Clinical AI research
Decision-support research at the intersection of oral medicine, imaging, and geometric AI — built with academic partners, designed for the clinic, not the lab.
onemosquito.ai
An African proverb, taken literally
AI is the lever. One idea, held long enough, is the place to stand.
Archimedes promised the rest.
onemosquito.ai is the umbrella for thirty years of research — begun, and still carried on, in Vienna, with the smallest of means and one conviction: scale is not a precondition for impact.
It started in the early 1990s with Interventional Video Tomography — teaching a camera to see the patient in three dimensions, so the surgeon could navigate what the eye could not. The idea has never changed, only its lever: from image-guided surgery to the Virtual Patient, and now to AIDOCVISION REMOTE, where artificial intelligence learns to read the oral cavity the way a surgeon does.
EK Nr: 1381/2026 AIDOCVISION REMOTE Multimodal AI-assisted early detection of oral malignancies with stereotactic intraoral scanner documentation in private practice — a prospective, blinded diagnostic pilot study. The scanner named in the title describes the Vienna acquisition standard, not a condition of participation: the primary modality at every site is photographic, and the scanner is a parallel channel where a device is already there for its own clinical purpose.
Oral cancer hides in plain sight. It sits on a surface a clinician can see and touch, yet more than six in ten cases are found only at stage III or IV, when five-year survival has already fallen below half. In 2022 it accounted for roughly 390,000 new cases and 188,000 deaths worldwide. The tumour is visible. What is missing is not the eye but the moment. AIDOCVISION REMOTE is a prospective, observer-blinded diagnostic pilot study built around that missing moment. It asks how well an AI-generated risk classification of an oral lesion agrees with the physician's own — and answers it where patients are actually seen, including a single private practice. That is the wager: a restrained instrument, placed at the edge of the system, aimed at a global problem. All inference runs locally, air-gapped, on an open-source stack — auditable before admired. Its geometry descends from Interventional Video Tomography, described thirty years ago Truppe et al., SPIE 1995 for surgery — its use in finding cancer legible only in retrospect. A mosquito is small enough to ignore and consequential enough to change a continent. So is a private praxis, given the right lever.
Big institutions move slowly. A small research group moves like a mosquito — light, precise, impossible to ignore. Evolution works the same way: its decisive turns are never announced, only recognized in retrospect — a small mutation in an overlooked lineage that, generations later, turns out to have changed everything. Every project under this umbrella follows that logic: find the one point where a small, exact intervention changes the whole system, and place the bite there. Recognition can come later.
The coral dot in our mark is not decoration. It is the point of contact — where thirty years of surgical experience touch the world through artificial intelligence.
Small bite. Global reach.
Decision-support research at the intersection of oral medicine, imaging, and geometric AI — built with academic partners, designed for the clinic, not the lab.
Specialist second opinions that travel farther than any patient has to. The team stays small; its judgment does not.
Research partnerships across Europe, Asia, and Africa — because the questions we work on do not stop at borders, and neither should the answers.
This site is the repository of a collaboration between three research groups — one in Vienna, one in Lagos, one in Athens. The proverb in our masthead is borrowed, with gratitude, from MAI Lab, the Medical Artificial Intelligence Laboratory in Lagos, which builds health AI for Africa on its own terms.
The work stands on three equal partners. Vienna supplies the clinical origin and the thirty-year geometry — the observation, the protocol, the model. Lagos brings a distinct disease: a polyaetiology cohort where the same tumour wears a different face, and the validation that a European model cannot claim on its own. Athens is where the three meet as peers, the collaboration held in common rather than owned. What begins as a clinical observation in Vienna becomes a dataset, a model, a validation study in Lagos — one deliberate step at a time, with resources that force clarity instead of excusing waste.
A collaboration across three time zones needs two things that are easy to confuse: one place where decisions are written down, and one place where people talk. They are not the same place, and keeping them apart is what makes the record trustworthy.
A single living document that carries the partners and contacts, the division of responsibilities, the imaging modalities for each site, the milestones, the open questions and the decision log. It is the record: if a decision is not written there, it has not been taken. It also fixes the modality hierarchy, so that no site reads an equipment threshold into the protocol: photographs taken with a conventional camera and with a smartphone, compared against the established ground truth for the same lesion, are the primary modality everywhere, while intraoral scanner imagery is a parallel channel — the Vienna standard, optional elsewhere, and no condition for a site's scientific contribution. Named collaborators hold commenting rights at onemosquito.ai/hub.
A WhatsApp group for scheduling, availability, logistics and notice that a document has changed — nothing more. No patient data, no clinical photographs, no scans, no datasets, not even a screenshot with the name removed. Study data move only through the secure study route under the signed Data Sharing Agreement. The rules are published as SOP EURODOC-COMM-001 at onemosquito.ai/rules.
Both are closed by design. Membership of the channel is by administrator invitation, every join request is approved by hand, and the invitation link is never published — not here, not in slides, not in conference material. Access to the hub is granted per named person rather than by link. Colleagues who should be on either list are welcome to write to hello@onemosquito.ai. Anything substantive said in the channel is transferred into the hub within two working days, which is also how a conversation becomes something a reviewer, an ethics committee or a court could read.
Partnerships, research, or a question worth losing sleep over:
hello@onemosquito.ai