A Modular Deep Learning Pipeline for Cell Culture Analysis: Investigating the Proliferation of Cardiomyocytes

Lars Leyendecker, Julius Haas, Tobias Piotrowski, Maik Frye, Cora Becker, Bernd K. Fleischmann, Michael Hesse, Robert H. Schmitt
Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, PMLR 172:760-773, 2022.

Abstract

Cardiovascular disease is a leading cause of death in the Western world. The exploration of strategies to enhance the regenerative capacity of the mammalian heart is therefore of great interest. One approach is the treatment of isolated transgenic mouse cardiomyocytes (CMs) with potentially cell cycle-inducing substances and assessment if this results in atypical cell cycle activity or authentic cell division. This requires the tedious and cost intensive manual analysis of microscopy images. Recent advances have led to an increasing use of deep learning (DL) algorithms in cellular image analysis. While developments in image or single-cell classification are well advanced, multi-cell classification in crowded image scenarios remains a challenge. This is reinforced by typically smaller dataset sizes in such laboratory-specific analyses. In this paper, we propose a modular DL-based image analysis pipeline for multi-cell classification of mononuclear and binuclear CMs in confocal microscopy imaging data. We trisect the pipeline structure into preprocessing, modelling and postprocessing. We perform semantic segmentation to extract general image features, which are further analyzed in postprocessing. In total, we conduct 173 experiments. We benchmark 18 encoder-decoder model architectures, perform hyperparameter optimization across 28 runs, and conduct 127 experiments to evaluate dataset-related effects. The results show that our approach has great potential for automating specific cell culture analyses even with small datasets.

Cite this Paper

BibTeX
@InProceedings{pmlr-v172-leyendecker22a, title = {A Modular Deep Learning Pipeline for Cell Culture Analysis: Investigating the Proliferation of Cardiomyocytes}, author = {Leyendecker, Lars and Haas, Julius and Piotrowski, Tobias and Frye, Maik and Becker, Cora and Fleischmann, Bernd K. and Hesse, Michael and Schmitt, Robert H.}, booktitle = {Proceedings of The 5th International Conference on Medical Imaging with Deep Learning}, pages = {760--773}, 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/leyendecker22a/leyendecker22a.pdf}, url = {https://proceedings.mlr.press/v172/leyendecker22a.html}, abstract = {Cardiovascular disease is a leading cause of death in the Western world. The exploration of strategies to enhance the regenerative capacity of the mammalian heart is therefore of great interest. One approach is the treatment of isolated transgenic mouse cardiomyocytes (CMs) with potentially cell cycle-inducing substances and assessment if this results in atypical cell cycle activity or authentic cell division. This requires the tedious and cost intensive manual analysis of microscopy images. Recent advances have led to an increasing use of deep learning (DL) algorithms in cellular image analysis. While developments in image or single-cell classification are well advanced, multi-cell classification in crowded image scenarios remains a challenge. This is reinforced by typically smaller dataset sizes in such laboratory-specific analyses. In this paper, we propose a modular DL-based image analysis pipeline for multi-cell classification of mononuclear and binuclear CMs in confocal microscopy imaging data. We trisect the pipeline structure into preprocessing, modelling and postprocessing. We perform semantic segmentation to extract general image features, which are further analyzed in postprocessing. In total, we conduct 173 experiments. We benchmark 18 encoder-decoder model architectures, perform hyperparameter optimization across 28 runs, and conduct 127 experiments to evaluate dataset-related effects. The results show that our approach has great potential for automating specific cell culture analyses even with small datasets.} }
Endnote
%0 Conference Paper %T A Modular Deep Learning Pipeline for Cell Culture Analysis: Investigating the Proliferation of Cardiomyocytes %A Lars Leyendecker %A Julius Haas %A Tobias Piotrowski %A Maik Frye %A Cora Becker %A Bernd K. Fleischmann %A Michael Hesse %A Robert H. Schmitt %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-leyendecker22a %I PMLR %P 760--773 %U https://proceedings.mlr.press/v172/leyendecker22a.html %V 172 %X Cardiovascular disease is a leading cause of death in the Western world. The exploration of strategies to enhance the regenerative capacity of the mammalian heart is therefore of great interest. One approach is the treatment of isolated transgenic mouse cardiomyocytes (CMs) with potentially cell cycle-inducing substances and assessment if this results in atypical cell cycle activity or authentic cell division. This requires the tedious and cost intensive manual analysis of microscopy images. Recent advances have led to an increasing use of deep learning (DL) algorithms in cellular image analysis. While developments in image or single-cell classification are well advanced, multi-cell classification in crowded image scenarios remains a challenge. This is reinforced by typically smaller dataset sizes in such laboratory-specific analyses. In this paper, we propose a modular DL-based image analysis pipeline for multi-cell classification of mononuclear and binuclear CMs in confocal microscopy imaging data. We trisect the pipeline structure into preprocessing, modelling and postprocessing. We perform semantic segmentation to extract general image features, which are further analyzed in postprocessing. In total, we conduct 173 experiments. We benchmark 18 encoder-decoder model architectures, perform hyperparameter optimization across 28 runs, and conduct 127 experiments to evaluate dataset-related effects. The results show that our approach has great potential for automating specific cell culture analyses even with small datasets.
APA
Leyendecker, L., Haas, J., Piotrowski, T., Frye, M., Becker, C., Fleischmann, B.K., Hesse, M. & Schmitt, R.H.. (2022). A Modular Deep Learning Pipeline for Cell Culture Analysis: Investigating the Proliferation of Cardiomyocytes. Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 172:760-773 Available from https://proceedings.mlr.press/v172/leyendecker22a.html.

Related Material