8 papers
From Training to Deployment: Post-Hoc Causal Feature Identification via Sensitivity Ratios
Athanasios Vlontzos, Giorgos Papanastasiou, Bernhard Kainz +1
The paper proposes the Normalised Sensitivity Ratio (NSR), a post‑hoc, model‑agnostic method to distinguish causal from spurious features by comparing model sensitivity across envi…
Entangled by Design: Spurious Intra-Variable Signal Routing in Tabular In-Context Learners
Athanasios Vlontzos, Giorgos Papanastasiou, Bernhard Kainz +1
Consider a model trained at a single hospital to predict patient recovery, where the measured feature bundles the patient's true health signal () with a systematic artefact…
Reason Like a Radiologist: Chain-of-Thought and Reinforcement Learning for Verifiable Report Generation
Peiyuan Jing, Kinhei Lee, Zhenxuan Zhang +7
Radiology report generation is critical for efficiency but current models lack the structured reasoning of experts, hindering clinical trust and explainability by failing to link v…
Causally Steered Diffusion for Automated Video Counterfactual Generation
Nikos Spyrou, Athanasios Vlontzos, Paraskevas Pegios +5
Adapting text-to-image (T2I) latent diffusion models (LDMs) to video editing has shown strong visual fidelity and controllability, but challenges remain in maintaining causal relat…
Advancing oncology with federated learning: transcending boundaries in breast, lung, and prostate cancer. A systematic review
Anshu Ankolekar, Sebastian Boie, Maryam Abdollahyan +11
Federated Learning (FL) has emerged as a promising solution to address the limitations of centralised machine learning (ML) in oncology, particularly in overcoming privacy concerns…
A Novel Coronary Artery Registration Method Based on Super-pixel Particle Swarm Optimization
Peng Qi, Wenxi Qu, Tianliang Yao +5
Percutaneous Coronary Intervention (PCI) is a minimally invasive procedure that improves coronary blood flow and treats coronary artery disease. Although PCI typically requires 2D…