Integration of light scattering with machine learning for label free cell detection

Wan, Wendy Yu; Liu, Lina; Liu, Xiaoxuan; Wang, Wei; Islam, Md. Zahurul; Dong, Chun‐Hua; Garen, Craig R.; Woodside, Michael T.; Gupta, Manisha; Mandal, Mrinal; Rozmus, W.; Tsui, Ying Y.

doi:10.1364/boe.424357

Cited by 13 publications

(26 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From a structural point of view, such behaviour seems to be related to small inner structure differences such as nuclei, lysosomes or/and mitochondria. In fact, mitochondria are known to add a significant contribution at side scattering angles, due to their dimension, optical density and structural location in the cell cytoplasm [37,42]. royalsocietypublishing.org/journal/rsos R. Soc.…”

Section: Resultsmentioning

confidence: 99%

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

et al. 2022

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: Resultsmentioning

confidence: 99%

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

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In our system, single cell profile is obtained via hydrodynamic focusing [32] In our high-content video flow cytometry, we specifically refer to the big-data property of the obtained 2D light scattering patterns of single cells, which provides the advantage for label-free cell analysis with machine learning. Moreover, the conventional imaging flow cytometry requires rigid focus-in-flow control for the obtaining of the pixel-limited raw optical images of cells that may also be limited by the optical objective depth of field, while the 2D light scattering technique has been reported to provide rich information of the whole single cells [13,14].…”

Section: High-content Video Flow Cytometrymentioning

confidence: 99%

“…However, the image size obtained in conventional imaging flow cytometry (about 30-60 pixels along the side) limits the image resolution of single cells [12]. Some algorithms such as support vector machine (SVM) [13,14] have already demonstrated strong capabilities in the field of cell classification. However, those machine learning methods rely highly on manual feature extraction of cell images [15], and the ability to extract effective features is largely depended on cytology knowledge and image processing experience, which is time-consuming and labor-intensive.…”

Section: Introductionmentioning

confidence: 99%

High‐content video flow cytometry with digital cell filtering for label‐free cell classification by machine learning

et al. 2022

View full text Add to dashboard Cite

Recent development of imaging flow cytometry (IFC) has enabled the measurements of single cells with high throughput, where fluorescent labels provide specificity for cellular diagnosis. The fluorescent labels may disturb the cell functions, and the requirements for high‐throughput measurements limit the cell image quality. Here, we develop the high‐content video flow cytometry (VFC) that measures unlabeled single cells with a rate of approximately 1000 cells per minute. For the obtained big data, the frame of interest (FOI) is automatically prepared by a digital cell filtering technique with machine learning. Cervical carcinoma cell lines (Caski, HeLa and C33‐A cells) are differentiated with an accuracy of 91.5%, 90.5%, and 90.5% by deep learning in a three‐way classification, respectively. The high‐content VFC not only provides high‐quality images of single cells with high throughput and rewinding, but also performs automatic digital cell filtering and label‐free cell classification that may have clinical applications.

show abstract

“…In recent years, the application of two-dimensional (2D) light scattering technology has gained significant traction in single-cell analysis, playing a pivotal role in cell detection and disease diagnosis. By analyzing and processing the binary scattered light information emanating from measured biological particles, researchers can extract a wealth of internal information concerning these particles 6,7 . Recent advances have witnessed the integration of machine learning algorithms with 2D light scattering technology, facilitating the label-free analysis of single cells and the exploration of the intricate information encoded in 2D light scattering patterns [8][9][10] .…”

Section: Introductionmentioning

confidence: 99%

High-throughput and label-free cell cluster monitoring based on light scattering imaging and microfluidic technique

Zhang,

Xu,

et al. 2023

Optics in Health Care and Biomedical Optics XIII

View full text Add to dashboard Cite

Efficient detection of cell clusters is of paramount importance in the production and packaging processes of single-cell suspensions, as it can significantly impact cell density uniformity, induce apoptosis, and compromise the accuracy of cell sorting outcomes. This study introduces a novel, high-throughput and label-free method for monitoring cell clusters, leveraging light scattering imaging and microfluidic technologies. Two dimensional (2D) light scattering, as a vital labelfree analytical approach, proves effective in detecting and analyzing biological particles with intricate structures. Through optical microscopy coupled with a high-speed camera, this study examines the 2D light scattering patterns produced by cell clusters, facilitating the discrimination between single cells and clustered cells. This label-free methodology offers distinct advantages over traditional labeling techniques, as it preserves cellular integrity without invasive disruptions. Furthermore, innovative microfluidic chip design enables continuous real-time monitoring of cell clusters, empowering rapid and high-throughput detection. Experimental validation involved monitoring silicon oxide (SiO2) microsphere suspensions, demonstrating the method's capacity for high-throughput and high-sensitivity cell cluster monitoring. This research presents a promising tool for efficiently handling and monitoring the production of single-cell suspensions, with potential applications in various fields of cell biology and biotechnology.

show abstract

Integration of light scattering with machine learning for label free cell detection

Cited by 13 publications

References 30 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

High‐content video flow cytometry with digital cell filtering for label‐free cell classification by machine learning

High-throughput and label-free cell cluster monitoring based on light scattering imaging and microfluidic technique

Contact Info

Product

Resources

About