Copyright ©The Author(s) 2021.
World J Gastroenterol. Sep 21, 2021; 27(35): 5908-5918
Published online Sep 21, 2021. doi: 10.3748/wjg.v27.i35.5908
Table 1 Summary of the studies on convolutional neural network algorithms for the optical diagnosis of colorectal polyps
Study design (training/testing)
Multi-centre study
Image quality
Classification system
Lesion number (training/testing)
SSL excluded
Endoscopic processor
Image modality (training)
Real-time capability
Komeda et al[37]RetrospectiveSingleVideoNot specifiedAdenoma/non-adenomaNot specified/10NoNot specifiedWLI, NBI, chromoendoscopyNot specified
Chen et al[25]Retrospective/prospectiveSingleStillHQHyperplastic/neoplastic2157/284YesOlympus 260 + 290Magnified NBIReal-time (approximately 450 ms)
Byrne et al[23]Retrospective/prospectiveSingleVideoAll imagesNICE Type 1/NICE Type 2220/125YesOlympus 190NBI-NFReal-time ( approximately 50 ms)
Zachariah et al[26]ProspectiveTwoStillAdequate and HQAdenomatous/serrated polyp5278/634NoOlympus 190 (90%), 180 (7%), Pentax i10(3%)WLI, NBI, i-SCANReal-time ( approximately 13 ms)
Ozawa et al[38]Retrospective/prospectiveSingleStillHQHyperplastic/adenomatous/SSL/CRC/otherWLI: 17566/783 NBI: 2865/290NoOlympus 260 + 290WLI, NBIReal-time (approximately 20 ms)
Jin et al[31]Retrospective/prospectiveSingleStillHQHyperplastic/adenomatous2150/300YesOlympus 290NBI-NFReal-time (approximately 10 ms)
Song et al[39]Retrospective/prospectiveSingleStillHQSerrated polyp/benign adenoma/MSM/DSMC624/545NoOlympus 290NBI-NFReal-time ( approximately 20-40 ms)
Rodriguez-Diaz et al[28]Retrospective/prospectiveTwoStillNot specifiedNeoplastic (adenomas, CRC)/non-neoplastic (hyperplastic, normal)607/280Training: Yes Testing: No Olympus 190NBI-NF, NBI (digital magnification)Real-time (approximately 100 ms)
van der Zander et al[27]Retrospective/prospectiveNot specifiedStillHQBenign (hyperplastic)/pre-malignant (adenomatous, SSL, T1 CRC)398/60NoFujifilm, PentaxWLI, BLI, i-SCANReal-time (approximately 14.8 ms)
Table 2 Summary of the per-polyp results of studies on convolutional neural network algorithms for the optical diagnosis of colorectal polyps (cross-validation results not included)
Image Modality (testing)
Sensitivity (%)
Specificity (%)
PPV (%)
NPV (%)
Accuracy for neoplasia (%)
PIVI 1 achieved (%)
PIVI 2 achieved (%)
Komeda et al[37]Not specified----70--
Chen et al[25]Magnified NBI96.378.189.691.590.1-Yes (91.5)
Byrne et al[23]NBI-NF9883909794-Yes (97)
Zachariah et al[26]NBI---96.593.1Yes (98.3)Yes (96.5)
WLI---88.992.8Yes (90.8)No (88.9)
Ozawa et al[38]1NBI97-8488---
Jin et alNBI-NF83.391.793.378.686.7--
Song et al[39]NBI-NF (test set 1)84.17488.367.7---
NBI-NF (test set 2)88.572.188.684.7---
Rodriguez-Diaz et al[28]NBI-NF (90%) + NBI (10%)9588-93-Yes (94 (20/90 LC))Yes (98 (6/68 LC))
van der Zander et al[27]WLI + BLI95.693.397.787.595.0-No (87.5)