Cosmin Bercea is a postdoctoral researcher at the Computational Imaging and AI in Medicine chair (Prof. Schnabel), TUM School of Computation, Information, and Technology, and at the AI for Image-Guided Diagnosis and Therapy chair (Prof. Wiestler), TUM School of Medicine and Health. His current research focuses on vision and multimodal learning for medical image analysis.

His research background encompasses machine learning for medical image analysis and computer vision for autonomous driving. During his doctoral studies at the Technical University of Munich, he focused on machine learning and image understanding, with a specific emphasis on creating robust algorithms capable of identifying a wide array of unknown anomalies in medical images. He earned his B.Sc. and M.Sc. degrees in Computer Science from FAU University in Erlangen, Germany, where he specialized in pattern recognition and medical image analysis.

Interests
  • Vision & Multimodal Learning
  • Generative AI
  • Foundation Models
  • Anomaly Detection
Education

  • Dr.rer.nat. in Computer Science, 2024 (expected)

    Technical University of Munich

  • M.Sc. in Computer Science, 2018

    FAU Erlangen

  • B.Sc. in Computer Science, 2015

    FAU Erlangen

Teaching

  • AI for Vision-Language Models in Medical Imaging

    Master seminar | WS24/25 | Seminar Page

  • Unsupervised Anomaly Detection in Medical Imaging

    Master seminar | WS23/24 | SS22/23 | WS22/23 | Seminar Page

Student Projects & Theses

  • Text-based Image Editing

    Master's Thesis | 1.06.2024 | Karim ElGhandour | running |

  • Vision-Language Models for Medical Imaging

    IDP | 1.06.2024 | Danica Rovó | running |

  • Multimodal Learning for Medical Imaging

    Master's Thesis | 1.06.2024 | Hanna Mykula | running |

  • Diffusion Models for Counterfactual Pathology Synthesis

    Master's Thesis | 1.11.2023 | Malek Ben Alaya | running | Paper [MICCAI Workshops]

  • Diffusion Models for Fetal US Anomaly Detection

    GRP | 12.03.2024 | Hanna Mykula | finished | Paper [MICCAI Workshops]

  • Unsupervised Representation Learning for Alzheimer’s Disease Quantification

    GRP & PMSD | 12.03.2024 | Mehmet Yigit Avci | finished | Paper [MICCAI Workshops]

  • Diffusion Models for Unsupervised Anomaly Detection

    GRP | 24.10.2023 | Michael Neumayr | finished | Paper [ICML Workshops]

  • Unsupervised Anomaly Detection in Fetal Brain Ultrasound

    Master's Thesis | 15.08.2023 | Ruxandra Petrescu | finished |

Latest