Abstract
Out-of-distribution data can substantially impede the performance of deep learning models. In medical imaging, domain shifts can, for instance, be caused by different image acquisition protocols. To address these domain shifts, domain adversarial training can be employed to constrain a model to domainagnostic features. This, however, requires prior knowledge about the domain variable, which might not always be accessible. Recent approaches make use of control regions to guide the training process and thereby alleviate the need for prior domain knowledge. In this work, we combine these approaches with traditional domain adversarial training to exploit the benefits of both methods.We test the proposed method on two medical datasets and demonstrate performance increases of up to 10 %, compared to a baseline trained without debiasing.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Aubreville M, Bertram CA, Marzahl C, Gurtner C, Dettwiler M, Schmidt A et al. Deep learning algorithms out-perform veterinary pathologists in detecting the mitotically most active tumor region. Sci Rep. 2020;10(1):16447.
Ganin Y, Ustinova E, Ajakan H, Germain P, Larochelle H, Laviolette F et al. Domainadversarial training of neural networks. J Mach Learn Res. 2016;17(59):1–35.
Wilm F, Marzahl C, Breininger K,Aubreville M. Domain adversarial RetinaNet as a reference algorithm for the mitosis domain generalization challenge. Proc MICCAI. 2022:5–13.
Mühlberg A, Katzmann A, Heinemann V, Kärgel R, Wels M, Taubmann O et al. The technome-a predictive internal calibration approach for quantitative imaging biomarker research. Sci Rep. 2020;10(1):1103.
Langer S, Taubmann O, Denzinger F, Maier A, Mühlberg A. Mitigating unknown bias in deep learning-based assessment of CT images deep technome. Proc BVM. 2023:177–82.
Van Griethuysen JJ, Fedorov A, Parmar C, Hosny A, Aucoin N, Narayan V et al. Computational radiomics system to decode the radiographic phenotype. Cancer Res. 2017;77(21):e104–e107.
Remy-Jardin MJ, Kaergel R, Suehling M, Faivre JB, Flohr TG, Remy J. Detection and phenotyping of emphysema using a new machine learning method. Proc RSNA. 2018.
Wilm F, Fragoso M, Bertram CA, Stathonikos N, Öttl M, Qiu J et al. Multi-scanner canine cutaneous squamous cell carcinoma histopathology dataset. Proc BVM. 2023:206–11.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 Der/die Autor(en), exklusiv lizenziert an Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature
About this paper
Cite this paper
Wilm, F., Reimann, M., Taubmann, O., Mühlberg, A., Breininger, K. (2024). Appearance-based Debiasing of Deep Learning Models in Medical Imaging. In: Maier, A., Deserno, T.M., Handels, H., Maier-Hein, K., Palm, C., Tolxdorff, T. (eds) Bildverarbeitung für die Medizin 2024. BVM 2024. Informatik aktuell. Springer Vieweg, Wiesbaden. https://doi.org/10.1007/978-3-658-44037-4_9
Download citation
DOI: https://doi.org/10.1007/978-3-658-44037-4_9
Published:
Publisher Name: Springer Vieweg, Wiesbaden
Print ISBN: 978-3-658-44036-7
Online ISBN: 978-3-658-44037-4
eBook Packages: Computer Science and Engineering (German Language)