Sup 219 - JSON Representation of DICOM Structured Reports

This draft resource describes a JSON representation of DICOM Structured Reports, similar to the PS3.18 JSON representation, to allow developers to encode image-derived results. It defines patterns for transforming measurement and annotation information for use-cases related to the reporting of artificial intelligence (AI), machine learning (ML) and quantitative imaging (QI) results. It can be used for export of AI and ML results as well as encoding of truth data for AI and ML training, testing and validation.

Main sections:

· Scope and field of application

· Normative and informative references

· Definitions

· Symbols and abbreviations

· Conventions

· XML encoding

· JSON encoding

· DICOM JSON model

· Data exchange models