Lävi Clinical Suite · Longitudinal brain MRI

Not every difference is disease.

Lävi Delta is in development and is not CE-marked.

We develop technology for detecting and assessing meaningful change between serial brain MRI examinations. Lävi Delta, our first product, supports the radiologist in follow-up brain MRI: it shows on a map where the signal has changed between two examinations. When the two cannot be compared on technical grounds, it says so and withholds the result.

Clinical validation and regulatory development in progress · not CE-marked

Baseline

Follow-up

Follow-up + change map

Slice –
Fig. 1 — Lävi Delta output Two MRI examinations of the same person, side by side, with Lävi Delta's change map on the follow-up. Colour key.

Public research data (MSLesSeg; Yale-Brain-Mets-Longitudinal, TCIA). CC BY 4.0. Skull removed, change map added.

Data and licences

Data: Guarnera, F., Rondinella, A., Crispino, E., Russo, G., Di Lorenzo, C., Maimone, D., Pappalardo, F., & Battiato, S. (2025). MSLesSeg: baseline and benchmarking of a new Multiple Sclerosis Lesion Segmentation dataset [Dataset]. figshare. https://doi.org/10.6084/m9.figshare.27919209.v1 · Licence: CC BY 4.0.

Data: Chadha, S., Weiss, D., Janas, A., Ramakrishnan, D., Hager, T., Osenberg, K., Willms, K., Zhu, J., Chiang, V., Bakas, S., Maleki, N., Sritharan, D. V., Schoenherr, S., Westerhoff, M., Zawalich, M., Davis, M., Malhotra, A., Bousabarah, K., Deuschl, C., Lin, M., Aneja, S., & Aboian, M. (2025). Yale longitudinal dataset of brain metastases on MRI with associated clinical data (Yale-Brain-Mets-Longitudinal) (Version 1) [Dataset]. The Cancer Imaging Archive. https://doi.org/10.7937/3YAT-E768 · Licence: CC BY 4.0.

Clark, K., Vendt, B., Smith, K., Freymann, J., Kirby, J., Koppel, P., Moore, S., Phillips, S., Maffitt, D., Pringle, M., Tarbox, L., & Prior, F. (2013). The Cancer Imaging Archive (TCIA): maintaining and operating a public information repository. Journal of Digital Imaging, 26(6), 1045–1057. https://doi.org/10.1007/s10278-013-9622-7

Images have been processed: skull removed, change map added.

Public research data, not patient data from our study. Lävi Delta is in development and is not CE-marked.

01 — What it does

What Lävi Delta does

Lävi Delta compares a person's new brain MRI with their previous one and shows, on a colour map, where the signal has changed. The radiologist checks each coloured area against the original images and decides what it means; the software makes no diagnosis. When two examinations cannot fairly be compared, it says so and shows no result rather than a misleading one.

  • Red: signal increased between the two scans.
  • Blue: signal decreased.
  • No colour: the map shows no change. The stronger the colour, the larger the change.

The map is not a list of lesions and not a diagnosis. The radiologist decides.

02 — Scanners

Same person, two scanners

A follow-up scan is often made on a different scanner from the first one, and some of what looks like change is only the difference between the two machines. Lävi Delta is being built to tell that apart from real change in the patient.

Scanner 1 · Philips

Axial FLAIR MRI of a healthy volunteer, first scanner (Philips).

Scanner 2 · Siemens

The same person and slice on a scanner from a different vendor (Siemens).

Plain subtraction

Plain subtraction of the two scans after alignment and standard intensity scaling.

Plain subtraction: grey means the two scans agree; lighter or darker means they differ.

Fig. 2 — Same person, two scanners One example pair from a public dataset (ON-Harmony, OpenNeuro ds004712). An illustration, not a performance result. Plain subtraction: rigid registration and intensity normalisation, then the difference of the two images.

In our internal technical tests, results across scanners from different vendors have been promising. Read what was tested and what was not.

03 — Development status

Where we are

Where we areFour stages without dates. Technical tests: done. Evaluation on public datasets: done, internal. Reader study: in preparation. Regulatory assessment: ahead. TECHNICAL TESTS done EVALUATION ON PUBLIC DATASETS done, internal READER STUDY in preparation REGULATORY ASSESSMENT ahead Where we areFour stages without dates. Technical tests: done. Evaluation on public datasets: done, internal. Reader study: in preparation. Regulatory assessment: ahead. TECHNICAL TESTS done EVALUATION ON PUBLIC DATASETS done, internal READER STUDY in preparation REGULATORY ASSESSMENT ahead

Fig. 3 — Where we arestages, not dates

Lävi Delta is in development and is not CE-marked.

Status as of 2026-11-17

04 — Contact

Talk to us

One address for everyone — the subject line tells us who is writing. Andreas, the CEO, answers his own email.

  • Hospitals

    If your department reads follow-up brain MRI routinely, we can talk through what a pilot would involve. Today a pilot is a research collaboration inside your own network, not clinical use. What a pilot involves.

    Talk to us about a pilot in your department

  • Partners and investors

    The evidence plan and the technical architecture, examined in detail. We maintain dated internal development, validation and evidence-planning documentation; selected material can be shared in qualified conversations under NDA or controlled data-room access.

    Research or technology partner? Write about research collaboration.

    Start an investor conversation →

  • Radiologists

    What the change map shows, how it would fit a follow-up read, and what it does not do. A neuroradiologist answers.

    Ask us about the software →

Looking for work, or interested in MS imaging? Careers · Lävi MS · The company and team