ModelRefs / Radiology Report Drafting — Canonical Workflow
Radiology Report Drafting — Canonical Workflow
Radiology Report Drafting: provisional AI workflow implementation reference with candidate models, providers, tools, and architecture.
Overview
Draft radiology reports from image-derived findings with structured templates and radiologist sign-off. Radiology Report Drafting is a provisional implementation reference with candidate models, providers, tools, benchmarks and deployment patterns to validate on the target workload. Healthcare deployment requires organization- and jurisdiction-specific review of privacy, security, access, retention, and applicable regulatory obligations. Outputs remain provisional and require qualified human review; no clinical autonomy or compliance claim is implied. Validate PHI flows, source traceability, model and prompt versions, reviewer actions, rollback, and incident handling before clinical use.
Implementation profile
| Category | multimodal-models |
|---|---|
| Implementation maturity | enterprise |
| Primary use cases | summarization, extraction |
| Deployment options | managed-api, hybrid |
| Architectures | serverless-api, managed-container, hybrid-private-cloud |
What this evidence does not establish
- No representative institution, modality, anatomy, rare-finding, or contradictory-case evaluation set is registered.
- No measured critical-omission threshold, clinician agreement, correction burden, or deployment-specific PHI flow is attached.
Candidate models with published references
- BGE-M3
- GPT-5
- GPT-5 Mini
- Claude Sonnet 4.5
- Claude Opus 4
- Gemini 3 Pro
- Llama 4 Scout
- DeepSeek R1
- Mistral Large 2
- Command R+
- o3
- o4 Mini
Coverage means the model is a candidate worth evaluating for this workflow, not a ranking or a recommendation. Models whose reference pages are still in review are omitted.
Benchmarks relevant to this workflow
- GPQA Diamond — Graduate-level Google-Proof Q&A in physics, chemistry, and biology.
- MMLU-Pro — Harder MMLU successor with 10-option questions and reduced contamination.
- MMLU — Massive Multitask Language Understanding — 57 academic and professional subjects.
These are the benchmarks whose task shape bears on this workflow. Each one only describes its own protocol and date, so confirm the harness matches your workload before treating a score as evidence.
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Radiology Report Drafting — Canonical Workflow.