the cancer biomedical informatics grid™ (cabig™): in vivo imaging workspace projects fred prior,...
TRANSCRIPT
The cancer Biomedical Informatics Grid™ (caBIG™):
In Vivo Imaging Workspace Projects
Fred Prior, Ph.D.Mallinckrodt Institute of RadiologyWashington University in St. Louis
caBIG will facilitate sharing of infrastructure, applications, and data
• Common, widely distributed informatics platform
• Shared vocabulary, data elements, data models
• Common standard for developing applications
In Vivo Imaging Workspace
• Project 1: Middleware • Project 2: AIM: Annotation and Image Markup• Project 3: Vocabulary • Project 4: XIP: Extensible Imaging Platform
Terminologies & CDEs
Image Annotation
Metadata storage formats
Queries & Analysis
Vocabularies & CDEs
Data CaptureFormats & Tools
Data Re-Use Applications
NLPMetadata for Images
• One of the goals of the In Vivo Imaging Workspace is to facilitate the increasing use of imaging based end points in clinical trials. To achieve this an easily extensible open source platform to support image analysis and visualization was defined as a key priority
• The eXtensible Imaging Platform (XIP) is an open source environment for rapidly developing medical imaging applications from an extensible set of modular elements.
• This platform will make it easier and less expensive to access specific post-processing applications at multiple sites, simplifying clinical trials, and most importantly, increasing the uniformity of imaging and analysis.
• Imaging applications developed by research groups will more easily be accessible within the clinical operating environment, simplifying workflows and speeding data processing and analysis.
• Once validated, the software should be readily transitioned into products through streamlined Federal Drug Administration, (FDA), approval processes due to the re-use of already approved libraries and open source development processes.
Deliverables• XIP.rad
– Development and application build environment– Extensive and extensible set of libraries for imaging and visualization– Uses Open Inventor framework – Includes code generating wizards to create new objects and wrap existing
libraries• XIP.ws
– A reference implementation of a medical imaging workstation developed using XIP.rad
– Integrated via middleware into caGRID– Optimized to support basic cancer research use cases– Includes two key components:
• XIP.app – a use case specific “plug-in” application integrated via the DICOM WG-23 Interface
• XIP.host – the hosting environment that provides XIP.apps access to services such as data stores, remote processing, etc.
XIP.ws - Reference Implementation
XIP.hostXIP.host
API (Socket)API (Socket)
API (Plug)API (Plug)
XIP.appXIP.app
Custom Custom XIP XIP
ClassesClasses
StandardStandardXIPXIP
ClassesClasses
Open Inventor• Open Inventor ® (http://oss.sgi.com/projects/inventor/ ) is an object-oriented toolkit offering a
comprehensive solution to interactive graphics programming problems. • It presents a programming model based on the Model/View/Controller design pattern and
the concept of Pipelines. • C++ modules represent Engines, Nodes and Manipulators
– Engines enable the creation of processing pipelines– Nodes support the concept of scene graphs, which are hierarchical structures of
objects describing what needs to be visualized in 2D/3D– Manipulators handle input devices, measurements and coordinate transforms in
response to user interaction
Integrating existing toolkits into
• Wrappers for ITK functions such as Region Growing, Neighborhood, Isolated, Confidence, Watershed, Thresholding, Edge Detection, Laplacian, Gaussian, …
• Support for ITK Data Meshes and Vector Fields
• Automatic Wrapper generation for 2D/3D libraries/toolkits such as ITK and VTK– Example: ITK for image processing, segmentation, registration
– User can review parsed results and choose to support only the desired data types, hide some methods, exclude some classes, etc.
XIP Framework & Architecture
XIP Application
(Can be replaced with any WG23-compatible Host)
XIP Host Adapter API
XIP
LIB
ITK
VTK
. .
.
Host-Specific Plugin Libraries
Rem
ote
Pro
cess
ing
caG
rid
Analy
tica
l S
vc.
Data
A
ccess
caG
rid
D
ata
S
vc.
An
nota
tion
an
d M
ark
up
AIM
Meta
Data
. .
..
. .
XIP ModulesHost Independent
WG23
XIPDevelopment
Tools
XIP Host
WG23 WG23 WG23
(Enables rapiddevelopment of
applications)
caGrid
• Grid Infrastructure for caBIG• caGrid Components
– Language (metadata, ontologies)– Security– Advertisement and Discovery– Workflow– Grid Service Graphical
Development Toolkit (Introduce)– Efficient Bulk Data Transport (IVI
middleware)– DICOM compatibility (IVI
middleware)
DICOM Interoperability• Interoperability Library
– Translate between DICOM and caBIG data models, and DICOM QR and caBIG query language
• DICOM Data Service
– Exposes existing DICOM QR aware data resources (PACS, etc) as caGrid compliant service
• VirtualPACS
– Allows DICOM-aware clients (review workstation, etc) to access DICOM caGrid data services over the grid
• caGrid-based security for data transport, authentication, and authorization
The caBIG AIM Project
• An ontology of image annotations– An ontology defines concepts in a domain and the relationships
between those concepts
• An ontology of image markups• Use of controlled terminologies
– RadLex, SNOMED, LOINC, UCUM
• Define a set of translatable standards-based representations
• Implement this functionality on the caBIG eXtensible Imaging Platform (XIP)
An Image, an Image Markup
The pixel at the tip of the arrow [coordinates (x,y)] inthis image[DICOM: 1.2.814.234543.23243]represents the Ascending Thoracic Aorta[SNOMED:A3310657]
and an Annotation
HW
XIPApplication
InventorApplication Modules
WG 23 System Services PLUG
WG 23 System Services SOCKET
GRIDCLIENT
SERVICES
DICOMSERVICES(DCMTK)
OTHERSERVICES
VTK ITK AIMTK other
OS
NCIA
XIPIDE
RadLex
AIM
NCI
ProtégéEVS
XIP
MIDDLEWARE
DICOM
DICOM Services
IVI MiddlewarecaGrid
CaBIG
caDSR, EVS, RadLex, AIM ontology, etc
Client accessService access
Grid Data Service
Grid Analytical Service
AIM Data Service
XIP App
ServiceHost
WG23
DICOM Image
Sources