neurolog
play

NeuroLOG Software technologies for integration of process, data and - PowerPoint PPT Presentation

Jul 11, 2023 •233 likes •467 views

NeuroLOG NeuroLOG Software technologies for integration of process, data and knowledge in medical imaging Software technologies for integration of process and data in medical imaging The NeuroLOG Platform Federating multi-centric neuroscience

  1. NeuroLOG NeuroLOG Software technologies for integration of process, data and knowledge in medical imaging Software technologies for integration of process and data in medical imaging The NeuroLOG Platform Federating multi-centric neuroscience resources Johan MONTAGNAT Franck MICHEL Vilnius, Apr. 13 th 2011 NeuroLOG ANR-06-TLOG-024 http:/ / neurolog.polytech.unice.fr

  2. Neurosciences requirements NeuroLOG Software technologies for integration of process, data and knowledge in medical imaging • Major challenge for this century  population aging, brain disorders growth, brain function understanding... • Large medical image databases Statistical studies   Population-specific atlases of the brain  Data intensive procedures • Heterogeneous data sets  Different acquisition conditions, centers Several imaging modalities   Associated clinical information • Complex data analysis procedures  Specific to some modalities, acquisition parameters  Minutes to hours of computation time each Chained into application pipelines (workflows)  • Sensitive data  Stringent access control requirements 2 NeuroLOG ANR-06-TLOG-024

  3. Collaborative approach NeuroLOG Software technologies for integration of process, data and knowledge in medical imaging • Sharing Computing algorithms and resources Research (populations studies, models design, validation, statistics) • Complex analysis algorithms & pipelines (compute intensive image • processing, time constraints...) Data Procedures Processing tools Computing power 3 NeuroLOG ANR-06-TLOG-024

  4. Brain atrophy measure workflow NeuroLOG Software technologies for integration of process, data and knowledge in medical imaging Detection of the longitudinal brain volume change is an issue of central relevance in neuroimaging. Early diagnosis for neurodegenerative  diseases (e.g. Alzheimer's).  Reduction of costs in clinical trials, increasing of the power in longitudinal studies. 4 NeuroLOG ANR-06-TLOG-024

  5. Inputs: longitudinal study NeuroLOG Software technologies for integration of process, data and knowledge in medical imaging Baseline image (T0) Other time point mages (T0 + 6 months, T0 + 12 months...) 5 NeuroLOG ANR-06-TLOG-024

  6. Image normalization NeuroLOG Software technologies for integration of process, data and knowledge in medical imaging Space alignment (registration) Intensity alignment 6 NeuroLOG ANR-06-TLOG-024

  7. Parameters extraction NeuroLOG Software technologies for integration of process, data and knowledge in medical imaging Mask Brain extraction Deformation field 1044901 -10294 -0.009 computation 1044901 -10484 -0.010 Quantitative parameters (atrophy measurement For Alzheimer's disease diagnosis) 7 NeuroLOG ANR-06-TLOG-024

  8. Generic infrastructure limitations NeuroLOG Software technologies for integration of process, data and knowledge in medical imaging • The grid provides a foundational layer for distributed, intensive computing Distributed files, large number of computing tasks • • Gap between grid infrastructures and medical environment  Low level foundational middlewares  Complex requirements from the health community Need for neuroradiological data integration • • Domain-specific data representation, mediation for existing databases Legacy neuroscience computing environments • • Bridging local and grid resources • Neurology data analysis pipelines Need to integrate neuro-data analysis codes and procedures • • Access control and privacy The foundational security layer needs to be refined with adapted • security policies 8 NeuroLOG ANR-06-TLOG-024

  9. NeuroLOG objectives NeuroLOG Software technologies for integration of process, data and knowledge in medical imaging • Enable the sharing of resources: Data & knowledge representation • • Ontologies + relational schema Neuroradiological data & associated metadata • • Distributed on neuroscience centers + EGI grid resources • Integration of heterogeneous data stores Image analysis tools • • Bundled, relocatable, remote invocation Application pipelines • Sites computing resources • • Four pathologies Multiple Sclerosis, brain strokes, brain tumors, Alzheimer's disease • 9 NeuroLOG ANR-06-TLOG-024

  10. Middleware design NeuroLOG Software technologies for integration of process, data and knowledge in medical imaging 10 NeuroLOG ANR-06-TLOG-024

  11. Software architecture NeuroLOG Software technologies for integration of process, data and knowledge in medical imaging 11 NeuroLOG ANR-06-TLOG-024

  12. Platform deployment NeuroLOG Software technologies for integration of process, data and knowledge in medical imaging • 5 sites connected • 4 collaborating hosiptals • Pitié Salpétrière (Paris) • Michalon (Grenoble) • CHU Rennes • Antoine Lacassagne (Nice) • 7 academic partners • I3S, IRISA, GIN, MIS, IFR49, INRIA Sophia, LRI • 2 companies • SAP, Visioscopie 12 NeuroLOG ANR-06-TLOG-024

  13. Data management layer NeuroLOG Software technologies for integration of process, data and knowledge in medical imaging  Provide a seamless access to heterogeneous distributed data Heterogeneous data (modality, clinical context…)   Heterogeneous legacy database providers & schemas…  Heterogeneous file systems, resource storage units (local, grid) • Need to provide: Federated view of the metadata   Common access to physical files • While enforcing strong constraints: Each partner site should keep control of access to their data  Keep autonomous data management on each site: weak coupling  Legacy data stores should not be altered   Ensure secure access to sensitive data and metadata 13 NeuroLOG ANR-06-TLOG-024

  14. Federated relational schema NeuroLOG Software technologies for integration of process, data and knowledge in medical imaging Ontology Variables Scores Instrument Common Assessment relational Examination schema Subject Study MR Protocols Dataset 14 NeuroLOG ANR-06-TLOG-024

  15. Data management layer NeuroLOG Software technologies for integration of process, data and knowledge in medical imaging • Approach  Derived the ontology into relational Federated Schema  A dynamic mediation & federation interface maps local database schemas to the federated schema  A file transfer interface makes files available to the end-user or processing tools  Come up with a global federated view that hides data distribution and heterogeneity from the end-user 15 NeuroLOG ANR-06-TLOG-024

  16. Sharing image analysis tools NeuroLOG Software technologies for integration of process, data and knowledge in medical imaging • Generic Application Service Wrapper (GASW)  Service wrapper to non instrumented code  Tool packaging in re-locatable self-contained executable units  Expose tools as web services, standard invocation interface  Handle data transfer  Remote execution capability on the EGI grid • Tools discovery through the federated view • Executable remotely by any authorized user 16 NeuroLOG ANR-06-TLOG-024

  17. Enabling processing pipelines NeuroLOG Software technologies for integration of process, data and knowledge in medical imaging • MOTEUR workflow engine  Generic workflow design and execution  Support for different interfaces to processors  Data and processing parallelism  Handles stand-alone (client) and client-server deployment 17 NeuroLOG ANR-06-TLOG-024

  18. Distributed data access control NeuroLOG Software technologies for integration of process, data and knowledge in medical imaging • Multiple credentials per user • Grid certificates (delivered by grid authority) • Middleware certificates (delivered by site authority) • Databases credential (SQL 92) • Health professional smartcards • … • Single sign-on enforced • NeuroLOG security policy • Individuals identification • Distributed security administration • No central point of control • Sites keep access control over all their data • Adapts to heterogeneous site security policies 18 NeuroLOG ANR-06-TLOG-024

  19. Distributed data access control NeuroLOG Software technologies for integration of process, data and knowledge in medical imaging • Each site data access policy prevails for the data items the site owns rule : { StudyA ; read ; } 19 NeuroLOG ANR-06-TLOG-024

  20. Results NeuroLOG Software technologies for integration of process, data and knowledge in medical imaging • NeuroLOG collaborating platform for multi-centric studies • Integrate heterogeneous & distributed legacy data sets • Share image analysis tools, distribute invocation • Build complex experiment pipelines • Distributed access control with prevailing local policies • Advanced functionality • High level ontology-based data representation • EGI Grid interface, large-scale distributed processing • The grid for neuroscientists • Transparent access to grid resources • Compliance with legacy environments 20 NeuroLOG ANR-06-TLOG-024

Recommend

More recommend