Home | Research | Groups | Daniel Rückert

Research Group Daniel Rückert

Link to Daniel Rückert

Daniel Rückert

Prof. Dr.

Director

Artificial Intelligence in Healthcare and Medicine

Daniel Rückert

is Alexander von Humboldt Professor for AI in Medicine and Healthcare at TU Munich. He is also a Professor at Imperial College London.

He gained a MSc from Technical University Berlin in 1993, a PhD from Imperial College in 1997, followed by a post-doc at King’s College London. In 1999 he joined Imperial College as a Lecturer, becoming Senior Lecturer in 2003 and full Professor in 2005. From 2016 to 2020 he served as Head of the Department of Computing at Imperial College. His field of research is the area of Artificial Intelligence and Machine Learning and their application to medicine and healthcare.

Team members @MCML

Link to Niklas Bubeck

Niklas Bubeck

Artificial Intelligence in Healthcare and Medicine

Link to Laurin Lux

Laurin Lux

Artificial Intelligence in Healthcare and Medicine

Link to David Mildenberger

David Mildenberger

Artificial Intelligence in Healthcare and Medicine

Link to Nil Stolt-Ansó

Nil Stolt-Ansó

Artificial Intelligence in Healthcare and Medicine

Link to Reihaneh Torkzadehmahani

Reihaneh Torkzadehmahani

Artificial Intelligence in Healthcare and Medicine

Link to Clara Sophie Vetter

Clara Sophie Vetter

Artificial Intelligence in Healthcare and Medicine

Publications @MCML

[6]
A. H. Berger, L. Lux, N. Stucki, V. Bürgin, S. Shit, A. Banaszaka, D. Rückert, U. Bauer and J. C. Paetzold.
Topologically faithful multi-class segmentation in medical images.
MICCAI 2024 - 27th International Conference on Medical Image Computing and Computer Assisted Intervention. Marrakesh, Morocco, Oct 06-10, 2024. DOI.
Abstract

Topological accuracy in medical image segmentation is a highly important property for downstream applications such as network analysis and flow modeling in vessels or cell counting. Recently, significant methodological advancements have brought well-founded concepts from algebraic topology to binary segmentation. However, these approaches have been underexplored in multi-class segmentation scenarios, where topological errors are common. We propose a general loss function for topologically faithful multi-class segmentation extending the recent Betti matching concept, which is based on induced matchings of persistence barcodes. We project the N-class segmentation problem to N single-class segmentation tasks, which allows us to use 1-parameter persistent homology, making training of neural networks computationally feasible. We validate our method on a comprehensive set of four medical datasets with highly variant topological characteristics. Our loss formulation significantly enhances topological correctness in cardiac, cell, artery-vein, and Circle of Willis segmentation.

MCML Authors
Link to Laurin Lux

Laurin Lux

Artificial Intelligence in Healthcare and Medicine

Link to Nico Stucki

Nico Stucki

Applied Topology and Geometry

Link to Daniel Rückert

Daniel Rückert

Prof. Dr.

Artificial Intelligence in Healthcare and Medicine

Link to Ulrich Bauer

Ulrich Bauer

Prof. Dr.

Applied Topology and Geometry


[5]
B. Jian, J. Pan, M. Ghahremani, D. Rückert, C. Wachinger and B. Wiestler.
Mamba? Catch The Hype Or Rethink What Really Helps for Image Registration.
WBIR @MICCAI 2024 - 11th International Workshop on Biomedical Image Registration at the 27th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2024). Marrakesh, Morocco, Oct 06-10, 2024. DOI.
Abstract

VoxelMorph, proposed in 2018, utilizes Convolutional Neural Networks (CNNs) to address medical image registration problems. In 2021 TransMorph advanced this approach by replacing CNNs with Attention mechanisms, claiming enhanced performance. More recently, the rise of Mamba with selective state space models has led to MambaMorph, which substituted Attention with Mamba blocks, asserting superior registration. These developments prompt a critical question: does chasing the latest computational trends with “more advanced” computational blocks genuinely enhance registration accuracy, or is it merely hype? Furthermore, the role of classic high-level registration-specific designs, such as coarse-to-fine pyramid mechanism, correlation calculation, and iterative optimization, warrants scrutiny, particularly in differentiating their influence from the aforementioned low-level computational blocks. In this study, we critically examine these questions through a rigorous evaluation in brain MRI registration. We employed modularized components for each block and ensured unbiased comparisons across all methods and designs to disentangle their effects on performance. Our findings indicate that adopting “advanced” computational elements fails to significantly improve registration accuracy. Instead, well-established registration-specific designs offer fair improvements, enhancing results by a marginal 1.5% over the baseline. Our findings emphasize the importance of rigorous, unbiased evaluation and contribution disentanglement of all low- and high-level registration components, rather than simply following the computer vision trends with “more advanced” computational blocks. We advocate for simpler yet effective solutions and novel evaluation metrics that go beyond conventional registration accuracy, warranting further research across various organs and modalities.

MCML Authors
Link to Bailiang Jian

Bailiang Jian

Artificial Intelligence in Radiology

Link to Morteza Ghahremani

Morteza Ghahremani

Dr.

Artificial Intelligence in Radiology

Link to Daniel Rückert

Daniel Rückert

Prof. Dr.

Artificial Intelligence in Healthcare and Medicine

Link to Christian Wachinger

Christian Wachinger

Prof. Dr.

Artificial Intelligence in Radiology

Link to Benedikt Wiestler

Benedikt Wiestler

Prof. Dr.

AI for Image-Guided Diagnosis and Therapy


[4]
P. Müller, G. Kaissis and D. Rückert.
ChEX: Interactive Localization and Region Description in Chest X-rays.
ECCV 2024 - 18th European Conference on Computer Vision. Milano, Italy, Sep 29-Oct 04, 2024. DOI. GitHub.
Abstract

Report generation models offer fine-grained textual interpretations of medical images like chest X-rays, yet they often lack interactivity (i.e. the ability to steer the generation process through user queries) and localized interpretability (i.e. visually grounding their predictions), which we deem essential for future adoption in clinical practice. While there have been efforts to tackle these issues, they are either limited in their interactivity by not supporting textual queries or fail to also offer localized interpretability. Therefore, we propose a novel multitask architecture and training paradigm integrating textual prompts and bounding boxes for diverse aspects like anatomical regions and pathologies. We call this approach the Chest X-Ray Explainer (ChEX). Evaluations across a heterogeneous set of 9 chest X-ray tasks, including localized image interpretation and report generation, showcase its competitiveness with SOTA models while additional analysis demonstrates ChEX’s interactive capabilities.

MCML Authors
Link to Georgios Kaissis

Georgios Kaissis

Dr.

Privacy-Preserving and Trustworthy AI

Link to Daniel Rückert

Daniel Rückert

Prof. Dr.

Artificial Intelligence in Healthcare and Medicine


[3]
N. Stolt-Ansó, V. Sideri-Lampretsa, M. Dannecker and D. Rückert.
Intensity-based 3D motion correction for cardiac MR images.
ISBI 2024 - IEEE 20th International Symposium on Biomedical Imaging. Athens, Greece, May 27-30, 2024. DOI.
Abstract

Cardiac magnetic resonance (CMR) image acquisition requires subjects to hold their breath while 2D cine images are acquired. This process assumes that the heart remains in the same position across all slices. However, differences in breathhold positions or patient motion introduce 3D slice misalignments. In this work, we propose an algorithm that simultaneously aligns all SA and LA slices by maximizing the pair-wise intensity agreement between their intersections. Unlike previous works, our approach is formulated as a subject-specific optimization problem and requires no prior knowledge of the underlying anatomy. We quantitatively demonstrate that the proposed method is robust against a large range of rotations and translations by synthetically misaligning 10 motion-free datasets and aligning them back using the proposed method.

MCML Authors
Link to Daniel Rückert

Daniel Rückert

Prof. Dr.

Artificial Intelligence in Healthcare and Medicine


[2]
Y. Zhang, N. Stolt-Ansó, J. Pan, W. Huang, K. Hammernik and D. Rückert.
Direct Cardiac Segmentation from Undersampled K-Space using Transformers.
ISBI 2024 - IEEE 20th International Symposium on Biomedical Imaging. Athens, Greece, May 27-30, 2024. DOI.
Abstract

The prevailing deep learning-based methods of predicting cardiac segmentation involve reconstructed magnetic resonance (MR) images. The heavy dependency of segmentation approaches on image quality significantly limits the acceleration rate in fast MR reconstruction. Moreover, the practice of treating reconstruction and segmentation as separate sequential processes leads to artifact generation and information loss in the intermediate stage. These issues pose a great risk to achieving high-quality outcomes. To leverage the redundant k-space information overlooked in this dual-step pipeline, we introduce a novel approach to directly deriving segmentations from sparse k-space samples using a transformer (DiSK). DiSK operates by globally extracting latent features from 2D+time k-space data with attention blocks and subsequently predicting the segmentation label of query points. We evaluate our model under various acceleration factors (ranging from 4 to 64) and compare against two image-based segmentation baselines. Our model consistently outperforms the baselines in Dice and Hausdorff distances across foreground classes for all presented sampling rates.

MCML Authors
Link to Daniel Rückert

Daniel Rückert

Prof. Dr.

Artificial Intelligence in Healthcare and Medicine


[1]
N. Stolt-Ansó, J. McGinnis, J. Pan, K. Hammernik and D. Rückert.
NISF: Neural implicit segmentation functions.
MICCAI 2023 - 26th International Conference on Medical Image Computing and Computer Assisted Intervention. Vancouver, Canada, Oct 08-12, 2023. DOI.
Abstract

Segmentation of anatomical shapes from medical images has taken an important role in the automation of clinical measurements. While typical deep-learning segmentation approaches are performed on discrete voxels, the underlying objects being analysed exist in a real-valued continuous space. Approaches that rely on convolutional neural networks (CNNs) are limited to grid-like inputs and not easily applicable to sparse or partial measurements. We propose a novel family of image segmentation models that tackle many of CNNs’ shortcomings: Neural Implicit Segmentation Functions (NISF). Our framework takes inspiration from the field of neural implicit functions where a network learns a mapping from a real-valued coordinate-space to a shape representation. NISFs have the ability to segment anatomical shapes in high-dimensional continuous spaces. Training is not limited to voxelized grids, and covers applications with sparse and partial data. Interpolation between observations is learnt naturally in the training procedure and requires no post-processing. Furthermore, NISFs allow the leveraging of learnt shape priors to make predictions for regions outside of the original image plane. We go on to show the framework achieves dice scores of on a (3D+t) short-axis cardiac segmentation task using the UK Biobank dataset. We also provide a qualitative analysis on our frameworks ability to perform segmentation and image interpolation on unseen regions of an image volume at arbitrary resolutions.

MCML Authors
Link to Daniel Rückert

Daniel Rückert

Prof. Dr.

Artificial Intelligence in Healthcare and Medicine