Deep learning for label-free nuclei detection from implicit phase information of mesenchymal stem cells

Abstract

Monitoring of adherent cells in culture is routinely performed in biological and clinical laboratories, and it is crucial for large-scale manufacturing of cells needed in cell-based clinical trials and therapies. However, the lack of reliable and easily implementable label-free techniques makes this task laborious and prone to human subjectivity. We present a deep-learning-based processing pipeline that locates and characterizes mesenchymal stem cell nuclei from a few bright-field images captured at various levels of defocus under collimated illumination. Our approach builds upon phase-from-defocus methods in the optics literature and is easily applicable without the need for special microscopy hardware, for example, phase contrast objectives, or explicit phase reconstruction methods that rely on potentially bias-inducing priors. Experiments show that this label-free method can produce accurate cell counts as well as nuclei shape statistics without the need for invasive staining or ultraviolet radiation. We also provide detailed information on how the deep-learning pipeline was designed, built and validated, making it straightforward to adapt our methodology to different types of cells. Finally, we discuss the limitations of our technique and potential future avenues for exploration.

Imaging approaches for monitoring three‐dimensional cell and tissue culture systems

“…NAD(P)H FLIM data of label‐free samples has also been demonstrated for detection of Microglia in a heterogeneous sample [256]. Similar approaches had been implemented for classification, such as healthy or diseased cells from image flow cytometry data [257], nuclei detection from phase information [258] and cell classification from intensity and phase data [259]. Similarly, characterisation of collagen from SHG data by ML approaches had been implemented for segmentation and orientation analysis via DL [260, 261] or by combining DL with gradient‐boosted regression trees [262].…”

“…NAD(P)H FLIM data of label-free samples has also been demonstrated for detection of Microglia in a heterogeneous sample [256]. Similar approaches had been implemented for classification, such as healthy or diseased cells from image flow cytometry data [257], nuclei detection from phase information [258] and cell s confocal [246,247] ultrasound [248] Raman [249] OCT [243], PTI Raman [221,222] PAM [223] OCT [224,225] a Typical values, excluding super-resolution techniques. Values dependent on NA, and illumination wavelengths.…”

Artificial intelligence supports automated characterization of differentiated human pluripotent stem cells

“…In contrast to traditional machine learning techniques, deep learning networks are able to automatically and efficiently learn higher-level representations of data without the need for manual feature engineering (Moen et al, 2019). Within the field of stem cell research, deep learning applied to cellular images holds the potential for accurate and automated analysis of cell cultures, as recent studies have demonstrated (Grafton et al, 2021; Guan et al, 2021; Imamura et al, 2021; Joy et al, 2021; Maddah et al, 2020; Zhang et al, 2021). In the study by Imamura et al, induced pluripotent stem cells (iPSCs) were generated from cells from healthy controls and patients with amyotrophic lateral sclerosis.…”

Unleashing the power of high-throughput bright-field imaging for enhanced mesenchymal cell separation: a novel supervised clustering approach in vitro augmentation of healthy and stressful conditions

“…Yet, manufacturing these therapeutic agents introduces unique challenges, including issues related to donor variability, tissue source, and differences in the media environment [5,6]. To address these constraints, the use of high-throughput imaging and artificial intelligence (AI) technologies has been recently advanced, offering speedy and in-depth insights to enhance bioprocess analytics in CT manufacturing [7][8][9].…”

“…AI and imaging technologies have been increasingly adopted to enhance CT manufacturing, with several researchers exploring diverse strategies to address CT manufacturing challenges. Examples include the work of Zhang et al, who employed deep learning for label-free nuclei detection from MSC implicit phase information [7], and Kim et al conducted a high-throughput screening of MSC lines using deep learning techniques [8]. Further, Imboden et al, who used AI-driven label-free imaging to examine MSC heterogeneities [9].…”