Determination of the Maturation Status of Dendritic Cells by Applying Pattern Recognition to High-Resolution Images

Abstract

The maturation or activation status of dendritic cells (DCs) directly correlates with their behavior and immunofunction. A common means to determine the maturity of dendritic cells is from high-resolution images acquired via scanning electron microscopy (SEM) or atomic force microscopy (AFM). While direct and visual, the determination has been made by directly looking at the images by researchers. This work reports a machine learning approach using pattern recognition in conjunction with cellular biophysical knowledge of dendritic cells to determine the maturation status of dendritic cells automatically. The determination from AFM images reaches 100% accuracy. The results from SEM images reaches 94.9%. The results demonstrate the accuracy of using machine learning for accelerating data analysis, extracting information, and drawing conclusions from high-resolution cellular images, paving the way for future applications requiring high-throughput and automation, such as cellular sorting and selection based on morphology, quantification of cellular structure, and DC-based immunotherapy.

Deep learning strategy for small dataset from atomic force microscopy mechano-imaging on macrophages phenotypes

“…The use of these parameters instead of images substantially decreases the dimension of the data space and the need for large datasets. AFM morphological maps were used to distinguish between neuronal cell development, ( Lohrer et al, 2020 ) showing higher performance than scanning electron microscopy to determine the maturation status of dendritic cells automatically. Their approach is interesting but applies only to morphology, while biomechanics is left unexplored.…”

Segmentation and Morphology Computation of a Spiky Nanoparticle Using the Hourglass Neural Network

“…Along with many computational fields, the applied natural sciences are benefiting from recent deep learning trends in artificial intelligence (AI). − Until now, the automated analysis of cell morphology has been performed using conventional techniques in computer vision and machine learning. A support vector machine with handcrafted features was used by Lohrer et al to analyze dendritic cell maturation . where electron microscopic images (AFM and SEM) of dendritic cells are acquired and processed using a conventional morphological operation.…”

“…A support vector machine with handcrafted features was used by Lohrer et al to analyze dendritic cell maturation. 5 where electron microscopic images (AFM and SEM) of dendritic cells are acquired and processed using a conventional morphological operation. Microscopic images are processed with noise removal, and image features are computed using histogram of oriented gradients (HOG) and classified using the error correcting output codes (ECOC) technique.…”

Corneal epithelial dendritic cells, tear neuropeptides and corneal nerves continue to be affected more than 12 months after LASIK

“…Inactivated CEDC are described as relatively small with a linear cell body shape, no dendrites or sometimes a few short non‐branching dendrites (Lagali et al, 2018; Ng et al, 2008; Postole et al, 2016). When the immune response is activated and in response to the presence of antigens, CEDC become larger and have longer dendrites (Levine et al, 2021; Lohrer et al, 2020; Obregon et al, 2006; Smedowski et al, 2017; Ward et al, 2007), particularly during dendrite surveillance extension and retraction cycling habitude (dSEARCH) activity—dSEARCH is described in mice as a unique motion to capture antigens and pathogens (Ward et al, 2007). Once an antigen is captured, rapid dendrite retraction towards the cell body is observed, resulting in shorter and thicker dendrites, and CEDC become more spherical in shape (Jamali et al, 2020; Lee et al, 2010; Seyed‐Razavi et al, 2018; Ward et al, 2007).…”