JSON Representation of DICOM Structured Reports

This Supplement describes a simplified JSON representation of DICOM Structured Reports, similar to the PS3.18 JSON representation, to allow AI developers to encode image-derived results.

This supplement describes a mapping between a simple JSON representation of the measurement and annotation result payload expected from an AI system, and the traditional binary DICOM SR encoding of the same information.

This supplement defines a new Part, PS3.22, to contain the alternative representation, and includes the existing Attribute level XML and JSON encodings factored out of PS3.19 and PS3.18.

DICOM PS3.16 defines templates for different applications. The TID 1500 Measurement Report template describes a generic pattern that is suitable for encoding AI results as well as other quantitative and qualitative (categorical or descriptive) results. The JSON representation is exemplified using TID 1500, but the conversion supports full fidelity round-trip encoding of any DICOM SR instance, regardless of the template.

The JSON representation leverages the "business name" concept from HL7 Green CDA, such that simple meaningful strings can be used in the JSON for coded tuples for concept names and values, as well as for DICOM Attributes in the top level Data Set. The business names are defined in a separate, potentially reusable, JSON file.

Supplement 219 will be further presented and discussed with the Base Working Group in a coming meeting before Public Comment voting.