AI to act as doctor’s second pair of eyes to spot nearly invisible colon cancer growths

https://www.straitstimes.com/tech/ai-to-act-as-doctor-s-second-pair-of-eyes-to-s
pot-nearly-invisible-colon-cancer-growths

  Developed with the help of biomedical company Medtronic, the tool is able
  to detect roughly 20^ more growths—or polyps—that doctors would
  otherwise miss with the human eye, according to studies by SKH.

  Endoscope image processing by AI to discern near invisible (to the naked
  eye) polyps during a gastroscopy.

  FDA's TPLC platform identifies, to date, 4 separate devices under Product
  Code QNP (gastrointestinal lesion software detection system). See
  https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfTPLC/tplc.cfm?id=2260&min_report_year=2018
  for device approval information. The polyp detector stack is defined as,
  “A gastrointestinal lesion software detection system is a
  computer-assisted detection device used in conjunction with endoscopy for
  the detection of abnormal lesions in the gastrointestinal tract. This
  device with advanced software algorithms brings attention to images to aid
  in the detection of lesions. The device may contain hardware to support
  interfacing with an endoscope.''

No medical device reports for device or patient problems. Stay tuned to this
space.

Among the many procedural risks (e.g., an unsterilized endoscope) for
gastroscopy is perforation—the endoscope, via the gastroenterologist,
pokes a hole through your intestine.

Need to wonder if the polyp detector false negative/positive outcome might
advise over-aggressive polyp biopsy frequency that elevates perforation
risk.