Superpixel Pre-segmentation of HER2 Slides for Efficient Annotation

Öttl M, Mönius J, Marzahl C, Rübner M, Geppert CI, Hartmann A, Beckmann M, Fasching P, Maier A, Erber R, Breininger K (2022)


Publication Type: Conference contribution, Conference Contribution

Publication year: 2022

Journal

Publisher: Springer Science and Business Media Deutschland GmbH

Pages Range: 254-259

Conference Proceedings Title: Informatik aktuell

Event location: Heidelberg, DEU

ISBN: 9783658369316

DOI: 10.1007/978-3-658-36932-3_54

Abstract

Supervised deep learning has shown state-of-the-art performance for medical image segmentation across different applications, including histopathology and cancer research; however, the manual annotation of such data is extremely laborious. In this work, we explore the use of superpixel approaches to compute a pre-segmentation of HER2 stained images for breast cancer diagnosis that facilitates faster manual annotation and correction in a second step. Four methods are compared: standard simple linear iterative clustering (SLIC) as a baseline, a domain adapted SLIC, and superpixels based on feature embeddings of a pretrained ResNet-50 and a denoising autoencoder. To tackle oversegmentation, we propose to hierarchically merge superpixels, based on their content in the respective feature space. When evaluating the approaches on fully manually annotated images, we observe that the autoencoder-based superpixels achieve a 23% increase in boundary F1 score compared to the baseline SLIC superpixels. Furthermore, the boundary F1 score increases by 73% when hierarchical clustering is applied on the adapted SLIC and the autoencoder-based superpixels. These evaluations show encouraging first results for a pre-segmentation for efficient manual refinement without the need for an initial set of annotated training data.

Authors with CRIS profile

How to cite

APA:

Öttl, M., Mönius, J., Marzahl, C., Rübner, M., Geppert, C.-I., Hartmann, A.,... Breininger, K. (2022). Superpixel Pre-segmentation of HER2 Slides for Efficient Annotation. In Klaus Maier-Hein, Thomas M. Deserno, Heinz Handels, Andreas Maier, Christoph Palm, Thomas Tolxdorff (Eds.), Informatik aktuell (pp. 254-259). Heidelberg, DEU: Springer Science and Business Media Deutschland GmbH.

MLA:

Öttl, Mathias, et al. "Superpixel Pre-segmentation of HER2 Slides for Efficient Annotation." Proceedings of the German Workshop on Medical Image Computing, 2022, Heidelberg, DEU Ed. Klaus Maier-Hein, Thomas M. Deserno, Heinz Handels, Andreas Maier, Christoph Palm, Thomas Tolxdorff, Springer Science and Business Media Deutschland GmbH, 2022. 254-259.

BibTeX: Download