< Back to news

30 November 2023

AI system helps spot early-stage oesophageal cancer

A new AI system can help endoscopists recognise oesophageal cancer early, according to a study by Amsterdam UMC and TU Eindhoven. "The earlier you recognise oesophageal cancer, the better the outcome for the patient," said Jacques Bergman, professor of endoscopy at Amsterdam UMC. "We are therefore very happy with this help from artificial intelligence."
The results were published today in The Lancet Digital Health. For this study, the endoscope used by the endoscopist to look into the patient's oesophagus was connected to the AI system that assesses the images during treatment. This form of artificial intelligence was developed specifically for patients with what is known as Barrett's oesophagus. These patients have an increased risk of oesophageal cancer. Because of subtle changes, oesophageal cancer is very difficult to recognise in them and doctors regularly miss it. The patients therefore receive endoscopic research once every few years. With AI help for better recognition, there will be more certainty for these patients.
 
Instantly seen on screen
 
A unique feature of this system is that - during the endoscopic research - it can recognise oesophageal cancer on the endoscopy screen. More than 100 endoscopists from different countries tested the system with video images on a computer. When assisted by the AI system, endoscopists were significantly more likely to recognise an early form of oesophageal cancer: in 79% of cases, compared with 67% of cases without assistance.
 
International experts
 
The system's accuracy was also compared with that of international experts: endoscopists specialising in this type of cancer. It was found that the system recognised oesophageal cancer about as often as these experts. With the results of the study, the researchers hope that AI's help can be used as soon as possible in endoscopic research among patients with Barrett's oesophagus.
This project was conducted by an international consortium of 15 hospitals, led by Amsterdam UMC and TU Eindhoven.
 

This article was published on the Amsterdam UMC website (in Dutch). 
© Amsterdam UMC

Vergelijkbaar >

Similar news items

>View all news items >
 CuspAI Introduces Itself at LAB42

6 September 2024

CuspAI Introduces Itself at LAB42 >

On September 5, 2024, Max Welling and Chad Edwards, founders of CuspAI, presented their innovative company during the IvI coffee & cake gathering. 

read more >

 Advanced AI for Surveillance Robots: A Collaborative Project by Dutch Institutions

5 September 2024

Advanced AI for Surveillance Robots: A Collaborative Project by Dutch Institutions >

A consortium of leading Dutch research institutions and government agencies, including TU Delft, the University of Amsterdam, TNO, and the Royal Netherlands Marechaussee, has launched an ambitious project aimed at developing advanced artificial intelligence (AI) for surveillance robots. Officially initiated on September 4, the OpenBots consortium focuses on creating AI systems designed to assist human security officers in various security settings.

read more >

NeuroAI: Charlotte Frenkel explores the future of AI inspired by the human brain

September 5, 2024

NeuroAI: Charlotte Frenkel explores the future of AI inspired by the human brain >

With the award of an AiNed Fellowship grant, Dr. Charlotte Frenkel from TU Delft delves into neuromorphic computing, pioneering research aimed at creating energy-efficient and powerful AI systems inspired by the human brain. This research bridges AI and neuroscience to develop faster, more energy-efficient, and smarter computing systems.

read more >