AI impressive as a second set of eyes in colonoscopy
Researchers have developed a deep convolutional neural network that can identify colorectal polyps with 90% accuracy while ruling out 80% of false flags.
The images used for that part of the trial were 116,529 single frames from colonoscopy videos of 278 patients.
When the network interpreted complete videos from 42 consecutive patients, it boosted detection rates by as much as 50% over physician-alone reads.
The work is described in a study running in the European Journal of Gastroenterology & Hepatology.
Senior author Timo Rath, MD, PhD, of Friedrich-Alexander University in Germany and colleagues note that, of 13 videoed lesions that the network flagged and the physicians missed, most were small and flat—and three of these were sessile serrated adenomas.
In earlier research the latter have been called the “evil twin among the colorectal cancer precursors. … These lesions should be on endoscopists’ most wanted list” (Ahnen and colleagues at the University of Colorado, Current Treatment Options in Gastroenterology, March 2015).
In the present study Rath and colleagues point out that the use of AI “represents an objective approach to increase endoscopist’s adenoma detection rate and limit interoperator variability.”
Their newly developed deep convolutional neural network, they add, “enables highly sensitive automated detection of colorectal polyps both ex vivo and during first in-human clinical testing and could potentially increase the detection of colorectal polyps during colonoscopy.”
The same edition of the European gastro journal presents an opinion piece on AI in gastroenterology by two gastroenterologists at the University of British Columbia.
Focusing on use of the technology for measuring colonic polyps, Roberto Trasolini, MD, and Michael Byrne, MD, write:
“Estimation of polyp size may be an ideal application of artificial intelligence given the historical challenge of this task documented in the gastroenterology literature. … While much work remains to be done, this is an important area which will no doubt be expanded upon.”
Byrne founded and leads a gastroenterology AI startup, Satisfai Health.
The opinion piece is available in full for free.
Dave P. has worked in journalism, marketing and public relations for more than 30 years, frequently concentrating on hospitals, healthcare technology and Catholic communications. He has also specialized in fundraising communications, ghostwriting for CEOs of local, national and global charities, nonprofits and foundations.