11 papers
A Modular Agent for Reliable and Auditable Spatial Relation Verification in CT Scans
Simon Vincent Abel, Heiko Hillenhagen, Michael Götz +3
Reliable spatial understanding is an important prerequisite for future medical vision-language systems that aim to support radiological report generation and structured image under…
SHIFT: Survival Prediction from Incomplete and Heterogeneous Genomic Data
Muhammet Sami Yavuz, Ayhan Can Erdur, Sabri Mustafa Kahya +2
Genomic prediction models often fail to transfer across institutions because sequencing panels differ across sites, creating structural feature missingness at deployment. Existing…
Agentic Large Language Models for Training-Free Neuro-Radiological Image Analysis
Ayhan Can Erdur, Daniel Scholz, Jiazhen Pan +3
State-of-the-art large language models (LLMs) show high performance in general visual question answering. However, a fundamental limitation remains: current architectures lack the…
TumorFlow: Physics-Guided Longitudinal MRI Synthesis of Glioblastoma Growth
Valentin Biller, Niklas Bubeck, Lucas Zimmer +6
Glioblastoma exhibits diverse, infiltrative, and patient-specific growth patterns that are only partially visible on routine MRI, making it difficult to reliably assess true tumor…
MultiMAE for Brain MRIs: Robustness to Missing Inputs Using Multi-Modal Masked Autoencoder
Ayhan Can Erdur, Christian Beischl, Daniel Scholz +4
Missing input sequences are common in medical imaging data, posing a challenge for deep learning models reliant on complete input data. In this work, inspired by MultiMAE [2], we d…
MM-DINOv2: Adapting Foundation Models for Multi-Modal Medical Image Analysis
Daniel Scholz, Ayhan Can Erdur, Viktoria Ehm +4
Vision foundation models like DINOv2 demonstrate remarkable potential in medical imaging despite their origin in natural image domains. However, their design inherently works best…
Contrastive Anatomy-Contrast Disentanglement: A Domain-General MRI Harmonization Method
Daniel Scholz, Ayhan Can Erdur, Robbie Holland +4
Magnetic resonance imaging (MRI) is an invaluable tool for clinical and research applications. Yet, variations in scanners and acquisition parameters cause inconsistencies in image…
Whole-body Representation Learning For Competing Preclinical Disease Risk Assessment
Dmitrii Seletkov, Sophie Starck, Ayhan Can Erdur +3
Reliable preclinical disease risk assessment is essential to move public healthcare from reactive treatment to proactive identification and prevention. However, image-based risk pr…
All Sizes Matter: Improving Volumetric Brain Segmentation on Small Lesions
Ayhan Can Erdur, Daniel Scholz, Josef A. Buchner +3
Brain metastases (BMs) are the most frequently occurring brain tumors. The treatment of patients having multiple BMs with stereo tactic radiosurgery necessitates accurate localizat…
Interpretable 2D Vision Models for 3D Medical Images
Alexander Ziller, Ayhan Can Erdur, Marwa Trigui +9
Training Artificial Intelligence (AI) models on 3D images presents unique challenges compared to the 2D case: Firstly, the demand for computational resources is significantly highe…
Exploiting segmentation labels and representation learning to forecast therapy response of PDAC patients
Alexander Ziller, Ayhan Can Erdur, Friederike Jungmann +3
The prediction of pancreatic ductal adenocarcinoma therapy response is a clinically challenging and important task in this high-mortality tumour entity. The training of neural netw…