Constantin Ulrich

Constantin Ulrich, Fabian Isensee, Tassilo Wald et al.

The medical imaging community generates a wealth of datasets, many of which are openly accessible and annotated for specific diseases and tasks such as multi-organ or lesion segmentation. Current practices continue to limit model training and supervised pre-training to one or a few similar datasets, neglecting the synergistic potential of other available annotated data. We propose MultiTalent, a method that leverages multiple CT datasets with diverse and conflicting class definitions to train a single model for a comprehensive structure segmentation. Our results demonstrate improved segmentation performance compared to previous related approaches, systematically, also compared to single dataset training using state-of-the-art methods, especially for lesion segmentation and other challenging structures. We show that MultiTalent also represents a powerful foundation model that offers a superior pre-training for various segmentation tasks compared to commonly used supervised or unsupervised pre-training baselines. Our findings offer a new direction for the medical imaging community to effectively utilize the wealth of available data for improved segmentation performance. The code and model weights will be published here: [tba]

Pedro R. A. S. Bassi, Wenxuan Li, Yucheng Tang et al.

How can we test AI performance? This question seems trivial, but it isn't. Standard benchmarks often have problems such as in-distribution and small-size test sets, oversimplified metrics, unfair comparisons, and short-term outcome pressure. As a consequence, good performance on standard benchmarks does not guarantee success in real-world scenarios. To address these problems, we present Touchstone, a large-scale collaborative segmentation benchmark of 9 types of abdominal organs. This benchmark is based on 5,195 training CT scans from 76 hospitals around the world and 5,903 testing CT scans from 11 additional hospitals. This diverse test set enhances the statistical significance of benchmark results and rigorously evaluates AI algorithms across various out-of-distribution scenarios. We invited 14 inventors of 19 AI algorithms to train their algorithms, while our team, as a third party, independently evaluated these algorithms on three test sets. In addition, we also evaluated pre-existing AI frameworks--which, differing from algorithms, are more flexible and can support different algorithms--including MONAI from NVIDIA, nnU-Net from DKFZ, and numerous other open-source frameworks. We are committed to expanding this benchmark to encourage more innovation of AI algorithms for the medical domain.

Katharina Eckstein, Constantin Ulrich, Michael Baumgartner et al.

Large-scale pre-training holds the promise to advance 3D medical object detection, a crucial component of accurate computer-aided diagnosis. Yet, it remains underexplored compared to segmentation, where pre-training has already demonstrated significant benefits. Existing pre-training approaches for 3D object detection rely on 2D medical data or natural image pre-training, failing to fully leverage 3D volumetric information. In this work, we present the first systematic study of how existing pre-training methods can be integrated into state-of-the-art detection architectures, covering both CNNs and Transformers. Our results show that pre-training consistently improves detection performance across various tasks and datasets. Notably, reconstruction-based self-supervised pre-training outperforms supervised pre-training, while contrastive pre-training provides no clear benefit for 3D medical object detection. Our code is publicly available at: https://github.com/MIC-DKFZ/nnDetection-finetuning.

Nico Albert Disch, Yannick Kirchhoff, Robin Peretzke et al.

Understanding temporal dynamics in medical imaging is crucial for applications such as disease progression modeling, treatment planning and anatomical development tracking. However, most deep learning methods either consider only single temporal contexts, or focus on tasks like classification or regression, limiting their ability for fine-grained spatial predictions. While some approaches have been explored, they are often limited to single timepoints, specific diseases or have other technical restrictions. To address this fundamental gap, we introduce Temporal Flow Matching (TFM), a unified generative trajectory method that (i) aims to learn the underlying temporal distribution, (ii) by design can fall back to a nearest image predictor, i.e. predicting the last context image (LCI), as a special case, and (iii) supports $3D$ volumes, multiple prior scans, and irregular sampling. Extensive benchmarks on three public longitudinal datasets show that TFM consistently surpasses spatio-temporal methods from natural imaging, establishing a new state-of-the-art and robust baseline for $4D$ medical image prediction.

Constantin Ulrich, Tassilo Wald, Emily Tempus et al.

Effortless and precise segmentation with minimal clinician effort could greatly streamline clinical workflows. Recent interactive segmentation models, inspired by METAs Segment Anything, have made significant progress but face critical limitations in 3D radiology. These include impractical human interaction requirements such as slice-by-slice operations for 2D models on 3D data and a lack of iterative refinement. Prior studies have been hindered by inadequate evaluation protocols, resulting in unreliable performance assessments and inconsistent findings across studies. The RadioActive benchmark addresses these challenges by providing a rigorous and reproducible evaluation framework for interactive segmentation methods in clinically relevant scenarios. It features diverse datasets, a wide range of target structures, and the most impactful 2D and 3D interactive segmentation methods, all within a flexible and extensible codebase. We also introduce advanced prompting techniques that reduce interaction steps, enabling fair comparisons between 2D and 3D models. Surprisingly, SAM2 outperforms all specialized medical 2D and 3D models in a setting requiring only a few interactions to generate prompts for a 3D volume. This challenges prevailing assumptions and demonstrates that general-purpose models surpass specialized medical approaches. By open-sourcing RadioActive, we invite researchers to integrate their models and prompting techniques, ensuring continuous and transparent evaluation of 3D medical interactive models.

Tassilo Wald, Constantin Ulrich, Gregor Köhler et al.

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 about their internal workings still remain largely unanswered, due to their internal high dimensionality and complexity. To address this, one approach is to measure the similarity of activation responses to various inputs. Representational Similarity Matrices (RSMs) distill this similarity into scalar values for each input pair. These matrices encapsulate the entire similarity structure of a system, indicating which input leads to similar responses. While the similarity between images is ambiguous, we argue that the spatial location of semantic objects does neither influence human perception nor deep learning classifiers. Thus this should be reflected in the definition of similarity between image responses for computer vision systems. Revisiting the established similarity calculations for RSMs we expose their sensitivity to spatial alignment. In this paper, we propose to solve this through semantic RSMs, which are invariant to spatial permutation. We measure semantic similarity between input responses by formulating it as a set-matching problem. Further, we quantify the superiority of semantic RSMs over spatio-semantic RSMs through image retrieval and by comparing the similarity between representations to the similarity between predicted class probabilities.