Platform · Radiology AI
An independent second reader for every study
The radiologist reads first. The AI analyses the same study on its own and, if it finds something suspicious or disagrees, presents its reasoning. The radiologist accepts or overrides.
In the reading room
Second-reader output, inside a familiar workflow
Flags appear alongside the worklist and viewer the radiologist already uses, after their read is recorded.
Radiologist read
Initial impression recorded by the reading physician.
Second reader flag
Possible finding not referenced in the initial read
The radiologist makes the final decision.
Illustrative example — not real patient data.
Capabilities
Designed to be checked, not trusted blindly
Read-first by design
AI output stays hidden until the radiologist has recorded their own impression, protecting independent judgement.
Localised flags
Each flag points to a specific region with a bounding box, so attention goes exactly where it is needed.
Heat regions
Attention overlays show which areas influenced the analysis, and can be toggled on or off at any time.
Measurements to verify
Measurement annotations are presented for the reader to check against their own, never as final values.
Plain-language reasoning
A short explanation of what prompted the flag, written for clinicians rather than data scientists.
Accept or override
One-step decisions. Overrides capture a brief rationale that feeds quality review and model monitoring.
Agree / disagree
Every flag comes with its evidence
Try the overlay toggles and decision buttons in the panel. In practice, each decision and its rationale is written to the audit trail.
Second reader flag
Possible finding not referenced in the initial read
- • Localised change in Region A (upper right)
- • Pattern differs from surrounding tissue
- • Reasoning and overlays attached for review
The radiologist makes the final decision.
Read comparison
DisagreementRadiologist
No focal finding recorded in Region A.
Second reader
Localised change suggested in Region A.
Reasoning
- 1. Texture in the boxed region differs from the surrounding area.
- 2. The heat region shows where the model focused its attention.
- 3. Measured extent is shown for the reader to verify.
Awaiting the radiologist's decision.
Illustrative example — not real patient data.
Governance
A complete record for clinical oversight
Reads, flags, decisions and rationales are captured in sequence, giving clinical leads what they need for audit, peer review and continuous improvement.
Discrepancy review
Filter for overridden or accepted flags to support peer-review meetings.
Model monitoring
Override patterns help surface where the second reader adds value and where it does not.
Role-based access
Access to studies, decisions and logs follows your lab's own roles and policies.
Study received
09:02 · System
Routed from PACS to the reading worklist
Radiologist read submitted
09:15 · Radiologist
Initial impression recorded before any AI output was shown
Second reader analysis completed
09:15 · Second reader
Independent analysis of the same study
Disagreement flagged
09:16 · Second reader
Reasoning, overlays and region references attached
Radiologist decision
09:21 · Radiologist
Flag reviewed; decision and written rationale captured
Report signed
09:24 · Radiologist
Final report signed by the radiologist
Each record is append-only and attributable.
Illustrative example — not real patient data.
FAQ
Questions radiologists ask us
Does the AI make the final call on a study?
No. The second reader provides decision support only. The radiologist reviews every flag and makes every decision, and only the radiologist can sign the report.
Why does the radiologist read first?
Showing AI output before a clinician forms their own view can anchor their judgement. Reading first keeps the two analyses independent, so a disagreement is meaningful.
What happens when the radiologist overrides a flag?
The override and a short rationale are recorded in the audit trail. Over time these records support quality review and help the lab and our team understand where the model is and isn't helpful.
Which modalities and study types are supported?
Scope depends on the deployment and the applicable regulatory status in your region. We'll walk through what is available for your lab during a demo rather than make general claims here.
Learn more
The science of the second look
How imaging works, how experts search a study, and why a second reader helps — with citations.
See the second reader in a live walkthrough
Book a walkthrough with our team. We'll show how doctor-in-the-loop decision support fits alongside your existing systems, and answer your clinical, technical and governance questions.