Bank Unlocked Their Mainframe
Digital Banking in the Cloud: How Citizens Bank Unlocked Their MainframeDigital Banking in the Cloud: How Citizens Bank Unlocked Their Mainframe
Digital Banking in the Cloud: How Citizens Bank Unlocked Their Mainframe
Precisely
 
What is an RPA CoE? Session 1 – CoE Vision
What is an RPA CoE?  Session 1 – CoE VisionWhat is an RPA CoE?  Session 1 – CoE Vision
What is an RPA CoE? Session 1 – CoE Vision
DianaGray10
 
Mutation Testing for Task-Oriented Chatbots
Mutation Testing for Task-Oriented ChatbotsMutation Testing for Task-Oriented Chatbots
Mutation Testing for Task-Oriented Chatbots
Pablo Gómez Abajo
 
Essentials of Automations: Exploring Attributes & Automation Parameters
Essentials of Automations: Exploring Attributes & Automation ParametersEssentials of Automations: Exploring Attributes & Automation Parameters
Essentials of Automations: Exploring Attributes & Automation Parameters
Safe Software
 
Main news related to the CCS TSI 2023 (2023/1695)
Main news related to the CCS TSI 2023 (2023/1695)Main news related to the CCS TSI 2023 (2023/1695)
Main news related to the CCS TSI 2023 (2023/1695)
Jakub Marek
 
Harnessing the Power of NLP and Knowledge Graphs for Opioid Research
Harnessing the Power of NLP and Knowledge Graphs for Opioid ResearchHarnessing the Power of NLP and Knowledge Graphs for Opioid Research
Harnessing the Power of NLP and Knowledge Graphs for Opioid Research
Neo4j
 
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAUHCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
panagenda
 
HCL Notes and Domino License Cost Reduction in the World of DLAU
HCL Notes and Domino License Cost Reduction in the World of DLAUHCL Notes and Domino License Cost Reduction in the World of DLAU
HCL Notes and Domino License Cost Reduction in the World of DLAU
panagenda
 
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
saastr
 
"Frontline Battles with DDoS: Best practices and Lessons Learned", Igor Ivaniuk
"Frontline Battles with DDoS: Best practices and Lessons Learned",  Igor Ivaniuk"Frontline Battles with DDoS: Best practices and Lessons Learned",  Igor Ivaniuk
"Frontline Battles with DDoS: Best practices and Lessons Learned", Igor Ivaniuk
Fwdays
 
Biomedical Knowledge Graphs for Data Scientists and Bioinformaticians
Biomedical Knowledge Graphs for Data Scientists and BioinformaticiansBiomedical Knowledge Graphs for Data Scientists and Bioinformaticians
Biomedical Knowledge Graphs for Data Scientists and Bioinformaticians
Neo4j
 
GraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph
GraphRAG for LifeSciences Hands-On with the Clinical Knowledge GraphGraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph
GraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph
Neo4j
 
Y-Combinator seed pitch deck template PP
Y-Combinator seed pitch deck template PPY-Combinator seed pitch deck template PP
Y-Combinator seed pitch deck template PP
c5vrf27qcz
 
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectorsConnector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
DianaGray10
 
zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...
zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...
zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...
Alex Pruden
 
The Microsoft 365 Migration Tutorial For Beginner.pptx
The Microsoft 365 Migration Tutorial For Beginner.pptxThe Microsoft 365 Migration Tutorial For Beginner.pptx
The Microsoft 365 Migration Tutorial For Beginner.pptx
operationspcvita
 
Northern Engraving | Nameplate Manufacturing Process - 2024
Northern Engraving | Nameplate Manufacturing Process - 2024Northern Engraving | Nameplate Manufacturing Process - 2024
Northern Engraving | Nameplate Manufacturing Process - 2024
Northern Engraving
 
GNSS spoofing via SDR (Criptored Talks 2024)
GNSS spoofing via SDR (Criptored Talks 2024)GNSS spoofing via SDR (Criptored Talks 2024)
GNSS spoofing via SDR (Criptored Talks 2024)
Javier Junquera
 

Recently uploaded (20)

Fueling AI with Great Data with Airbyte Webinar
Fueling AI with Great Data with Airbyte WebinarFueling AI with Great Data with Airbyte Webinar
Fueling AI with Great Data with Airbyte Webinar
 
“How Axelera AI Uses Digital Compute-in-memory to Deliver Fast and Energy-eff...
“How Axelera AI Uses Digital Compute-in-memory to Deliver Fast and Energy-eff...“How Axelera AI Uses Digital Compute-in-memory to Deliver Fast and Energy-eff...
“How Axelera AI Uses Digital Compute-in-memory to Deliver Fast and Energy-eff...
 
Digital Banking in the Cloud: How Citizens Bank Unlocked Their Mainframe
Digital Banking in the Cloud: How Citizens Bank Unlocked Their MainframeDigital Banking in the Cloud: How Citizens Bank Unlocked Their Mainframe
Digital Banking in the Cloud: How Citizens Bank Unlocked Their Mainframe
 
What is an RPA CoE? Session 1 – CoE Vision
What is an RPA CoE?  Session 1 – CoE VisionWhat is an RPA CoE?  Session 1 – CoE Vision
What is an RPA CoE? Session 1 – CoE Vision
 
Mutation Testing for Task-Oriented Chatbots
Mutation Testing for Task-Oriented ChatbotsMutation Testing for Task-Oriented Chatbots
Mutation Testing for Task-Oriented Chatbots
 
Essentials of Automations: Exploring Attributes & Automation Parameters
Essentials of Automations: Exploring Attributes & Automation ParametersEssentials of Automations: Exploring Attributes & Automation Parameters
Essentials of Automations: Exploring Attributes & Automation Parameters
 
Main news related to the CCS TSI 2023 (2023/1695)
Main news related to the CCS TSI 2023 (2023/1695)Main news related to the CCS TSI 2023 (2023/1695)
Main news related to the CCS TSI 2023 (2023/1695)
 
Harnessing the Power of NLP and Knowledge Graphs for Opioid Research
Harnessing the Power of NLP and Knowledge Graphs for Opioid ResearchHarnessing the Power of NLP and Knowledge Graphs for Opioid Research
Harnessing the Power of NLP and Knowledge Graphs for Opioid Research
 
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAUHCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
 
HCL Notes and Domino License Cost Reduction in the World of DLAU
HCL Notes and Domino License Cost Reduction in the World of DLAUHCL Notes and Domino License Cost Reduction in the World of DLAU
HCL Notes and Domino License Cost Reduction in the World of DLAU
 
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
 
"Frontline Battles with DDoS: Best practices and Lessons Learned", Igor Ivaniuk
"Frontline Battles with DDoS: Best practices and Lessons Learned",  Igor Ivaniuk"Frontline Battles with DDoS: Best practices and Lessons Learned",  Igor Ivaniuk
"Frontline Battles with DDoS: Best practices and Lessons Learned", Igor Ivaniuk
 
Biomedical Knowledge Graphs for Data Scientists and Bioinformaticians
Biomedical Knowledge Graphs for Data Scientists and BioinformaticiansBiomedical Knowledge Graphs for Data Scientists and Bioinformaticians
Biomedical Knowledge Graphs for Data Scientists and Bioinformaticians
 
GraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph
GraphRAG for LifeSciences Hands-On with the Clinical Knowledge GraphGraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph
GraphRAG for LifeSciences Hands-On with the Clinical Knowledge Graph
 
Y-Combinator seed pitch deck template PP
Y-Combinator seed pitch deck template PPY-Combinator seed pitch deck template PP
Y-Combinator seed pitch deck template PP
 
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectorsConnector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
 
zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...
zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...
zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...
 
The Microsoft 365 Migration Tutorial For Beginner.pptx
The Microsoft 365 Migration Tutorial For Beginner.pptxThe Microsoft 365 Migration Tutorial For Beginner.pptx
The Microsoft 365 Migration Tutorial For Beginner.pptx
 
Northern Engraving | Nameplate Manufacturing Process - 2024
Northern Engraving | Nameplate Manufacturing Process - 2024Northern Engraving | Nameplate Manufacturing Process - 2024
Northern Engraving | Nameplate Manufacturing Process - 2024
 
GNSS spoofing via SDR (Criptored Talks 2024)
GNSS spoofing via SDR (Criptored Talks 2024)GNSS spoofing via SDR (Criptored Talks 2024)
GNSS spoofing via SDR (Criptored Talks 2024)
 

Deep-Learning and HPC to Boost Biomedical applications for health

  • 1. 1 The project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 825111.The project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 825111. BDV ppp virtual workshop: How to exchange and grant access to heath data in a secure way: approaches and recommendations Monica Caballero (Project Manager) - monica.caballero.galeote@everis.com Jon Ander Gómez (Technical Manager) - jon@upv.es May 14th 2020 Deep-Learning and HPC to Boost Biomedical Applications for Health
  • 2. 4 The project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 825111. About DeepHealth Aim & Goals • Put HPC computing power at the service of biomedical applications with DL needs and apply DL techniques on large and complex image biomedical datasets to support new and more efficient ways of diagnosis, monitoring and treatment of diseases. • Facilitate the daily work and increase the productivity of medical personnel and IT professionals in terms of image processing and the use and training of predictive models without the need of combining numerous tools. • Offer a unified framework adapted to exploit underlying heterogeneous HPC and Cloud architectures supporting state-of-the-art and next-generation Deep Learning (AI) and Computer Vision algorithms to enhance European-based medical software platforms. Duration: 36 months Starting date: Jan 2019 Budget 14.642.366 € EU funding 12.774.824 € 22 partners from 9 countries: Research centers, Health organizations, large industries and SMEs Research Organisations Health Organisations Large Industries SMEs Key facts
  • 3. 5 The project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 825111. Developments & Expected Results • The DeepHealth toolkit • Free and open-source software: 2 libraries + front-end. • EDDLL: The European Distributed Deep Learning Library • ECVL: the European Computer Vision Library • Ready to run algorithms on Hybrid HPC + Cloud architectures with heterogeneous hardware (Distributed versions of the training algorithms) • Ready to be integrated into end-user software platforms or applications • HPC infrastructure for an efficient execution of the training algorithms which are computational intensive by making use of heterogeneous hardware in a transparent way • Seven enhanced biomedical and AI software platforms provided by EVERIS, PHILIPS, THALES, UNITO, WINGS, CRS4 and CEA that integrate the DeepHealth libraries to improve their potential • Proposal for a structure for anonymised and pseudonymised data lakes • Validation in 14 use cases (Neurological diseases, Tumor detection and early cancer prediction, Digital pathology and automated image annotation). EU libraries
  • 4. 6 The project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 825111. The Concept SOFTWARE PLATFORM BIOMEDICAL APPLICATION Medical image (CT , MRI , X-Ray,…) Health professionals (Doctors & Medical staff) ICT Expert users New image to be analysed Prediction Score and/or highlighted RoI returned to the doctor Load trained predictive models to the platform Use toolkit to train predictive models Data used to train models Platform uses the toolkit to train models (optional) Images labelled by doctors Add validated images Production environment Training environment Using loaded/trained predictive models (Optional) Train predictive models using the platform and the toolkit Samples to be pre-processed and validated Images pending to be pre-processed and validated HPC infrastructure TOOLKIT
  • 5. 7 The project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 825111. Current status at May 2020 (M1–M16) • Design & specification of libraries APIs, HPC system and use-cases finished. • Definition of the structure for anonymised and pseudonymised data lakes in progress • DeepHealth Toolkit: • EDDL & ECVL: • First stable versions publicly available in GitHub (non-distributed): https://github.com/deephealthproject/eddl / | https://github.com/deephealthproject/ecvl • Work in progress: improving non-distributed version, Python wrapper, distributed version using COMPSs from BSC to run on hybrid HPC + Cloud architectures, also using FPGAs kernels • Front-end: • GUI mostly finished • Supporting back-end to load and transform images on the fly during training ready
  • 6. 8 The project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 825111. Current status at May 2020 (M1–M16) • HPC Infrastructure Adaptation – in progress: • Development of heterogeneous support for the DeepHealth libraries • Communication and Synchronisation optimizations to make training and inference algorithms efficient • HPC runtime support and custom hardware support for both libraries • Design an hybrid cloud computing solution to support DeepHealth libraries • Integration of libraries and use cases in application platforms— in progress: • Adaptation of application platforms to use cases specifics • Design of the “how to” integrate libraries into the platforms finished. Iterative integration in progress • Testing and pilots: • About to start 1st technical validation setting complete pipelines • Example: https://github.com/deephealthproject/use_case_pipeline • Use-cases preparing data-sets for pilots (acquiring, labelling, curation, etc.)
  • 7. 9 The project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 825111. Challenges/difficulties identified 1. Data sharing among project’s partners is not always possible 2. Data is not curated enough
  • 8. 10 The project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 825111. Challenge 1: Data sharing among project’s partners is not always possible • Even under signed NDAs • Different legal advisors do different interpretations of the same Law • GDPR and other data protection rules of EU member states • Health data is very sensitive data that may include patient’s information —so involved people (doctors, IT staff, researchers, industry, etc.) must guarantee no patient’s information is disclosed • Validated/certified anonymization/pseudonymization and de-identification techniques not easy to achieve • No scientific progress without risks • Proposal for addressing this challenge in the Health sector: • Privacy and security by design in the standard protocols to collect and annotate data —protocols to be defined • Legal-technical-ethical committees must be created to issue data-sharing authorisations in order to avoid the responsibility falling on individual doctors or medical teams • Federated and split learning under software restrictions where only training algorithms have access to data
  • 9. 11 The project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 825111. Challenge 2: Data is not curated enough • Data is partially labelled/annotated • Non-standard protocols were followed to collect datasets for the same diseases • Relevant differences depending on the source/origin (hospital across Europe) • In particular regarding metadata that affects how labels and/or annotations are stored • Proposal for addressing this challenge in the Health sector: • Standard ontologies must be a priority • Standard protocols to collect and store for sharing FAIR data in Europe must be a priority • Make medical personnel more involved in technical projects —difficult to explain
  • 10. 12 The project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 825111.The project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 825111. Questions? @DeepHealthEU https://deephealth-project.eu Project Coordinator: Mónica Caballero monica.caballero.galeote@everis.com Technical Manager: Jon Ander Gómez jon@upv.es