Enhancing high-content imaging for studying microtubule networks at large-scale

Hao-Chih Lee, Sarah T. Cherng, Riccardo Miotto, Joel T. Dudley
Proceedings of the 4th Machine Learning for Healthcare Conference, PMLR 106:592-613, 2019.

Abstract

Given the crucial role of microtubules for cell survival, many researchers have found success using microtubule-targeting agents in the search for effective cancer therapeutics. Understanding microtubule responses to targeted interventions requires that the microtubule network within cells can be consistently observed across a large sample of images. However, fluorescence noise sources captured simultaneously with biological signals while using wide-held microscopes can obfuscate fine microtubule structures. Such requirements are particularly challenging for high-throughput imaging, where researchers must make decisions related to the trade-off between imaging quality and speed. Here, we propose a computational framework to enhance the quality of high-throughput imaging data to achieve fast speed and high quality simultaneously. Using CycleGAN, we learn an image model from low-throughput, high-resolution images to enhance features, such as microtubule networks in high-throughput low-resolution images. We show that CycleGAN is effective in identifying microtubules with 0.93+ AUC-ROC and that these results are robust to different kinds of image noise. We further apply CycleGAN to quantify the changes in microtubule density as a result of the application of drug compounds, and show that the quantified responses correspond well with known drug effects.

Cite this Paper


BibTeX
@InProceedings{pmlr-v106-lee19a, title = {Enhancing high-content imaging for studying microtubule networks at large-scale}, author = {Lee, Hao-Chih and Cherng, Sarah T. and Miotto, Riccardo and Dudley, Joel T.}, booktitle = {Proceedings of the 4th Machine Learning for Healthcare Conference}, pages = {592--613}, year = {2019}, editor = {Doshi-Velez, Finale and Fackler, Jim and Jung, Ken and Kale, David and Ranganath, Rajesh and Wallace, Byron and Wiens, Jenna}, volume = {106}, series = {Proceedings of Machine Learning Research}, month = {09--10 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v106/lee19a/lee19a.pdf}, url = {https://proceedings.mlr.press/v106/lee19a.html}, abstract = {Given the crucial role of microtubules for cell survival, many researchers have found success using microtubule-targeting agents in the search for effective cancer therapeutics. Understanding microtubule responses to targeted interventions requires that the microtubule network within cells can be consistently observed across a large sample of images. However, fluorescence noise sources captured simultaneously with biological signals while using wide-held microscopes can obfuscate fine microtubule structures. Such requirements are particularly challenging for high-throughput imaging, where researchers must make decisions related to the trade-off between imaging quality and speed. Here, we propose a computational framework to enhance the quality of high-throughput imaging data to achieve fast speed and high quality simultaneously. Using CycleGAN, we learn an image model from low-throughput, high-resolution images to enhance features, such as microtubule networks in high-throughput low-resolution images. We show that CycleGAN is effective in identifying microtubules with 0.93+ AUC-ROC and that these results are robust to different kinds of image noise. We further apply CycleGAN to quantify the changes in microtubule density as a result of the application of drug compounds, and show that the quantified responses correspond well with known drug effects.} }
Endnote
%0 Conference Paper %T Enhancing high-content imaging for studying microtubule networks at large-scale %A Hao-Chih Lee %A Sarah T. Cherng %A Riccardo Miotto %A Joel T. Dudley %B Proceedings of the 4th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2019 %E Finale Doshi-Velez %E Jim Fackler %E Ken Jung %E David Kale %E Rajesh Ranganath %E Byron Wallace %E Jenna Wiens %F pmlr-v106-lee19a %I PMLR %P 592--613 %U https://proceedings.mlr.press/v106/lee19a.html %V 106 %X Given the crucial role of microtubules for cell survival, many researchers have found success using microtubule-targeting agents in the search for effective cancer therapeutics. Understanding microtubule responses to targeted interventions requires that the microtubule network within cells can be consistently observed across a large sample of images. However, fluorescence noise sources captured simultaneously with biological signals while using wide-held microscopes can obfuscate fine microtubule structures. Such requirements are particularly challenging for high-throughput imaging, where researchers must make decisions related to the trade-off between imaging quality and speed. Here, we propose a computational framework to enhance the quality of high-throughput imaging data to achieve fast speed and high quality simultaneously. Using CycleGAN, we learn an image model from low-throughput, high-resolution images to enhance features, such as microtubule networks in high-throughput low-resolution images. We show that CycleGAN is effective in identifying microtubules with 0.93+ AUC-ROC and that these results are robust to different kinds of image noise. We further apply CycleGAN to quantify the changes in microtubule density as a result of the application of drug compounds, and show that the quantified responses correspond well with known drug effects.
APA
Lee, H., Cherng, S.T., Miotto, R. & Dudley, J.T.. (2019). Enhancing high-content imaging for studying microtubule networks at large-scale. Proceedings of the 4th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 106:592-613 Available from https://proceedings.mlr.press/v106/lee19a.html.

Related Material