Project Background

Personalised cancer treatment remains a major challenge, as standard protocols often fail to account for the unique biological complexity of individual tumours. One critical factor is the tumour microenvironment (TME), which significantly impacts drug resistance and treatment outcomes. Currently, clinicians lack tools that can simulate how a patient’s tumour might respond to specific drugs based on its unique cellular and molecular makeup.

CancerScan addresses this gap by developing an innovative digital pathology slide scanner capable of generating patient-specific tumour digital twins. These twins integrate multi-omics data and histopathology to model tumour behaviour and simulate treatment effects. CancerScan combines expertise in biology, AI, and hardware engineering to capture tumour communication patterns, and translate them into personalised simulations.

By embedding this capability directly into diagnostic workflows, CancerScan lays the foundation for a new class of decision-support tools that empower clinicians to determine exactly which drug works best for a particular patient, at what time, in what sequence, and in what dose.

Project Objectives

MAP

the influence of the tumour microenvironment (TME) on the efficacy of chemotherapeutic treatments.

DEVELOP

a standardised knowledge graph that integrates experimental, public, and ontological data to represent the TME’s influence on drug efficacy.

LEARN

the proto-grammar of tumour communication identifying structural properties and implementing statistical pattern analysis and machine learning.

DESIGN & VALIDATE

a platform for the automated generation of tumour digital twins for specific tumour scenarios.

CREATE

an embedded hardware/ software system for automating the creation of tumour digital twins from digital slides and getting simulation results.

BOOST

awareness of the project outcomes through communication and dissemination activities and engage main target groups.

Project Facts

August 2025 – July 2028

Programme

Horizon Europe

HORIZON-EIC-2024-PATHFINDEROPEN-01-01

HORIZON-EIC (HORIZON EIC Grants)

Grant ID

101186829

Coordinator

Agencia Estatal Consejo Superior de Investigaciones Científicas

Project Methodology

Tumour Models & Drug Testing

Develop tumour organoids with different microenvironments to reflect real patient conditions. Apply treatments and study how different conditions influence drug response.

Data Structuring & Knowledge Base

Convert experimental results into structured digital data. Build a shared knowledge system combining project data with public scientific resources.

Digital Twin Creation

Use insights from biology and data analysis to build digital tumour models that simulate treatment effects for individual patients.

Integration & Validation

Embed the system into a smart scanner. Validate results with clinical data, ensure ethical compliance, and support future use through open science.

Project Impacts

IMPACT 1

ENABLED smarter diagnosis and treatment planning in cancer care by developing a new digital pathology tool that supports personalised decisions and improves treatment outcomes.

IMPACT 2

REDUCED healthcare costs through better first-line therapies and fewer recurrences, supporting a more efficient and sustainable cancer care system across Europe.

IMPACT 3

SUPPORTED uptake of precision oncology by integrating AI-driven models, digital twins, and omics data, aligned with EU policies and cancer initiatives.

IMPACT 4

BOOSTED innovation and job creation in digital health by linking interdisciplinary expertise to accelerate diagnostics, data use, and personalised medicine.

IMPACT 5

STRENGTHENED public trust in cancer care through more accurate diagnoses and improved survival, helping patients return to daily life faster.

IMPACT 6

CONTRIBUTED to a connected and secure European health data space by building tools in line with IHE standards and EU efforts in data interoperability.

Project Structure

WP 1

CHARACTERISE: Organoid Models, Drug Testing, Biomarker Profiling, and Clinical Alignment

The main objective of WP1 is to develop advanced tumour organoids, study treatment effects, and analyse key biological signals to support comparison with clinical samples and guide personalised therapeutic strategies.

WP 2

STRUCTURE: Data Modelling, Image Analysis, Interaction Networks, and Knowledge Graph Integration

The main objective of WP2 is to develop a flexible digital framework that organises complex biological data into structured models and knowledge graphs to support analysis, simulation, and personalised insights.

WP 3

SIMULATE: Tumour Communication Patterns, Digital Twin Development, and Multi-Level Validation

The main objective of WP3 is to model tumour communication, build a digital twin from experimental data, and validate it through simulations and comparisons with laboratory and clinical reference points.

WP 4

EMBED: Simulator Optimisation, Hardware Integration, and Proof of Concept

The main objective of WP4 is to optimise the simulator, co-design hardware/software architecture, and embed it into a functional concept for real-world testing and use.

WP 5

MANAGE: Coordination, Communication, Dissemination, Exploitation, and Impact Monitoring

The main objective of WP5 is to ensure smooth project execution, promote visibility and uptake of results, protect intellectual property, and lay the foundation for future commercial and societal impact.

Project Deliverables

  • D1.2 Images of tumor organoids
  • D1.3 Clinical validation
  • D2.1 First draft of the semantic model
  • D3.2 Tumor proto-grammar
  • D3.4 Validation testing
  • D3.5 Uncertainty analysis
  • D4.1 Front-end definition and formats
  • D4.2 Metrics of HW/SW partitioning
  • D4.4 Proof-of-concept
  • D5.1 Website and project logo
  • D5.4 Data management plan (i)
  • D5.9 Data Management Plan (ii)