Researchers at Chulalankorn University, a public university in Thailand, have developed an AI-based system for the detection of gastrointestinal disorders.
What does this mean?
DPGI (Deep Technology for the Gastrointestinal Tract) marks 90% accuracy of indicating abnormal tissues, such as polyps, indicating early colonic neoplasm in the colon, according to Dr. Pirapan Bhatekul, a member of the research team at Furnace Engineering.
The software is trained using in-depth learning, a machine learning technique and using colonoscopy data images collected since 2019 with the help of Chulalankorn University Technology Center and ESM Solutions Company.
The system can also create a feature of detected polyps and identify them as neoplastic (malignant) or hyperplastic (benign) without the need for biopsy.
Why it matters
Colorectal cancer is the third most common type of cancer found in the Thai population. About 15 million people aged 50 and over are known to be at risk. Unfortunately, there are only About one thousand endoscopists are available in the country for colonoscopy.
In addition, the current standard method for diagnosing colorectal cancer includes colonoscopy or low GI endoscopy, which, according to researchers, has shown a variety of limitations in the shape, size and color of polyps. They point out that up to 22% of tests can be defective.
Dr Pirapon hopes that their AI polyp detection tool will be “widely used as an aid to the practice of endoscopists in other hospitals, especially those in community settings who lack medical and technical personnel”.
The technology has been applied to actual patients at King Chulalankorn Memorial Hospital since late last year.
In addition to the vendor being agnostic, DPGI can also be extended to detect abnormal biopsies in other parts of the human body. Dr Pirapon shared that his team wanted to test the system on other organs such as the stomach and bile ducts.
The research team is currently in the process of applying for a national patent for their polyp detection software.
Snapshots of the market
The previous year saw some releases of new AI support tools for diagnosis Gastrointestinal Abnormality
Chinese startup Vision AI received a CE mark in November for rolling out its AI polyp detection software. Endoscreener in Europe.
Japanese electronics firm NEC launches its own AI Diagnosis Support Tool in Japan WISE VISION Endoscopy which automatically identifies potential lesions in the colon.