✚ ✘ ✙ ✘ ✖✗ ✕ ☎ ✠ ✔ ✞ ✓✎ ✏ ☛ ✌ ✞ ✗ ✁ ✡☛ ✟✠ � ✁ ✁ ✂ ✄ ☎ ✆ ✆ ✞ MEDIGRID ACI-GRID project French ministry of research Medical image processing on grids ☎✝✆ ☞✍✌ ☞✍✎ ✑✝✒ Johan Montagnat MEDIGRID project, 3/11/2003 1
Partners French National Center for Scientific Research CREATIS Signal & image processing Radiology department Communicating IS Information system ERIC Image processing MEDIGRID project, 3/11/2003 2
Medical applications on GRIDs Medical applications have specific requirements for grid computing: Data: Are heterogeneous Have a strong semantic Are distributed over medical sites Are confidential (security issues) Processings Are often correlated (pipelines of processings) Computation time is often important (physicians will accept to wait for minutes at most) Computation time is sometimes critical (e.g. real time simulation) Emergency situation: ambulance jobs Existing grids are not taking into account all these requirements today MEDIGRID project, 3/11/2003 3
MEDIGRID Objectives Use computation GRIDs to face recent challenges in medical data analysis. We are focusing on two application kinds: Computation intensive image processing algorithms Parallelization Reduced computation time Management of very large datasets Distributed storage Massive distributed processing Statistical analysis MEDIGRID project, 3/11/2003 4
1. Complex modeling of anatomical structures Anatomical modeling for: Segmentation Quantitative analysis Linear Finite Element Modeling of biomechanics Parallelization of large linear systems Modeling / segmentation of 3D+T cardiac sequences in a reasonnably short amount of time (few minutes) MEDIGRID project, 3/11/2003 5
❴❁ ✸ ❲ ❳ ❳ ❳ ❚ ❨ ❩❬ ❭ ❀ ✿ ▲ ✾ ❂ ❭ ✽❪ ❨ ❫ ✾ ❁ ❴ ❯ ❱ ❛ ❄ ❑ ■ ❈ ▼ ◗ ◗ ◗ ❙ ❚ ❉ ▼ ❈❯ ❊ ❅ ■ ❯ ❏ ● ▲ ❈ ❵ ✽ ●❏ ✽❪ ❢ ❴ ✹ ✿ ❭ ❂ ❭ ❵ ❭ ✸ ✽❪ ✽ ❭ ❪ ❵ ❣ ❤ ❂ ✸ ❜ ❨ ❭ ❀❜ ❞ ❝ ❪ ❁ ❵ ❭ ❴ ❝ ❛ ❜ ❭ ❵ ❁ ❪ ❵ ❨ ❩ ❁ ✾ ❜ ❡ ❜ ▲ ❑ ●■ ✧ ✪✩ ✤ ★ ✦ ✯ ✭ ✪ ✦ ✩ ✱ ✤ ✜ ✰ ✣ ✩ ✯ ✧ ❄ ✲ ✥ ✰ ✛ ✫✬ ✣✤ ✥ ✦ ✜ ✦ ✤ ✪ ✩ ✭ ✥ ✦ ✜ ✦ ✧ ✩ ✤ ✮ ✥✯ ✤ ✫ ✦ ✱✳ ✻ ✭ ✥ ✤ ✪ ✥ ✳ ✺ ✼ ★ ✽ ❀❁ ❂ ❃❄ ❈ ● ❍ ✥✷ ✸✹ ✱✳ ✭ ✫✜ ✣ ✥ ✛ ✧ ✯ ✦ ✴ ✜ ✥ ✦ ✩ ✪ ✵ ✰ ✶ MEDIGRID project, 3/11/2003 Produce simulated images from a perfectly known model for: 2. Simulation of MRIs MRI sequences testing and design 6 ✧✢✩ ρ Artifacts study and correction ✧✢★ Image processing evaluation ◆P❘ ◆P❖ ✛✢✜ ❉❋❊ ✾✝✿ ❅❇❆ Overview
➁ t ⑨ ✐ t ⑩ ⑥ q ❹❺ ❻ ♦ ⑦ ⑧ ⑨ ④ ✉ ❼ ❧ ➅ ➄ ➃ ➂ ➁ ➀ ❾❿ ❼ ❽ ➁ ➃➄ ➂ ➁ ➀ ❾❿ ① ⑧ ⑦ ✉ ♦ r s t ✉ ❥ ♦ ① ② ❧ r ❥ ⑤ ❧ t s ②③ q ⑥ ④ r First results Synthetized images ❶❸❷ Computation time ✐❦❥ 2D: small cluster (1024 ❧♥♠ ♣✍q 3D: full scale grid (128 ❧♥♠ ♣✍q s✇✈ MEDIGRID project, 3/11/2003 7
3. Mammographies analysis More than 10000 images, 450 Gbytes 400 sub regions (e.g.) per image About 250 variables extracted on each region for training and for CBIR Texture, gray-levels and shape analysis Image indexation Indexing requires about 30 minutes of computations per image (Sun Ultra-10, 440 MHz), no optimization MEDIGRID project, 3/11/2003 8
➏ ➑ ➇ ➑ ➑ ➌ ➍ ➎ ➇ ➔ ➉ ➊ ➋ ➒ ➍ ➓ ➐ ➏ ➏ ➍ ➒ ➑ ➑ ➇ ➐ ➓ ➎ ➍ ➌ ➋ ➉➊ First results ➆➈➇ MEDIGRID project, 3/11/2003 9
4. Shared and distributed data management Distributed data and distributed metadata Metadata Distribution/Location Service (similar to GRID replication services for metadata) Metadata and data should be synchronized (same lifetime, access authorization...) Data traceability (How was data B produced? Which result was obtained from data A?) High level layer Intelligent proxy hierarchy Distributed dynamic indices for queries Optimisation / caching of search requests MEDIGRID project, 3/11/2003 10
4. Medical data security RC Replica Grid middleware Replication interface Catalog Service Storage MSS Element Metadata interface Replica File metadata ACD Client 1 Client 2 RS size interface interface interface checksum Storage core ... Element Application metadata grid - server header blanking ACD encryption interface encryption key sensitive metadata Medical server ... Master File Medical (trusted) site MEDIGRID project, 3/11/2003 11
Fine grain data control User Data administrator (owner, site admin, ...) Access certificate access User ID certificate Admin ID Target data ID authenticated Authorized access modes certificate Certificate validity Identification and Admin signature authorization control Data and metadata MEDIGRID project, 3/11/2003 12
5. Hybrid (content-based and metadata) queries Content-based queries Queries images over their content (medical images indexing and research) Mixed content-based and metadata-based queries Job submission / data / metadata synchronisation Use queries over metadata to describe input datasets for jobs A job should be able to process a set of files (data) A job should be able to process a set of files corresponding to some metadata (query + processing) MEDIGRID project, 3/11/2003 13
First experiment on the EDG testbed 1. Query the medical image database and retrieve a patient image Exam image patient key ACL ... Medical Metadata images 2. Compute similarity measures over the database images Submit 1 job per image 3. Retrieve most similar cases Similar images Low score images MEDIGRID project, 3/11/2003 14
Data and users Medical Data Images and metadata Nominative (critical) and non-nominative (private) data DICOM3 standard compliance for medical images Users Patient: has free access to its medical data. Physician: has complete read access to his/her patients data. Few persons have read/write access. Researchers: may obtain read access to anonymous medical data for research purposes. Nominative data should be blanked before transmission to these users. MEDIGRID project, 3/11/2003 15
Testbed 4 image sources, 3 sites: Heart sequences acquired at the Lyon cardiological hospital Bone structure database from ESRF Grenoble Mammographies from the DDSM Simulated MRI images Cardiological DLT Heart INSA Bone hospital MRI Simulated MRI University Breast Lyon 2 images EDG testbed Local (CERN, UK, Italy, France cluster The Netherlands) MEDIGRID project, 3/11/2003 16
Conclusions Significant growth of the grid awarness in the medical imaging community Healthgrid'04, Clermont-Ferrand, France, January 2004 http://clermont04.healthgrid.org EU projects (DataGrid, CrossGrid...), e-Science, BIRN... Limitations of existing middlewares for biomedical applications Complex datasets management Security Interactivity ... MEDIGRID project, 3/11/2003 17
Recommend
More recommend
