Student Conference Proceedings
Vol. 1 No. 1 (2025): Stud Conf Proc
https://doi.org/10.18416/SCP.2025.1952

Medical Informatics, ID 1952

Anomaly-guided image segmentation on retinal OCT images

Main Article Content

Bennet Kahrs (Study program Medical Informatics, Universität zu Lübeck, Lübeck, Germany), Julia Andresen (Institute of Medical Informatics, University of Luebeck, Luebeck, Germany), Timo Kepp (German Research Center for Artificial Intelligence, Luebeck, Germany), Heinz Handels (Institute of Medical Informatics, University of Luebeck, Luebeck, Germany; 2) German Research Center for Artificial Intelligence, Luebeck, Germany)

Copyright (c) 2025 Bennet Kahrs, Julia Andresen, Timo Kepp, Heinz Handels

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

Medical image segmentation can profit from the integration of contextual information provided by anomaly detection methods. This work investigates different strategies for using anomaly detection results as guidance in supervised segmentation of pathological retinal scans. Three state-of-the-art anomaly detection algorithms, differing in architecture, training methods, and original use cases, are evaluated in five guidance strategies, including an Attention MobileNet architecture. The best-performing approach achieves an improvement of 6.7% in the detection rate score compared to the baseline. This framework offers an enhanced tool for automated analysis of retinal scans, supporting earlier diagnosis and improved treatment planning.

Article Details

How to Cite

Kahrs, B., Andresen, J., Kepp, T., & Handels, H. (2025). Anomaly-guided image segmentation on retinal OCT images. Student Conference Proceedings, 1(1), 1952. https://doi.org/10.18416/SCP.2025.1952