AI for Oncology conference - Milan, May 7-8th 2025
- 7 Sections
- 29 Lessons
Session 1 - Data-driven models and platforms
- Francisco-Sanchez Vega - Real-World Data-Driven Models in Oncology
- Leonardo Provenzano - APOLLO 11: a biodata-driven model for lung cancer patients treated with targeted and immunotherapies
- Claes Lundström - AIDA - A triple helix ecosystem for imaging diagnostics
- Daniel Truhn - Federated learning and Swarm Learning for decentralized data sharing
- Oliver Saldanha - ODELIA: A Retrospective Analysis of MRI Data for Breast Cancer Screening
Session 2 - Literacy and Education
- Vanja Misković - Interpreting AI outputs: explanations for patients and carers, from discovery to therapeutic decisions
- Gabriella Pravettoni - Codecision-making tools for improving patients’ choices in NSCLC patients treated with immunotherapy
- Evangelia Christodoulou - Guidelines and metrics for image analysis validation
- Carlo Rossi Chauvenet - From code to Care: navigating regulation and ethics in MedTech
- Lorenzo Righetto - Empowering AI research: how Nature Portfolio Supports Innovative AI Publications
Session 3 - AI in Clinical Research
- Mihaela Aldea - AI-driven biomarkers: how to incorporate and validate them in clinical trials
- Massimo Di Maio - Enhancing the Impact of Real-World Data in Oncology through AI
- Filippo De Braud - The role of AI in Molecular Tumor Boards: the clinician's point of view
- Loic Verlingue - How LLMs can assist Molecular Tumor Boards
- Marina Chiara Garassino - AI for cancer drug discovery in the era of immunotherapy and targeted therapy
- Dean Ho - The CURATE.AI algorithm for treatment response assessment and personalised dosing
Session 4 - AI for Imaging
- Alexander T. Pearson - Digital pathology: where are we in clinical cancer practice?
- Julien Calderaro - Digital pathology for liver cancer and immunotherapy prediction
- Raquel Pérez-Lopez - Radiomics: where are we in clinical cancer practice?
- Luca Boldrini - AI applied to image-guided radiation therapy in colorectal cancer
Session 5 - Multimodal AI
- Mireia Crispin Ortuzar - AI-Driven Multiomic Science for Predictive Cancer Therapy
- Jana Lipkova - Explaining embedded multimodal data in oncology
- Francesco Trovò - I3LUNG: how to select 1st line immunotherapy in NSCLC patient
- Kevin Boehm - Integrating H&E whole-slide images and targeted DNA sequencing data for tumor sub
Keynote Talks
Flash Talks
- Hania Paverd - From radiology reports to early prognostic markers: benchmarking LLMs in chronic liver disease
- Flavia Jacobs - Accelerating Translational Research with Synthetic Data: Enhancing Multi-State Digital Twin Models for Disease State Prediction in Breast Cancer
- Cristina Maria Licciardello - Multimodal Cough Analysis as a Pre-Screening Tool for Lung Cancer Detection
This course provides a comprehensive overview of how artificial intelligence (AI) is being applied in oncology across clinical care, diagnostics, research, and decision support. It is based on recorded lectures and presentations delivered by leading clinicians, data scientists, and researchers during the 3rd AI for Oncology conference held in Milan in May 2025.
Participants will gain exposure to current use cases, limitations, and methodologies in areas such as radiomics, digital pathology, predictive modeling, real-world data integration, and AI-supported clinical trials. Emphasis is placed on the practical aspects of implementing AI in cancer care, including the design of multimodal models, validation strategies, regulatory considerations, and patient-centered decision tools.
Topics are organized into thematic sessions covering
- Data-driven models and real-world datasets in oncology
- AI applications in radiology, pathology, and imaging diagnostics
- Multimodal and multiomic data integration
- Clinical trial design, biomarker discovery, and treatment response prediction using AI
- Ethical, regulatory, and communication aspects of AI in healthcare
The course is aimed at medical professionals, researchers, data scientists, and others involved in oncology or biomedical innovation who seek to understand current AI practices in the field.
Format
- Self-paced video modules from conference presentations
- Approx. 12 hours of recorded content
- Speaker bios included
- No live instruction or assignments
No formal prerequisites, though familiarity with oncology, clinical research, or data science is recommended for full benefit.
You must be logged in to submit a review .
