Skip to main content

Artificial intelligence designed to recognize different types of pastries could be an essential tool in the medical world.

BakeryScan, developed by Japanese company Brain Co., scans baked goods on a tray with a camera and uploads each person’s official name to a system to facilitate payment at a bakery – but scientists have found that it can, too. identify cancer.

A doctor at the Louise Pasteur Medical Research Center in Kyoto had the system checked to spot cancer cells on a microscope slide with 99% accuracy.

Instead of studying donut holes and bread ridges, the redesigned system, called Cyto-AisCAN, analyzes a urine cell to identify and measure its nucleus to determine if it is diseased.

Scroll down for video

BakeryScan, developed by Japanese company Brain Co., scans baked goods on a tray with a camera and uploads each person’s official name to a system to facilitate payment at a bakery – but scientists have found that it can, too. identify cancer.

BakeryScan, first released in 2013, was designed by computer systems engineer Hisashi Kambe who sold the innovation to Brain Co.

It is currently used by over 400 retail stores across Japan and each unit costs $ 20,000.

BakeryScan operates via a camera mounted above a backlit checkout tray.

Customers place their selections on the platter, then the camera scans the bread or pastries, cataloging their size, shape, and color to match one of 100 different types stored in the checkout system.

A doctor at the Louise Pasteur Center for Medical Research in Kyoto had the system revised to spot cancer cells on a microscope slide with 99% accuracy

A doctor at the Louise Pasteur Center for Medical Research in Kyoto had the system revised to spot cancer cells on a microscope slide with 99% accuracy

The cashier confirms the correspondence via a touchscreen, then the customer pays – a complete process that takes place in seconds.

Four years after BakeryScan helped retail stores, a doctor spotted the technology on a TV show and wondered if it could do the same for cancer – he realized cancer cells look like bread when they are under a microscope, The New Yorker reports.

The system uses deep learning for object recognition and instead of differentiating between baked goods, the doctor hoped the technology could save lives.

Identifying cancer cells to determine whether the tumors are benign or malignant can be a lot of work.

But having an AI assistant would dramatically speed up the process and lead to earlier diagnoses and more effective treatment for patients.

Brain Co revised BakeryScan for Medical Purposes to scan small microscope slides instead of puff pastry.

Cyto-AiscAN was then on its way to two large hospitals in Kobe and Kyoto, where doctors tested and trained the system with cancer cells.

Over time, the AI ​​was able to analyze an entire slide at a time and not just each cell individually.

James Somers, author of the New York article, said: “The system apparently worked with ninety-nine percent accuracy.”

“I asked Kambe how it worked: did he use deep learning? “Original way,” he said. Then, with a big smile, ‘Like bread.’

AI has come a long way from identifying faces to helping doctors help save lives.

Last year a A computer algorithm developed by British and American scientists found that AI was able to show a 1.2% reduction in the number of false positives and a 2.7% reduction in false negatives.

Instead of studying donut holes and bread ridges, the redesigned system, called Cyto-AISCAN, analyzes a urine cell to identify and measure its nucleus to determine if it is diseased.

Instead of studying donut holes and bread ridges, the redesigned system, called Cyto-AISCAN, analyzes a urine cell to identify and measure its nucleus to determine if it is diseased.

The breakthrough has been compared to “a spell checker for writing emails” and may reduce the number of “false negatives” that can lead to life-threatening processing delays.

The technology has also taken off amid the coronavirus pandemic, with many medical experts turning to the system for help.

Researchers at the University of Copenhagen have designed software that can tell if you are likely to die from the virus using health data.

The team used a computer program with health data from 3,944 Danish COVID-19 patients, along with any underlying conditions.

They then trained him to look for patterns in a patient’s previous illnesses to determine risk factors and potential Covid-19 outcomes and found that BMI, age, and being a man were the highest risk factors for the likelihood of death.

Source link

Leave a Reply