Copyright ©The Author(s) 2022.
World J Gastroenterol. Dec 21, 2022; 28(47): 6632-6661
Published online Dec 21, 2022. doi: 10.3748/wjg.v28.i47.6632
Table 1 Meta-analyses on efficacy of real-time computer aided detection
Ref.Studies, patientsADR
Adenoma per patient
Withdrawal time
False positives
Mean difference
Mean difference CADe vs control
Aziz et al[112], 20203 studies, 2815 patients32.9%20.8%1.580.470.260.200.9 min (P = 0.03)4.87% (n = 137)
Hassan et al[113], 20215 studies, 4354 patients36.6%25.2%1.440.580.360.220.34 min (P = 0.13)-
Spadaccini et al[114], 20216 studies, 5178 patients34.0%26.6%1.78---No significant difference-
Barua et al[115], 20215 studies, 4311 patients29.6%19.3%1.520.410.230.180.5 min11.2%
Table 2 Summary of strengths and weakness of advanced imaging technologies in adenoma detection
HD-WLIWidely availableMarginal incremental benefit over SD-WLI
Increased detection of flat, right-sided adenomas and SSAs
ChromoendoscopyIncreased detection of small and flat adenomasNo significant increase in detection of advanced adenomas
Increased dysplasia detection in IBD (compared to SD-WLI)Increased procedural time
May increase polyp detection in high-risk syndromes (serrated polyposis syndrome, HNPCC)
Virtual chromoendoscopyNBIMay improve flat lesion detectionLoss of brightness and familiarity of colour patterns
Effective in those with experience using NBINo evidence of increased total adenoma detection
Less effective when used by proceduralists inexperienced in NBI
i-SCANMay reduce miss-rates in high-risk populationsNot widely available
No difference in adenoma detection in larger studies
Insufficient evidence to recommend use
FICERetains familiar colour patternsNot widely available
No difference in ADR
LCIRetains familiar colour patternsNot widely available
Effective when used by non-LCI experienced proceduralistsVariable evidence regarding overall adenoma detection
Improve adenoma detection, particularly right sided and flat lesions
BLIImproved adenoma detection and miss rate in smaller studiesNot widely available
No difference in ADR in largest study to date
TXIRetains familiar colour patternsNot widely available
New technology therefore insufficient evidence
AFIImproved detection of flat/right sided polypsNot widely available
Increased procedure time
No difference in overall ADR
AIImproves ADRExpensive currently
Improves consistency between proceduralistsNot widely available
Quality assuranceSome increase in procedure time
FMEIn theory may improve detection of flat/poorly visible polypsInsufficient evidence
Requires injection/ingestion of tracer
Table 3 Summary of existing classification systems using advanced mucosal imaging
Imaging modality
Polyp features
TA/TVAs included
SSAs included
KudoAnyPitsAUC 0.94[143]ComplexYesNo
NICENBIVessels and pitsSensitivity 98%, NPV 97.8%[145]ModerateYesNo
JNETNBIVessels and pitsAUC 0.97 for JNET 1, 0.84 for JNET 2A, 0.9 for JNET 3 but less accurate for JNET 2B (AUC 0.72)[152]ModerateYesNo
BASICBLIVessels, pits and surfaceAccurate surveillance prediction in 90%, NPV for rectosigmoid polyps 91%[160]ModerateYesNo
WASPAnyPits, surface, shapeMay improve SSA detection[162]SimpleNoYes
mSanoNBIVessels, pits and surfaceAUC 0.92[169]SimpleYesYes
Table 4 Studies on the accuracy of AI for polyp histology prediction
Study type
Imaging modality
Number of patients/polyps
Accurate surveillance interval
Kominami et al[209], 2016RetrospectiveNBI41 patients, 118 polyps93%95%93%92.7%
Chen et al[210], 2018RetrospectiveNBI284 polyps96%78%90%-
Mori et al[211], 2018ProspectiveNBI325 patients, 466 polyps93%90%95%-
Renner et al[212], 2018RetrospectiveWLI, NBI100 polyps92%63%90%-
Byrne et al[213], 2019RetrospectiveNBI125 polyps98%83%97%-
Min et al[214], 2019ProspectiveLCI91 patients, 217 polyps83%70%71%-
Sánchez-Montes et al[206], 2019RetrospectiveWLI225 polyps92%89%87%-
Horiuchi et al[215], 2019ProspectiveAFI95 patients, 258 polyps80%95%93%-
Ozawa et al[216], 2020RetrospectiveWLI, NBI309 polyps97% for NBI, 90% for WLI-91% for NBI, 85% for WLI-
Jin et al[205], 2020RetrospectiveNBI300 polyps83%90%94%-
Zacharia et al[208], 2020RetrospectiveWLI, NBI524 polyps96%90%93%94%
Rodriguez-Diaz et al[217], 2021RetrospectiveNBI119 patients, 280 polyps96%84%91%94%
Van der Zander et al[218], 2021RetrospectiveWLI, BLI54 patients, 60 polyps96%93%88%-
Yoshida et al[220], 2021RetrospectiveBLI25 patients, 100 polyps91%85%92%-
Sakamoto et al[219], 2022RetrospectiveWLI, BLI604 polyps96% for WLI, 96% for BLI84% for WLI, 89% for BLI--
Table 5 Summary and conclusions for each form of advanced mucosal imaging discussed
HD-WLIAdvantages: Marginal benefit in overall adenoma detection; and improved detection of right-sided, flat polyps, and SSAs1Advantage: Marginal benefit for small adenomas; disadvantage: Insufficient evidence for large polypsAdvantage: Widely available
Chromo-endoscopyAdvantage: Increases polyp detection; disadvantage: Increases withdrawal timeAdvantages: Highly effective for small polyps (although inefficient); and useful in prediction of invasion depth for large polyps1Disadvantage: Increases procedural time
Virtual chromo-endoscopyNBIDisadvantage: No significant difference in ADRAdvantages: Accurate for distinguishing neoplastic from non-neoplastic small and diminutive polyps; and accurate for prediction of invasion depth1Disadvantage: Loss of brightness; neutral: Greater efficacy when used by expert proceduralists
i-SCANNeutral: Variable results, increased detection of flat and right-sided polypsAdvantage: Effective for diminutive and small polyps
FICEDisadvantage: No significant difference in ADRDisadvantage: Inferior to NBIAdvantage: Familiar colour spectrum
LCIAdvantages: Improves adenoma detection; and effective for non-expert proceduralists1Disadvantage: Insufficient evidenceAdvantage: Familiar colour spectrum
BLIDisadvantage: No significant difference in ADRAdvantage: Similar to NBI in terms of colour spectrum and accuracy1Advantage: Similar colour spectrum to NBI
TXIAdvantage: Increases polyp visibility in image-based studiesDisadvantage: Insufficient evidenceDisadvantage: Insufficient evidence; advantage: Familiar colour spectrum
AFIDisadvantage: Insufficient evidence; advantage: Improves detection of flat, right-sided polyps and reduces miss ratesDisadvantage: Inferior to NBIDisadvantage: Not widely available
AIAdvantage: Increases adenoma detection; no significant difference in withdrawal time1Advantages: Highly accurate; superior to non-expert endoscopists for histology prediction; not superior to experts using NBI1Disadvantage: Not yet widely available
FMEDisadvantages: Expensive; insufficient evidenceDisadvantage: Not widely available
Endo-cystoscopyNeutral: Accurate but requires expertise for interpretation; advantages: Uptake may increase with incorporation of AIDisadvantages: Requires additional equipment; and not widely available
Multiphoton microscopyDisadvantage: Insufficient evidenceDisadvantage: Requires additional equipment