CP2Image: Generating high-quality single-cell images using CellProfiler representations

Yanni Ji, Marie Cutiongco, Bj\orn Sand Jensen, Ke Yuan
Medical Imaging with Deep Learning, PMLR 227:274-285, 2024.

Abstract

Single-cell high-throughput microscopy images contain key biological information underlying normal and pathological cellular processes. Image-based analysis and profiling are powerful and promising for extracting this information but are made difficult due to substantial complexity and heterogeneity in cellular phenotype. Hand-crafted methods and machine learning models are popular ways to extract cell image information. Representations extracted via machine learning models, which often exhibit good reconstruction performance, lack biological interpretability. Hand-crafted representations, on the contrary, have clear biological meanings and thus are interpretable. Whether these hand-crafted representations can also generate realistic images is not clear. In this paper, we propose a CellProfiler to image (CP2Image) model that can directly generate realistic cell images from CellProfiler representations. We also demonstrate most biological information encoded in the CellProfiler representations is well-preserved in the generating process. This is the first time hand-crafted representations be shown to have generative ability and provide researchers with an intuitive way for their further analysis.

Cite this Paper

BibTeX
@InProceedings{pmlr-v227-ji24a, title = {CP2Image: Generating high-quality single-cell images using CellProfiler representations}, author = {Ji, Yanni and Cutiongco, Marie and Jensen, Bj\orn Sand and Yuan, Ke}, booktitle = {Medical Imaging with Deep Learning}, pages = {274--285}, year = {2024}, editor = {Oguz, Ipek and Noble, Jack and Li, Xiaoxiao and Styner, Martin and Baumgartner, Christian and Rusu, Mirabela and Heinmann, Tobias and Kontos, Despina and Landman, Bennett and Dawant, Benoit}, volume = {227}, series = {Proceedings of Machine Learning Research}, month = {10--12 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v227/ji24a/ji24a.pdf}, url = {https://proceedings.mlr.press/v227/ji24a.html}, abstract = {Single-cell high-throughput microscopy images contain key biological information underlying normal and pathological cellular processes. Image-based analysis and profiling are powerful and promising for extracting this information but are made difficult due to substantial complexity and heterogeneity in cellular phenotype. Hand-crafted methods and machine learning models are popular ways to extract cell image information. Representations extracted via machine learning models, which often exhibit good reconstruction performance, lack biological interpretability. Hand-crafted representations, on the contrary, have clear biological meanings and thus are interpretable. Whether these hand-crafted representations can also generate realistic images is not clear. In this paper, we propose a CellProfiler to image (CP2Image) model that can directly generate realistic cell images from CellProfiler representations. We also demonstrate most biological information encoded in the CellProfiler representations is well-preserved in the generating process. This is the first time hand-crafted representations be shown to have generative ability and provide researchers with an intuitive way for their further analysis.} }
Endnote
%0 Conference Paper %T CP2Image: Generating high-quality single-cell images using CellProfiler representations %A Yanni Ji %A Marie Cutiongco %A Bj\orn Sand Jensen %A Ke Yuan %B Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2024 %E Ipek Oguz %E Jack Noble %E Xiaoxiao Li %E Martin Styner %E Christian Baumgartner %E Mirabela Rusu %E Tobias Heinmann %E Despina Kontos %E Bennett Landman %E Benoit Dawant %F pmlr-v227-ji24a %I PMLR %P 274--285 %U https://proceedings.mlr.press/v227/ji24a.html %V 227 %X Single-cell high-throughput microscopy images contain key biological information underlying normal and pathological cellular processes. Image-based analysis and profiling are powerful and promising for extracting this information but are made difficult due to substantial complexity and heterogeneity in cellular phenotype. Hand-crafted methods and machine learning models are popular ways to extract cell image information. Representations extracted via machine learning models, which often exhibit good reconstruction performance, lack biological interpretability. Hand-crafted representations, on the contrary, have clear biological meanings and thus are interpretable. Whether these hand-crafted representations can also generate realistic images is not clear. In this paper, we propose a CellProfiler to image (CP2Image) model that can directly generate realistic cell images from CellProfiler representations. We also demonstrate most biological information encoded in the CellProfiler representations is well-preserved in the generating process. This is the first time hand-crafted representations be shown to have generative ability and provide researchers with an intuitive way for their further analysis.
APA
Ji, Y., Cutiongco, M., Jensen, B.S. & Yuan, K.. (2024). CP2Image: Generating high-quality single-cell images using CellProfiler representations. Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 227:274-285 Available from https://proceedings.mlr.press/v227/ji24a.html.

Related Material