Presentation + Paper
7 April 2023 Overcoming the sensor delta for semantic segmentation in OCT images
Author Affiliations +
Abstract
The performance of a segmentation network optimized on data from a specific type of OCT sensor will decrease when applied to data from a different sensor. In this work, we deal with the research question of adapting models to data from an unlabeled new sensor with new properties in an unsupervised way. This challenge is known as unsupervised domain adaptation and can alleviate the need for costly manual annotation by radiologists. We show that one can strongly improve a model’s result that was trained in a supervised way on the source OCT sensor domain on the target sensor domain. We do this by aligning the source and target domain distributions in the feature space through a semantic clustering method. Apart from the unsupervised domain adaptation, we improved even the supervised training compared to the results in the RETOUCH challenge by employing a sophisticated training strategy. The RETOUCH challenge contains three different types of OCT scanners and provides annotations for the task of disease-related fluid classes.
Conference Presentation
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Joshua Niemeijer, Jan Ehrhardt, Timo Kepp, Jörg P. Schäfer, and Heinz Handels "Overcoming the sensor delta for semantic segmentation in OCT images", Proc. SPIE 12465, Medical Imaging 2023: Computer-Aided Diagnosis, 1246511 (7 April 2023); https://doi.org/10.1117/12.2654187
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Education and training

Image segmentation

Sensors

Optical coherence tomography

Semantics

Scanners

Data modeling

Back to Top