INFSO-RI Enabling Grids for E-sciencE NA4/Biomed Demonstration Medical Data Management and processing EGEE 3 rd review rehearsal, May 4 th, 2006 Johan Montagnat Tristan Glatard

NA4/biomed demonstration, 3 rd EGEE review rehearsal, May 4 th Enabling Grids for E-sciencE INFSO-RI Demonstration content Medical Data Manager –Interface to clinical data storage (DICOM) –Integrated to gLite 1.5 middleware –Tackling data security and privacy needs –Result of MDM TCG Working Group Application to medical images registration assessment –Data intensive workflow-based application –Scientific results in the medical image processing area with consequences for clinical use Immediate scheduling of jobs submitted for the demonstration –Torque+MAUI configuration for efficient handling of short jobs –Result of the SDJ TCG Working Group

NA4/biomed demonstration, 3 rd EGEE review rehearsal, May 4 th Enabling Grids for E-sciencE INFSO-RI Medical Data Manager Objectives –Expose an standard grid interface (SRM) for medical image servers (DICOM) –Fulfill application security requirements without interfering with clinical practice DICOM server gLiteIO server SRM-DICOM interface AMGA Metadata User Interface Worker Node Hydra Key store The MDM components DICOM clients Fireman File Catalog

NA4/biomed demonstration, 3 rd EGEE review rehearsal, May 4 th Enabling Grids for E-sciencE INFSO-RI Interfacing sensitive medical data Computing interface to medical DICOM storage –Data are acquired from the hospital imagers in native DICOM format –Standard SRM interface exposed to the grid –DICOM slices are assembled in 3D images Privacy –Fireman provides file level ACLs –gLiteIO provides transparent access control –AMGA provides metadata secured communication and ACLs –SRM-DICOM provides on-the-fly data anonimization  It is based on the dCache implementation (SRM v1.1) Data protection –Hydra provides encryption/decryption transparently gLite 1.5 service ARDA service

NA4/biomed demonstration, 3 rd EGEE review rehearsal, May 4 th Enabling Grids for E-sciencE INFSO-RI Medical Data Registration DICOM server AMGA Metadata Hydra Key store gLiteIO server 1. Image is acquired 2. Image is stored in DICOM server 3. glite-eds-put 3a. Image is registered (a GUID is associated) 3b. Image key is produced and registered 4. image metadata are registered Fireman File Catalog

NA4/biomed demonstration, 3 rd EGEE review rehearsal, May 4 th Enabling Grids for E-sciencE INFSO-RI Medical Data Retrieval DICOM server SRM-DICOM interface AMGA Metadata User Interface Worker Node Hydra Key store gLiteIO client 2. glite-eds-get 3. get SURL from GUID 4. request file 5. get file key 6. on-the-fly encryption and anonimyzation return encrypted file 7. get file key and decrypt file locally Metadata ACL control Key ACL control Anonimization & encryption In-memory decryption 1. get GUID from metadata gLiteIO server Fireman File Catalog File ACL control

NA4/biomed demonstration, 3 rd EGEE review rehearsal, May 4 th Enabling Grids for E-sciencE INFSO-RI Data replication and retrieval usecase gLiteIO server DICOM server SRM-DICOM interface User Interface Worker Node Hydra Key store gLiteIO client gLiteIO client Any SE SRM interface Any file 1. Request replication 6. Request file 2. Get SURL 3. Get file 8. Get file 4. Get file key 5. (encrypted) File replication 7. Get SURL 9. Return (encrypted) file gLiteIO server Fireman File Catalog File ACL control

NA4/biomed demonstration, 3 rd EGEE review rehearsal, May 4 th Enabling Grids for E-sciencE INFSO-RI Bronze Standard application Medical image registration algorithms assessment –Registration needed in many clinical procedures –Real clinical impact Interfaced to the medical data manager –To retrieve suitable input images Compute intensive –Medical image registration algorithms: minutes to hours of computations on PCs Data intensive –Hundreds to thousands of image pairs Workflow-based –Using the MOTEUR service-based workflow manager –Developed in the French ACI “Masse de données” AGIR project No execution infrastructure gLite 1.5 phased out May 4, 2:30pm update B-plan should work: - pre-install glite 1.5 DMS on prod. - Use production infrastructure for the demo

NA4/biomed demonstration, 3 rd EGEE review rehearsal, May 4 th Enabling Grids for E-sciencE INFSO-RI After registrationBefore registration Image Registration

NA4/biomed demonstration, 3 rd EGEE review rehearsal, May 4 th Enabling Grids for E-sciencE INFSO-RI Variability of a registration algorithm Registration algorithm Final transformation External parameters Data (image) 1 Data (image) 2 Acquisition noise Patient effects Varying internal parameters Initial transformation (…) Robustness: ability to find the right transformation (success/failure) Repeatability: w.r.t. some parameters (e.g. initialization) Accuracy: Variability w.r.t. the ground truth for typical data Fixed internal parameters Multiscale resolution (Typical variance…)

NA4/biomed demonstration, 3 rd EGEE review rehearsal, May 4 th Enabling Grids for E-sciencE INFSO-RI Performance Evaluation without Gold Std Bronze standard: The exact result is an unknown variable Unbiased estimation: use redundant information –use many different registration algorithms (average biases, so that precision ~ accuracy) –Use many different data (redundant information to ensure precision) –Average transformations (maximal consistency)

NA4/biomed demonstration, 3 rd EGEE review rehearsal, May 4 th Enabling Grids for E-sciencE INFSO-RI Bronze Standard workflow

NA4/biomed demonstration, 3 rd EGEE review rehearsal, May 4 th Enabling Grids for E-sciencE INFSO-RI Data-intensive service-based applications Service-based approach versus task-based approach Service0 Service1 Service2 Service3 input0 4 instances Job0 Job1Job2 Job3 Graph of services DAG of tasks Job0 Job1Job2 Job3 Job0 Job1Job2 Job3 Job0 Job1Job2 Job3 Job0 Job1Job2 Job3 Job0 Job1Job2 Job3 Job0 Job1Job2 Job3 Job0 Job1Job2 Job3 Job0 Job1Job2 Job3 Job0 Job1Job2 Job3 Job0 Job1Job2 Job3 Job0 Job1Job2 Job3 Job0 Job1Job2 Job3 Job0 Job1Job2 Job3 Job0 Job1Job2 Job3 Job0 Job1Job2 Job3

NA4/biomed demonstration, 3 rd EGEE review rehearsal, May 4 th Enabling Grids for E-sciencE INFSO-RI Data composition strategies Data composition patterns : data intensive applications –One-to-oneAll-to-all –In our case: register all images of  the same patient  the same modality  A different exam date Set 0 Set 1 I 0 J 0 I 1 J 1 I 2 J 2 Set 0 Set 1 I 0 J 0 I 1 J 1 I 2 J 2

NA4/biomed demonstration, 3 rd EGEE review rehearsal, May 4 th Enabling Grids for E-sciencE INFSO-RI workflow manager MOTEUR services orchestration EGEE User Interface EGEE Resources Input 0 Service B Output 0 Input 0 Input 1 Service A Output 0 Data 0 Img Ref 0 Data 1 Img Ref 1 Data 2 Img Ref 2 Img Ref 1 Img Ref 2

NA4/biomed demonstration, 3 rd EGEE review rehearsal, May 4 th Enabling Grids for E-sciencE INFSO-RI workflow manager Legacy code encapsulation Input 0 Input 1 Generic service Output 0 Input 0 Input 1 Generic service Output 0 Algorithm parameters description Algorithm parameters description Legacy code 2 Legacy code 1

NA4/biomed demonstration, 3 rd EGEE review rehearsal, May 4 th Enabling Grids for E-sciencE INFSO-RI Short Deadline Jobs Torque + MAUI specific configuration –Virtual processors allocation –Does not interfere with normal batch scheduling (shared processor time) –Enables efficient processing of short tasks on the production infrastructure –Ersatz for lack of jobs prioritization Special submission queues –Three SDJ queues deployed on biomed-compliant sites –Time-limited queues Submit-or-reject paradigm –Jobs are immediately executed or rejected if a too high number of short jobs are already executing.

NA4/biomed demonstration, 3 rd EGEE review rehearsal, May 4 th Enabling Grids for E-sciencE INFSO-RI Workflow execution

NA4/biomed demonstration, 3 rd EGEE review rehearsal, May 4 th Enabling Grids for E-sciencE INFSO-RI Post-mortem trace

NA4/biomed demonstration, 3 rd EGEE review rehearsal, May 4 th Enabling Grids for E-sciencE INFSO-RI Scientific production 4 rigid-registration algorithms precision estimated on brain image database To be published in [HealthGrid’06] Algorithm  reg (deg)  trans (mm) CrestMatch PFRegister Baladin Yasmina

NA4/biomed demonstration, 3 rd EGEE review rehearsal, May 4 th Enabling Grids for E-sciencE INFSO-RI Why grids? From days to hours –10s to 100s of algorithms  To adapt to many clinical cases –Virtually illimited parameterization –Virtually illimited number of image databases  Different modalities, different body regions Complex computation procedure –Difficult experimental set up –Future plan: application portal Data federation –Obtain data sources needed for validation Algorithms sharing –Use registration services developed in different research groups –Reproducible results

NA4/biomed demonstration, 3 rd EGEE review rehearsal, May 4 th Enabling Grids for E-sciencE INFSO-RI Conclusions Medical data management –Advanced Data management functionalities –Application area-level layer on top of foundation middleware –Dependent on the deployment of gLite 1.5 services Bronze Standard application –Complex, workflow-based application –Data intensive  Non-trivial parallel computations  Data federation using grid data management services –Production of scientific results Short deadline jobs –Immediate scheduling of short tasks –Submit-or-reject paradigm