AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |
Back to Blog
Input a freecell game online4/10/2024 ![]() ![]() Machine-learning algorithms can be used for cell classification. In contrast, label-free imaging flow cytometry 5, 6 presents a more natural approach and is based on using an internal contrast mechanism of the cells rather than external chemical labeling. Imaging flow cytometry is typically performed with cell labeling 1, 2, 3, 4, with the risk of damaging the cell viability. On-chip image-based classification of cells is an essential tool in cell analysis for pathology, profiling, and diagnosis of various types of cells. This approach has the potential to significantly improve both speed and robustness of imaging flow cytometry, enabling real-time label-free classification of individual cells. We demonstrate the effectiveness of this approach using four types of cancer cells. To obtain this, we built a convolutional neural network, which is invariant to the spatial frequencies and directions of the interference fringes of the off-axis holograms. Here, we present a new approach for label-free classification of individual cells based directly on the raw off-axis holographic images, each of which contains the complete complex wavefront (amplitude and quantitative phase profiles) of the cell. However, classification of the cells typically requires reconstruction of their quantitative phase profiles, which is time-consuming. ![]() Off-axis holography enables real-time acquisition of cells during rapid flow. We present a rapid label-free imaging flow cytometry and cell classification approach based directly on raw digital holograms. ![]()
0 Comments
Read More
Leave a Reply. |