Diagnostics & imaging AI · Breast imaging AI
ScreenPoint Medical
ScreenPoint Medical makes Transpara, FDA-cleared AI software that reads screening mammograms and 3D tomosynthesis exams with the radiologist, marks suspicious areas, and scores each exam for cancer risk.
Strong fit
- Breast imaging centers and radiology groups that read large volumes of screening mammograms and tomosynthesis exams
- National and regional screening programs that want AI with published trial results
- Radiologists who want a score for each exam so they can read the riskiest studies first
Weak fit
- Groups that want one AI vendor for chest, brain, and bone imaging
- U.S. buyers who want AI to read normal exams on its own, which FDA clearance does not cover
- Buyers who need a published price list
Bottom line
ScreenPoint Medical is worth using for breast imaging groups and screening programs that want AI support backed by randomized trial results. Its FDA-cleared Transpara software marks suspicious areas on mammograms and scores each exam's likelihood of cancer. Programs focused on breast or thyroid ultrasound should look at Koios Medical.
Score breakdown
Weights: Outcomes 35% · Product 30% · Implementation 20% · Pricing clarity 15%.
ScreenPoint Medical, based in Nijmegen in the Netherlands, makes Transpara, AI software that reads screening mammograms and 3D tomosynthesis exams alongside the radiologist.
Nico Karssemeijer, who had led computer-aided detection research at Radboud University Medical Center for 25 years, founded the company in 2014 with Sir Michael Brady, an emeritus professor at the University of Oxford.
Transpara works on 2D mammograms and 3D tomosynthesis from the major equipment makers. It marks regions that may be cancer and gives each exam a score from 1 to 10, so a radiologist can see which exams need the closest look.
It is FDA-cleared and used in more than 30 countries, including at Johns Hopkins. ScreenPoint says Transpara has processed more than 12 million mammograms.
In January 2026 The Lancet published final results of MASAI, a randomized trial in Sweden that used Transpara. It found favorable results against standard double reading by two radiologists.
Pieter Kroese, the chief operating officer for five years, became chief executive in April 2024. In April 2026 ScreenPoint raised $14 million from Insight Partners and Siemens Healthineers, plus $2 million in research grants.
Its FDA clearance does not cover uses in which the AI rules out normal exams on its own.
Compare Koios Medical when the need is breast and thyroid ultrasound, Aidoc when a health system wants AI across many imaging types, and Ferrum Health when the job is managing AI tools from several vendors.
Competitor landscape
| Vendor | Overall | Ease of implementation |
|---|---|---|
| Aidoc | 7.9 | 7.5 |
| ScreenPoint Medical | 7.9 | 7.6 |
| Harrison.ai | 7.7 | 7.5 |
| Qure.ai | 7.4 | 7.1 |
| Riverain Technologies | 7.3 | 6.9 |
| Subtle Medical | 7.2 | 6.8 |
| DeepTek | 7.1 | 6.8 |
| AZmed | 6.9 | 6.7 |
| Enlitic | 6.9 | 6.5 |
| Avicenna.AI | 6.9 | 6.6 |
| Ferrum Health | 6.8 | 6.5 |
| Koios Medical | 6.7 | 6.3 |
Pricing
| Item | Detail |
|---|---|
| Model | Subscription quoted by ScreenPoint Medical or through imaging partners. |
| What usually drives cost | Exam volume, 2D or 3D mammography, the number of sites, and whether it is bought directly or through a PACS or imaging equipment partner. |
| What to ask before you buy | The price per study or per site, what counts as a study, and the cost of connecting to your mammography reading workstation. |
| Published pricing | ScreenPoint Medical does not publish a price list. |
Prerequisites for purchase
| Need | Why it matters |
|---|---|
| What you need to get ScreenPoint Medical to function | |
| Lead breast radiologist | Sets how scores are used. |
| Reading workstation and PACS connection | Results show where radiologists read. |
| Baseline recall and cancer detection rates | You need them to show the change later. |
| Policy on AI in screening | Radiologists need clear rules. |
| IT time for integration | Studies must route to the AI. |
| What will maximize your value | |
| Read high-score exams first | Gets suspicious cases seen sooner. |
| Track recall rate by reader | Shows whether AI changes callbacks. |
| Review missed cancers with AI marks | Builds trust in the tool. |
| Deal-breakers | |
| Wants one vendor for all imaging | |
| Expects autonomous reading in the U.S. | |
| No owner for screening quality | |
Value creation time frame
| # | Stage | Typical range |
|---|---|---|
| 1 | Contract and integration plan | 1-3 months |
| 2 | Live on first sites | 2-4 months |
| 3 | All sites and 3D exams | 4-9 months |
Leadership
Methodology
| Weight | Factor | What it measures |
|---|---|---|
| 35% | Customer outcomes | Whether buyers get measurable operational or clinical-workflow results after go-live |
| 30% | Product | Capability depth, reliability, and fit for the job the category buys |
| 20% | Implementation | How hard it is to stand up, integrate, train, and stabilize |
| 15% | Pricing clarity | Whether a buyer can model total cost without a mystery quote |
| Label | Meaning |
|---|---|
| Highly recommend | Strong outcomes and product with manageable caveats |
| Recommend | Solid fit for the right buyer; know the tradeoffs |
| Conditional | Only with a specific use case or heavy caveats |
| Not recommended | Avoid for most buyers in this category |
Read our full methodology for how we weight scores and assign recommend labels.