AIConfPaper
← Search

Constantin Ulrich

8 accepted papers

2026

CRONOS: Continuous time reconstruction for 4D medical longitudinal series

Nico Disch, Saikat Roy, Constantin Ulrich, Yannick Kirchhoff, Maximilian Rouven Rokuss, Robin Peretzke +2
ICLR 2026poster

Forecasting how 3D medical scans evolve along 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.…

Cited by 0Source ↗code ↗Scholar ↗
2026

VoxTell: Free-Text Promptable Universal 3D Medical Image Segmentation

Maximilian Rokuss, Moritz Langenberg, Yannick Kirchhoff, Fabian Isensee, Benjamin Hamm, Constantin Ulrich +5
CVPR 2026

We introduce VoxTell, a vision-language model for text-prompted volumetric medical image segmentation. It maps free-form descriptions, from single words to full clinical sentences, to 3D masks. Trained on 62K+ CT, MRI, and PET volumes spanning 1K+ anatomical and pathological classes, VoxTell uses mu

Cited by 0Source ↗code ↗Scholar ↗
2025

An OpenMind for 3D Medical Vision Self-supervised Learning

Tassilo Wald, Constantin Ulrich, Jonathan Suprijadi, Sebastian Ziegler, Michal Nohel, Robin Peretzke +2
ICCV 2025poster

The field of self-supervised learning (SSL) for 3D medical images lacks consistency and standardization. While many methods have been developed, it is impossible to identify the current state-of-the-art, due to i) varying and small pretraining datasets, ii) varying architectures, and iii) being eval…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

LesionLocator: Zero-Shot Universal Tumor Segmentation and Tracking in 3D Whole-Body Imaging

Maximilian Rokuss, Yannick Kirchhoff, Seval Akbal, Balint Kovacs, Saikat Roy, Constantin Ulrich +4
CVPR 2025poster

In this work, we present LesionLocator, a framework for zero-shot longitudinal lesion tracking and segmentation in 3D medical imaging, establishing the first end-to-end model capable of 4D tracking with dense spatial prompts. Our model leverages an extensive dataset of 23,262 annotated medical scans…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Revisiting MAE Pre-training for 3D Medical Image Segmentation

Tassilo Wald, Constantin Ulrich, Stanislav Lukyanenko, Andrei Goncharov, Alberto Paderno, Maximilian Miller +3
CVPR 2025highlight

Self-Supervised Learning (SSL) presents an exciting opportunity to unlock the potential of vast, untapped clinical datasets, for various downstream applications that suffer from the scarcity of labeled data. While SSL has revolutionized fields like natural language processing and computer vision, it…

Cited by 5Source ↗PDF ↗Scholar ↗
2024

Decoupling Semantic Similarity from Spatial Alignment for Neural Networks.

Tassilo Wald, Constantin Ulrich, Priyank Jaini, Gregor Koehler, David Zimmerer, Stefan Denner +3
NeurIPS 2024poster

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…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

Skeleton Recall Loss for Connectivity Conserving and Resource Efficient Segmentation of Thin Tubular Structures

Yannick Kirchhoff*, Maximilian R Rokuss*, Saikat Roy*, Balint Kovacs, Constantin Ulrich, Tassilo Wald +5
ECCV 2024poster

"Accurately segmenting thin tubular structures, such as vessels, nerves, roads or concrete cracks, is a crucial task in computer vision. Standard deep learning-based segmentation loss functions, such as Dice or Cross-Entropy, focus on volumetric overlap, often at the expense of preserving structural…

Cited by 17Source ↗PDF ↗code ↗Scholar ↗
2024

Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?

Pedro R. A. S. Bassi, Wenxuan Li, Yucheng Tang, Fabian Isensee, Zifu Wang, Jieneng Chen +47
NeurIPS 2024poster

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…

Cited by 9Source ↗PDF ↗code ↗Scholar ↗