AI research lab

Grounded AI for oncology.

We are building toward a physician copilot for the whole cancer journey, from diagnosis to theranostics to treatment. It reads the patient's evidence like a specialist, shows where every statement comes from, and knows when to defer.

  1. A Liver Multiple focal lesions
  2. B Right lower abdomen Lesion or bowel? Flagged
  3. C Bladder Physiologic uptake
Real FDG PET scan by Jens Maus, public domain. Annotations are illustrative of our design intent.

Why now

Answers got cheap. Reading a case did not.

Before a tumour board, someone gathers each patient's letters, results and scans by hand. In the US, PET scan volume is growing and many sites report waits of eight days or more.

2023 2024 100 112.2

+12.2%

Growth in US PET scan volume from 2023 to 2024.

IMV PET Market Summary, June 2025

40%

of US PET sites report waits of eight days or more for outpatient scans.

IMV PET Market Summary, June 2025

Approach

Designed the way a specialist reads.

Gathers its own context

Designed to pull priors, reports and the treatment line itself. No copy-paste, no prompts.

Numbers come from tools

Every measurement is designed to be computed by code, never generated.

Evidence before conclusion

Each statement is designed to link to the record, image region or paper it rests on.

Knows when it isn't sure

Below its threshold, it is designed to flag 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 are designed to close the loop.

  • Grounded evidence
  • 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 stage at a time.

  1. Now

    Grounded case summaries

    A research prototype designed to turn a cancer patient's records into a source-linked summary for tumour boards, with the supporting literature. Clinicians review and edit it. It does not recommend treatment.

  2. Now

    Imaging reasoning over time

    Research on telling a real change in the cancer from measurement noise or a record error, so each new scan is read against the patient's history.

  3. Next

    Nuclear medicine reader

    Designed to draft grounded reports for PET/CT and theranostics, for physician review.

  4. Later · gated

    Oncology copilot

    Support for the treating team across diagnosis, theranostics and treatment.

  5. Later · gated

    Outcome-linked patient model

    Aims to link imaging to outcomes: who responds, who relapses.

Later stages are gated: they start only after earlier work has proven itself with physicians.

Team

Researchers, engineers and physicians.

From leading universities, hospitals and technology companies. ViVi originated at the University of Toronto.

Sketch portrait of Van Ngo
  • Strategy
  • Product
  • Partnerships

Van Ngo

Co-founder

Sketch portrait of Khai Le-Duc
  • Research
  • Multimodal AI

Khai Le-Duc

Co-founder

Sketch portrait of Viet Han Vo
  • Clinical protocols
  • Hospital partners

Viet Han Vo, MD

Co-founder

Our team comes from

Work with us

We collaborate across the board.

  • Hospitals
  • Clinicians
  • Universities
  • Engineers
  • Industry
  • Funders