Posts

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

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

Stefan M. Fischer’s submission to the MICCAI2023 Lymph Node Quantification Challenge won the 3rd price. Therefore, the challenge team was invited for a presentation at MICCAI 2023 and to a Special Issue Submission at the MELBA Journal.

Hannah Eichhorn has been elected as Trainee Representative of the ISMRM Motion Detection & Correction Study Group. She started her term at the ISMRM Annual Meeting in Singapore in the beginning of May.

The Alfred Breit Prize 2024 of the Radiological Society was awarded to Prof. Julia Schnabel, Professor at the Technical University of Munich and Director at the Institute of Machine Learning in Biomedical Imaging at Helmholtz Munich.

Anna Reithmeir’s paper ‘Learning Physics-Inspired Regularization for Medical Image Registration with Hypernetworks’ was accepted at SPIE Medical Imaging 2024 which was held 18-22 Feb. 2024 in San Diego, US. The paper is among the finalists for the best student paper award.

Johannes Kiechle’s paper has been accepted to be presented at International Symposium on Biomedical Imaging 2024 Annual Meeting in Athens. Johannes Kiechle will present his work “Unifying Local and Global Shape Descriptors to Grade Soft-Tissue Sarcomas using Graph Convolutional Networks”.

Johannes Kiechle’s abstract has been accepted to be presented as an oral at The European SocieTy for Radiotherapy and Oncology (ESTRO) 2024 Annual Meeting in Glasgow. Johannes Kiechle will present his work “Investigating the role of morphology in deep learning-based liposarcoma grading” on Monday, 06 May 2024.