papers

Publications (8)

cs.CV2026

The TopCoW Challenge -- Topology-Aware Circle of Willis Segmentation for CT and MR Angiography

Kaiyuan Yang, Fabio Musio, Yihui Ma +112

The paper introduces the TopCoW Challenge, a benchmark for automatically segmenting the Circle of Willis in CT and MR angiography using deep learning, and provides a new annotated…

#circle of willis segmentation#angiography#deep learning#benchmark challenge
eess.IV2020

On The Usage Of Average Hausdorff Distance For Segmentation Performance Assessment: Hidden Bias When Used For Ranking

Orhun Utku Aydin, Abdel Aziz Taha, Adam Hilbert +5

Average Hausdorff Distance (AVD) is a widely used performance measure to calculate the distance between two point sets. In medical image segmentation, AVD is used to compare ground…

cs.LG2025

Interplay between Federated Learning and Explainable Artificial Intelligence: a Scoping Review

Luis M. Lopez-Ramos, Florian Leiser, Aditya Rastogi +6

The joint implementation of federated learning (FL) and explainable artificial intelligence (XAI) could allow training models from distributed data and explaining their inner worki…

cs.CV2026

HemExp: Clinically-Guided Latent Diffusion for Modeling Hematoma Expansion

Orhun Utku Aydin, Satoru Tanioka, Tzu I Chuang +7

Hematoma expansion (HE) after spontaneous intracerebral hemorrhage (ICH) is a major determinant of acute triage and treatment decisions in neurosurgical care. However, most existin…

cs.LG2023

From Single-Hospital to Multi-Centre Applications: Enhancing the Generalisability of Deep Learning Models for Adverse Event Prediction in the ICU

Patrick Rockenschaub, Adam Hilbert, Tabea Kossen +3

Deep learning (DL) can aid doctors in detecting worsening patient states early, affording them time to react and prevent bad outcomes. While DL-based early warning models usually w…

eess.IV2025

RELICT: A Replica Detection Framework for Medical Image Generation

Orhun Utku Aydin, Alexander Koch, Adam Hilbert +5

Despite the potential of synthetic medical data for augmenting and improving the generalizability of deep learning models, memorization in generative models can lead to unintended…