3 papers
cs.CV2025
ViConEx-Med: Visual Concept Explainability via Multi-Concept Token Transformer for Medical Image Analysis
Cristiano PatrÃcio, LuÃs F. Teixeira, João C. Neves
Concept-based models aim to explain model decisions with human-understandable concepts. However, most existing approaches treat concepts as numerical attributes, without providing…
cs.CV2025
CBVLM: Training-free Explainable Concept-based Large Vision Language Models for Medical Image Classification
Cristiano PatrÃcio, Isabel Rio-Torto, Jaime S. Cardoso +2
The main challenges limiting the adoption of deep learning-based solutions in medical workflows are the availability of annotated data and the lack of interpretability of such syst…
cs.CV2025
Unsupervised contrastive analysis for anomaly detection in brain MRIs via conditional diffusion models
Cristiano PatrÃcio, Carlo Alberto Barbano, Attilio Fiandrotti +4
Contrastive Analysis (CA) detects anomalies by contrasting patterns unique to a target group (e.g., unhealthy subjects) from those in a background group (e.g., healthy subjects). I…