Self-Supervised Representation Learning for High-Content Screening

Daniel Siegismund, Mario Wieser, Stephan Heyse, Stephan Steigele
Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, PMLR 172:1108-1124, 2022.

Abstract

Biopharma drug discovery requires a set of approaches to find, produce, and test the safety of drugs for clinical application. A crucial part involves image-based screening of cell culture models where single cells are stained with appropriate markers to visually distinguish between disease and healthy states. In practice, such image-based screening experiments are frequently performed using highly scalable and automated multichannel microscopy instruments. This automation enables parallel screening against large panels of marketed drugs with known function. However, the large data volume produced by such instruments hinders a systematic inspection by human experts, which consequently leads to an extensive and biased data curation process for supervised phenotypic endpoint classification. To overcome this limitation, we propose a novel approach for learning an embedding of phenotypic endpoints, without any supervision. We employ the concept of archetypal analysis, in which pseudo-labels are extracted based on biologically reasonable endpoints. Subsequently, we use a self-supervised triplet network to learn a phenotypic embedding which is used for visual inspection and top-down assay quality control. Extensive experiments on two industry-relevant assays demonstrate that our method outperforms state-of-the-art unsupervised and supervised approaches.

Cite this Paper

BibTeX
@InProceedings{pmlr-v172-siegismund22a, title = {Self-Supervised Representation Learning for High-Content Screening}, author = {Siegismund, Daniel and Wieser, Mario and Heyse, Stephan and Steigele, Stephan}, booktitle = {Proceedings of The 5th International Conference on Medical Imaging with Deep Learning}, pages = {1108--1124}, year = {2022}, editor = {Konukoglu, Ender and Menze, Bjoern and Venkataraman, Archana and Baumgartner, Christian and Dou, Qi and Albarqouni, Shadi}, volume = {172}, series = {Proceedings of Machine Learning Research}, month = {06--08 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v172/siegismund22a/siegismund22a.pdf}, url = {https://proceedings.mlr.press/v172/siegismund22a.html}, abstract = {Biopharma drug discovery requires a set of approaches to find, produce, and test the safety of drugs for clinical application. A crucial part involves image-based screening of cell culture models where single cells are stained with appropriate markers to visually distinguish between disease and healthy states. In practice, such image-based screening experiments are frequently performed using highly scalable and automated multichannel microscopy instruments. This automation enables parallel screening against large panels of marketed drugs with known function. However, the large data volume produced by such instruments hinders a systematic inspection by human experts, which consequently leads to an extensive and biased data curation process for supervised phenotypic endpoint classification. To overcome this limitation, we propose a novel approach for learning an embedding of phenotypic endpoints, without any supervision. We employ the concept of archetypal analysis, in which pseudo-labels are extracted based on biologically reasonable endpoints. Subsequently, we use a self-supervised triplet network to learn a phenotypic embedding which is used for visual inspection and top-down assay quality control. Extensive experiments on two industry-relevant assays demonstrate that our method outperforms state-of-the-art unsupervised and supervised approaches.} }
Endnote
%0 Conference Paper %T Self-Supervised Representation Learning for High-Content Screening %A Daniel Siegismund %A Mario Wieser %A Stephan Heyse %A Stephan Steigele %B Proceedings of The 5th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2022 %E Ender Konukoglu %E Bjoern Menze %E Archana Venkataraman %E Christian Baumgartner %E Qi Dou %E Shadi Albarqouni %F pmlr-v172-siegismund22a %I PMLR %P 1108--1124 %U https://proceedings.mlr.press/v172/siegismund22a.html %V 172 %X Biopharma drug discovery requires a set of approaches to find, produce, and test the safety of drugs for clinical application. A crucial part involves image-based screening of cell culture models where single cells are stained with appropriate markers to visually distinguish between disease and healthy states. In practice, such image-based screening experiments are frequently performed using highly scalable and automated multichannel microscopy instruments. This automation enables parallel screening against large panels of marketed drugs with known function. However, the large data volume produced by such instruments hinders a systematic inspection by human experts, which consequently leads to an extensive and biased data curation process for supervised phenotypic endpoint classification. To overcome this limitation, we propose a novel approach for learning an embedding of phenotypic endpoints, without any supervision. We employ the concept of archetypal analysis, in which pseudo-labels are extracted based on biologically reasonable endpoints. Subsequently, we use a self-supervised triplet network to learn a phenotypic embedding which is used for visual inspection and top-down assay quality control. Extensive experiments on two industry-relevant assays demonstrate that our method outperforms state-of-the-art unsupervised and supervised approaches.
APA
Siegismund, D., Wieser, M., Heyse, S. & Steigele, S.. (2022). Self-Supervised Representation Learning for High-Content Screening. Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 172:1108-1124 Available from https://proceedings.mlr.press/v172/siegismund22a.html.

Related Material