Available for contract work
The evidence is below: three problems I take on as a contractor, on model work that has to survive a regulatory file and not only a benchmark.
Three of them. Each one has published work behind it.
Reconstruction
Two angiographic planes. A freehand ultrasound sweep. A stack of slices with gaps between them. The volume still has to be anatomically plausible where the acquisition never looked, and that is what a learned shape prior is for.
Label efficiency
Self-supervised pretraining, annotation-efficient segmentation, and evaluation on the cohort you actually have rather than the one you wish you had. I report the failures too: modality-invariant pretraining helped on several tasks in our hands and hurt lesion segmentation.
Signals
Voice and handwriting carry the diagnosis too, and they are cheaper to collect than a scan. Parkinson's disease from voice recordings is my most cited work, at 180 citations.
Also a second opinion on a pipeline: where the metric is leaking, and whether the plan holds.
The first piece of work
Most first conversations do not need a contractor line and a headcount request. They need a result you can act on. So the first piece of work is a fixed scope at a fixed price, both agreed before it starts.
A negative result is a valid outcome and you get it in writing. If the method does not beat your current number, the report says so and we stop there.
Price quoted after the call, once the scope is agreed.
What is delivered
On your data, or on a public proxy if the data cannot leave. Which one is agreed before the ten days start.
One, chosen for your problem. Ten days does not buy a survey.
The result, how it was measured, and a go or no-go recommendation.
So the decision is made with me in the room, not from a PDF.
Mitral and aortic valves, found and segmented automatically in 2D echocardiograms. Ultrasound is low in contrast and high in noise, so the U-Net was tuned for that data.
An LLM pipeline that reads PubMed papers, finds bioactive substances and their therapeutic effects, and maps each molecule to a disease with entity and relation extraction. It processed 30,000 papers.
Experience
Robotic cardiovascular imaging at a cardiac device company in the Shifamed portfolio, since December 2022
Private cloud infrastructure for telecom, 2017 to 2022
LLM for bioactive molecules and disease mapping
Medical imaging diagnostics
Education
Technical University of Kosice, 2023
Visiting PhD, Polytechnique Montréal, 2022
MICCAI 2025
Foundation Model Challenge for Brain MRI
Awards and funding

I am Matej Gazda. PhD in artificial intelligence from the Technical University of Kosice, a visiting year in Samuel Kadoury's lab at Polytechnique Montréal, and papers in IEEE TSMC, Medical Image Analysis and npj Digital Medicine.
The part that matters to a head of R&D is the other half. Five years of software engineering at TietoEVRY, 2017 to 2022, and since December 2022 AI Research Scientist at Laza Medical, a cardiac device company in the Shifamed portfolio, on robotic cardiovascular imaging. I know what happens to a model between the paper and the clinic.
I work as an external contractor, not as a candidate for a headcount line. The usual first step is the ten day engagement above.
Thirty minutes on the problem and the metric you are judged on
If the engagement is a go, the method goes into your pipeline and your tests
Code, weights and the write-up your team needs to keep it running
Research & Collaboration
TUKE
Technical University of Kosice
PolyMTL
Polytechnique Montréal
IEEE
MICCAI
UNLP
Louis Pasteur Hospital
Grouped by the three problems above.
Reconstruction
End-To-End Deformable Attention Graph Neural Network for Liver Mesh Reconstruction
IEEE ISBI
Whole-heart SSM
arXiv:2608.19932
Label efficiency
Towards Annotation-Efficient Segmentation via Image-to-Image Translation
Medical Image Analysis
FOMO25, Foundation Model Challenge for Brain MRI: 3rd in the method track
MICCAI
One paragraph is enough: what you are trying to measure, what you get now, and what the data looks like. I answer within a working day and I will say if it is not my problem.
Working together