5 papers
Out-of-Distribution Detection in Medical Imaging via Diffusion Trajectories
Lemar Abdi, Francisco Caetano, Amaan Valiuddin +3
In medical imaging, unsupervised out-of-distribution (OOD) detection offers an attractive approach for identifying pathological cases with extremely low incidence rates. In contras…
Zero-Shot Image Anomaly Detection Using Generative Foundation Models
Lemar Abdi, Amaan Valiuddin, Francisco Caetano +2
Detecting out-of-distribution (OOD) inputs is pivotal for deploying safe vision systems in open-world environments. We revisit diffusion models, not as generators, but as universal…
MedSymmFlow: Bridging Generative Modeling and Classification in Medical Imaging through Symmetrical Flow Matching
Francisco Caetano, Lemar Abdi, Christiaan Viviers +2
Reliable medical image classification requires accurate predictions and well-calibrated uncertainty estimates, especially in high-stakes clinical settings. This work presents MedSy…
Can Your Generative Model Detect Out-of-Distribution Covariate Shift?
Christiaan Viviers, Amaan Valiuddin, Francisco Caetano +4
Detecting Out-of-Distribution (OOD) sensory data and covariate distribution shift aims to identify new test examples with different high-level image statistics to the captured, nor…
Segmentation-based Assessment of Tumor-Vessel Involvement for Surgical Resectability Prediction of Pancreatic Ductal Adenocarcinoma
Christiaan Viviers, Mark Ramaekers, Amaan Valiuddin +9
Pancreatic ductal adenocarcinoma (PDAC) is a highly aggressive cancer with limited treatment options. This research proposes a workflow and deep learning-based segmentation models…