Composition Counts: A Machine Learning View on Immunothrombosis using Quantitative Phase Imaging

David Fresacher, Stefan Röhrl, Christian Klenk, Johanna Erber, Hedwig Irl, Dominik Heim, Manuel Lengl, Simon Schumann, Martin Knopp, Martin Schlegel, Sebastian Rasch, Oliver Hayden, Klaus Diepold
Proceedings of the 8th Machine Learning for Healthcare Conference, PMLR 219:208-229, 2023.

Abstract

Thrombotic complications are a leading cause of death worldwide, often triggered by inflammatory conditions such as sepsis and COVID-19, due to a close relationship between inflammation and hemostasis known as immunothrombosis. Platelet activation and leukocyte-platelet aggregation play key roles in microthrombotic events, yet there are no routine diagnostic predictive biomarkers based on these factors. This work presents a novel processing pipeline using label-free Quantitative Phase Imaging (QPI) for the detection and quantitative analysis of blood cell aggregates without sample preparation. For evaluation, we use different test scenarios and measure performance at different stages of the pipeline to gain a better understanding of the critical points. We show that, among other classical and machine learning techniques, the Mask R-CNN approach achieves the best results for detection, segmentation, and classification of cell aggregates. The method successfully identifies aggregate levels in whole blood samples and shows elevated levels in >90% of patients with COVID-19 or sepsis compared to healthy reference samples, indicating the potential of platelet and leukocyte-platelet aggregates as biomarkers for thrombotic diseases.

Cite this Paper

BibTeX
@InProceedings{pmlr-v219-fresacher23a, title = {Composition Counts: A Machine Learning View on Immunothrombosis using Quantitative Phase Imaging}, author = {Fresacher, David and R\"ohrl, Stefan and Klenk, Christian and Erber, Johanna and Irl, Hedwig and Heim, Dominik and Lengl, Manuel and Schumann, Simon and Knopp, Martin and Schlegel, Martin and Rasch, Sebastian and Hayden, Oliver and Diepold, Klaus}, booktitle = {Proceedings of the 8th Machine Learning for Healthcare Conference}, pages = {208--229}, year = {2023}, editor = {Deshpande, Kaivalya and Fiterau, Madalina and Joshi, Shalmali and Lipton, Zachary and Ranganath, Rajesh and Urteaga, Iñigo and Yeung, Serene}, volume = {219}, series = {Proceedings of Machine Learning Research}, month = {11--12 Aug}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v219/fresacher23a/fresacher23a.pdf}, url = {https://proceedings.mlr.press/v219/fresacher23a.html}, abstract = {Thrombotic complications are a leading cause of death worldwide, often triggered by inflammatory conditions such as sepsis and COVID-19, due to a close relationship between inflammation and hemostasis known as immunothrombosis. Platelet activation and leukocyte-platelet aggregation play key roles in microthrombotic events, yet there are no routine diagnostic predictive biomarkers based on these factors. This work presents a novel processing pipeline using label-free Quantitative Phase Imaging (QPI) for the detection and quantitative analysis of blood cell aggregates without sample preparation. For evaluation, we use different test scenarios and measure performance at different stages of the pipeline to gain a better understanding of the critical points. We show that, among other classical and machine learning techniques, the Mask R-CNN approach achieves the best results for detection, segmentation, and classification of cell aggregates. The method successfully identifies aggregate levels in whole blood samples and shows elevated levels in >90% of patients with COVID-19 or sepsis compared to healthy reference samples, indicating the potential of platelet and leukocyte-platelet aggregates as biomarkers for thrombotic diseases.} }
Endnote
%0 Conference Paper %T Composition Counts: A Machine Learning View on Immunothrombosis using Quantitative Phase Imaging %A David Fresacher %A Stefan Röhrl %A Christian Klenk %A Johanna Erber %A Hedwig Irl %A Dominik Heim %A Manuel Lengl %A Simon Schumann %A Martin Knopp %A Martin Schlegel %A Sebastian Rasch %A Oliver Hayden %A Klaus Diepold %B Proceedings of the 8th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2023 %E Kaivalya Deshpande %E Madalina Fiterau %E Shalmali Joshi %E Zachary Lipton %E Rajesh Ranganath %E Iñigo Urteaga %E Serene Yeung %F pmlr-v219-fresacher23a %I PMLR %P 208--229 %U https://proceedings.mlr.press/v219/fresacher23a.html %V 219 %X Thrombotic complications are a leading cause of death worldwide, often triggered by inflammatory conditions such as sepsis and COVID-19, due to a close relationship between inflammation and hemostasis known as immunothrombosis. Platelet activation and leukocyte-platelet aggregation play key roles in microthrombotic events, yet there are no routine diagnostic predictive biomarkers based on these factors. This work presents a novel processing pipeline using label-free Quantitative Phase Imaging (QPI) for the detection and quantitative analysis of blood cell aggregates without sample preparation. For evaluation, we use different test scenarios and measure performance at different stages of the pipeline to gain a better understanding of the critical points. We show that, among other classical and machine learning techniques, the Mask R-CNN approach achieves the best results for detection, segmentation, and classification of cell aggregates. The method successfully identifies aggregate levels in whole blood samples and shows elevated levels in >90% of patients with COVID-19 or sepsis compared to healthy reference samples, indicating the potential of platelet and leukocyte-platelet aggregates as biomarkers for thrombotic diseases.
APA
Fresacher, D., Röhrl, S., Klenk, C., Erber, J., Irl, H., Heim, D., Lengl, M., Schumann, S., Knopp, M., Schlegel, M., Rasch, S., Hayden, O. & Diepold, K.. (2023). Composition Counts: A Machine Learning View on Immunothrombosis using Quantitative Phase Imaging. Proceedings of the 8th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 219:208-229 Available from https://proceedings.mlr.press/v219/fresacher23a.html.

Related Material