Applied Research in Healthcare

Medical AI &
Computer Vision.

LlimonaLab is an independent team of biomedical engineers and data scientists. We combine deep academic research with full-stack engineering to tackle complex challenges in medical imaging, data harmonization, and clinical AI.

Deep Learning
Advanced Neural Networks
Data Curation
DICOM & Clinical Metadata
Radiomics
Quantitative Imaging Biomarkers
Validation
In-silico Clinical Testing

Our Core Skills

Applied Medical Computer Vision.

Image Processing & AI

Multimodal Analysis & Segmentation

Our background encompasses the design of deep learning architectures for the segmentation of oncological lesions (e.g., glioblastoma, prostate cancer) across multiple modalities. We have extensive experience in multiplanar image registration (CT/MR), pseudo-CT synthesis, and extracting reproducible radiomic biomarkers for survival and risk assessment.

Semantic Segmentation Radiomics Image Registration
Clinical Integration

Data Quality & Validation

We build robust data pipelines for clinical environments. From creating DICOM integrity checker tools and orchestrating large multicenter databases, to developing in-silico validation dashboards and integrating AI workflows into medical viewers like OHIF.

Who We Are

Team Members.

A collaborative team of biomedical engineers combining deep academic rigor with production-ready software development.

Pedro Miguel Martínez-Gironés

Biomedical Engineer & CV Specialist

MSc in Computer Vision and current PhD candidate in Technologies for Health and Well-Being. His expertise spans the full radiological AI pipeline, from DICOM metadata quality control to designing artificial vision systems for clinical oncology. He specializes in multiplanar image registration, pseudo-CT synthesis, and ensuring AI solutions are robust and transferrable.

Adrián Galiana Bordera

Biomedical Engineer & Full-Stack Developer

MSc in Computer Vision and current PhD candidate. His research focuses on ensuring the absolute reproducibility of deep learning metrics in cancer imaging. He is highly experienced in structuring robust multicenter databases, developing in-silico validation dashboards, and designing neural networks for complex oncological lesion segmentation and feature regression.

Our Origin

From Shared Research to Collaborative Solutions

Meeting through our shared background in Biomedical Engineering and Computer Vision, we formed LlimonaLab as a joint initiative to participate in AI challenges and push the boundaries of medical research. Drawing from our roots in Cehegín (Murcia) and L'Alfàs del Pi (Alicante), we are dedicated to building ethical, accurate, and reproducible AI tools for the healthcare community.