Healthcare · head to head
Annalise.ai vs Therapixel

Annalise.ai
Healthcare
Multi-finding chest X-ray and head CT triage AI with FDA clearance on named findings, not on the whole model
- From
- On request
- Rated
- -
Therapixel
Healthcare
French mammography AI with FDA clearances for 2D and tomosynthesis breast screening
- From
- On request
- Rated
- -
The short version
- Each has a real cost: Annalise.ai the United States cleared indication covers roughly ten findings for triage and notification, far fewer than the model reports, so a buyer who evaluates the full multi-finding output and then contracts in the United States gets a much narrower cleared use.; Therapixel european and American regulatory positions were established under different regimes, and under the EU Medical Device Regulation this class of diagnostic AI faces a higher classification and notified body scrutiny, so European buyers must verify the current MDR certificate and expiry rather than relying on a legacy CE reference.
- They diverge on capability: Annalise.ai covers Annalise Enterprise CXR, Therapixel covers MammoScreen 2D.
- Prices and features above were last checked on 1 September 2026.
Where they differ
Only the attributes on which Annalise.ai and Therapixel actually diverge.
| Attribute | Annalise.ai | Therapixel |
|---|---|---|
| Platforms | Web, Cloud, On-premise | Web |
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 Annalise.ai
- Annalise Enterprise CXR
- Annalise Enterprise CTB
- Triage and notification
- Worklist reprioritisation
- Localisation overlays
- Confidence output
- PACS-native deployment
- On-premise or cloud inference
Only in Therapixel
- MammoScreen 2D
- MammoScreen DBT
- One to ten suspicion score
- Summary report
- Workstation and PACS delivery
- Reading workflow configurations
What people use each for
The jobs each tool is most often brought in to do.
Annalise.ai
- An emergency department wanting pneumothorax and intracranial haemorrhage pushed to the front of the reading queue overnight when cover is thinnestnot Therapixel
- A teleradiology provider covering many small hospitals that needs consistent triage before a human readsnot Therapixel
- A screening programme in Europe where the broader CE marked decision support indication, rather than the narrow United States triage clearance, is what is being deployednot Therapixel
- A radiology department building an AI governance programme that wants one vendor covering both chest radiograph and head CT rather than contracting two separate algorithm suppliersnot Therapixel
Therapixel
- A European breast screening programme running mandatory double reading that wants to evaluate AI as a concurrent or second reader within what national guidance permitsnot Annalise.ai
- An American breast centre that has moved to tomosynthesis and needs reading support on DBT specifically, which Therapixel holds a clearance fornot Annalise.ai
- A screening service wanting a graded suspicion score rather than a binary flag so readers can calibrate their own thresholdnot Annalise.ai
- A radiology group evaluating multiple mammography AI vendors head to head on their own historic case set before committingnot Annalise.ai
Where each one falls short
Documented limitations, not opinions. Every one is a constraint you would hit in normal use.
Annalise.ai
- The United States cleared indication covers roughly ten findings for triage and notification, far fewer than the model reports, so a buyer who evaluates the full multi-finding output and then contracts in the United States gets a much narrower cleared use.
- Triage AI reprioritises a worklist but does not change clinical decisions on its own, so departments that do not redesign how urgent studies are picked up see no measurable improvement in time to treatment.
- Published validation is largely reader study evidence on detection of individual findings; prospective evidence of shorter time to treatment in routine emergency care is thin.
- The Annalise brand is being migrated under the Harrison.ai name for the critical care offering, which creates ambiguity in multi-year contracts about what product name is actually being supported.
- A high finding count raises the alert burden, and departments report that low prevalence findings generate false positives that erode radiologist trust unless the alerting thresholds are tuned locally.
Therapixel
- European and American regulatory positions were established under different regimes, and under the EU Medical Device Regulation this class of diagnostic AI faces a higher classification and notified body scrutiny, so European buyers must verify the current MDR certificate and expiry rather than relying on a legacy CE reference.
- MammoScreen does mammography only, so a hospital wanting AI across head CT, chest and breast needs several vendors and several PACS integrations, or an orchestration layer bought from someone else.
- Therapixel is a small French company competing against Hologic and iCAD, which have incumbency inside the mammography reading workstation, so integration into an American breast centre is more work than it is for the workstation vendor own AI.
- Detection performance is sensitive to the mammography unit vendor and acquisition protocol, so published results do not transfer between estates and each site needs local validation it must fund itself.
- Whether AI can substitute for one of two human readers is a national workforce and liability question, not a product capability, so the labour saving that justifies the purchase in one country is not permitted in another.
Pricing, plan by plan
Annalise.ai
On request- Annalise Enterprise$undefined/year
- Priced per study analysed or as an annual volume subscription
- CXR and CTB licensed separately
- Cleared finding set differs by market, which changes what you are buying
Therapixel
On request- MammoScreen$undefined/year
- Priced per examination or by annual screening volume
- 2D and tomosynthesis licensed by the versions cleared for each
- Cloud or on premises deployment quoted differently
Which should you pick?
Choose Annalise.ai if
- You need annalise enterprise cxr.
- You work on Web, Cloud, On-premise.
- You also want annalise enterprise ctb.
Questions people ask
- Is Annalise.ai or Therapixel better?
- Neither clearly leads. Annalise.ai starts at On request and Therapixel at On request, and user ratings are close enough to be indistinguishable. Choose on capability and platform support.
- Which is cheaper, Annalise.ai or Therapixel?
- Annalise.ai starts at On request and Therapixel at On request.
- Does Annalise.ai or Therapixel run on more platforms?
- Annalise.ai runs on Web, Cloud, On-premise. Therapixel runs on Web.
- What is Annalise.ai best used for?
- Annalise.ai is most often used for an emergency department wanting pneumothorax and intracranial haemorrhage pushed to the front of the reading queue overnight when cover is thinnest, a teleradiology provider covering many small hospitals that needs consistent triage before a human reads, a screening programme in europe where the broader ce marked decision support indication, rather than the narrow united states triage clearance, is what is being deployed, a radiology department building an ai governance programme that wants one vendor covering both chest radiograph and head ct rather than contracting two separate algorithm suppliers. Of those, an emergency department wanting pneumothorax and intracranial haemorrhage pushed to the front of the reading queue overnight when cover is thinnest and a teleradiology provider covering many small hospitals that needs consistent triage before a human reads are not what Therapixel is typically brought in for.
- What can Annalise.ai do that Therapixel cannot?
- Annalise.ai covers Annalise Enterprise CXR, Annalise Enterprise CTB, Triage and notification, Worklist reprioritisation. Therapixel covers MammoScreen 2D, MammoScreen DBT, One to ten suspicion score, Summary report.
Answered from the vendors’ own pages
Annalise.ai: How many findings are FDA cleared?
Around ten across chest X-ray and head CT, for triage and notification only. The model reports far more findings than that; the rest are not cleared in the United States.
Therapixel: Is MammoScreen FDA cleared?
Yes. It holds 510(k) clearance K192854 for two dimensional mammography from July 2020, a November 2021 clearance for digital breast tomosynthesis, and two further clearances in October 2024 for later versions.
Annalise.ai: Is the European position different?
Yes. CE marking under the medical device regulation covers a broader decision support indication than the United States triage and notification clearances, so the same software is a different regulatory product depending on where you deploy it.
Therapixel: Is it CE marked?
Yes, but European buyers should ask specifically for the current certificate under the Medical Device Regulation and its expiry date, because this class of diagnostic AI moved to a higher classification under MDR.
Annalise.ai: Does it diagnose?
No. In the United States it is a triage and notification device: it flags studies for earlier review, and the radiologist makes the diagnosis.
Therapixel: What does the one to ten score mean?
It is a graded suspicion score per finding and per study, designed to be integrated alongside a radiologist BI-RADS assessment rather than treated as a positive or negative result.
Annalise.ai: Is Annalise.ai becoming Harrison.ai?
The critical care offering is now marketed under the Harrison.ai name. Ask the vendor to name the contracted product explicitly before signing a multi-year deal.
Therapixel: Does it cover anything besides mammography?
No. It is a mammography product only, including tomosynthesis. Other body regions need a different vendor.
Related pages
More on Annalise.ai
Other head to heads
- Annalise.ai vs Gleamer
- Annalise.ai vs Rad AI
- Annalise.ai vs Sectra
- Annalise.ai vs Aidoc
- Annalise.ai vs Ibex Medical Analytics
- Annalise.ai vs Paige
- Annalise.ai vs Philips IntelliSpace PACS
- Annalise.ai vs Fujifilm Synapse
- Annalise.ai vs Visage Imaging
- Annalise.ai vs Lunit
- Annalise.ai vs Techcyte
- Annalise.ai vs PathAI
- Annalise.ai vs Epocrates
- Annalise.ai vs Figure 1
- Annalise.ai vs Fullscript
- Annalise.ai vs GNU Health
- Annalise.ai vs GoodRx
- Annalise.ai vs Halaxy
- Annalise.ai vs Clue
- Annalise.ai vs Rx30
- Annalise.ai vs Quantum Health
- Annalise.ai vs Sysmex
- Therapixel vs Gleamer
- Therapixel vs Rad AI
- Therapixel vs Sectra
- Therapixel vs Aidoc
- Therapixel vs Ibex Medical Analytics
- Therapixel vs Paige
- Therapixel vs Philips IntelliSpace PACS
- Therapixel vs Fujifilm Synapse
- Therapixel vs Visage Imaging
- Therapixel vs Lunit
- Therapixel vs Techcyte
- Therapixel vs PathAI
- Therapixel vs Epocrates
- Therapixel vs Figure 1
- Therapixel vs Fullscript
- Therapixel vs GNU Health
- Therapixel vs GoodRx
- Therapixel vs Halaxy
- Therapixel vs Clue
- Therapixel vs Rx30
- Therapixel vs Quantum Health
- Therapixel vs Sysmex
