Summary: Fujifilm’s AI CAD Eye system, approved by the FDA, enhances the detection and removal of precancerous colorectal lesions by providing real-time visual and auditory alerts, improving the accuracy and efficiency of colonoscopies and reducing missed lesions.

Key Takeaways

  1. Fujifilm Healthcare Americas Corp. received FDA 510(k) clearance for CAD Eye, an AI system for real-time detection of colonic mucosal lesions during colonoscopy procedures.
  2. CAD Eye uses deep learning to aid in detecting difficult-to-spot lesions, providing real-time visual and auditory alerts to improve accuracy and efficiency in identifying and removing pre-cancerous lesions.
  3. Studies show CAD Eye improves colorectal cancer detection by increasing adenoma detection rates by 17% compared to conventional colonoscopy, with performance comparable to experts.


Fujifilm Healthcare Americas Corp. has received U.S. FDA 510(k) clearance for CAD Eye, an AI detection system for endoscopic imaging. CAD Eye detects colonic mucosal lesions, such as polyps and adenomas, in real-time during colonoscopy procedures, aiding endoscopists in identifying and removing pre-cancerous lesions of various sizes, shapes, and colors.

Real-Time Alerts for Polyp Detection

CAD Eye includes the Fujifilm EX-1 expansion unit and endoscopy support software (EW10-EC02), enhancing the ELUXEO Endoscopic Imaging System with AI image processing. Developed using deep learning at Fujifilm’s AI technology center in Tokyo, CAD Eye has been validated in studies using histologically confirmed polyps in clinical images.

The technology aids in detecting difficult-to-spot lesions, such as flat lesions, those at the edge of the endoscopic view, and multiple lesions in a single frame. When CAD Eye detects a suspicious polyp, it provides visual and auditory alerts: a “Detection Box” appears, a “Visual Assist Circle” highlights the area, and an adjustable alert sounds. These visual cues overlay the clinical images without interfering with the physician’s workflow.

Boosting Early Colorectal Cancer Detection

“Colorectal cancer is the second leading cause of cancer deaths in U.S. women and men combined, despite screening—primarily colonoscopy—being one of the most reliable and effective methods for cancer prevention and early intervention,” says Tai Fujita, FujiFilm’s general manager of endoscopy. “Today, we’re thrilled to take that a step further with the introduction of Cad Eye, which has the potential to dramatically improve the quality of colonoscopy.”

Studies indicate that CAD Eye can improve colorectal cancer detection and diagnosis by:

  • Detecting more adenomas during screening and surveillance compared to conventional high-definition colonoscopy without AI assistance, without increasing procedure time.
  • Achieving a 17% higher adenoma per colonoscopy (APC) rate compared to high-definition conventional colonoscopy.
  • Detecting colorectal neoplastic lesions at a level comparable to experts and superior to beginners.

Advancement in Gastrointestinal Healthcare

“As a gastroenterologist dedicated to patient care and safety, I’m heartened by the FDA’s approval of Fujifilm’s AI CAD polyp detection algorithm,” says Sravanthi Parasa MD, FASGE, a gastroenterologist at Swedish Medical Center in Englewood, Colo.

Parasa adds, “This breakthrough not only enables the early detection of precancerous lesions that can lead up to colorectal cancer but also significantly reduces the risk of missed lesions, enhancing our precision and improving patient outcomes. It marks a pivotal advancement in our ability to safeguard patient health, reinforcing our commitment to embracing technological innovations in gastrointestinal healthcare.”