I am interested in interpretable machine learning algorithms for unsupervised anomaly detection.

Interests
  • Interpretable Machine Learning
  • Unsupervised Anomaly Detection
Education

  • Ph.D. Interpretable Machine Learning in Medical Image Analysis, ongoing

    Technical University of Munich

  • M.Sc. in Computer Science, 2018

    FAU Erlangen

  • B.Sc. in Computer Science, 2015

    FAU Erlangen

News

3 papers accepted @MICCAI 2023

Projects: MorphAEus, PHANES , and Bias

Jul 21, 2023 1 min read
3 papers accepted @MICCAI 2023
Paper accepted @ICML IMLH 2023
Jul 1, 2023 1 min read
Paper accepted @ICML IMLH 2023
New Talk @MIDL2023, Nashville

Video: Towards Unbiased Pathology Screening

May 25, 2023 1 min read
New Talk @MIDL2023, Nashville

Research

autoDDPM
Automatic diffusion models for anomaly detection.
autoDDPM
PHANES
Reversing the Abnormal: Pseudo-Healthy Generative Networks for Anomaly Detection.
PHANES
MorphAEus
Novel deformable auto-encoders for unsupervised outlier detection.
MorphAEus
See all

Publications

Cosmin I. Bercea, Esther Puyol-Antón, Benedikt Wiestler, Daniel Rückert, Julia A Schnabel, Andrew P. King (2023). Bias in Unsupervised Anomaly Detection in Brain MRI. In arXiv.

PDF Cite Dataset Project

Cosmin I. Bercea, Michael Neumayr, Daniel Rueckert, Julia Schnabel (2023). Mask, Stitch, and Re-Sample: Enhancing Robustness and Generalizability in Anomaly Detection through Automatic Diffusion Models. In ICML IMLH.

PDF Cite Code Dataset Project Poster

Cosmin I. Bercea, Benedikt Wiestler, Daniel Rückert, Julia A Schnabel (2023). Generalizing Unsupervised Anomaly Detection: Towards Unbiased Pathology Screening. In MIDL.

PDF Cite Code Dataset Project Project Poster Video

Cosmin I. Bercea, Benedikt Wiestler, Daniel Rueckert, Julia Schnabel (2023). Reversing the Abnormal: Pseudo-Healthy Generative Networks for Anomaly Detection. In arxiv.

PDF Cite Code Project

Cosmin I. Bercea, Benedikt Wiestler, Daniel Rückert, Shadi Albarqouni (2022). Federated Disentangled Representation Learning for Unsupervised Brain Anomaly Detection. In Nature Machine Intelligence.

PDF Cite Code Project Video

See all publications

Teaching

If you are interested in BSc/MSc projects in unsupervised anomaly detection please contact me and attach a motivation letter, transcript of academic records and CV.

*
All Bachelor Thesis Master Thesis Seminars
Unsupervised Anomaly Detection in Medical Imaging

Unsupervised Anomaly Detection in Medical Imaging

Winter semester 2023. TUM Informatics. Master Seminar.

Unsupervised Anomaly Detection for Medical Imaging (f/m/x)

Unsupervised Anomaly Detection for Medical Imaging (f/m/x)

Bachelor/Master Thesis)