Non-invasive and label-free identification of human natural killer cell subclasses by biophysical single-cell features in microfluidic flow

Dannhauser, David; Rossi, Domenico; Palatucci, Anna Teresa; Rubino, Valentina; Carriero, Flavia; Ruggiero, Giuseppina; Ripaldi, Mimmo; Toriello, Mario; Maisto, Giovanna; Netti, Paolo Antonio; Terrazzano, Giuseppe; Causa, Filippo

doi:10.1039/d1lc00651g

Cited by 9 publications

(12 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The machine learning (ML) approach was carried out with a Matlab (R2020b, MathWorks) routine to classify circulating monocytes from macrophages, as well as the main subtypes of macrophage phenotypes (M0, M1 and M2) based on their biophysical properties retrieved from optical cell signatures. Several classification methods were set up with operational parameters chosen based on previous experiments of our working group [ 31 , 33 ]. For ML training, a randomly chosen subset of data (all donors) was used, followed by testing classification accuracy on the remaining data (all donors), while the classification accuracy was measured by fivefold cross-validation.…”

Section: Methodsmentioning

confidence: 99%

“…More importantly, measurements are realized using a lab-on-a-chip approach permitting the measurement of living cells in suspension, which furthermore are collectable and re-usable for other diagnostic investigations or therapeutic approaches. We have already investigated such optical signature of other human cell types and subtypes [32][33][34][35][36].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Single cell classification of macrophage subtypes by label-free cell signatures and machine learning

et al. 2022

Self Cite

View full text Add to dashboard Cite

Pro-inflammatory (M1) and anti-inflammatory (M2) macrophage phenotypes play a fundamental role in the immune response. The interplay and consequently the classification between these two functional subtypes is significant for many therapeutic applications. Albeit, a fast classification of macrophage phenotypes is challenging. For instance, image-based classification systems need cell staining and coloration, which is usually time- and cost-consuming, such as multiple cell surface markers, transcription factors and cytokine profiles are needed. A simple alternative would be to identify such cell types by using single-cell, label-free and high throughput light scattering pattern analyses combined with a straightforward machine learning-based classification. Here, we compared different machine learning algorithms to classify distinct macrophage phenotypes based on their optical signature obtained from an ad hoc developed wide-angle static light scattering apparatus. As the main result, we were able to identify unpolarized macrophages from M1- and M2-polarized phenotypes and distinguished them from naive monocytes with an average accuracy above 85%. Therefore, we suggest that optical single-cell signatures within a lab-on-a-chip approach along with machine learning could be used as a fast, affordable, non-invasive macrophage phenotyping tool to supersede resource-intensive cell labelling.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Single cell classification of macrophage subtypes by label-free cell signatures and machine learning

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…In fact, the viscoelastic fluid (polyethylene oxide, MW = 4 MDa) forces of the resulting fluid, tuned with the flow velocity and geometry of the channel, result in cellular alignment maintained throughout the readout channel. [19,22] Note that cells can be recovered for further cell studies.…”

Section: Microfluidic Devicementioning

confidence: 99%

“…In more detail, a microfluidic device combined with an optical single cell investigation readout (combination of forward-and side-direction) was used for data recording of different cell classes. [19][20][21] Machine learning uses the scattering information as input to predict the searched for cell types. A prediction model was trained for a set of human peripheral blood cells.…”

Section: Introductionmentioning

confidence: 99%

Out of distribution detection in deep learning-based scattering pattern classification

Dannhauser,

Netti,

Causa

2023

Optical Methods for Inspection, Characterization, and Imaging of Biomaterials VI

View full text Add to dashboard Cite

Intrinsic biophysical cell properties hold an enormous potential for cell class and state classification in microfluidics, allowing to avoid the need of cost intensive fluorescence labelling. Several methods can accomplish cell identification, while convolutional neural networks show an outstanding performance compared to other state-of-the-art classification methods, regarding accuracy and speed. In fact, neural networks show high performance for known image class prediction but struggles when unknown (out of distribution) image classes need to be identified. In such a scenario no prior knowledge of the unknown cell class can be used for the model training, which inevitably results in image misclassification. In fact, to distinguish unknown cell classes, a neural network must first construct an in-distribution of known images to afterwards detect out of distribution as unknowns, which is also called open-set classification assumption. Ones, a new cell class is identified, the neural network can be retrained with the obtained knowledge to dynamically update its cell class database. This process can be simply repeated for each new detected cell class. We applied this open-set idea to scattering pattern snapshots of different classes of living cells obtained in microfluidics. Our outcome shows a proof-of-concept for openset based convolutional neural network for cell image classification, which can be applied to a wide range of single cell classification approaches to reduce uncertainty in machine learning based technologies.

show abstract

“…Park et al compared flow cytometry and ECIS based cytotoxicity assays and found slightly discrepant results, however they used different target cells [310]. NK cell subpopulations (the mature cytotoxic CD56dim and the regulatory CD56bright) can be distinguished in the microfluidic system designed by Dannhauser et al based on their light scattering properties with the help of machine learning [311]. Examples of labelfree characterization of lymphocytes are shown in Fig.…”

Section: Lymphocytesmentioning

confidence: 99%

Functional blood cell analysis by label-free biosensors and single-cell technologies

Szittner

Péter

Kurunczi

et al. 2022

Advances in Colloid and Interface Science

View full text Add to dashboard Cite

Non-invasive and label-free identification of human natural killer cell subclasses by biophysical single-cell features in microfluidic flow

Abstract: Natural Killer (NK) are indicated as favorite candidates for innovative therapeutic treatment and are divided in two subclasses: immature regulatory NK CD56bright and mature cytotoxic NK CD56dim. Therefore, the ability...

Cited by 9 publications

References 72 publications

Single cell classification of macrophage subtypes by label-free cell signatures and machine learning

Single cell classification of macrophage subtypes by label-free cell signatures and machine learning

Out of distribution detection in deep learning-based scattering pattern classification

Functional blood cell analysis by label-free biosensors and single-cell technologies

Contact Info

Product

Resources

About