AI Results - Brief Proposal

1. Proposed Workitem: AI Results (AIR) Profile

Proposal Editor: Kevin O'Donnell
Editor: TBA
Domain: Radiology

2. The Problem

There is significant interest and activity applying AI methods (deep learning, etc) to the analysis of medical images.

Interoperable results: The results of such AI analysis need to be presented to radiologists in their reading environment. This depends on interoperability between AI result generation products and radiology reading workstation systems/software.

Study Integrated results: Radiologists interpreting studies likely expect AI-generated results to supplement rather than replace traditional image analysis results and thus a given study will be composed of acquired images, AI results, traditional clinical data.

Convergence of result encoding: Many AI results are results a human could otherwise have produced, and those human results may be used as training data for the AI, and AI results may be used by other AIs in an adversarial network. AI and non-AI results need to handled together. Also want to facilitate data pooling and sharing between sites.

For AI to productively live up to it's promise, results and data must be reliably, and conveniently, assembled and managed.

3. Key Use Case

The goal is for AI packages to be able to store AI results that can be retrieved and presented consistently by a variety of imaging display systems.

The display would present the result in the context of the medical imaging study to which it applies.

To minimize the implementation complexity for the displays, and to avoid having to change software for each new AI result, it would make sense to compose AI results from a reasonable set of primitives.

4. Standards and Systems

Result Creators - AI algorithms running in PACS, cloud, processing servers, standalone workstations, etc.

Storage - PACS, VNA, etc.

Result Displays - reading workstations (could argue this is a special case of consumer, but might want to have specific required display features/behaviors)

Result Consumers - databases, clinical analysis, report creators (import results)

Standards

DICOM SR - TID 1500

TID 1500
WG-23 is working to catalog result types and identify any gaps in TID 1500
An initial set of primitives have been identified
WG-23 AI Results Workplan Doc

DICOM Segmentations

DICOM Sup XXX Simplified SR in JSON for AI

David Clunie has a significant draft that will be presented at WG-06 in September. He has also been working on tooling to test/confirm the transcoding logic.
This work is what really makes this accessible to the AI community, and bridges into the existing radiology infrastructure

RSNA CDE (Common Data Elements)

helps with longitudinal data and automation logic for reporting and decision support
http://radelement.org

IHE Evidence Documents Profile

Should review to see if there anything we should borrow/revive

IHE Query for Existing Data for Mobile

consider using this to query the EHR for diagnostic reports and observations about the patient

IHE Results Distribution

consider the critical results status flags since AI results may be used to prioritize reading worklists

5. Discussion

This fits the IHE model of profiles as tools for convergence.

Display products that support those primitives can declare they are “AI-Ready”
Users can motivate display vendors to be AI-Ready
AI products that output their result using those primitives will know that a variety of displays will be able to present their results.
Users can motivate AI vendors to conform since that will simplify deployment for the users

IHE Rad may want to consider defining some baseline presentation requirements or conventions for certain results.

There are many other radiology applications of AI that are not about processing images. This proposal is initially image-centric.

5. Technical Approach

<This section can be very short but include as much detail as you like. The Technical Committee will flesh it out when doing the effort estimation.>

Existing actors

<Indicate what existing actors could be used or might be affected by the profile.>

New actors

<List possible new actors>

Existing transactions

<Indicate how existing transactions might be used or might need to be extended.>

New transactions (standards used)

<Describe possible new transactions (indicating what standards might be used for each).>

<Transaction diagrams are very helpful here. Go into as much detail as seems useful.>

Impact on existing integration profiles

<Indicate how existing profiles might need to be modified.>

New integration profiles needed

<Indicate what new profile(s) might need to be created.>

Breakdown of tasks

<As the basis for the effort estimation, enumerate the tasks to develop the Profile text. E.g.>

<Discuss/Confirm use case list (currently 5) to decide in/out of scope and details>
<Analyze/choose which report guidelines to use>
<Resolve open issue on the degree of computer parsability>
<Draft/Review content definition for Oncology Report (profile use of CCDA)>
<Draft/Review transaction for Retrieve Report>

6. Support & Resources

DICOM WG-23 is engaged on the topic of AI Results and has completed work useful to this activity

<Identify anyone who as indicated an interest in implementing/prototyping the Profile if it is published this cycle.>

7. Risks

The JSON SR supplement could get hung up on technical hitches.
Debates on alternative standards
Scope creep - AI is a large space

8. Open Issues

<Point out any key issues or design problems. This will be helpful for estimating the amount of work and demonstrates thought has already gone into the candidate profile.>

9. Tech Cmte Evaluation

<The technical committee will use this area to record details of the effort estimation, etc.>

Effort Evaluation (as a % of Tech Cmte Bandwidth):

35% for ...

Candidate Editor:

TBA