Deep learning approach takes a few milliseconds to ID cancer cells in blood
Researchers at the University of California Los Angeles (UCLA; Los Angeles, CA) and biotechnology company NantWorks (Culver City, CA) have developed an artificial intelligence (AI)-powered device that detects cancer cells in a few milliseconds. With that speed, the deep learning- and photonic time stretch-based approach could make it possible to extract cancer cells from blood immediately after they are detected, which could in turn help prevent the disease from spreading in the body.
Deep learning is a type of machine learning, an AI technique in which algorithms are "trained" to perform tasks using large volumes of data. In deep learning, algorithms called neural networks are modeled after how the human brain works. Compared to other types of machine learning, deep learning has proven to be especially effective for recognizing and generating images, speech, music, and videos.
Photonic time stretch is an ultrafast measurement technology that was invented at UCLA—these instruments use ultrashort laser bursts to capture trillions of data points per second. The technology has helped scientists discover rare phenomena in laser physics and invent new types of biomedical instruments for 3D microscopy, spectroscopy, and other applications.
The system also uses imaging flow cytometry, which measures cell characteristics by using a laser to take images of the cells one at a time as they flow through a carrier fluid. Although there are already techniques for categorizing cells in imaging flow cytometry, those techniques' processing steps occur so slowly that devices don't have time to physically separate cells from one another.
Building on previous work, senior author Bahram Jalali, a professor of electrical and computer engineering at the UCLA Samueli School of Engineering and a member of the California NanoSystems Institute at UCLA, and colleagues developed a deep learning pipeline that solves that problem by operating directly on the laser signals that are part of the imaging flow cytometry process, eliminating the time-intensive processing steps of other techniques."We optimized the design of the deep neural network to handle the large amounts of data created by our time-stretch imaging flow cytometer—upgrading the performance of both the software and instrument," says Yueqin Li, a visiting doctoral student and the paper's first author.
Ata Mahjoubfar, a UCLA postdoctoral researcher and a co-author of the paper, said the technique allows the instrument to determine whether a cell is cancerous virtually instantaneously, as it eliminates the need to extract biophysical parameters. Instead, he says, deep neural networks rapidly analyze the raw data itself.
The code for the neural network was developed using an advanced graphics processing unit donated by Nvidia (Santa Clara, CA). Other contributors to the study were Kayvan Reza Niazi of NantWorks and Claire Lifan Chen, a former UCLA doctoral student.
Full details of the work appear in the journal Nature Scientific Reports.
BioOptics World Editors
We edited the content of this article, which was contributed by outside sources, to fit our style and substance requirements. (Editor’s Note: BioOptics World has folded as a brand and is now part of Laser Focus World, effective in 2022.)