Abstract
Transmitted light microscopy can readily visualize the morphology of living cells. Here, we introduce artificial-intelligence-powered transmitted light microscopy (AIM) for subcellular structure identification and labeling-free functional analysis of live cells. AIM provides accurate images of subcellular organelles; allows identification of cellular and functional characteristics (cell type, viability, and maturation stage); and facilitates live cell tracking and multimodality analysis of immune cells in their native form without labeling.
Highlights
Transmitted light microscopy can readily visualize the morphology of living cells
The artificial-intelligence-powered transmitted light microscopy (AIM) package consists of a hierarchical k-means clustering algorithm of unsupervised machine learning, convolutional neural networks in deep learning and a complementary learner solving regression problems of machine learning
ClassNet is designed for cell location and status classification (Fig. 1a) and is implemented through two convolutional neural networks (CNNs): one region-proposal CNN for cell searching and another CNN for cell classification (Fig. 1c and Supplementary Note 3)[23,24]
Summary
We introduce artificial-intelligence-powered transmitted light microscopy (AIM) for subcellular structure identification and labeling-free functional analysis of live cells. AIM provides accurate images of subcellular organelles; allows identification of cellular and functional characteristics (cell type, viability, and maturation stage); and facilitates live cell tracking and multimodality analysis of immune cells in their native form without labeling. Subcellular structure visualizations are typically performed using fluorescence labeling Cell status characteristics such as their viability, type, and activity can be classified by dyeing representative biomarkers and evaluating their expression levels. Digital image processing heavily extends the ability of the optical microscopy Algorithms such as detection and segmentation allow making measurements and quantifications from the microscopic images[3]. (3) accurate live cell tracking with subsequent analysis of the multimodality functions described above is presented, which enables completely label-free and multiplexed live cell imaging
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
