David Zimmerer
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
David Zimmerer has a total of 75 co-authors. Here are the top co-authors by number of shared publications:
Klaus Maier-Hein
German Cancer Research Center (DKFZ) Heidelberg, Division of Medical Image Computing
6 shared publicationsJens Petersen
German Cancer Research Center
5 shared publications- Lena Maier-Hein
German Cancer Research Center
4 shared publications Fabian Isensee
German Cancer Research Center
3 shared publicationsAnnika Reinke
German Cancer Research Center
2 shared publicationsAntanas Kascenas
University of Glasgow
2 shared publications
Latest Publications
- Open Access
CRONOS: Continuous Time Reconstruction for 4D Medical Longitudinal Series
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 single prior scan, fixed grid times, or target global labels, which limits voxel-level forecasting under irregular sampling. We present CRONOS, a unified framework for many-to-one prediction from multiple past scans that supports both discrete (grid-based) and continuous (real-valued) timestamps in one model, to the best of our knowledge the first to achieve continuous sequence-to-image forecasting for 3D medical data. CRONOS learns a spatio-temporal velocity field that transports context volumes toward a target volume at an arbitrary time, while operating directly in 3D voxel space. Across three public datasets spanning Cine-MRI, perfusion CT, and longitudinal MRI, CRONOS outperforms other baselines, while remaining computationally competitive. We will release code and evaluation protocols to enable reproducible, multi-dataset benchmarking of multi-context, continuous-time forecasting.
Open AccessCRONOS: Continuous Time Reconstruction for 4D Medical Longitudinal Series
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 single prior scan, fixed grid times, or target global labels, which limits voxel-level forecasting under irregular sampling. We present CRONOS, a unified framework for many-to-one prediction from multiple past scans that supports both discrete (grid-based) and continuous (real-valued) timestamps in one model, to the best of our knowledge the first to achieve continuous sequence-to-image forecasting for 3D medical data. CRONOS learns a spatio-temporal velocity field that transports context volumes toward a target volume at an arbitrary time, while operating directly in 3D voxel space. Across three public datasets spanning Cine-MRI, perfusion CT, and longitudinal MRI, CRONOS outperforms other baselines, while remaining computationally competitive. We will release code and evaluation protocols to enable reproducible, multi-dataset benchmarking of multi-context, continuous-time forecasting.
- Open Access
- 15 July 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 196 (Pt A) , 110640
Leveraging foundation models for content-based image retrieval in radiology
- 15 July 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 196 (Pt A) , 110640
Open AccessLeveraging foundation models for content-based image retrieval in radiology
- 13 April 2025
- Published by Springer Nature
- p. 15-25
Back to the Future: Challenges of Sparse and Irregular Medical Image Time Series
- 13 April 2025
- Published by Springer Nature
- p. 15-25
Back to the Future: Challenges of Sparse and Irregular Medical Image Time Series
- 3 October 2024
- Published by Springer Nature
- p. 138-148
Beyond Heatmaps: A Comparative Analysis of Metrics for Anomaly Localization in Medical Images
- 3 October 2024
- Published by Springer Nature
- p. 138-148
Beyond Heatmaps: A Comparative Analysis of Metrics for Anomaly Localization in Medical Images
- Top Cited PapersOpen Access
- 25 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 41 (10) , 2728-2738
MOOD 2020: A Public Benchmark for Out-of-Distribution Detection and Localization on Medical Images
Detecting Out-of-Distribution (OoD) data is one of the greatest challenges in safe and robust deployment of machine learning algorithms in medicine. When the algorithms encounter cases that deviate from the distribution of the training data, they often produce incorrect and over-confident predictions. OoD detection algorithms aim to catch erroneous predictions in advance by analysing the data distribution and detecting potential instances of failure. Moreover, flagging OoD cases may support human readers in identifying incidental findings. Due to the increased interest in OoD algorithms, benchmarks for different domains have recently been established. In the medical imaging domain, for which reliable predictions are often essential, an open benchmark has been missing. We introduce the Medical-Out-Of-Distribution-Analysis-Challenge (MOOD) as an open, fair, and unbiased benchmark for OoD methods in the medical imaging domain. The analysis of the submitted algorithms shows that performance has a strong positive correlation with the perceived difficulty, and that all algorithms show a high variance for different anomalies, making it yet hard to recommend them for clinical practice. We also see a strong correlation between challenge ranking and performance on a simple toy test set, indicating that this might be a valuable addition as a proxy dataset during anomaly detection algorithm development.
- 25 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 41 (10) , 2728-2738
Top Cited PapersOpen AccessMOOD 2020: A Public Benchmark for Out-of-Distribution Detection and Localization on Medical Images
Detecting Out-of-Distribution (OoD) data is one of the greatest challenges in safe and robust deployment of machine learning algorithms in medicine. When the algorithms encounter cases that deviate from the distribution of the training data, they often produce incorrect and over-confident predictions. OoD detection algorithms aim to catch erroneous predictions in advance by analysing the data distribution and detecting potential instances of failure. Moreover, flagging OoD cases may support human readers in identifying incidental findings. Due to the increased interest in OoD algorithms, benchmarks for different domains have recently been established. In the medical imaging domain, for which reliable predictions are often essential, an open benchmark has been missing. We introduce the Medical-Out-Of-Distribution-Analysis-Challenge (MOOD) as an open, fair, and unbiased benchmark for OoD methods in the medical imaging domain. The analysis of the submitted algorithms shows that performance has a strong positive correlation with the perceived difficulty, and that all algorithms show a high variance for different anomalies, making it yet hard to recommend them for clinical practice. We also see a strong correlation between challenge ranking and performance on a simple toy test set, indicating that this might be a valuable addition as a proxy dataset during anomaly detection algorithm development.
- 12 February 2020
- Published by Springer Nature
- p. 199
Abstract: Unsupervised Anomaly Localization Using Variational Auto-Encoders
- 12 February 2020
- Published by Springer Nature
- p. 199
Abstract: Unsupervised Anomaly Localization Using Variational Auto-Encoders
- Open Access
A Case for the Score: Identifying Image Anomalies using Variational Autoencoder Gradients
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 anomaly detection has primarily focused on the reconstruction error. We argue instead, that pixel-wise anomaly ratings derived from a Variational Autoencoder based score approximation yield a theoretically better grounded and more faithful estimate. In our experiments, Variational Autoencoder gradient-based rating outperforms other approaches on unsupervised pixel-wise tumor detection on the BraTS-2017 dataset with a ROC-AUC of 0.94.
Open AccessA Case for the Score: Identifying Image Anomalies using Variational Autoencoder Gradients
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 anomaly detection has primarily focused on the reconstruction error. We argue instead, that pixel-wise anomaly ratings derived from a Variational Autoencoder based score approximation yield a theoretically better grounded and more faithful estimate. In our experiments, Variational Autoencoder gradient-based rating outperforms other approaches on unsupervised pixel-wise tumor detection on the BraTS-2017 dataset with a ROC-AUC of 0.94.
- 10 October 2019
- Published by Springer Nature
- p. 289-297
Unsupervised Anomaly Localization Using Variational Auto-Encoders
- 10 October 2019
- Published by Springer Nature
- p. 289-297
Unsupervised Anomaly Localization Using Variational Auto-Encoders