Barrett's esophagus is a pre-cancerous condition in which the inner lining of the esophagus is replaced by a lining that resembles that of the stomach. Worldwide prevalence of Barrett's esophagus is 1% of the entire population but much higher (7%) in patients with acid-reflux symptoms (*3). Patients with Barrett's esophagus have 30-40 fold higher risk of developing cancer of the esophagus as compared to the normal population (*4).

However, if this cancer can be detected at an early stage, then it can be removed through the endoscope and a patient can be cured. Patients with Barrett's esophagus have to undergo regular endoscopy (every 2-3 years) to detect early cancer, but this is still challenging as the early changes of cancer are very subtle and difficult to identify. As a result, current recommendations are to take multiple random biopsies throughout the length of Barrett's esophagus to identify any focus of early cancer (*5, 6). However, random biopsies are expensive and time consuming and are only performed in accordance with official clinical guidelines by an estimated 30-51% of endoscopists (*7, 8, 9, 10). Consequently, it has been pointed out that up to 40% of neoplasia may be missed (*7) resulting in delayed cancer diagnosis and poor outcomes for the patients.

To help resolve this issue, NEC collaborated with Professor Pradeep Bhandari (Portsmouth, UK), Chair of the European Society of Gastrointestinal Endoscopy (ESGE) Research Committee, in development of this new technology to support doctors to detect Barrett's neoplasia during examination. WISE VISION® Endoscopy has been trained with more than 1 million Barrett's esophagus endoscopy images, together with the knowledge of expert endoscopists, enabling it to meet the requirements for CE mark labeling. In developing this solution, NEC applied its face recognition technology that has been highly evaluated (*11) by the National Institute of Standards and Technology (NIST) in the United States, and belongs to NEC's portfolio of cutting-edge AI technologies, 'NEC the WISE.'

On clinical evaluation, WISE VISION® Endoscopy could find more than 90% of Barrett's neoplasia (*12). WISE VISION® Endoscopy is expected to significantly reduce the neoplasia miss rate during endoscopy and improve the outcome for patients with Barrett's esophagus all around the world.

The abstract applying this technology has received the Gut Award from the British Society of Gastroenterology (BSG), which was presented in the plenary session of the BSG Campus. It was also selected one of the best endoscopy abstracts in UEG Week Virtual 2020 held by United European Gastroenterology.

'I am delighted that NEC, as one of the world's leaders in AI technology, has entered the field of endoscopy and developed WISE VISION® Endoscopy to detect and help manage Gastrointestinal neoplasia. Barrett's neoplasia can be very flat and easily missed during endoscopy, despite taking multiple biopsies. I worked with NEC to develop the Barrett's neoplasia detection arm of WISE VISION® Endoscopy and am super impressed by the speed with which NEC has produced this as the World's first AI engine to obtain the CE mark for notifying Barrett's neoplasia.

'WISE VISION® Endoscopy can notify very flat and subtle lesions and much faster than most endoscopists. Once the neoplasia is found, this system takes a still image and transfers it to the top right corner of a screen as a reference image for endoscopists. It doesn't stop here, as it also has a heat map which shows the area of the AI-predicted neoplasia. WISE VISION® Endoscopy is set to revolutionize the endoscopic detection and management of Barrett's neoplasia in the western world. I'm sure that clinicians involved in the management of Barrett's esophagus are looking forward to the dawn of this new (Wise) era in Endoscopy,' said Professor Pradeep Bhandari, Chair of the ESGE Research Committee.

Attachments

  • Original document
  • Permalink

Disclaimer

NEC Corporation published this content on 28 May 2021 and is solely responsible for the information contained therein. Distributed by Public, unedited and unaltered, on 28 May 2021 08:10:04 UTC.