papers

Publications (24)

cs.CV2024

Decoupling Semantic Similarity from Spatial Alignment for Neural Networks

Tassilo Wald, Constantin Ulrich, Gregor Köhler +6

What representation do deep neural networks learn? How similar are images to each other for neural networks? Despite the overwhelming success of deep learning methods key questions…

cs.CV2025

CRONOS: Continuous Time Reconstruction for 4D Medical Longitudinal Series

Nico Albert Disch, Saikat Roy, Constantin Ulrich +5

Forecasting how 3D medical scans evolve over time is important for disease progression, treatment planning, and developmental assessment. Yet existing models either rely on a singl…

cs.CV2025

Visual Prompt Engineering for Vision Language Models in Radiology

Stefan Denner, Markus Bujotzek, Dimitrios Bounias +3

Medical image classification plays a crucial role in clinical decision-making, yet most models are constrained to a fixed set of predefined classes, limiting their adaptability to…

cs.CV2025

Leveraging Foundation Models for Content-Based Image Retrieval in Radiology

Stefan Denner, David Zimmerer, Dimitrios Bounias +8

Content-based image retrieval (CBIR) has the potential to significantly improve diagnostic aid and medical research in radiology. However, current CBIR systems face limitations due…

cs.CV2023

Why is the winner the best?

Matthias Eisenmann, Annika Reinke, Vivienn Weru +122

International benchmarking competitions have become fundamental for the comparative performance assessment of image analysis methods. However, little attention has been given to in…

eess.IV2019

A Case for the Score: Identifying Image Anomalies using Variational Autoencoder Gradients

David Zimmerer, Jens Petersen, Simon A. A. Kohl +1

Through training on unlabeled data, anomaly detection has the potential to impact computer-aided diagnosis by outlining suspicious regions. Previous work on deep-learning-based ano…

cs.LG2018

Context-encoding Variational Autoencoder for Unsupervised Anomaly Detection

David Zimmerer, Simon A. A. Kohl, Jens Petersen +2

Unsupervised learning can leverage large-scale data sources without the need for annotations. In this context, deep learning-based auto encoders have shown great potential in detec…

cs.CV2024

Comparative Benchmarking of Failure Detection Methods in Medical Image Segmentation: Unveiling the Role of Confidence Aggregation

Maximilian Zenk, David Zimmerer, Fabian Isensee +4

Semantic segmentation is an essential component of medical image analysis research, with recent deep learning algorithms offering out-of-the-box applicability across diverse datase…

eess.IV2021

The Federated Tumor Segmentation (FeTS) Challenge

Sarthak Pati, Ujjwal Baid, Maximilian Zenk +29

This manuscript describes the first challenge on Federated Learning, namely the Federated Tumor Segmentation (FeTS) challenge 2021. International challenges have become the standar…

cs.CV2026

nnLandmark: A Self-Configuring Method for 3D Medical Landmark Detection

Alexandra Ertl, Stefan Denner, Robin Peretzke +8

Landmark detection is central to many medical applications, such as identifying critical structures for treatment planning or defining control points for biometric measurements. Ho…

cs.CV2023

CRADL: Contrastive Representations for Unsupervised Anomaly Detection and Localization

Carsten T. Lüth, David Zimmerer, Gregor Koehler +4

Unsupervised anomaly detection in medical imaging aims to detect and localize arbitrary anomalies without requiring annotated anomalous data during training. Often, this is achieve…

eess.IV2023

SAM.MD: Zero-shot medical image segmentation capabilities of the Segment Anything Model

Saikat Roy, Tassilo Wald, Gregor Koehler +5

Foundation models have taken over natural language processing and image generation domains due to the flexibility of prompting. With the recent introduction of the Segment Anything…

cs.LG2019

High- and Low-level image component decomposition using VAEs for improved reconstruction and anomaly detection

David Zimmerer, Jens Petersen, Klaus Maier-Hein

Variational Auto-Encoders have often been used for unsupervised pretraining, feature extraction and out-of-distribution and anomaly detection in the medical field. However, VAEs of…

cs.CV2018

nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation

Fabian Isensee, Jens Petersen, Andre Klein +8

The U-Net was presented in 2015. With its straight-forward and successful architecture it quickly evolved to a commonly used benchmark in medical image segmentation. The adaptation…

eess.IV2021

Continuous-Time Deep Glioma Growth Models

Jens Petersen, Fabian Isensee, Gregor Köhler +9

The ability to estimate how a tumor might evolve in the future could have tremendous clinical benefits, from improved treatment decisions to better dose distribution in radiation t…

cs.CV2023

Biomedical image analysis competitions: The state of current participation practice

Matthias Eisenmann, Annika Reinke, Vivienn Weru +352

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known abou…

eess.IV2020

Context-encoding Variational Autoencoder for Unsupervised Anomaly Detection -- Short Paper

David Zimmerer, Simon Kohl, Jens Petersen +2

Unsupervised learning can leverage large-scale data sources without the need for annotations. In this context, deep learning-based autoencoders have shown great potential in detect…

cs.CV2026

Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation

Jonathan Suprijadi, Raphael Stock, Moritz Langenberg +10

Vision-language models offer a promising path toward automating radiology report generation, but applying them to full 3D CT volumes poses substantial computational challenges. Mod…

cs.CV2025

Temporal Flow Matching for Learning Spatio-Temporal Trajectories in 4D Longitudinal Medical Imaging

Nico Albert Disch, Yannick Kirchhoff, Robin Peretzke +5

Understanding temporal dynamics in medical imaging is crucial for applications such as disease progression modeling, treatment planning and anatomical development tracking. However…

cs.LG2019

Unsupervised Anomaly Localization using Variational Auto-Encoders

David Zimmerer, Fabian Isensee, Jens Petersen +2

An assumption-free automatic check of medical images for potentially overseen anomalies would be a valuable assistance for a radiologist. Deep learning and especially Variational A…

cs.LG2021

GP-ConvCNP: Better Generalization for Convolutional Conditional Neural Processes on Time Series Data

Jens Petersen, Gregor Köhler, David Zimmerer +3

Neural Processes (NPs) are a family of conditional generative models that are able to model a distribution over functions, in a way that allows them to perform predictions at test…

cs.LG2023

Exploring new ways: Enforcing representational dissimilarity to learn new features and reduce error consistency

Tassilo Wald, Constantin Ulrich, Fabian Isensee +4

Independently trained machine learning models tend to learn similar features. Given an ensemble of independently trained models, this results in correlated predictions and common f…

cs.CV2018

Exploiting the potential of unlabeled endoscopic video data with self-supervised learning

Tobias Ross, David Zimmerer, Anant Vemuri +12

Surgical data science is a new research field that aims to observe all aspects of the patient treatment process in order to provide the right assistance at the right time. Due to t…

cs.CV2023

RecycleNet: Latent Feature Recycling Leads to Iterative Decision Refinement

Gregor Koehler, Tassilo Wald, Constantin Ulrich +6

Despite the remarkable success of deep learning systems over the last decade, a key difference still remains between neural network and human decision-making: As humans, we cannot…