Softwr

Healthcare · head to head

Lunit vs Rad AI

Lunit logo

Lunit

Healthcare

FDA cleared and CE marked AI for mammography, tomosynthesis and chest radiography

From
On request
Rated
-
Full reviewWebsite
Rad AI logo

Rad AI

Healthcare

Generative reporting and follow-up tracking for radiology, positioned outside the diagnostic device boundary

From
On request
Rated
-
Full reviewWebsite

The short version

  • Each has a real cost: Lunit the regulatory permission differs by product and by region, and INSIGHT Risk has been filed with the FDA but not cleared, so a buyer who reads a corporate press release rather than the specific clearance for their product and jurisdiction will plan a deployment they cannot legally run.; Rad AI the products are not FDA cleared devices and are not intended to be, so any claim that Rad AI improves diagnostic accuracy is unsupported; what has been measured is reporting speed and follow-up completion, not detection.
  • They diverge on capability: Lunit covers Lunit INSIGHT MMG, Rad AI covers Impressions.
  • Prices and features above were last checked on 1 September 2026.

Where they differ

Only the attributes on which Lunit and Rad AI actually diverge.

Attributes where Lunit and Rad AI differ
AttributeLunitRad AI
PlatformsWebWindows, Web, Cloud

Identical on both: starting price (On request), pricing model (quote), free tier (No), user rating (Not yet rated), category (Healthcare).

What each one covers

Drawn from each product's published feature list. An absence here means we hold no record of it - not that the product lacks it.

Only in Lunit

  • Lunit INSIGHT MMG
  • Lunit INSIGHT DBT
  • Lunit INSIGHT CXR
  • Volpara density assessment
  • Volpara RiskPathways
  • Volpara dose tracking
  • PACS and mammography workstation integration

Only in Rad AI

  • Impressions
  • Reporting
  • Continuity
  • Style learning
  • Omni Reconcile
  • PACS and dictation embedding
  • Patient outreach workflows
  • Audit reporting

What people use each for

The jobs each tool is most often brought in to do.

Lunit

  • A national breast screening programme evaluating AI as a second reader to reduce double reading workload where two human readers are currently mandatednot Rad AI
  • A breast centre that moved to tomosynthesis and now has reading times it cannot staff, wanting detection support on DBT specificallynot Rad AI
  • An American breast imaging centre needing automated volumetric density assessment to meet patient density notification requirements, which is what Volpara is bought fornot Rad AI
  • A tuberculosis or lung screening programme in a high volume, radiologist scarce setting using chest radiography triage to prioritise filmsnot Rad AI

Rad AI

  • A private radiology practice whose read volume has grown faster than it can recruit and that wants dictation time per study reduced without changing PACSnot Lunit
  • A health system losing revenue and exposing itself to liability because recommended follow-up imaging on incidental findings is never bookednot Lunit
  • A radiology department standardising impression quality across a mixed group of employed and locum radiologistsnot Lunit
  • A group deploying an AI tool that must not trigger a device validation programme, because governance capacity is already consumed by a triage algorithm rolloutnot Lunit

Where each one falls short

Documented limitations, not opinions. Every one is a constraint you would hit in normal use.

Lunit

  • The regulatory permission differs by product and by region, and INSIGHT Risk has been filed with the FDA but not cleared, so a buyer who reads a corporate press release rather than the specific clearance for their product and jurisdiction will plan a deployment they cannot legally run.
  • Detection AI changes recall rates in screening, and the downstream cost of additional diagnostic workup lands on the programme rather than on the software budget, which is the cost most screening business cases omit.
  • Performance is sensitive to the mammography vendor and acquisition protocol, so published results from a Hologic estate do not transfer to a GE or Siemens estate without local validation the buyer must fund.
  • MMG, DBT and CXR are licensed separately and Volpara modules are separate again, so a breast centre wanting detection, density and risk pathways is assembling four line items rather than buying one product.
  • Using AI as a replacement for one of two human readers is a workforce and liability decision that regulators and professional bodies treat differently in each country, so the saving that justifies the purchase may not be permitted where you operate.

Rad AI

  • The products are not FDA cleared devices and are not intended to be, so any claim that Rad AI improves diagnostic accuracy is unsupported; what has been measured is reporting speed and follow-up completion, not detection.
  • Generated impressions require radiologist review and signature, so the time saving evaporates in any group whose radiologists rewrite the draft rather than edit it, and adoption varies sharply by individual.
  • It is bound to your dictation platform, so a group planning to move off PowerScribe should sequence that decision first or expect to redo the Rad AI integration.
  • Continuity depends on the quality of recommendation language in historical reports, and departments with inconsistent phrasing get poor recall until reporting practice is standardised.
  • Pricing is not published and is structured per radiologist or per study depending on the product mix, which makes it hard to compare against image-analysis AI vendors that price per scan.

Pricing, plan by plan

Lunit

On request
  • Lunit INSIGHT$undefined/year
    • Priced per study or per annual examination volume by product
    • MMG, DBT and CXR licensed separately
    • Volpara density and RiskPathways modules quoted separately

Rad AI

On request
  • Rad AI platform$undefined/year
    • Priced per radiologist or per study volume depending on product and contract
    • Impressions, Reporting and Continuity licensed separately
    • Annual subscription with implementation and integration scoped per site

Which should you pick?

Choose Lunit if

  • You need lunit insight mmg.
  • You also want lunit insight dbt.
Lunit review

Choose Rad AI if

  • You need impressions.
  • You work on Windows, Web, Cloud.
  • You also want reporting.
Rad AI review

Questions people ask

Is Lunit or Rad AI better?
Neither clearly leads. Lunit starts at On request and Rad AI at On request, and user ratings are close enough to be indistinguishable. Choose on capability and platform support.
Which is cheaper, Lunit or Rad AI?
Lunit starts at On request and Rad AI at On request.
Does Lunit or Rad AI run on more platforms?
Lunit runs on Web. Rad AI runs on Windows, Web, Cloud.
What is Lunit best used for?
Lunit is most often used for a national breast screening programme evaluating ai as a second reader to reduce double reading workload where two human readers are currently mandated, a breast centre that moved to tomosynthesis and now has reading times it cannot staff, wanting detection support on dbt specifically, an american breast imaging centre needing automated volumetric density assessment to meet patient density notification requirements, which is what volpara is bought for, a tuberculosis or lung screening programme in a high volume, radiologist scarce setting using chest radiography triage to prioritise films. Of those, a national breast screening programme evaluating ai as a second reader to reduce double reading workload where two human readers are currently mandated and a breast centre that moved to tomosynthesis and now has reading times it cannot staff, wanting detection support on dbt specifically are not what Rad AI is typically brought in for.
What can Lunit do that Rad AI cannot?
Lunit covers Lunit INSIGHT MMG, Lunit INSIGHT DBT, Lunit INSIGHT CXR, Volpara density assessment. Rad AI covers Impressions, Reporting, Continuity, Style learning.

Answered from the vendors’ own pages

Lunit: Is Lunit FDA cleared?

Yes for specific products. INSIGHT MMG, INSIGHT DBT and INSIGHT CXR Triage hold FDA 510(k) clearances. INSIGHT Risk, the five year risk prediction model, has been filed but was not cleared at the time of writing.

Rad AI: Is Rad AI FDA cleared?

No, and by design. The products draft text and manage follow-up workflow rather than interpreting images, so they fall outside the device pathway. Treat any diagnostic accuracy claim with scepticism.

Lunit: Can Lunit replace a second human reader in screening?

That depends entirely on your jurisdiction and professional body guidance, not on the software. The CE mark permits clinical use; it does not authorise a workforce model.

Rad AI: Does the radiologist still sign the report?

Yes. Output is a draft that the radiologist reviews and signs; nothing is released autonomously.

Lunit: What did the Volpara acquisition add?

Volumetric breast density measurement, dose tracking and RiskPathways high risk programme management, which are the things American breast centres buy for density notification compliance rather than for detection.

Rad AI: Which product actually pays for itself?

Continuity has the clearest financial case, because recommended follow-up imaging that gets completed is billable work that currently does not happen.

Lunit: Is pricing published?

No. It is quoted per study or per annual volume, by product, with on premises and cloud priced differently.

Rad AI: Will it work with our dictation system?

It is deepest with Nuance PowerScribe. Confirm your specific dictation and PACS combination before contracting, because integration depth is the main deployment variable.

Share

Related pages

More on Lunit

More on Rad AI

Keep looking

Other head to heads