Team

AIM-Net is a national research network that unites leading Spanish groups working at the intersection of microscopy, quantitative biology, and artificial intelligence. Its mission is to integrate imaging data across molecular, cellular, and tissue scales to achieve a comprehensive understanding of biological organization and dynamics.

AIM-Net promotes collaboration among physicists, biologists, microscopists, and computer scientists to develop AI-based strategies for data integration, interpretation, and modeling. The network also fosters training, open science, and outreach activities to strengthen the Spanish research community in AI-driven bioimaging and to project its leadership internationally.

— Meet the minds behind our network

Executive Committee

The Executive Committee provides scientific leadership, monitors the progress of the network’s activities, and defines its strategic directions.

  • María García-Parajo (ICFO) — Coordinator
  • Carlos Ortiz de Solórzano (CIMA-UNAV)
  • Luis M. Escudero (University of Seville)
  • Carlo Manzo (UVic-UCC)
  • Diego Megías (ISCIII)

Data Integration and Analysis

Responsible for ensuring coherent integration and analysis of multiscale imaging data using advanced computational and AI-based approaches.

  • Carlos Ortiz de Solórzano (CIMA-UNAV)
  • Arrate Muñoz Barrutia (UC3M)
  • Jónathan Heras (University of La Rioja)

Network Performance and Strategic Plan

Oversees the monitoring of AIM-Net’s activities, evaluates its impact, and plans long-term strategic actions, including major scientific events.

  • Diego Megías (ISCIII)
  • Carlo Manzo (UVic-UCC)
  • Oriol Gallego (UPF)

Training and Outreach

Coordinates the network’s educational and outreach activities, such as the biennial Summer School, workshops, and public engagement initiatives.

  • Luis M. Escudero (University of Seville)
  • Isabel Peset Martín (CNIO)
  • Pedro Gómez (University of Seville)
  • Oriol Gallego (UPF)
  • Jónathan Heras (University of La Rioja)

Communications and Events

Manages AIM-Net’s internal and external communications, maintains the network’s website and social media presence, and organizes scientific meetings and dissemination events.

  • María García-Parajo (ICFO)
  • Victoria Neguembor (IBMB)
  • Oriol Gallego (UPF)
  • José Requejo (CSIC)
parallax background

Core members

Maria Garcia-Parajo

Single Molecule Biophotonics

Institute of Photonic Sciences (ICFO)

Barcelona, Spain

About the group
Our research focuses on the development of advanced optical techniques to the study of biological processes at the single molecular level on living cells. We focus on the development and application of different forms of super-resolution microscopy (STED, STORM, NSOM) as well as photonic antennas to reach spatial resolutions around 10nm on intact cells. Fluorescence correlation spectroscopy in ultra-confined volumes, and multi-color single particle tracking are exploited to gain access to dynamic processes down to the microsecond time resolution. Using these combined approaches, we aim at understanding how spatiotemporal compartmentalization of biomolecules inside cells regulates and control cell function. This fundamental question has important implications for health and disease, touching the fields of cell biology and immunology.
Main research lines
Our group exploits different machine learning strategies to analyze extensive data sets obtained through different forms of super-resolution microscopy and multi-color single particle tracking methods. Our aim is to provide quantitative and physical understanding of biological processes at the single cell and single molecule levels.
Key techniques
STED super-resolution microscopy, Single Molecule Localization Methods (SMLM) including STORM and DNA-PAINT, single-molecule tracking.
Key members

Dr. Amaris Guevara Garcia — PostDoc with expertise in biotechnology, super-resolution microscopy & mechanobiology.

Dr. Joaquim Torra — Senior research fellow with expertise in photochemistry, photobiology, and fluorescence imaging.

Contact
maria.garcia-parajo@icfo.eu

Mª Gloria Bueno

Computer Vision and Artificial Intelligence - Optics and Artificial Intelligence

University of Castilla-La Mancha (UCLM)

Ciudad Real, Spain

About the group
VISILAB (Computer Vision and Artificial Intelligence Group) and OPTICAI (CSIC–UCLM Associated Unit on Optics & AI) form a joint research effort bringing together faculty and researchers from the Industrial Engineering School at the UCLM in Ciudad Real and scientists from the Instituto de Óptica “Daza de Valdés” (CSIC, Madrid). Since 1999, VISILAB/OPTICAI has developed computer vision and AI methods for image understanding and decision support, with applications spanning biomedical engineering and image-based diagnosis, as well as other domains (e.g., security and quality inspection). Within AIM-Net, VISILAB/OPTICAI contributes a strong track record in AI for multiscale imaging pipelines, from acquisition and enhancement to analysis, interpretation, and deployment. Our recent work aligns directly with AIM-Net’s scope by advancing: (i) computational microscopy and imaging workflows, including edge computing for microscopy solutions and practical software tools (e.g., ImageJ and QuPath extensions); (ii) multimodal and data-efficient AI-based methods for microscopic organism identification; and (iii) digital pathology and quantitative tissue analytics, leveraging deep learning methods for histopathology, biomarker-driven WSI assessment and clinically oriented imaging tasks such as breast ultrasound classification. We also develop curated datasets and benchmarks and place emphasis on robustness and trustworthiness, which is essential for deployable AI in biomedical imaging.
Main research lines
  • AI-assisted microscopy and computational imaging (enhancement, fusion, quality, deployment).
  • Multiscale bioimage analysis from microorganisms and cells to tissue/whole-slide pathology.
  • Data-efficient learning for limited/variable microscopy data (few-shot, semi-supervised, multimodal).
  • Graph-based learning for tissue microenvironment and structure-aware pathology.
  • Trustworthy AI for imaging: robustness, generalization, and adversarial detection.
Key techniques
  • 2D/3D segmentation, instance segmentation, and detection transformers for microscopy tasks.
  • CNNs, transformers, and multimodal fusion; few-shot/prototypical learning for taxonomy-like problems.
  • Graph neural networks for structured tissue units and decision support.
  • Reproducible tooling and practical pipelines (QuPath/ImageJ extensions; low-cost/edge microscopy systems).
  • Robustness evaluation and adversarial example detection using chaos-based and activation-map methods.
Key members

Oscar Deniz — Co. Principal Investigator.

Maria Viñas — Tenured CSIC scientist.

Contact
gloria.bueno@uclm.es

Luis M. Escudero

Mechanisms of Tissue Organization

University of Seville. Institute of Biomedicine of Seville (IBiS)

Seville, Spain

About the group
Understanding how tissues self-organise in homeostasis is key to uncover the causes and mechanisms of pathological variations. We combine Developmental Biology, Computational Biology, Physics, Mathematics and Biomedicine concepts to obtain relevant quantitative information about how living tissues are organised. After analysing epithelial 3D organization in a series of living organisms, we found that cells can exchange their neighbours along the apico-basal axis by adopting a new geometrical shape that we named “scutoids”. We have been investigating how this new paradigm affects different processes in development and disease to shed light on the biomechanical mechanisms of organ morphogenesis and tissue maintenance. In parallel, we are developing new image analysis tools that provide a more realistic framework for understanding and explaining epithelial architecture. We have established our group at the Cell Biology Department of the University of Seville (computational lab) and the Instituto de Biomedicina de Sevilla (IBiS) (wet lab).
Main research lines
We implement and apply AI based models to process microscopy images in 3D and 4D (3D+t) and to generate synthetic training datasets. We also design computational and mathematical methods to quantify the organisation of the elements (cells) from the processed images. In addition to our main research line, we develop other image analysis tools to quantify the organization of tissues combining supervised and unsupervised learning methods: The diagnosis of neuromuscular diseases relies heavily on the histological characterisation of muscle biopsies. However, in clinical practice this analysis is largely subjective and difficult to quantify. To address this, our laboratory has developed NDICIA, a method that extracts meaningful information from muscle samples in an objective, automated, rapid and precise manner. NDICIA has been validated in both preclinical models (mice) and human muscle samples. It enables the quantification of disease severity (i.e. how different mutant samples are from controls) and highlights the most relevant features underlying these differences. Most recently, we applied NDICIA to identify and characterise potential imaging biomarkers of Amyotrophic Lateral Sclerosis (ALS) in the G93A-SOD1 transgenic mouse model during ageing. Our analysis revealed early pathological signatures in SOD1 mice, detectable even before the onset of motor symptoms.
Key techniques
  • Segmentation of 3D/4D epithelial images based on U-Net like training.
  • Synthetic datasets generation for subsequent packed tissue segmentation using 3D cycleGANs.
  • NDICIA (Neuromuscular DIsease Computerised Image Analysis) to quantify severity of the mutant condition and detect the most relevant features compared with a control group.
Key members

Pedro Gómez-Gálvez — Co-PI. PostDoc researcher specialized in computational biology (image processing, machine/deep-learning methods, math and biophysical modeling), cell biology and neuroscience.

Jesús Ángel Andrés-San Román — PhD student with expertise in physics, cell biology and deep-learning based methodology applied to image analysis.

Contact
lmescudero-ibis@us.es

Carlo Manzo

QuBI Lab

Universitat de Vic (UVIC)

Vic, Spain

About the group
Our research seeks to uncover the quantitative principles underlying key biological processes by integrating advanced computational analysis with cutting-edge microscopy and cell biology. We develop artificial intelligence tools tailored for single-molecule and super-resolution fluorescence microscopy, enabling the extraction of meaningful information from complex imaging data. A major focus of our work is understanding the spatiotemporal organization and dynamics of cell-membrane components—such as receptors and adhesion molecules—and how these nanoscale processes influence cellular behavior in health and disease. Through this interdisciplinary approach, we aim to bridge the gap between quantitative imaging, AI-driven data analysis, and mechanistic biophysics.
Main research lines
Main research lines related to AIM-Net: Geometric and physics-informed deep learning for quantitative analysis of the spatiotemporal organization and dynamic behavior of cell membrane components.
Key techniques
AI, Graph Neural Networks SPT, PALM/STORM
Key members

Juan Bertran

Marta Cullell

Sergi Masó

Montse Masoliver

Contact
carlo.manzo@uvic.cat

Diego Megias Vazquez

Advanced Optical Microscopy Unit

Instituto de Salud Carlos III (ISCIII)

Spain

About the group
The Advanced Optical Microscopy Unit (AOM) provides comprehensive support services in state-of-the-art optical microscopy. It focuses on experimental design, automated image acquisition, and advanced data analysis. The unit offers expertise in super-resolution microscopy, live-cell imaging, confocal laser scanning microscopy, wide-field microscopy, and high-content screening. Automated imaging systems enable large-scale, high-throughput data collection with precise control of imaging parameters, facilitating reproducible and quantitative studies. In addition to traditional 2D image processing, the MOA applies advanced 3D and 4D image analysis techniques to visualize and quantify dynamic biological processes in space and time. Overall, the AOM supports researchers throughout the entire imaging pipeline, from experiment planning to high-dimensional data interpretation and visualization.
Main research lines
Artificial intelligence and machine learning algorithms integration into the optical microscopy workflow to enhance image segmentation, feature extraction, and data mining, enabling the discovery of subtle patterns and correlations within complex datasets.
Key techniques
High Content screening, Super – resolution, confocal, image analysis, automated microscopy, feedback microscopy.
Key members

Juliana Manosalva — Microscopist Degree in Biology.

Dr. Joaquim Torra — Senior research fellow with expertise in photochemistry, photobiology, and fluorescence imaging.

Contact
diego.megias@isciii.es

Ignacio Arganda-Carreras

Computer Vision and Pattern Discovery

University of the Basque Country (UPV/EHU)

San Sebastián, Spain

About the group
The Computer Vision and Pattern Discovery (CVPD) group at the University of the Basque Country (UPV/EHU) focuses on developing novel computer vision and machine learning methods for the quantitative analysis of biological and biomedical images. Our research aims to design interpretable and data-efficient AI models capable of handling the challenges of microscopy imaging — including data scarcity, variability across imaging modalities, and multiscale integration. We work at the interface of computer science, physics, and biology, combining algorithmic innovation with strong collaborations in the life sciences. Within AIM-Net, the CVPD group contributes expertise in deep learning for bioimage analysis, with applications ranging from the segmentation and tracking of subcellular structures to tissue-level image interpretation. We are committed to open science and reproducibility, actively developing open-source software and benchmark datasets to support the broader imaging and AI communities.
Main research lines
  • Deep learning and computer vision for microscopy image analysis.
  • Multiscale image integration across molecular, cellular, and tissue levels.
  • Self-supervised, few-shot, and interpretable learning frameworks for bioimages.
  • Quantitative modeling of biological processes from imaging data.
Key techniques
  • 2D, 3D, and 4D image segmentation and instance detection.
  • Domain adaptation and generalization for microscopy datasets.
  • Foundation models and self-supervised learning in bioimaging.
  • Development of reproducible open-source pipelines.
Key members

Fadi Dornaika — Co-Principal Investigator.

Nagore Barrena — Associate Professor.

• Unai Elordi — Associate Professor.

Contact
ignacio.arganda@ehu.eus

Oriol Gallego

Biophysics in Cell Biology

Universitat Pompeu Fabra (UPF)

Barcelona, Spain

About the group
The main target of our research is membrane dynamics, and our favorite model organism is the budding yeast. We combine advanced microscopy, biochemistry and data modelling to understand the concerted action of protein networks and the mechanisms that preserve cellular functions under environmental threats, with the aim of bridging quantitative cell biology and environmental sciences.
Main research lines
  • Development of quantitative microscopy for structural biology (e.g. PICT, automatized pipelines for SPT analysis)
  • Integrative structural biology: Modelling molecular interactions in 3D by using quantitative live-cell imaging measurements as constraints.
  • Structural cell biology: We investigate cell mechanisms in situ by integrating SLML, SPT and cryo-CLEM
Key techniques
PICT, SMLM, cryo-CLEM, SPT
Key members

Sébastien Tosi — Staff scientist. Senior bioimage analyst.

Xavier Sanjua — Technical support, Maintenance of microscope systems.

Contact
oriol.gallego@upf.edu

Jonathan Heras

Grupo de Informática de la Universidad de La Rioja

Universidad de la Rioja (ULR)

Logroño, Spain

About the group
The Grupo de Informática de la Universidad de La Rioja is an interdisciplinary research team with expertise in artificial intelligence, computer vision, pattern recognition, database and natural language processing. Since its foundation in 2015, the group has advanced innovative approaches for complex computational problems, bridging theory and real-world applications.
Main research lines
Reliable, traceable, and explainable multimodal agents in healthcare: Fundamentals, models and applications: development of methods that combine natural language processing and computer vision to analyse biomedical images.
Key techniques
  • Deep learning methods for computer vision in biomedicine
  • Image processing in biomedicine
Key members

• Gadea Mata Martínez. Lecturer — Expert in biomedical image processing.

Contact
jonathan.heras@unirioja.es

Maria Pia Cosma

Reprogramming & Regeneration Laboratory

Centre for Genomic Regulation (CRG)

Barcelona, Spain

About the group
The main interests of Cosma’s group are to dissect the mechanisms and factors that control somatic cell reprogramming and tissue regeneration in mammals. In this context, we study chromatin organization and 3D genome folding and looping in somatic, stem, and cancer cells. We have developed an integrated and innovative methodology that combines state-of-the-art super-resolution microscopy with genomic approaches, providing new perspectives on genome structure and regulation.
Main research lines
Studying the 3D genome organization and looping in somatic, stem and cancer cells.
Key techniques
Single molecule localization microscopy, stem cell biology.
Contact
pia.cosma@crg.es

Jose Requejo Isidro

Single Molecule Optical Spectroscopy

Centro Nacional de Biotecnologia (CNB-CSIC)

Madrid, Spain

About the group
Jose Requejo-Isidro’s research interest sits at the interface of applied physics, optics and biology. He is focused on the physics of molecular events at biomembranes, a problem he addresses using single-molecule imaging techniques, advanced imaging spectroscopy and stochastic modelling. This quantitative description of molecular events provides insights inaccessible through conventional biochemistry techniques deepening our understanding of the physical basis of biological processes. His research has a strong emphasis on the development and application of novel fluorescence imaging methodologies.
Main research lines
Physical basis of molecular events at biomembranes, Single Molecule Imaging and Spectroscopy, Stochastic Modelling.
Key techniques
Single Molecule Imaging, Hidden Markov Modelling, Quantitative Imaging Spectroscopy (FLIM, FCS, Imaging Membrane Packing & Tension), Single Molecule FRET.
Contact
jose.requejo@csic.es

Carlos Ortiz de Solórzano

Laboratory of Microphysiological Systems and Quantitative Biology

Centro de Investigación Médica Aplicada, Universidad de Navarra (CIMA-UNAV)

Pamplona, Spain

About the group
The group, integrated in the Cancer Center Clínica Universidad de Navarra, develops microphysiological systems to validate hypotheses and test drug effectiveness. These systems, which simulate the cellular composition and physiology of specific tissues through the development of three-dimensional cultures in microfluidic support (organ-on-chip), are useful in a wide variety of biomedical research areas. In our laboratory these systems are applied to the study of pancreatic cancer and infectious processes in the airways of patients with chronic obstructive pulmonary disease (COPD). On the other hand, the group develops tools for analysis and quantification of biomedical images, aimed at improving research and diagnosis of different diseases. In particular, these tools are applied to the analysis and interpretation of multidimensional microscopy images, which can be included within the concept of Computational Pathology, mainly in the context of the study of cancer, as well as radiological images for non-invasive diagnosis and monitoring of prevalent diseases (COPD, lung cancer, Parkinson's disease, Lewy Body dementia).
Main research lines
  • Development of quantitative image analysis algorithms for to the detection and study of the genetics and etiology of cancer.
  • Implementation of cell segmentation and tracking algorithms for the study of the mechanobiology of cell migration.
  • Development of novel image filtering, registration and segmentation methods.
  • Non-invasive imaging of the disease in both humans and pre-clinical models.
  • Development of combined microscopy and microfluidic-based solutions for cell and organ-on-a-chip assays.
  • Development of liquid biopsy systems based on microfluidic systems.
Key techniques
  • AI based Cell Segmentation and Tracking.
  • Computational Pathology tools for Multispectral Immunostained Samples.
  • Tools for Spatial Transcriptomic Analysis.
Contact
codesolorzano@unav.es

Armando del Río Hernández

Cellular and  Molecular Biomechanics Laboratory

Universidad Carlos III de Madrid (UC3M)

Getafe, Spain

About the group

The research group led by Armando del Rio at UC3M focuses on the biomechanical and biophysical regulation of cells and tissues in health and disease. The lab works to understand how mechanical forces, physical constraints, and microenvironmental cues shape cellular behavior, tissue organization, and pathological progression. By integrating approaches from cell biology, physics, engineering, and quantitative imaging, the group seeks to uncover fundamental mechanisms by which cells sense, generate, and respond to mechanical stimuli.

A central theme of the group’s work is understanding how mechanical regulation influences processes such as morphogenesis, tissue homeostasis, and disease development, including cancer. The lab develops and applies advanced experimental platforms (combining microfabrication, live-cell imaging, and computational modeling) to measure forces and mechanical properties across scales, from single cells to multicellular systems.

Through this interdisciplinary strategy, the group aims to bridge molecular mechanisms with tissue-level dynamics, contributing to a predictive understanding of how mechanical regulation controls complex biological systems. Their research provides insights with potential implications for regenerative medicine, cancer biology, and mechanobiology-driven therapeutic strategies.

Main research lines
  • Multiscale mechanobiology and mechanotransduction: Investigating how mechanical forces regulate protein conformation, cytoskeletal organization, and cell signalling. Using quantitative microscopy and bioengineering tools, this line aligns with AIM-Net’s multiscale framework linking physical cues to cellular function.
  • Force-sensitive adhesion and integrin signalling: Studying mechanosensitive proteins (e.g., talin/vinculin) and force-dependent signalling pathways controlling cell fate and disease progression through quantitative imaging and molecular perturbation.
  • Biomechanics of the tumour microenvironment: Characterising how stromal mechanics and extracellular matrix stiffness regulate breast and pancreatic cancer progression, integrating biomechanical measurements with imaging-based analysis.
  • Microfluidic platforms for biomarker discovery: Developing microfluidic systems for isolation and imaging-based analysis of circulating biomarkers, supporting early and minimally invasive cancer detection.
Key techniques
  • Confocal and advanced microscopy for high-resolution imaging of cellular and molecular mechanobiology.
  • Elastic pillar arrays to quantify cellular traction forces and substrate mechanics.
  • Protein expression and purification enabling mechanistic and structural studies of mechanosensitive proteins.
  • Tissue culture systems for controlled mechanobiological experiments in cells relevant to cancer and stromal biology.
  • Atomic Force Microscopy for nanomechanical probing of cells and biomolecules.
  • Single-Molecule Force Spectroscopy to investigate force-dependent molecular level.
  • Magnetic tweezers for precise application and measurement of forces at the molecular level.
  • Microfluidics for mechanical manipulation, biomarker isolation, and integrated bioengineering assays.
Contact
mamunozb@ing.ucm.es

Partners

Isabel Peset Martin

Conofocal Microscopy Unit

Centro Nacional de Investigaciones Oncológicas (CNIO)

Madrid, Spain

About the group
The Confocal Microscopy Unit at the Spanish National Cancer Research Centre (CNIO) provides advanced imaging technologies and expertise to support cancer research. Our mission is to enable high-quality, quantitative imaging for studies ranging from live-cell dynamics to complex tissue architecture. A key focus of the unit is on digital pathology and AI-assisted image analysis, integrating high-content microscopy with computational approaches to extract meaningful biological insights from complex datasets. We collaborate closely with researchers to develop and implement imaging and analysis workflows tailored to specific scientific and translational questions. Our multidisciplinary team brings together expertise in optical microscopy, cell biology, image analysis, and data science. We are committed to fostering innovation, training, and collaboration within CNIO and the broader biomedical imaging community.
Main research lines
Develop AI-asssited image analysis methods for automatic pattern recognitation of tumour invation Cell phenotyping and spatial relation wihtin the tissue arquitecture in 2D and 3D Morphological cellular profiling by tailored cell painting methods for Phenotypic screening, Mechanism-of-action studies, AI-driven drug discovery.
Key techniques
Multiplex, High-Content Imaging (HCI or HCS), Whole Slide Imaging (WSI), Advanced microscopy methods, Tissue Image analysis, Deep Learning models for tissue classification and cell segmentation.
Key members

Ana Cayuela — Bioimage analyst.

Maria Calvo — Data Scientist and AI.

Manuel Pérez — Image specialist.

Contact
ipeset@cnio.es

Maria Victoria Neguembor

Chromatin Folding and Nanoscopy

Molecular Biology Institute of Barcelona (IBMB-CSIC)

Barcelona, Spain

About the group
Our research group focuses on understanding the interplay between genome organization and gene function. We employ cutting-edge techniques such as super-resolution microscopy and we develop tools to investigate chromatin topology and its impact on cellular processes like transcription, as well as on differentiation and disease.
Main research lines
Chromatin folding and Dynamics: we study the interplay between cohesin and topoisomerases and their impact in chromatin topology. Gene folding and dynamics in super-resolution: we develop tools to visualize chromatin folding and motion in single cells. Topoquest: we explore the role of topoisomerases in chromatin organization and gene regulation.
Key techniques
• Super-resolution microscopy (STORM, DNA-PAINT, Oligopaints/OligoSTORM) • Single-molecule tracking • CRISPR-based methods for visualizing endogenous loci (PoSTAC) • Multimolecular SR imaging (Nucleotides + Proteins) and modeling (iOS, MiOS) • Epigenomic/Transcriptomics techniques: ChIP-seq, RNA-seq
Key members

ria Helena de Donato Pérez — PhD student.

Alba Sitjes Tomás — PhD student.

Irene Cortés Ferreño — MSc Student.

Contact
vnebmc@ibmb.csic.es

Arrate Muñoz Barrutia

Computational Imaging for Biomedical Discovery

Universidad Carlos III de Madrid (UC3M)

Getafe, Spain

About the group

The Computational Imaging for Biomedical Discovery group and Universidad Carlos III de Madrid (UC3M), led by Prof. Arrate Muñoz Barrutia, develops artificial intelligence and computational modelling frameworks to understand complex diseases through quantitative imaging and multimodal data integration. The group combines bioimage analysis, machine learning, and multiscale modelling to transform heterogeneous biomedical data into reproducible and clinically meaningful insights.

Research spans computational oncology -linking 3D histology, tumour microenvironment organization, and mechanobiology- with neurodegeneration modelling, including prediction of Alzheimer’s disease biomarkers from sleep EEG data. The group is strongly committed to open science and sustainable AI, leading developments such as deepImageJ and contributing to the BioImage Model Zoo within the European AI4Life infrastructure.

Through international collaborations and leadership in benchmarking initiatives (e.g., Cell Tracking Challenge), the group promotes robust, FAIR, and deployable AI technologies that bridge methodological innovation and real biomedical applications.

Main research lines
  • AI-driven quantitative bioimaging for robust, reproducible extraction of information from complex biomedical imaging data, including foundation models, benchmarking, and sustainable AI practices.
  • Computational oncology and tumor microenvironment modelling, integrating 3D histology, spatial analysis, and mechanobiology to derive computational biomarkers for precision medicine.
  • Multiscale modelling and FAIR data infrastructures, connecting molecular to organ-level information through open, interoperable platforms aligned with European research infrastructures.
Key techniques
  • AI-based bioimage analysis (segmentation, tracking, restoration, domain adaptation, foundation models).
  • 3D histological reconstruction and spatial tissue modelling for tumour microenvironment characterization.
  • Multimodal data integration frameworks (imaging, EEG, molecular biomarkers).
  • Quantitative mechanobiology image analysis linking physical cues with cellular phenotypes.
  • Benchmarking and validation methodologies (challenge organization, objective performance assessment).
  • FAIR and interoperable AI deployment tools (deepImageJ, BioImage Model Zoo integration).
Contact
mamunozb@ing.ucm.es