Scientists use AI and machine learning to detect cancer with more accuracy

Scientists in California have developed a microscope that uses machine learning and photonic time stretch to locate cancer cells more efficiently.

The microscope, invented by UCLA scientists, uses artificial intelligence (AI) to analyse 36 million images per second, more accurately identifying cancer cells present in blood samples.

Currently, doctors track cancerous cells by adding biochemicals to blood samples, which then add labels to them for later detection.

However, this can damage the cells, making the samples useless. Other techniques include identifying cancer cells by their physical characteristics, but they can be inaccurate.

The AI microscope images cells without destroying them and can identify characteristics such as size, granularity and biomass.

This is possible because of a photonic time stretch microscope invented by the UCLA scientists, which has allowed cell identification to reach 95 per cent accuracy.

The photonic time stretch works by taking pictures of flowing blood cells with laser bursts, boosting clarity and slowing them down enough to be detected and digitised.

Commenting on the technology, Ata Mahjoubfar, said: "Each frame is slowed down in time and optically amplified so it can be digitised. This lets us perform fast cell imaging that the artificial intelligence component can distinguish."

"The photonic time stretch technique allows us to identify rogue cells in a short time with low-level illumination," added Chen.