Lower Adenoma Miss Rate of Computer-Aided Detection-Assisted Colonoscopy vs Routine White-Light Colonoscopy in a Prospective Tandem Study

Abstract

See Covering the Cover synopsis on page 1193. BACKGROUND AND AIMS: Up to 30% of adenomas might be missed during screening colonoscopy-these could be polyps that appear on-screen but are not recognized by endoscopists or polyps that are in locations that do not appear on the screen at all. Computer-aided detection (CADe) systems, based on deep learning, might reduce rates of missed adenomas by displaying visual alerts that identify precancerous polyps on the endoscopy monitor in real time. We compared adenoma miss rates of CADe colonoscopy vs routine white-light colonoscopy. METHODS: We performed a prospective study of patients, 18-75 years old, referred for diagnostic, screening, or surveillance colonoscopies at a single endoscopy center of Sichuan Provincial People's Hospital from June 3, 2019 through September 24, 2019. Same day, tandem colonoscopies were performed for each participant by the same endoscopist. Patients were randomly assigned to groups that received either CADe colonoscopy (n¼184) or routine colonoscopy (n¼185) first, followed immediately by the other procedure. Endoscopists were blinded to the group each patient was assigned to until immediately before the start of each colonoscopy. Polyps that were missed by the CADe system but detected by endoscopists were classified as missed polyps. False polyps were those continuously traced by the CADe system but then determined not to be polyps by the endoscopists. The primary endpoint was adenoma miss rate, which was defined as the number of adenomas detected in the second-pass colonoscopy divided by the total number of adenomas detected in both passes. RESULTS: The adenoma miss rate was significantly lower with CADe colonoscopy (13.89%; 95% CI, 8.24%-19.54%) than with routine colonoscopy (40.00%; 95% CI, 31.23%-48.77%, P<.0001). The polyp miss rate was significantly lower with CADe colonoscopy (12.98%; 95% CI, 9.08%-16.88%) than with routine colonoscopy (45.90%; 95% CI, 39.65%-52.15%) (P<.0001). Adenoma miss rates in ascending, transverse, and descending colon were significantly lower with CADe colonoscopy than with routine colonoscopy (ascending colon 6.67% vs 39.13%; P¼.0095; transverse colon 16.33% vs 45.16%; P¼.0065; and descending colon 12.50% vs 40.91%, P¼.0364). CONCLUSIONS: CADe colonoscopy reduced the overall miss rate of adenomas by endoscopists using white-light endoscopy. Routine use of CADe might reduce the incidence of interval colon cancers. chictr.org.cn study no: ChiCTR1900023086

Current status and future perspective on artificial intelligence for lower endoscopy

“…reported a randomized back‐to‐back study using a CADe system that they developed. The adenoma miss rate was significantly lower with than without CADe (13.89% vs 40.00%, P < 0.001) 32 …”

Establishing key research questions for the implementation of artificial intelligence in colonoscopy: a modified Delphi method

“…However, retrospective, in-silico studies, using carefully curated benchmark datasets, may be important for comparisons of different algorithms, and external validation purposes, particularly since they may allow for a more objective measure of standalone technical performance. [17], and one prospective CADx trial [18]. Many considerations regarding AI trial designs are similar to the general evaluation of novel endoscopic technologies and have been discussed in detail elsewhere [19].…”

Artificial intelligence in gastrointestinal endoscopy

“…Initial CADe studies used traditional handcrafted algorithms for image analysis 17,18 ; however, several recent publications have reported on the use of DL for polyp detection. 12,[19][20][21] A small study assessed a computer-aided polyp detection model by using 24 archived colonoscopy videos containing 31 polyps. 17 Polyp location was marked by an expert endoscopist and was used as the criterion standard.…”

“…It is likely that endoscopists, with the help of a virtual chromoendoscopy or a CADx system, could render a high-confidence optical diagnosis of diminutive hyperplastic rectosigmoid polyps supporting a detect, diagnose, and leave in situ strategy, which would result in workload and cost reductions. 22 Wang et al 21 performed another CADe study that aimed to assess the ability of AI to improve colon polyp detection, measured as a reduction in the adenoma miss rate (AMR). This was a single-center, open-label, prospective, tandem colonoscopy study of patients randomly assigned to undergo CADe colonoscopy (n Z 184) or routine colonoscopy (n Z 185), followed immediately by the endoscopist performing the other procedure.…”