EIBIR Session

EIBIR 7 - Artificial intelligence (AI) for health imaging: pioneering cancer image repositories for diagnosis and analysis

February 29, 08:00 - 09:00 CET

6 min
Chairperson's introduction
Luis Marti-Bonmati, Valencia / Spain
12 min
CHAIMELEON: accelerating the lab to market transition of AI tools for cancer management
Alejandro Vergara, Valencia / Spain
1. To learn how to build pan-cancer imaging and multi-omics data registries in a public-private collaborative environment.
2. To understand how to overcome challenges related to image quality heterogeneity across European sites.
3. To appreciate the main challenges to be solved by the AI community in different types of solid tumours.
12 min
EuCanImage: towards a European cancer imaging platform for enhanced AI in oncology
Maciej Bobowicz, Gdansk / Poland
1. To learn about European infrastructures for large-scale biomedical data.
2. To appreciate how these infrastructures can be leveraged to build secure cancer imaging repositories.
3. To understand how these cancer imaging repositories can enhance AI in cancer imaging.
12 min
INCISIVE: a federated data infrastructure enabling AI-supported cancer diagnosis and prediction
Gianna Tsakou, Marousi / Greece
1. To elaborate on benefits and challenges related to decentralised data storage.
2. To elaborate on how health data sharing empowers AI-supported tools for cancer diagnosis and prediction.
3. To highlight the role of healthcare professionals in the development of AI tools.
12 min
ProCancer-I: AI models of prostate cancer diagnosis
Nikolaos Papanikolaou, Lisbon / Portugal
1. To elaborate on challenges in a multicentric setup.
2. To present initial results focusing on AI-powered prostate cancer detection and characterisation.
3. To discuss safe translation to the clinics.
6 min
EUCAIM: integrating the AI for health imaging results into the European Cancer Imaging Initiative
Luis Marti-Bonmati, Valencia / Spain
1. To learn how a pan-European digital federated infrastructure of cancer-related images and data can be used for the development of AI tools toward precision medicine.
2. To appreciate the seamless access to de-identified, high-quality real-world data, to foster collaboration among clinicians, researchers, and innovators.
3. To understand how AI data-driven decisions can be designed in diagnosis and treatment.