activity
20242026
collaborators

8 papers

cs.AI2026

Option-Aware Retrieval and Task-Specific VLM Adaptation for Medical VQA

Tristan Kirscher, Niklas C. Koser, Soren Pirk

We describe our submission to the MedReason 2026 challenge, covering multiple-choice (MCQ) and open-ended (OE) medical visual question answering (VQA) under fully offline, containe…

cs.CV2026

Assessing nnU-Net Generalization across Brain Tumor Populations in BraTS-GoAT 2026

Tristan Kirscher, Vivian Metzger, Philippe Meyer +1

BraTS-GoAT evaluates tumor segmentation across heterogeneous populations. We trained a conventional 3D nnU-Net on 1,351 labeled cases using five-fold cross-validation and 1,000 epo…

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.LG2026

TwinTrack: Post-hoc Multi-Rater Calibration for Medical Image Segmentation

Tristan Kirscher, Alexandra Ertl, Klaus Maier-Hein +3

Pancreatic ductal adenocarcinoma (PDAC) segmentation on contrast-enhanced CT is inherently ambiguous: inter-rater disagreement among experts reflects genuine uncertainty rather tha…

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…