Radiological.ai
How it works
Radiology AI platform AI radiology assistant AI for radiologists Teleradiology software AI chest X-ray AI CT scan analysis Structured reporting Worklist prioritization See all →
Aidoc alternative Rad AI alternative Annalise.ai alternative Nuance PowerScribe alternative Qure.ai alternative Viz.ai alternative Nuance DAX alternative Lunit alternative Gleamer alternative
Pricing Blog

By modality · AI pulmonary embolism detection

AI pulmonary embolism detection that flags suspected PE on CTPA and routine chest CT

The short answer

AI pulmonary embolism detection is software that reviews a contrast-enhanced chest CT as it arrives, flags studies that appear to show a filling defect in the pulmonary arteries, and moves them up the reading worklist. Two jobs matter to a radiology group: dedicated CTPA ordered for suspected PE, where the value is speed, and incidental PE on a routine contrast CT ordered for something else, where the value is that a small segmental clot on a staging scan gets a second look. Radiological.ai works as decision support. It flags and prioritizes, publishes no accuracy figures and claims no regulatory status, and the radiologist reviews every study and signs the report.

Pulmonary embolism is the finding that punishes a busy list twice. On a dedicated CTPA the clock is running, and the study needs to be opened before the eleven routine follow-ups that landed ahead of it. On a routine contrast chest or abdominal CT ordered for staging or abdominal pain, nobody is looking for PE at all, and a small segmental clot sits in a scan that gets read for a different question entirely.

Radiological.ai works on both halves of that problem. As each contrast-enhanced chest study arrives from the scanner, the assistant reviews the pulmonary arteries, flags the ones that look like a suspected embolus, and pushes those studies toward the top of the queue so the urgent one is the next one opened. On routine studies it does the same quietly, marking the series for a closer look rather than reordering the whole list. It then drafts the structured report in your template, with the vascular section already populated for you to edit.

What it does not do is call the study positive. It flags nothing as a confirmed embolism, publishes no accuracy figures and claims no regulatory status. The radiologist opens the study, interprets it, overrides any priority that is wrong, and signs.

Last updated July 2026

The Reading Station

Worklist

SERIES 1 · AX
SLICE 24/64
SAMPLE STUDY
NOT FOR DIAGNOSTIC USE
W 80 · L 40
ILLUSTRATIVE SAMPLE

Structured report

Draft

Run the assistant to draft this report for review.

You review & sign

Illustrative sample · not a real patient study, not a diagnosis

Drafted in · you review & sign Worklist re-prioritized

Decision support for qualified clinicians. Radiological.ai does not provide a diagnosis and is not a substitute for professional judgment.

Run the assistant

Flag · prioritize · draft · you review and sign

X-RAY CT MRI BUILT WITH RADIOLOGISTS

Decision support not a diagnosis

You review & sign

Why it works

What your group gets with AI pulmonary embolism detection

CTPA read sooner, not later

A dedicated CT pulmonary angiogram that looks like a suspected embolus is surfaced for review and moved up the worklist, so it is not waiting behind routine follow-up imaging. The flag is a prompt to look now, never a finding and never a diagnosis.

Incidental PE on the scan nobody ordered for it

Routine contrast chest and upper abdominal CT gets the same pass. When the pulmonary arteries on a staging or abdominal study look suspicious, the assistant marks the series so the finding is seen on a scan that was ordered for a completely different question.

The vascular section already drafted

Once you open the study, the structured report is drafted in your own template with the pulmonary vascular section populated, including the descriptive language your group uses for clot burden and right heart size. You edit every line and you sign.

What it handles

Flagged, prioritized and drafted for your review

The assistant pre-reads each study, surfaces a region of interest for review, re-prioritizes the worklist, and drafts the structured report in your template. You confirm, edit and sign.

  • Flags suspected pulmonary embolism on CTPA for review
  • Reviews routine contrast chest and upper abdominal CT for incidental PE
  • Moves suspected-positive studies toward the top of the worklist
  • Drafts the structured report with the vascular section populated
  • Works inside your existing PACS, worklist and RIS over DICOM and HL7 or FHIR
  • Radiologist reviews every study, overrides any priority and signs
AI PULMONARY EMBOLISM DETECTION STAT

Region of interest flagged for review

A focal region is surfaced on the sample study for the radiologist to review. The assistant does not characterize it as a diagnosis.

Draft impression

Suspected finding flagged for radiologist review. Correlate clinically and confirm. Draft for review and sign-off.

Illustrative sample · not for diagnostic use You review & sign

Why Radiological.ai

One assistant across the whole read

Not three vendors stitched together. Flag, prioritize and draft in one calm pane, on X-ray, CT and MRI, with the radiologist signing every study.

Flags suspected findings

A second set of eyes surfaces regions of interest for review on every study, so a suspected finding is less likely to slip past late in a shift.

Prioritizes the worklist

Suspected-critical studies move to the top, so urgent reads surface ahead of routine follow-ups across your sites and shifts.

Drafts the report

A structured draft arrives in your template, ready to edit and sign. The draft saves the typing and the measuring, never the judgment.

Good questions

Questions about AI pulmonary embolism detection

It is software that reviews a contrast-enhanced chest CT as it arrives and flags studies that appear to show a filling defect in the pulmonary arteries, moving those studies up the reading worklist. It changes the reading order and prompts a closer look. It does not interpret the study. Radiological.ai flags and prioritizes as decision support, and the radiologist reads and signs every case.
Suspected emboli can be flagged on any contrast-enhanced study where the pulmonary arteries are opacified, which in practice means routine contrast chest CT and many upper abdominal studies as well as dedicated CTPA. Coverage is best on dedicated angiograms, because that is what the protocol is timed for. On routine studies the assistant marks the series for review rather than reordering your worklist.
Published external validations of commercial PE algorithms report a wide range of results depending on the study population, the protocol and whether emboli are central or subsegmental, and reviewers consistently find cases the software misses. We publish no accuracy figures for Radiological.ai and make no regulatory-status claims. Run it on your own studies in shadow mode and measure it against your own signed reports before it changes anything live.
No. It changes which study is opened next and what is drafted before you open it. The interpretation, the clot burden call, the right heart assessment and the report all stay with the radiologist, who can override any priority and edits and signs every draft. A missing flag means nothing on its own and should never make an unflagged study feel safer.
Studies reach the assistant from your PACS over standard DICOM, and the priority signal returns to your worklist and RIS over HL7 or FHIR. Where you run a PE response team, that priority can start the notification earlier, but the confirming read and the clinical decision stay with your clinicians exactly as they do today.
Because nobody is looking for it. A staging chest CT is read for the tumor, the search pattern follows the clinical question, and a small segmental filling defect in a peripheral vessel sits outside where attention is going. Volume and shift length make it worse. A second pass that only looks at the pulmonary arteries catches what a question-directed search is not aimed at.
The study is never hidden, relabeled or marked positive. It moves position in the worklist and carries a flag you can open or dismiss, and the images themselves are untouched. Radiologists keep the same viewer, the same worklist and the same reporting tool, with no second login and no extra monitor to watch.
Vendors price this three ways: per study, per radiologist per month, or as a platform fee with the finding modules bundled. A single-finding PE module usually looks cheap per study and stops being cheap once you add the second and third finding you actually wanted. Radiological.ai is priced per radiologist, with flagging, worklist prioritization and report drafting included rather than sold as separate modules, so the number does not move when your case mix does. Our pricing page lists the current figures.
The work is integration work, not model work. You need a DICOM route from PACS, a return path into the worklist over HL7 or FHIR, and a shadow period where the assistant runs on live studies without changing what anyone sees. Most groups spend the first few weeks comparing flags against signed reports, then turn on worklist reordering for one study type before extending it.
Read every AI radiology question

Explore more

More ways teams read with Radiological.ai

AI chest X-ray

A second set of flags on high-volume chest films, drafted and ready.

Learn more

AI CT scan analysis

Triage and draft on CT, where minutes matter most.

Learn more

AI MRI analysis

Support across long MRI reads and the reports they generate.

Learn more
See every radiology use case See radiology AI pricing Back to the AI radiology assistant

From the blog: best AI radiology software in 2026, how much radiology AI costs, how to implement AI in a radiology workflow, and AI radiology companies.

Read more studies, with the assistant alongside you

Flag suspected findings, prioritize the worklist, and draft the structured report. You review and sign every study.

See pricing

Radiological.ai is a workflow and decision-support tool for qualified clinicians. It does not provide a diagnosis and is not a substitute for professional medical judgment.