Published online Aug 21, 2021. doi: 10.3748/wjg.v27.i31.5232
Peer-review started: February 19, 2021
First decision: March 28, 2021
Revised: April 10, 2021
Accepted: July 20, 2021
Article in press: July 20, 2021
Published online: August 21, 2021
Processing time: 180 Days and 5.1 Hours
Artificial intelligence in colonoscopy is an emerging field, and its application may help colonoscopists improve inspection quality and reduce the rate of missed polyps and adenomas. Several deep learning-based computer-assisted detection (CADe) techniques were established from small single-center datasets, and unrepresentative learning materials might confine their application and generalization in wide practice. Although CADes have been reported to identify polyps in colonoscopic images and videos in real time, their diagnostic performance deserves to be further validated in clinical practice.
To train and test a CADe based on multicenter high-quality images of polyps and preliminarily validate it in clinical colonoscopies.
With high-quality screening and labeling from 55 qualified colonoscopists, a dataset consisting of over 71000 images from 20 centers was used to train and test a deep learning-based CADe. In addition, the real-time diagnostic performance of CADe was tested frame by frame in 47 unaltered full-ranged videos that contained 86 histologically confirmed polyps. Finally, we conducted a self-controlled observational study to validate the diagnostic performance of CADe in real-world colonoscopy with the main outcome measure of polyps per colonoscopy in Changhai Hospital.
The CADe was able to identify polyps in the test dataset with 95.0% sensitivity and 99.1% specificity. For colonoscopy videos, all 86 polyps were detected with 92.2% sensitivity and 93.6% specificity in frame-by-frame analysis. In the prospective validation, the sensitivity of CAD in identifying polyps was 98.4% (185/188). Folds, reflections of light and fecal fluid were the main causes of false positives in both the test dataset and clinical colonoscopies. Colonoscopists can detect more polyps (0.90 vs 0.82, P < 0.001) and adenomas (0.32 vs 0.30, P = 0.045) with the aid of CADe, particularly polyps < 5 mm and flat polyps (0.65 vs 0.57, P < 0.001; 0.74 vs 0.67, P = 0.001, respectively). However, high efficacy is not realized in colonoscopies with inadequate bowel preparation and withdrawal time (P = 0.32; P = 0.16, respectively).
CADe is feasible in the clinical setting and might help endoscopists detect more polyps and adenomas, and further confirmation is warranted.
Core Tip: Our study indicated that the deep learning-based computer-assisted detection system trained from the dataset consisting of the largest number of polyps achieved high diagnostic performance on the test dataset of images, colonoscopy videos and clinical validation. This system might aid colonoscopists in finding more polyps and adenomas and deserves to be further validated in multicenter randomized trials.