MedPAO-Assist enables Edge-Deployable radiology report structuring
medpao-assist is an agentic framework designed to generate structured radiology reports directly from dictation and voice commands. It supports four major imaging modalities – chest x‑ray, chest ct, abdomen ct, and brain mri – and is built around a small language model in the 0.6B‑parameter range.
Key points
- supports chest x‑ray, chest ct, abdomen ct, and brain mri using a 0.6B‑parameter small language model
- uses extract‑ground‑generate agents and speech‑driven human‑in‑the‑loop correction for a no‑touch reporting workflow
the architecture follows an extract‑ground‑generate paradigm, performing concept extraction, SNOMED‑CT grounding, and structured report generation before a speech‑driven human‑in‑the‑loop correction phase. This creates a fully “no‑touch” workflow that requires no keyboard input, external API calls, or internet connectivity. Individual pipeline stages were evaluated for concept extraction, ontology grounding, and categorization, and hardware profiling confirms feasibility for real‑time, CPU‑only clinical deployment.
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Agents & Tools
All →- TTEC Digital launches GovEx AI Agent Suite with 40+ prebuilt agents on Google Cloud Gemini · 1 src
- Cisco report says small businesses struggle to monitor AI agents and control costs · 1 src
- Hermes Desktop lets users build custom bots like OpenAI’s dots · 1 src
- Visa, BILL and Billtrust launch AI-driven payments pilot for businesses · 1 src
- Simon Willison releases Battle Drones, an audio‑multiplayer RTS built with Claude · 1 src
Comments
via GitHub Discussions