4 papers · 1 filter
VoxCor: Training-Free Volumetric Features for Multimodal Voxel Correspondence
Guney Tombak, Ertunc Erdil, Ender Konukoglu
Cross-modal 3D medical image analysis requires voxelwise representations that remain anatomically consistent across imaging contrasts, scanners, and acquisition protocols. Recent w…
Spatial Autoregressive Modeling of DINOv3 Embeddings for Unsupervised Anomaly Detection
Ertunc Erdil, Nico Schulthess, Guney Tombak +1
DINO models provide rich patch-level representations that have recently enabled strong performance in unsupervised anomaly detection (UAD). Most existing methods extract patch embe…
Conformal forecasting for surgical instrument trajectory
Sara Sangalli, Gary Sarwin, Ertunc Erdil +4
Forecasting surgical instrument trajectories and predicting the next surgical action recently started to attract attention from the research community. Both these tasks are crucial…
Do Vision Foundation Models Enhance Domain Generalization in Medical Image Segmentation?
Kerem Cekmeceli, Meva Himmetoglu, Guney I. Tombak +3
Neural networks achieve state-of-the-art performance in many supervised learning tasks when the training data distribution matches the test data distribution. However, their perfor…