Unlocking hidden spatial information.
Medical images are more than individual snapshots. Each medical image captures only part of the story.
The information that matters often lies in the spatial relationships between images — showing how anatomy changes over time or how complementary information relates across imaging modalities.
CONVEA develops AI-based image registration technology that establishes these spatial relationships. By precisely aligning anatomical structures across medical images, CONVEA makes hidden spatial information accessible.
Connect
Bring medical images into spatial alignment.
Compare
Reveal what lies between them.
Change
Turn spatial relationships into clinical insight.
Clinical information is hidden between the images.
Modern imaging generates large amounts of data across modalities, examinations and time points. Yet most imaging workflows still treat individual images or studies separately.
As a result, important spatial relationships remain difficult to access:
- between examinations of the same patient
- across time points and treatment stages
- across complementary imaging modalities such as CT, MRI, PET and CBCT
Establishing these relationships reliably is challenging, especially when anatomy changes, modalities differ or imaging conditions vary.
This is where CONVEA comes in.
CONVEA connects what belongs together.
We develop AI-based deformable image registration technology that automatically establishes spatial correspondence between heterogeneous medical images.
CONVEA aligns anatomical structures even when anatomy has changed or imaging conditions vary — creating a common spatial reference across images.
Universal
Across anatomies, modalities and time points.
Accurate
State-of-the-art medical image registration technology.
Integratable
Designed as an OEM and SDK component for integration into existing workflows.
Built on advanced image registration research
CONVEA builds on research in AI-based medical image registration and combines foundation-model approaches with advanced optimization methods to enable robust deformable registration across heterogeneous imaging data.
Our technology builds on research published in leading medical imaging venues and evaluated in international image registration benchmarks.
- Method
- Siebert H, Grossbroehmer C, Hansen L, Heinrich MP. ConvexAdam: Self-Configuring Dual-Optimization-Based 3D Multitask Medical Image Registration. IEEE Trans Med Imaging. 2025. IEEE Xplore
- Evaluated in
- Hering A, et al. Learn2Reg: comprehensive multi-task medical image registration challenge, dataset and evaluation in the era of deep learning. IEEE Trans Med Imaging. 2022. IEEE Xplore
One technology. Multiple clinical possibilities.
CONVEA is exploring applications where the spatial relationship between images matters.
Compare longitudinal imaging to support the assessment of disease progression, treatment response and anatomical change.
Enable precise image alignment for image guidance and adaptive treatment planning.
Quantify and analyse anatomical changes across imaging studies.
Connect complementary information from CT, MRI, PET and CBCT.
These are only the first possibilities.
We are only beginning to explore what becomes possible when medical images can be understood in relation to one another.
We are looking for partners to shape what comes next.
CONVEA is currently in the research and development phase and preparing to spin off from the University of Lübeck.
We are working with clinical and technology partners to translate our technology into solutions that address real-world needs and fit existing workflows.
This is the stage where we want to build together.
PACS & MedTech partners
Explore how CONVEA's spatial intelligence could be integrated into existing imaging platforms and future OEM solutions.
Clinical partners
Identify relevant applications, explore new clinical use cases, and validate clinical value.
Technology partners
Explore new applications and integration opportunities enabled by reliable spatial alignment.
Let’s explore together.
Get in touch
