Daniel Truhn

Counterfactual Diffusion Models for Interpretable Explanations of Artificial Intelligence Models in Pathology

MoPaDi generates counterfactual explanations for histopathology images to reveal morphological features driving classifier predictions, improving interpretability in digital pathology.

Oncodevelopmental plasticity of the skeleton in myeloid neoplasms

This study identifies a novel mechanism in myelofibrosis where a single mutation drives both bone formation and resorption, revealing THBS1 as a therapeutic target.

Swarm learning for decentralized artificial intelligence in cancer histopathology

This paper demonstrates swarm learning for training AI models on decentralized histopathology data to predict molecular features in colorectal cancer.

Adversarial attacks and adversarial robustness in computational pathology

This paper evaluates adversarial robustness of CNNs and ViTs in computational pathology, finding ViTs are more robust to attacks.

Benchmarking artificial intelligence methods for end-to-end computational pathology

This study benchmarks AI methods for end-to-end computational pathology, showing ResNet and ViT outperform MIL and CLAM in mutation prediction but not in tumor subtyping.

Breaking Medical Data Sharing Boundaries by EmployingArtificial Radiographs

This paper introduces a method to generate high-resolution artificial radiographs using generative models to overcome data sharing barriers in medicine.