Tommasino / Russo / Bernardini Artificial Intelligence for Biomedical Data

First International Workshop, AIBio 2025, Held in Conjunction with the European Conference on Artificial Intelligence, ECAI 2025, Bologna, Italy, October 25–26, 2025, Proceedings
Erscheinungsjahr 2026
ISBN: 978-3-032-17216-7
Verlag: Springer International Publishing
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 266 Seiten

Reihe: Artificial Intelligence (R0)

This volume constitutes the proceedings of the First International Workshop on Artificial Intelligence for Biomedical Data, AIBio 2025, held in Conjunction with the European Conference on Artificial Intelligence, ECAI 2025, in Bologna, Italy, during October 25–26, 2025.

The 12 full papers and 5 short papers were carefully reviewed and selected from 29 submissions. The papers have been divided into the following topical sections: AI for Disease; Data Generation and Augmentation; Multimodal Techniques; and Image Segmentation. 

The 4 remaining papers included in these proceedings are from the keynote speakers.

Zielgruppe

Research

Autoren/Hrsg.

Tommasino, Cristian

Russo, Cristiano

Bernardini, Michele

Inhaltsverzeichnis

.- AI for Desease.
.- Improving Early Sepsis Onset Prediction Through Federated Learning.
.- Experimenting Federated AI Models for Hematological Diseases.
.- Hearing Impairment Assessment in Infants through Explainable Computer Vision Analysis of Facial Features.
.- Type 2 Diabetes Prediction from multi-center Electronic Health Records in General Practice using Machine Learning.
.- Self-Attention as a Predictor of EEG Anomalies.
.- Cross-dataset Multivariate Time-series Model for Parkinson’s Diagnosis via Keyboard Dynamics.
.- Assessment and Compliance of Personalized Machine Learning Pharmacokinetic Models in the European Regulatory Environment.
.- Data Generation and Augmentation.
.- Knowledge Graph-Enhanced Retrieval-Augmented Generation for Nutrigenetics.
.- Generative Data Augmentation by Dataset Distillation.
.- Semantic Similarity in Radiology Reports via LLMs and NER.
.- From Scarce to Sufficient: Imaginary Image-like Features via Diffusion Models for Imbalanced Medical Data.
.- Flow-Based Synthetic Data Generation: A Unified Approach for Biomedical Tasks.
.- Multimodal Techniques.
.- Multimodal Machine Learning Architecture for Predictive Diagnosis and Treatment of Ophthalmic Diseases.
.- GNN-based Multimodal Analysis of Brain Anatomical and Functional Features for Parkinson’s Disease and Cognitive Decline Detection.
.- Data Donation for Digital Twins in Healthcare: Potential and Challenges in the European Context.
.- Image Segmentation.
.- Quality-Guided Focal Loss: Enhancing Minority Class Detection in Haematological Imaging.
.- Auto-prompting Foundation Models for Clinical Segmentation: The Case of Pathological Scapula.
.- Keynote Papers.
.- Towards Segmenting the Invisible: An End-to-End Registration and Segmentation Framework for Weakly Supervised Tumour Analysis.
.- Transcending the Annotation Bottleneck: AI-Powered Discovery in Biology and Medicine.
.- Increasing Data Availability Through Standardization: Unlocking AI in Digital Pathology.
.- Why accuracy isn’t enough. Rethinking Model Evaluation in Clinical AI with a user-centered utility metric.