AIRS Medical vs Lunit (2026)
Two Korean imaging AI companies doing opposite things to a department's workload. AIRS Medical changes the image: SwiftMR removes noise and sharpens MRI after acquisition so scans can run shorter, across scanner makers and field strengths, with the original series archived separately. Lunit finds cancer on mammography, tomosynthesis and chest radiographs, and its strongest evidence is ScreenTrustCAD, a prospective study of 55,581 women in which AI with one radiologist was non inferior to two radiologists. One returns scanner capacity, the other returns findings. If MRI capacity is the constraint, start with AIRS. If breast screening is the program, start with Lunit.
- Scanner capacity is the problem: SwiftMR enhances MRI of all body parts at field strengths from 0.25 to 3.0 tesla, validated on scans up to 50 percent shorter.
- It runs beside the scanner makers' own reconstruction: its latest clearance was validated on images already processed that way.
- The original survives: original and processed series can be archived separately.
- Screening evidence from a prospective study: ScreenTrustCAD, 55,581 women in Sweden, found AI with one radiologist non inferior to two radiologists.
- A breast cancer platform: INSIGHT for mammography and tomosynthesis sits alongside Lunit International's density, risk and quality products, formerly Volpara.
- Subgroup results exist: an Emory led evaluation with Lunit coauthors reports INSIGHT DBT performance by patient subgroup.
This comparison is published by AI Health Index, an independent research platform that compares healthcare AI vendors objectively. AIRS Medical and Lunit are each graded against the same capability taxonomy, from each vendor's own public materials and the regulatory record, under the AI Health Index verification standard. No vendor pays for placement, and no vendor has reviewed this page. How this evidence is graded
Plain facts
| Fact | AIRS Medical | Lunit |
|---|---|---|
| Primary category | Radiology & Imaging AI | Radiology & Imaging AI |
| Founded | 2018 | 2013 |
| Headquarters | Seoul, South Korea | Seoul, South Korea |
| Website | airsmed.com | lunit.io |
Side by Side
Select any grade to read the note behind it.
Product updates
The latest logged changes from each vendor, newest first, each linked to its source.
AIRS Medical
-
Product / capability
AIRS Medical released version 1.0.0.2 of SwiftSight Body Composition for the cloud.
Source -
Regulatory / FDA
AIRS Medical received FDA 510(k) clearance for SwiftSight Body Composition, which measures visceral and subcutaneous fat, abdominal and thigh muscle, muscle quality and balance, and liver fat from an MRI scan of under five minutes.
Source
Each vendor in one paragraph
Written to be quoted whole. Each paragraph opens the AI Health Index profile of the vendor: what the product is, who buys it and what it does.
Seoul based MRI AI company with US operations. SwiftMR is a deep learning enhancement tool that reduces noise and sharpens MRI images after acquisition, so sites can scan faster or get better images from the same scan. It works across scanners from the major manufacturers and field strengths from 0.25 to 3.0 tesla, and now alongside scanner makers' own deep learning reconstruction.
Source: AI Health Index, September 2026
Lunit is a cancer focused medical AI company founded in 2013, headquartered in Seoul and listed on KOSDAQ. Its radiology line is Lunit INSIGHT: MMG for 2D mammography (FDA cleared 2021), DBT for tomosynthesis (cleared 2023) and CXR for chest X-ray (CXR Triage cleared 2021).
Source: AI Health Index, September 2026
Questions buyers ask
How do AIRS Medical and Lunit work with the EHR?
AIRS Medical says SwiftMR is compatible with MRI scanners from Siemens Healthineers, GE HealthCare, Philips and Canon Medical. The K253775 validation also covered Esaote, Fonar and Fujifilm scanners.
Lunit embeds its algorithms in imaging hardware and viewers through equipment and technology partners, more than 100 by its count, and also delivers through the cloud, so a customer can acquire the AI as part of a scanner or viewer purchase rather than as a separate integration project. From the AI Health Index, drawn from each vendor's own published materials and the regulatory record, verified September 27, 2026. No vendor pays for placement.
How are AIRS Medical and Lunit priced and sold?
In AIRS Medical's case, the site has an ROI calculator and case studies framed on throughput: shorter scans, appointment slots moving from 30 to 20 minutes, and capacity from scanners a site already owns instead of a new purchase. SwiftMR and SwiftSight are separate products, and access starts with a demo request.
Lunit sells INSIGHT and its breast platform direct and through imaging equipment and viewer partners, so the software can arrive inside or alongside a scanner or viewer purchase. From the AI Health Index, drawn from each vendor's own published materials and the regulatory record, verified September 27, 2026. No vendor pays for placement.
How do AIRS Medical and Lunit handle patient data?
With AIRS Medical, the cloud service is designed not to store, transmit or display PHI or personal information. Data is encrypted with AES-256 at rest and TLS 1.3 in transit, and an on premises deployment keeps images inside the hospital altogether.
In Lunit's case, the INSIGHT MMG FAQ says images from commercial sites are retained only for the duration of processing and are not used for retraining, that the models do not learn in real time, and that training data is biopsy proven material sourced through formal collaboration agreements. From the AI Health Index, drawn from each vendor's own published materials and the regulatory record, verified September 27, 2026. No vendor pays for placement.
What evidence is published for AIRS Medical and Lunit?
AIRS Medical reports more than 1,700 institutions in over 40 countries and more than 7 million MRI exams a year. It names site results: routine brain scans on a GE 3T scanner already running the maker's own deep learning reconstruction cut from 15 to 9 minutes, and 3T Radiology & Research in Miami reporting higher throughput.
An independent external evaluation in JAMA Oncology (Salim and colleagues, 2020) compared three commercial algorithms on a retrospective Swedish screening cohort, and Lunit's had the highest accuracy. From the AI Health Index, drawn from each vendor's own published materials and the regulatory record, verified September 27, 2026. No vendor pays for placement.
Related comparisons
Other published head to head assessments involving these vendors or their closest peers. The full set for this category is on the Radiology & Imaging AI page.
AIRS Medical's clearance was tested on image quality, not diagnostic accuracy, and a degraded enhancement model can produce a cleaner image that lost something, so keep the original series. In the US, Lunit INSIGHT MMG is cleared as an adjunct viewed after the radiologist's initial read. Site and publication counts are the companies' own.