The health crisis due to COVID-19 is shaping a new reality in which the exchange and access to health data in a secure way will be more and more necessary. In this complex challenge converge both the respect for the individual rights as well as the interests of the patients and the need to promote the research in pursuit of the public interest. To face this challenge, we can find different approaches across Europe. In this webinar, we will present the experiences of three EU-funded projects (BigMedilytics, BodyPass, and DeepHealth), besides an overview of the legal framework and recommendations to enforce both national regulations and GDPR by an expert in data privacy and security.
Presentation on how to chat with PDF using ChatGPT code interpreter
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