ScanQueue
An AI radiology worklist that flags suspected critical findings on incoming CT, MR and X-ray studies and orders every read by acuity and SLA — so the sickest patient is read first, not FIFO.
// The priority worklist — queue-depth over the shift, critical-flag KPIs, and an acuity-ordered table where the sickest patient is read first, not FIFO.
Overview
ScanQueue gives a reading room an acuity-first worklist instead of a first-in-first-out queue. As imaging studies arrive, the AI reads each one, flags suspected critical findings — intracranial hemorrhage, pulmonary embolism, large-vessel occlusion, pneumothorax — for a STAT read, and re-orders every radiologist's list by acuity and SLA. BuildspaceLabs designed and built the MVP front end: a dark reading-room worklist for shift-wide triage and a per-study detail view with an AI findings panel, a region-of-interest overlay, a priors comparison and a structured report draft — turning a raw stream of studies into a queue a radiologist can trust, with the physician in the loop on every read.
Highlights
- Reads the sickest patient first — critical findings jump the queue instead of waiting behind routine films
- Every study carries an acuity rank and a live SLA countdown, so nothing quietly breaches
- Radiologist-in-the-loop: the AI orders the list, the physician reads and signs every study
- One reading-room view of queue depth, critical findings and turnaround for the whole shift
Gallery
Outcomes
- Delivered a production-quality MVP of the priority worklist and study detail view in a 10-week engagement
- Cut average report turnaround by moving from first-in-first-out to acuity-and-SLA ordering
- Consolidated detection, prioritization and reporting into a single reading-room surface
- Established a reusable dark reading-room design system (acuity pills, SLA countdowns, ROI overlays) for the product's next screens
Tech Stack
Chosen per constraint, not per habit — the stack shifts with the problem.
Features
- Priority worklist ordered by AI acuity and SLA, with live queue-depth, critical-flag and turnaround KPIs
- Critical-finding detection for CT, MR and X-ray, each flag carrying a confidence score
- Live SLA countdown per study so emergent reads never quietly breach their window
- Study detail with an AI findings panel — suspected finding, confidence and severity
- Region-of-interest overlay and auto-registered priors comparison flagging interval change
- Structured report draft with a recommended next action — the radiologist edits and signs
See ScanQueue as its own site.
Beyond the build, we designed and shipped ScanQueue a standalone landing page — its own look, copy and motion. Here's a live preview; scroll inside it, or open it full-screen.
// next
Building something in this space?
A 30-minute call is enough for us to understand your situation and tell you whether we're the right team. Usable version in the first two weeks if we are.