Dermatology Image Annotation FHIR Implementation Guide
0.1.0 - ci-build
Dermatology Image Annotation FHIR Implementation Guide
0.1.0 - ci-build
Dermatology Image Annotation FHIR Implementation Guide - Local Development build (v0.1.0) built by the FHIR (HL7® FHIR® Standard) Build Tools. See the Directory of published versions
Contents:
This page provides a list of the FHIR artifacts defined as part of this implementation guide.
The following artifacts define the specific capabilities that different types of systems are expected to have in order to comply with this implementation guide. Systems conforming to this implementation guide are expected to declare conformance to one or more of the following capability statements.
| Annotate MD Server Capability Statement |
Defines the expected capabilities of a server implementing the Dermatology Image Annotation IG. |
These define the properties by which a RESTful server can be searched. They can also be used for sorting and including related resources.
| observation-derived-from |
Search observations by source image reference (ImagingStudy, DocumentReference, or Media) |
| observation-method |
Search observations by annotation method (expert, clinician, AI-assisted, AI inference) |
These define constraints on FHIR resources for systems conforming to this implementation guide.
| AI Prediction |
AI model prediction for dermatology image classification. Represents machine output before clinician review. Status is always preliminary until a clinician acts on it. |
| Annotation Series |
Groups dermatology annotations for the same lesion over time. Enables longitudinal tracking and change detection. |
| Dermatology Image Annotation |
Structured annotation result from clinical dermatology photography. Produced by expert annotators, clinicians, or AI-assisted workflows. |
These define sets of codes used by systems conforming to this implementation guide.
| AI Prediction Status |
Allowed status values for AI predictions. Never final — AI output requires human review. |
| Annotation Methods |
Methods by which dermatology annotations are produced. Required binding — implementations must use these codes. |
| Body Sites - Skin |
SNOMED CT body site codes relevant to dermatology. Extensible — implementations may add any SNOMED CT body structure code. |
| Change Type Values |
Types of changes detected between temporal annotations |
| Dermatology Annotation Status |
Allowed status values for dermatology image annotations |
| Dermatology Findings |
SNOMED CT codes for common dermatology findings. Extensible — implementations may add any SNOMED CT code from the Skin finding hierarchy (106076001). |
| QA Review Status Values |
Allowed values for QA review status |
These define new code systems used by systems conforming to this implementation guide.
| Annotation Method |
Method by which a dermatology annotation was produced. Aligns with HL7 AI Transparency on FHIR by distinguishing human, AI-assisted, and pure AI annotation. |
| Annotation Type |
Types of dermatology image annotation and component codes for annotation Observation profiles |
| Change Type |
Types of changes detected between temporal annotation observations |
| QA Review Status |
Quality assurance review status for annotation results |
These define transformations to convert between codes by systems conforming with this implementation guide.
| ISIC Diagnostic Categories to SNOMED CT |
Maps International Skin Imaging Collaboration (ISIC) diagnostic categories to SNOMED CT codes used in this IG. |
These are example instances that show what data produced and consumed by systems conforming with this implementation guide might look like.