collaborators

7 papers

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.CV2026

Rethinking Post-Hoc Calibration in Semantic Segmentation

Tristan Kirscher, Kim-Celine Kahl, Balint Kovacs +5

Reliable confidence estimates are essential in semantic segmentation, especially in safety-critical settings where overconfident errors can mislead downstream decisions. Yet modern…

cs.CV2026

Lost in the Folds: When Cross-Validation Is Not a Deep Ensemble for Uncertainty Estimation

Tristan Kirscher, Markus Bujotzek, Yannick Kirchhoff +5

Ensemble disagreement is widely used as a proxy for epistemic uncertainty in medical image segmentation. In practice, many studies form ensembles via K-fold cross-validation (CV),…

cs.CV2026

Assessing Pancreatic Ductal Adenocarcinoma Vascular Invasion: the PDACVI Benchmark

M. Riera-Marín, O. K. Sikha, J. Rodríguez-Comas +23

Surgical resection remains the only potentially curative treatment for pancreatic ductal adenocarcinoma (PDAC), and eligibility depends on accurate assessment of vascular invasion…

cs.CV2026

Finally Outshining the Random Baseline: A Simple and Effective Solution for Active Learning in 3D Biomedical Imaging

Carsten T. Lüth, Jeremias Traub, Kim-Celine Kahl +6

Active learning (AL) has the potential to drastically reduce annotation costs in 3D biomedical image segmentation, where expert labeling of volumetric data is both time-consuming a…

cs.CV2025

nnActive: A Framework for Evaluation of Active Learning in 3D Biomedical Segmentation

Carsten T. Lüth, Jeremias Traub, Kim-Celine Kahl +6

Semantic segmentation is crucial for various biomedical applications, yet its reliance on large annotated datasets presents a bottleneck due to the high cost and specialized expert…