Available for new projects

Production-Ready AI
for Healthcare

From medical imaging to computer vision. I turn complex ML challenges into deployed solutions that patients depend on. 410+ citations. Trusted by healthcare innovators.

410+
Citations
14+
Publications
PhD
Credentials

Problems I Solve

From research papers to hospital-deployed systems

Education

PhD Computer Science

Technical University of Kosice

+ Polytechnique Montréal

Core Expertise
Medical Imaging AI
Computer Vision
Deep Learning
Signal Processing
Tech Stack
PyTorchTensorFlowPythonCUDAOpenCVTransformersFastAPIDockerAWSscikit-learnONNXMLflowWeights & BiasesRay
Experience
Laza MedicalAI Engineer

Cardiac AI & medical robotics

TietoEVRYSoftware Engineer

Laboratory & medical devices

Cortex VisionResearcher

Medical imaging diagnostics

Currently accepting 3 projects this quarter

Have a challenging AI problem?

Let's discuss your use case in a free strategy call.

Book Free Consultation

Selected Projects

Real-world AI solutions deployed in production

Medical Imaging|Deployed segmentation model

Cardiac Valve Segmentation from 2D Echocardiography

Deep learning algorithms for automatic detection and segmentation of mitral and aortic valves from 2D echocardiographic images. U-Net architecture optimized for low-contrast ultrasound data with high noise levels.

U-Net CNN architectureClinical validation with cardiologistsProduction-ready prototype
MICCAI Competition|6th Place Worldwide

KiTS21 - Kidney Tumor Segmentation Challenge

Participation in the prestigious international KiTS21 challenge for automatic segmentation of kidneys, kidney tumors, and cysts from CT scans. Solution based on 3D residual U-Net architectures with advanced augmentation techniques.

6th place globally3D residual U-NetAdvanced augmentation
LLM / NLP|89.3% accuracy

Bioactive Molecule Extraction from Scientific Literature

LLM-based system for automated identification and extraction of bioactive substances and their therapeutic effects from PubMed publications. Advanced NER and relation extraction for mapping molecules to specific diseases.

30,000 papers processed89.3% extraction accuracyChEMBL/DrugBank validation
Cloud / DevOps|Production platform

Enterprise Cloud Infrastructure

Design and implementation of scalable cloud infrastructure for a major telecommunications provider. Containerized microservices architecture with automated deployment pipelines and integration with distributed compute resources.

Docker & KubernetesCI/CD automationEnterprise scale
Dr. Matej Gazda speaking at a conference

Research depth.
Engineering pragmatism.

I'm Dr. Matej Gazda, bridging the gap between academic AI research and real-world systems that scale.

My work in medical imaging has been published in IEEE Transactions, deployed in healthcare settings, and cited by researchers worldwide. I specialize in taking complex ML problems from Jupyter notebooks to production infrastructure.

Whether you need a custom vision system, technical advisory, or help deploying AI at scale, I bring both the research rigor and practical know-how.

Selected Research

Peer-reviewed publications in top venues

View all on Google Scholar

Multiple-Fine-Tuned CNNs for Parkinson's Disease Diagnosis From Offline Handwriting

IEEE Trans. on Systems, Man, and Cybernetics

2022

Self-Supervised Deep CNN for Chest X-Ray Classification

IEEE Access

2021

CNN Ensemble for Parkinson's Disease Detection from Voice Recordings

Computers in Biology and Medicine

2022

End-To-End Deformable Attention Graph Neural Network for Liver Mesh Reconstruction

IEEE ISBI

2023

Generative Adversarial Networks in Ultrasound Imaging: Extending Field of View

Medical Imaging

2024

Let's create
something great

Have a challenging AI problem? I'd love to hear about it. Drop me a message and let's explore what's possible.