Difference between revisions of "AI Results"

From IHE Wiki
Jump to: navigation, search
(Details)
 
(20 intermediate revisions by the same user not shown)
Line 1: Line 1:
  
'''AI Results''' specifies how medical imaging analysis results are exchanged and stored.  The central use case involves results generated by artificial intelligence (AI Model) algorithms.
+
'''AI Results''' specifies how medical imaging analysis results are reliably stored, retrieved, and displayed.  The central use case involves results generated by artificial intelligence (AI Model) algorithms.
  
 
__TOC__
 
__TOC__
  
 
==Summary==
 
==Summary==
''<Describe the profile in about a paragraph using user-oriented languageFocus on what it accomplishes for a user (i.e. the Use Cases).  Don't get into how it works, leave that to the Details section.>''
+
This profile standardizes storage & display of AI Results for image interpretationIt establishes baseline data handling and presentation capabilities for an image display product to be “AI-Ready”. Result generation products can leverage these data formats to be compatible with a variety of displays and site workflows.
  
''<Insert a simple graphic that, at a glance, visually summarizes what the profile is about.  Do not use an actor/transaction diagram here.  Show your graphic to someone for 5 seconds (literally) and ask them what it's about.  If what they say hits the main points in your summary paragraph, you have succeeded.  E.g. a graphic of a hospital, a clinic, and a lab with patient records moving between them.  .>''
+
AIR defines:
 +
* a set of '''result “primitives”'''
 +
* '''Encoding requirements''' for each primitive (DICOM-based storage)
 +
* transactions for moving that content around
 +
* '''Baseline display requirements''' for each primitive
  
 
==Benefits==
 
==Benefits==
''<If the profile can improve Cost, Safety, Quality or Efficiency then list the specific examples of that benefit (e.g. error reduction, increased throughput) and how they come about (e.g. SWF reduces patient errors due to mistyped demographics at the modality by transfering demographics electronically from the Order Filler). Consider using a bullet list for readability.  Such benefits help users and vendors make the business case for the profile.  If the profile does not improve any aspect of Cost, Safety, Quality or Efficiency feel free to talk about something else here.>''
+
'''Interoperable Results''':
 +
* Results need to be presented to radiologists in their reading environment. This profile provides interoperability between result generation products and radiology reading workstation systems/software.
 +
 
 +
'''Study Integrated Results''':
 +
* Radiologists expect AI-generated results to be presented in the context of the study to which they apply and expect them to supplement (rather than replace) traditional image analysis results and thus a given study will be composed of acquired images, AI results, and traditional clinical data. The result objects defined in this profile are defined for the existing imaging data storage infrastructure.
 +
 
 +
'''Effective Presentation''':
 +
* Effective use of results hinges on presenting them in conjunction with the associated images during the busy process of reading the study.
 +
 
 +
'''Convergence of Result Encoding''':
 +
* Many AI results are results that a human could otherwise have produced, and those human results may be used as training data for the AI. Analysis results might also be used by other AIs, e.g., in a GAN (generative adversarial network). AI and non-AI results need to be handled together. Convergent encoding of results facilitates this, as well as data pooling and sharing between sites.
 +
 
 +
'''Display Primitives''':
 +
* It is unrealistic to expect radiology displays to implement specific display capabilities for each of the myriad of algorithms being developed. To minimize implementation complexity for displays, and avoid needing different software for each new analysis result, compose analysis results from a reasonable set of primitives.
  
 
==Details==
 
==Details==
  
''<A few paragraphs, if appropriate, providing more details (mostly in user-speak, not tech-speak) on what the profile does and how it works.>''
+
AI Result Primitives:
 +
* '''Qualitative Findings''': E.g. Breast composition is Extremely Dense, Pneumothorax is Present
 +
* '''Measurements''': E.g. Adrenal Gland Nodule Length = 52mm
 +
* '''Locations''': E.g. Blood clot at (123.9, 57.2, 752.3)
 +
* '''Segmentations''': E.g. Lung Nodule surface
 +
* '''Parametric Maps''': E.g. Saliency Map for pneumonia
 +
* '''Tracking IDs''': E.g. Primary tumor for patient 32457 (longitudinal)
 +
* '''Image References''': E.g. Best view of brain hemorrhage
  
''<If the user might be familiar with the mechanisms used by the profile, you can mention them here.  E.g. Evidence Documents is based on DICOM Structured Report (SR) Templates.>''
 
 
''<If the user might have an appreciation for the problems addressed in the profile, you can mention them here, but keep it short.  E.g. Mapping HL7 Order fields to DICOM Modality Worklist attributes can be inconsistent in the marketplace, so Scheduled Workflow provides vendors with more detailed instructions.>''
 
 
 
==Systems Affected==
 
==Systems Affected==
''<List (in user terms) the types of systems they might expect to have implemented actors from this profile, e.g. RIS, PACS, HIS, CAD Workstation, etc. and for each, how it would participate.>''
+
* '''Evidence Creator''' - encodes results as specified
 
+
:* May an analysis or AI software package itself, or it may be a proxy, gateway, or partner system that encodes and transmits results on behalf of such software. The profile does not distinguish between analysis executed locally, in the cloud, hosted in processing servers, or running in standalone workstations.
* ''PACS systems may store, manage, and/or display Evidence Documents.''
+
* '''Image Manager (PACS)''' - stores and manages AI result objects as part of study
* ''Display systems may query, retrieve and display Evidence Documents.''
+
* '''Image Display''' - retrieves results and displays as specified
* ''Reporting workstations may retrieve, process and include details from Evidence Documents in reports
+
* '''Imaging Document Consumer''' - uses results in ways other than displaying them
 +
:* May include decision support systems, clinical databases, and report creators. 
  
 
'''Actors & Transactions:'''
 
'''Actors & Transactions:'''
  
''<Insert an actor-transaction diagram, and or list of Content Definitions>''
+
[[Image:AIR Actor Diagram.png|500px]]
  
 
==Specification==
 
==Specification==
Line 35: Line 56:
 
'''Profile Status:''' [[Comments| Trial Implementation]]   
 
'''Profile Status:''' [[Comments| Trial Implementation]]   
  
'''Documents:'''  
+
'''Documents:''' [https://www.ihe.net/uploadedFiles/Documents/Radiology/IHE_RAD_Suppl_AIR.pdf AI Results Profile - TI]
 +
* For an overview of the '''scope and goals''', see "Introduction to this Supplement", and Volume 3 Section 6.5.1.
 +
* For an overview of the participating '''actors and the transactions''' between them, see Volume 1 Section 49.1 and Section 49.4.2.
 +
* For '''key concepts''' that affect implementation and deployment and may be helpful in understanding the rest of the profile, see Volume 1 Section 49.4.1.
 +
* For the '''key technical requirements on encoding and displaying''' analysis results, see Volume 3 Section 6.5.3 and Volume 2 Section 4.136.4.1.3 respectively.
  
''<Provide direct links to the specific volumes or supplements, and list the volume sections relevant to this profile.  This is a simple inventory of official normative and informative text.  If you would like to provide a reading guide or walkthrough of what is in each of the different sections for implementers or users, do that in the Profile FAQ or the Profile Implementation Page linked below.  If the profile uses transactions from multiple Tech. Frameworks, repeat the structure below.>''
 
 
[http://www.ihe.net/Technical_Framework/index.cfm#radiology IHE Radiology Technical Framework:]
 
:* [http://www.ihe.net/Technical_Framework/upload/ihe_tf_rev8.pdf Vol. 1] - Section 5 (SWF Profile)
 
:* [http://www.ihe.net/Technical_Framework/upload/ihe_tf_rev8-2.pdf Vol. 2] - Sections 4.8 to 4.10, 4.14 to 4.19, and 4.23
 
:* [http://www.ihe.net/Technical_Framework/upload/ihe_tf_rev8-3.pdf Vol. 3] - Appendix E
 
  
 
'''Underlying Standards:'''
 
'''Underlying Standards:'''
 
 
:* [http://dicom.nema.org DICOM]
 
:* [http://dicom.nema.org DICOM]
  
Line 52: Line 70:
 
'''Related Profiles'''
 
'''Related Profiles'''
  
''<List profiles this one depends on, profiles that depend on this one, profiles that are synergistic with this one.  Start with the name of the other profile as a link and then explain the relationship.>''
+
* '''AI Workflow for Imaging''' [AIW-I] can be used to coordinate and manage the execution of AI algorithms whose results can be encoded and displayed using AIR.
  
* ''[[Reporting Workflow]] [RWF] may use Evidence Documents as inputs to the reporting process.''
 
* ''[[Simple Image & Numeric Reports]] [SINR] may include data copied from Evidence Documents.''
 
* ''[[Cross-enterprise Document Sharing for Imaging]] [XDS-I] can be used to share Evidence Documents between sites over a network.''
 
* ''[[Portable Data for Imaging]] [PDI] can store Evidence Documents on media such as CDs.''
 
* ''[[Import Reconciliation Workflow]] [IRWF] can fix patient ids, etc. of Evidence Documents when importing.''
 
 
[[Category:Profiles]]
 
  
 
This page is based on the [[Profile Overview Template]]
 
This page is based on the [[Profile Overview Template]]
  
 +
[[Category:Profiles]]
 
[[Category:RAD Profile]]
 
[[Category:RAD Profile]]
 
[[Category:DICOM]]
 
[[Category:DICOM]]
 
[[Category:DICOMweb]]
 
[[Category:DICOMweb]]

Latest revision as of 18:20, 9 December 2020

AI Results specifies how medical imaging analysis results are reliably stored, retrieved, and displayed. The central use case involves results generated by artificial intelligence (AI Model) algorithms.

Summary

This profile standardizes storage & display of AI Results for image interpretation. It establishes baseline data handling and presentation capabilities for an image display product to be “AI-Ready”. Result generation products can leverage these data formats to be compatible with a variety of displays and site workflows.

AIR defines:

  • a set of result “primitives”
  • Encoding requirements for each primitive (DICOM-based storage)
  • transactions for moving that content around
  • Baseline display requirements for each primitive

Benefits

Interoperable Results:

  • Results need to be presented to radiologists in their reading environment. This profile provides interoperability between result generation products and radiology reading workstation systems/software.

Study Integrated Results:

  • Radiologists expect AI-generated results to be presented in the context of the study to which they apply and expect them to supplement (rather than replace) traditional image analysis results and thus a given study will be composed of acquired images, AI results, and traditional clinical data. The result objects defined in this profile are defined for the existing imaging data storage infrastructure.

Effective Presentation:

  • Effective use of results hinges on presenting them in conjunction with the associated images during the busy process of reading the study.

Convergence of Result Encoding:

  • Many AI results are results that a human could otherwise have produced, and those human results may be used as training data for the AI. Analysis results might also be used by other AIs, e.g., in a GAN (generative adversarial network). AI and non-AI results need to be handled together. Convergent encoding of results facilitates this, as well as data pooling and sharing between sites.

Display Primitives:

  • It is unrealistic to expect radiology displays to implement specific display capabilities for each of the myriad of algorithms being developed. To minimize implementation complexity for displays, and avoid needing different software for each new analysis result, compose analysis results from a reasonable set of primitives.

Details

AI Result Primitives:

  • Qualitative Findings: E.g. Breast composition is Extremely Dense, Pneumothorax is Present
  • Measurements: E.g. Adrenal Gland Nodule Length = 52mm
  • Locations: E.g. Blood clot at (123.9, 57.2, 752.3)
  • Segmentations: E.g. Lung Nodule surface
  • Parametric Maps: E.g. Saliency Map for pneumonia
  • Tracking IDs: E.g. Primary tumor for patient 32457 (longitudinal)
  • Image References: E.g. Best view of brain hemorrhage

Systems Affected

  • Evidence Creator - encodes results as specified
  • May an analysis or AI software package itself, or it may be a proxy, gateway, or partner system that encodes and transmits results on behalf of such software. The profile does not distinguish between analysis executed locally, in the cloud, hosted in processing servers, or running in standalone workstations.
  • Image Manager (PACS) - stores and manages AI result objects as part of study
  • Image Display - retrieves results and displays as specified
  • Imaging Document Consumer - uses results in ways other than displaying them
  • May include decision support systems, clinical databases, and report creators.

Actors & Transactions:

AIR Actor Diagram.png

Specification

Profile Status: Trial Implementation

Documents: AI Results Profile - TI

  • For an overview of the scope and goals, see "Introduction to this Supplement", and Volume 3 Section 6.5.1.
  • For an overview of the participating actors and the transactions between them, see Volume 1 Section 49.1 and Section 49.4.2.
  • For key concepts that affect implementation and deployment and may be helpful in understanding the rest of the profile, see Volume 1 Section 49.4.1.
  • For the key technical requirements on encoding and displaying analysis results, see Volume 3 Section 6.5.3 and Volume 2 Section 4.136.4.1.3 respectively.


Underlying Standards:

See Also

Related Profiles

  • AI Workflow for Imaging [AIW-I] can be used to coordinate and manage the execution of AI algorithms whose results can be encoded and displayed using AIR.


This page is based on the Profile Overview Template