Reducing the impact of domain shift in deep learning for OCT segmentation using image manipulations

Marc S. Seibel; Joshua Niemeijer; Marc Rowedder; Helge Sudkamp; Timo Kepp; Gereon Hüttmann; Heinz Handels

doi:10.1117/12.3008702

3 April 2024 Reducing the impact of domain shift in deep learning for OCT segmentation using image manipulations

Marc S. Seibel, Joshua Niemeijer, Marc Rowedder, Helge Sudkamp, Timo Kepp, Gereon Hüttmann, Heinz Handels

Proceedings Volume 12927, Medical Imaging 2024: Computer-Aided Diagnosis; 1292719 (2024) https://doi.org/10.1117/12.3008702
Event: SPIE Medical Imaging, 2024, San Diego, California, United States

Abstract

Medical segmentation of optical coherence tomography (OCT) images using deep neural networks (DNNs) has been intensively studied in recent years, but generalization across datasets from different OCT devices is still a considerable challenge. In this work, we focus on the novel self-examination low-cost full-field (SELFF)- OCT, a handheld imaging device for home-monitoring of retinopathies, and the clinically used Spectralis-OCT. Images from both devices exhibit different characteristics, leading to different representations within DNNs and consequently to a reduced segmentation quality when switching between devices. To robustly segment OCT images from an OCT-scanner unseen during training, we alter the appearance of the images using manipulation methods ranging from traditional data augmentation to noise-based methods to learning-based style transfer methods. We evaluate the effect of the manipulation methods with respect to segmentation quality and changes in the feature space of the DNN. Reducing the domain shift with style transfer methods results in a significantly better segmentation of pigment epithelial detachment (PED). Investigations of the feature space show that the segmentation quality of PED is negatively correlated with the distance between training and test distributions. Our methods and results help researchers to choose and evaluate image manipulation methods for developing OCT segmentation models which are robust against domain shifts.

Conference Presentation

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Marc S. Seibel, Joshua Niemeijer, Marc Rowedder, Helge Sudkamp, Timo Kepp, Gereon Hüttmann, and Heinz Handels "Reducing the impact of domain shift in deep learning for OCT segmentation using image manipulations", Proc. SPIE 12927, Medical Imaging 2024: Computer-Aided Diagnosis, 1292719 (3 April 2024); https://doi.org/10.1117/12.3008702

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available