English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Deep learning has achieved spectacular performance in image and speechrecognition and synthesis. It outperforms other machine learning algorithms inproblems where large amounts of data are available. In the area of measurementtechnology, instruments based on the photonic time stretch have establishedrecord real-time measurement throughput in spectroscopy, optical coherencetomography, and imaging flow cytometry. These extreme-throughput instrumentsgenerate approximately 1 Tbit/s of continuous measurement data and have led tothe discovery of rare phenomena in nonlinear and complex systems as well as newtypes of biomedical instruments. Owing to the abundance of data they generate,time-stretch instruments are a natural fit to deep learning classification.Previously we had shown that high-throughput label-free cell classificationwith high accuracy can be achieved through a combination of time-stretchmicroscopy, image processing and feature extraction, followed by deep learningfor finding cancer cells in the blood. Such a technology holds promise forearly detection of primary cancer or metastasis. Here we describe a new deeplearning pipeline, which entirely avoids the slow and computationally costlysignal processing and feature extraction steps by a convolutional neuralnetwork that directly operates on the measured signals. The improvement incomputational efficiency enables low-latency inference and makes this pipelinesuitable for cell sorting via deep learning. Our neural network takes less thana few milliseconds to classify the cells, fast enough to provide a decision toa cell sorter for real-time separation of individual target cells. Wedemonstrate the applicability of our new method in the classification of OT-IIwhite blood cells and SW-480 epithelial cancer cells with more than 95%accuracy in a label-free fashion.

Deep Cytometry: Deep learning with Real-time Inference in Cell Sorting and Flow Cytometry