Medical Image Quality Assurance with Automated Constraint Validation - PowerPoint PPT Presentation

About This Presentation
Title:

Medical Image Quality Assurance with Automated Constraint Validation

Description:

XML Encoding of Constraints. Use an XML document to specify predicates ... Pixel data exist and is either not compressed or compressed with a compatible codec ... – PowerPoint PPT presentation

Number of Views:88
Avg rating:3.0/5.0
Slides: 22
Provided by: medica4
Learn more at: https://dicom.nema.org
Category:

less

Transcript and Presenter's Notes

Title: Medical Image Quality Assurance with Automated Constraint Validation


1
Medical Image Quality Assurance with Automated
Constraint Validation
  • Dongbai Guo
  • Architect and Senior Development Manager
  • Oracle Corporation
  • db.guo_at_oracle.com, dbguo_at_ieee.org
  • Nashua, NH 03062, USA

2
Market Trends
  • Growth in medical imaging
  • New applications and new branches of medicine
  • Increased utilization
  • Increased spatial and temporal resolution
  • Exponential growth in data volume
  • Computer aided detection (CAD) and diagnosis
    (CADx)
  • Data integration and centralization
  • Knowledge management, sharing and discovery

3
Impacts to DICOM
  • Wider, but sometimes hasty, adoption
  • Variant implementation quality
  • Non-compliant images lead to integration
    nightmare for
  • Clinical care
  • Research
  • Clinical trials
  • We need ways to specify and validate constraints

4
Validation Applications
  • Validate the conformance of a DICOM object with
    respect to
  • The DICOM standard (www.dvtk.org)
  • An institutional guideline
  • A jurisdictional requirement
  • A DICOM application

5
Formal Language Representation of Constraints
  • Formal language representation
  • Unambiguously specify constraints
  • Unambiguously exchange constraints
  • Object can be validated at the site of
    origination
  • Stand-alone validation services
  • Computer interpretable formal syntax

6
XML Encoding of Constraints
  • Use an XML document to specify predicates to
    evaluate against a DICOM object
  • Easy to exchange
  • Constraint can be managed, enhanced,
    version-controlled
  • Good readability
  • Wide range of tools
  • Using XML schema to validate syntax

7
Constraint Design
8
Sample Constraint, 1
  • (1) SOPCommonModule
  • (1.0) / Based on P3.3 2007 table C.12-1
    /
  • (1.1)           ( type1(00080016)
  • (1.2)           AND
  • (1.3)           type1(00080018) )
  • (1.4)           when false log (SOP common
    module validation failed)
  • (1.5)           when false error
    (Validation error missing mandatory attribute
    for SOP common module)

9
XML Mapping, 1
  • lt?xml version"1.0" encoding"UTF-8"?gt
  • ltCONFORMANCE_CONSTRAINT_DEFINITION
    xmlns"http//xmlns.oracle.com/ord/dicom/constrain
    t" xmlnsdt"http//xmlns.oracle.com/ord/dicom/dat
    atype" xmlnsxsi"http//www.w3.org/2001/XMLSchema
    -instance" xsischemaLocation"http//xmlns.oracle
    .com/ord/dicom/constraint http//xmlns.oracle.com/
    ord/dicom/constraint"gt lt!-- line (0) --gt
  • ltGLOBAL_RULE name"SOPCommonModule"gt lt!-- line
    (1) --gt
  • ltDESCRIPTIONgtBased on P3.3 2007 table
    C.12-1lt/DESCRIPTIONgt lt!-- line (1.0) --gt
  • lt!-- line (1.2) The child predicates of a rule
    and implicitly combined with logical AND --gt
  • ltPREDICATEgt lt!-- line (1.1) --gt
  • ltBOOLEAN_FUNC operator"notEmpty"gt
  • ltATTRIBUTE_TAGgt00080016lt/ATTRIBUTE_TAGgt
  • lt/BOOLEAN_FUNCgt
  • lt/PREDICATEgt
  • ltPREDICATEgt lt!-- line (1.3) --gt
  • ltBOOLEAN_FUNC operator"notEmpty"gt
  • ltATTRIBUTE_TAGgt00080018lt/ATTRIBUTE_TAGgt
  • lt/BOOLEAN_FUNCgt
  • lt/PREDICATEgt
  • ltACTION action"log" when"false"gt SOP common
    module validation failed lt/ACTIONgt lt!-- line
    (1.4) --gt
  • ltACTION action"error" when"false"gtmissing
    mandatory attribute for SOP common
    modulelt/ACTIONgt lt!-- line (1.5) --gt
  • lt/GLOBAL_RULEgt

10
Sample Constraint, 2
  • (2) CTImage
  • (2.1)
  • (2.1.1) ( (000800161.2.840.10008.5.1.
    4.1.1.2)
  • (2.1.2) implies
  • (2.1.3) (( type1(00080008) AND
    (00080008 IN AXIAL, LOCALIZER ) )
  • (2.2) AND
  • (2.2.1) (000800161.2.840.10008.5.1.
    4.1.1.2)
  • (2.2.2) implies
  • (2.2.3) ( type1(00280002) AND
    (00280002 1 ))
  • (2.3) AND SOPCommonModule)
  • (2.4) when false warning(Validation
    warning not a valid CT image)

11
XML Mapping, 2
  • ltGLOBAL_RULE name"ctImage"gt lt!-- line (2) --gt
  • ltPREDICATEgt lt!-- line (2.1.2) --gt
  • ltLOGICAL operator"derive"gt
  • ltPREDICATEgt lt!-- line (2.1.1) --gt
  • ltRELATIONAL operator"eq"gt
  • ltATTRIBUTE_TAGgt00080016lt/ATTRIBUTE_TAGgt
  • ltSTRING_VALUEgt1.2.840.10008.5.1.4.1.1.2lt
    /STRING_VALUEgt
  • lt/RELATIONALgt lt/PREDICATEgt
  • ltPREDICATEgtlt!-- line (2.1.3) --gt
  • ltLOGICAL operator"and"gt
  • ltPREDICATEgt
  • ltBOOLEAN_FUNC operator"notEmpty"gt
  • ltATTRIBUTE_TAGgt00080008lt/ATTRIBUT
    E_TAGgt
  • lt/BOOLEAN_FUNCgt lt/PREDICATEgt
  • ltPREDICATEgt
  • ltRELATIONAL operator"in"gt
  • ltATTRIBUTE_TAGgt00080008lt/ATTRIBUTE_TA
    Ggt
  • lt CODE_STRINGgtAXIALlt/ CODE_STRINGgt
  • ltCODE_STRINGgtLOCALIZERlt/
    CODE_STRINGgt

12
Sample Constraint, 3
  • Context Sensitive Structure
  • The value of an attribute determines the
    structure of a DICOM object
  • Common in DICOM structured report
  • Example Table C.17-4 SR document content module
    attributes, PS 3.3 2007,
  • Can be broken down to attribute level predicates
  • (value(0040A040)TEXT ? notNULL(0040A160))

13
Validation Flow
14
Implementation
  • System implemented with PL/SQL, Java and C
  • Part of Oracle database 11gR1
  • Data model manages user-defined constraints
  • Changes to constraints does not interrupt
    database services
  • Can batch-validate DICOM content stored in or
    managed by a database

15
Quality Assurance (QA)
  • Validation of DICOM content
  • By the capturing device
  • At the PACS protocol layer
  • Within an image archive
  • At enterprise data exchange gateway
  • As a quality assurance service component of any
    service oriented architecture
  • Prevent application errors
  • Avoid costly rescan of patients
  • Eliminate waste in computation and network
    bandwidth

16
Using the QA Components
  • Distributed QA agent
  • Enable nation-wide radiation safety monitoring

17
Experiment Setup
  • A clinical trial requires images contain all
    DICOM image related tags for an image processing
    application
  • Verify part-10 file header exist
  • Verify all general image module tags exist
  • Image size (row/column) fell within the required
    range
  • Pixel data exist and is either not compressed or
    compressed with a compatible codec

18
Experiment Result
  • 15413 sample images collected from clinical trial
    sites
  • 121 of them failed validation.
  • All images passed validation can be analyzed by
    the image processing software

19
Conformance-aware Data Set
  • The same DICOM object can be verified by
    different QA requirements
  • Passed CT content validation
  • Failed CT CAD application validation
  • DICOM object and data flow can be associated with
    conformance results

20
Conformance-aware Dataflow
21
Summary
  • Formal language representation of DICOM
    constraint
  • XML encoding of constraint document
  • User-defined constraints
  • Conformance-aware data flow
Write a Comment
User Comments (0)
About PowerShow.com