The MAIBAI consortium participated to the 2025 IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE), held in Ancona (Italy) from 22 to 24 October 2025, with a special session devoted to the project MAIBAI.
The special session covered different topics, like the development of large-scale and high-quality medical imaging databases, the categorization of data based on clinically relevant subgroups and image acquisition key factors, their integration with synthetic data generated with data-driven information approaches, the AI benchmarking in terms of robustness, accuracy and fairness, and the provision of visual explanation techniques, to make the decision process more transparent and interpretable.
Five contributions were presented, namely:
- AI in breast cancer screening, where is it coming in?
Ruben Van Engen (Dutch Expert Centre for Screening – LRCB, Nijmegen, Netherlands) - Trials and tribulations of collecting sufficient mammography images to cover the various sub-groups within a screening population
Alistair Mackenzie (Royal Surrey NHS Foundation Trust, Guildford, UK) - Role of synthetic data in the development of AI models for breast cancer screening
Alessandra Manzin (Istituto Nazionale di Ricerca Metrologica – INRiM, Torino, Italy) - Practical considerations and quality assessment of breast cancer detection models using mammography
Danny Panknin (Physikalisch-Technische Bundesanstalt – PTB, Berlin, Germany) - Beyond regions of interest: reconciling radiologist expectations with diverse XAI approaches in mammography
Aleksander Sadikov (University of Ljubljana, Faculty of Computer and Information Science, Ljubljana,
Slovenia)