The Second International Workshop on Trustworthy Artificial Intelligence for Healthcare (TAI4H) 

Scope and Topics

The manuscript and final version are up to 12 pages excluding references and supplementary materials. We invite both types of papers for oral and poster presentations. We also welcome perspectives and poster papers to discuss major challenges and future trends. 

Interested topics will include, but not be limited to:

• Generalization to out-of-distribution samples.  

• Explainability of machine learning models in healthcare.  

• Reasoning, intervening, or causal inference.  

• Debiasing AI models from learning from shortcuts.  

• Fairness in medical imaging.  

• Uncertainty estimation of machine learning models and medical data.  

• Privacy-preserving AI for medical data.  

• Learning informative and discriminative features under weak annotations.  

• Human-machine cooperation (human-in-the-loop, active learning, etc.) in healthcare, such as medical image analysis.  

• Multi-modal fusion and learning, such as computed tomography (CT), magnetic resonance imaging (MRI), ultrasound, pathology, genetics, electronical healthcare records, etc.  

• Adversarial attack and defence in healthcare.  

• Benchmarks that quantify the trustworthiness of AI models in medical imaging tasks.  

• Foundation model pre-training and adaptation.