Cosmin I. Bercea
Cosmin I. Bercea
Home
News
Research
Publications
Teaching
Light
Dark
Automatic
Projects
autoDDPM
Automatic diffusion models for anomaly detection.
PHANES
Reversing the Abnormal: Pseudo-Healthy Generative Networks for Anomaly Detection.
MorphAEus
Novel deformable auto-encoders for unsupervised outlier detection.
Bias
UAD faces significant challenges tied to biases from different sources, including scanners, sex, and race. Future UAD models should maintain sensitivity to pathological shifts while minimizing sensitivity to non-pathological factors.
RA
Moving beyond hyperintensity thresholding. This work analyzes the challenges and outlines opportunities for advancing the field of unsupervised anomaly detection.
FedDis
Implicit disentanglement of shape and appearance with federated learning for unsupervised brain pathology segmentation.
Cite
×