Olivier Morelle

Machine Learning Engineer and Medical Imaging Specialist

University Bonn - Visualization and Medical Image Analysis Group

About Me

Olivier Morelle is a PhD candidate specializing in medical image analysis and the developer of EyePy, a Python software package designed to streamline the reading and visualization of ophthalmological OCT datasets. His research focuses on developing deep learning models for OCT data segmentation.

By combining a strong academic foundation with hands-on software development, Olivier aims to contribute to advancements in medical AI and data science, particularly in roles that connect research and industry applications.

Interests

Deep Learning
Computer Vision
Ophthalmology
Medical Imaging
Python

Education

PhD Medical Image Analysis
University of Bonn
MSc Life Science Informatics
Bonn-Aachen International Center for Information Technology (b-it)
BSc Biology
University of Cologne

Featured Publications

Optical Coherence Tomography

Foundation Models Permit Retinal Layer Segmentation Across OCT Devices

Segmenting retinal layers in OCT images is crucial for ophthalmological diagnosis, but current CNN models struggle with images from different devices. We introduce the first OCT layer segmentation method using Vision Transformer (ViT) foundation models, which significantly improve generalization to unseen devices and demonstrate that generic foundation models outperform equally large OCT-specific models in robustness.

Sep 10, 2024

Computer Science

Accurate drusen segmentation in optical coherence tomography via order-constrained regression of retinal layer heights

A novel deep learning based architecture that directly predicts the position of layers in OCT and guarantees their correct order is introduced, achieving state-of-the-art results for retinal layer segmentation.

May 19, 2023

Recent Publications

Olivier Morelle, Justus Bisten, Maximilian W. M. Wintergerst, Robert P. Finger, Thomas Schultz (2025). Weakly Supervised Segmentation of Hyper-Reflective Foci with Compact Convolutional Transformers and SAM2. In Arxiv.

PDF Cite DOI

Christian Muth, Olivier Morelle, Renata Raidou, Maximilian Wintergerst, Robert Finger, Thomas Schultz (2024). Exploring Drusen Type and Appearance using Interpretable GANs. In EG Workshop on Visual Computing for Biology and Medicine Short Papers, 2024.

PDF Cite DOI

Olivier Morelle, Thomas Schultz (2024). Foundation Models Permit Retinal Layer Segmentation Across OCT Devices. In DAGM GCPR.

PDF Cite Poster

Olivier Morelle, Maximilian WM Wintergerst, Robert P Finger, Thomas Schultz (2023). Accurate drusen segmentation in optical coherence tomography via order-constrained regression of retinal layer heights. In Sci. Rep..

PDF Cite Code Project Project DOI

Leon Von Der Emde, Marlene Saßmannshausen, Olivier Morelle, Geena Rennen, Frank G Holz, Maximilian WM Wintergerst, Thomas Ach (2023). Reliability of Retinal Layer Annotation with a Novel, High-Resolution Optical Coherence Tomography Device: A Comparative Study. In Bioengineering.

PDF Cite DOI

See all publications