Posts

Two members of our lab were recognized with Best Paper Awards at this year’s CHC Summer Awards at Helmholtz Munich (📸 from the award ceremony):

Temporal Neural Cellular Automata: Application to modeling of contrast enhancement in breast MRI Daniel Lang, Richard Osuala, Veronika Spieker, Karim Lekadir, Rickmer Braren, Julia Schnabel (https://arxiv.org/abs/2506.18720) Influence of Classification Task and Distribution Shift Type on OOD Detection in Fetal Ultrasound

Anneliese Riess’s abstract has been accepted for presentation as a poster at the Helmholtz AI Conference 2025 in Karlsruhe. She presented her work, “Bounding the Success of Real-World Data Reconstruction Attacks with Differential Privacy,” on Tuesday, June 3, 2025.

Zeyad Mahmoud’s abstract has been selected for an oral presentation at the Helmholtz Imaging Conference 2025. Zeyad presented his Master’s thesis research, titled “Unsupervised Temporal Diffusion-Based Interpolation for 4D CT”. In this study, he investigated the ability of deep generative models, specifically diffusion models, for interpolating temporal 4D chest CT scans.

Four abstracts from our group have been accepted at the 2025 ISMRM & ISMRT Annual Meeting.

MCML Junior Member Anna Reithmeir is writing her doctoral thesis at the Chair of Computational Imaging and AI in Medicine at TUM. Her work addresses the complexity of aligning images from different times or modalities, enabling the comparison of anatomical changes such as tumor growth.

Evaluating Normative Representation Learning in Generative AI for Robust Anomaly Detection in Brain Imaging" by Cosmin I. Bercea et al. has been accepted for publication in Nature Communications.

Selective Test-Time Adaptation using Neural Implicit Representations for Unsupervised Anomaly Detection [Best Paper Award] Sameer Ambekar, Julia Schnabel, and Cosmin I. Bercea. https://arxiv.org/abs/2410.03306 MedEdit: Counterfactual Diffusion-based Image Editing on Brain MRI

Diffusion Models with Implicit Guidance for Medical Anomaly Detection Cosmin I. Bercea, Benedikt Wiestler, Daniel Rueckert, and Julia A. Schnabel (https://arxiv.org/abs/2403.08464) Physics-Informed Deep Learning for Motion-Corrected Reconstruction of Quantitative Brain MRI