Gathers its own context
Pulls priors, reports and labs itself. No copy-paste, no prompts.
Clinical AI research lab
Clinical AI that shows its evidence.
A physician copilot that reads patient evidence like a specialist, shows where every conclusion comes from, and knows when to defer. Starting in nuclear medicine, growing into oncology imaging.
- A Liver Multiple focal lesions
- B Right lower abdomen Lesion or bowel? Flagged
- C Bladder Physiologic uptake
Why now
Answers got cheap. Reading a case did not.
Demand for PET imaging is outgrowing the capacity to read it.
+12.2%
IMV PET Market Summary, 2025
40%
IMV PET Market Summary, 2025
Approach
Built the way a specialist reads.
Numbers come from tools
Every measurement is computed by validated code, never generated.
Evidence before conclusion
Each statement links to the region or record it rests on.
Knows when it isn't sure
Below its threshold, it flags for review instead of guessing.
How the lab works
Research and product, one loop.
We build on frontier models and own the layer above them. Physician edits close the loop.
- Grounded perception
- Longitudinal reasoning
- Verification & calibration
- Clinical agents
- Evaluation & benchmarks
Research
New methods, datasets and open benchmarks.
Roadmap
Deeper along the patient's journey, one proven stage at a time.
-
Now
Foundations
Physician-annotated imaging data, benchmarks, evaluation.
-
Next
Nuclear medicine reader
Grounded draft reports, reviewed by physicians.
-
Then
Oncology imaging copilot
Follows each cancer patient across scans and time.
-
Later
Care-team copilot
Imaging-grounded support for the treating team.
Each stage starts only after the one before has proven itself with physicians.
Team
Researchers, engineers and physicians.
From leading universities, hospitals and technology companies. ViVi originated at the University of Toronto.
Our team comes from
Work with us
We collaborate across the board.
- Hospitals
- Clinicians
- Universities
- Engineers
- Industry
- Funders