Orthovision AI FHIR Implementation Guide
0.2.0 - ci-build

Orthovision AI FHIR Implementation Guide - Local Development build (v0.2.0) built by the FHIR (HL7® FHIR® Standard) Build Tools. See the Directory of published versions

Artifacts Summary

This page provides a list of the FHIR artifacts defined as part of this implementation guide.

Behavior: Capability Statements

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.

Orthovision AI Service Capability Statement

Describes the base capabilities that all implementations of the Orthovision AI classification service must support. Implementers should create their own CapabilityStatement instances that extend this base with their specific supported DICOM tags using the supported-dicom-tags extension.

Structures: Resource Profiles

These define constraints on FHIR resources for systems conforming to this implementation guide.

Orthovision AI Binary

This profile enforces non empty Binaries.

Orthovision AI Bundle

A Bundle containing all resources needed for AI image processing: Binary with image data, optional ImagingStudy for context, and Task for processing request.

Orthovision AI Model

This profile represents an AI model used by the Orthovision service for DICOM image classification.

Orthovision AI Task

This profile represents a task for the Orthovision AI service to infer proper DICOM tags.

OrthovisionAI Observation

This profile represents an observation capturing the AI-predicted value for a specific DICOM tag.

Structures: Extension Definitions

These define constraints on FHIR data types for systems conforming to this implementation guide.

AI Confidence Score

Confidence score for AI prediction (0.0-1.0)

Performer Device Extension

Extension to reference a Device that performed the task. This extension addresses the gap in FHIR R4 and R5 specifications for tracking which specific AI system performed a task, providing forward compatibility with FHIR R6 native device performer support.

Supported DICOM Tags

Extension to declare which DICOM tags this server can classify using AI. Supports DICOM tag numbers (e.g., '0008,0060'), DICOM keywords (e.g., 'Modality'), or custom identifiers.

Example: Example Instances

These are example instances that show what data produced and consumed by systems conforming with this implementation guide might look like.

Example: AI Service Implementation Capability Statement

Example showing how an implementer would declare their supported DICOM tags using the supported-dicom-tags extension