File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Feedback from artificial intelligence improved the learning of junior endoscopists on histology prediction of gastric lesions

TitleFeedback from artificial intelligence improved the learning of junior endoscopists on histology prediction of gastric lesions
Authors
KeywordsLYMPH-NODE METASTASIS
INTESTINAL METAPLASIA
MAGNIFYING ENDOSCOPY
CANCER
DIAGNOSIS
Issue Date2020
PublisherThieme Open. The Journal's web site is located at https://www.thieme-connect.de/products/ejournals/journal/10.1055/s-00025476
Citation
Endoscopy International Open, 2020, v. 8 n. 2, p. E139-E146 How to Cite?
AbstractBackground and study aims Artificial intelligence (AI)-assisted image classification has been shown to have high accuracy on endoscopic diagnosis. We evaluated the potential effects of use of an AI-assisted image classifier on training of junior endoscopists for histological prediction of gastric lesions. Methods An AI image classifier was built on a convolutional neural network with five convolutional layers and three fully connected layers A Resnet backbone was trained by 2,000 non-magnified endoscopic gastric images. The independent validation set consisted of another 1,000 endoscopic images from 100 gastric lesions. The first part of the validation set was reviewed by six junior endoscopists and the prediction of AI was then disclosed to three of them (Group A) while the remaining three (Group B) were not provided this information. All endoscopists reviewed the second part of the validation set independently. Results The overall accuracy of AI was 91.0 % (95 % CI: 89.2-92.7 %) with 97.1 % sensitivity (95 % CI: 95.6-98.7%), 85.9 % specificity (95 % CI: 83.0-88.4 %) and 0.91 area under the ROC (AUROC) (95 % CI: 0.89-0.93). AI was superior to all junior endoscopists in accuracy and AUROC in both validation sets. The performance of Group A endoscopists but not Group B endoscopists improved on the second validation set (accuracy 69.3 % to 74.7 %; P = 0.003). Conclusion The trained AI image classifier can accurately predict presence of neoplastic component of gastric lesions. Feedback from the AI image classifier can also hasten the learning curve of junior endoscopists in predicting histology of gastric lesions.
Persistent Identifierhttp://hdl.handle.net/10722/284573
ISSN
2023 Impact Factor: 2.2
2020 SCImago Journal Rankings: 0.108
PubMed Central ID
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorLui, TKL-
dc.contributor.authorWong, KKY-
dc.contributor.authorMak, LLY-
dc.contributor.authorTo, EWP-
dc.contributor.authorTsui, VWM-
dc.contributor.authorDeng, Z-
dc.contributor.authorGuo, J-
dc.contributor.authorNi, L-
dc.contributor.authorCheung, MKS-
dc.contributor.authorLeung, WK-
dc.date.accessioned2020-08-07T08:59:33Z-
dc.date.available2020-08-07T08:59:33Z-
dc.date.issued2020-
dc.identifier.citationEndoscopy International Open, 2020, v. 8 n. 2, p. E139-E146-
dc.identifier.issn2364-3722-
dc.identifier.urihttp://hdl.handle.net/10722/284573-
dc.description.abstractBackground and study aims Artificial intelligence (AI)-assisted image classification has been shown to have high accuracy on endoscopic diagnosis. We evaluated the potential effects of use of an AI-assisted image classifier on training of junior endoscopists for histological prediction of gastric lesions. Methods An AI image classifier was built on a convolutional neural network with five convolutional layers and three fully connected layers A Resnet backbone was trained by 2,000 non-magnified endoscopic gastric images. The independent validation set consisted of another 1,000 endoscopic images from 100 gastric lesions. The first part of the validation set was reviewed by six junior endoscopists and the prediction of AI was then disclosed to three of them (Group A) while the remaining three (Group B) were not provided this information. All endoscopists reviewed the second part of the validation set independently. Results The overall accuracy of AI was 91.0 % (95 % CI: 89.2-92.7 %) with 97.1 % sensitivity (95 % CI: 95.6-98.7%), 85.9 % specificity (95 % CI: 83.0-88.4 %) and 0.91 area under the ROC (AUROC) (95 % CI: 0.89-0.93). AI was superior to all junior endoscopists in accuracy and AUROC in both validation sets. The performance of Group A endoscopists but not Group B endoscopists improved on the second validation set (accuracy 69.3 % to 74.7 %; P = 0.003). Conclusion The trained AI image classifier can accurately predict presence of neoplastic component of gastric lesions. Feedback from the AI image classifier can also hasten the learning curve of junior endoscopists in predicting histology of gastric lesions.-
dc.languageeng-
dc.publisherThieme Open. The Journal's web site is located at https://www.thieme-connect.de/products/ejournals/journal/10.1055/s-00025476-
dc.relation.ispartofEndoscopy International Open-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.subjectLYMPH-NODE METASTASIS-
dc.subjectINTESTINAL METAPLASIA-
dc.subjectMAGNIFYING ENDOSCOPY-
dc.subjectCANCER-
dc.subjectDIAGNOSIS-
dc.titleFeedback from artificial intelligence improved the learning of junior endoscopists on histology prediction of gastric lesions-
dc.typeArticle-
dc.identifier.emailMak, LLY: lungyi@hku.hk-
dc.identifier.emailCheung, MKS: cks634@hku.hk-
dc.identifier.emailLeung, WK: waikleung@hku.hk-
dc.identifier.authorityMak, LLY=rp02668-
dc.identifier.authorityCheung, MKS=rp02532-
dc.identifier.authorityLeung, WK=rp01479-
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1055/a-1036-6114-
dc.identifier.pmid32010746-
dc.identifier.pmcidPMC6976335-
dc.identifier.hkuros312214-
dc.identifier.volume8-
dc.identifier.issue2-
dc.identifier.spageE139-
dc.identifier.epageE146-
dc.identifier.isiWOS:000508588000007-
dc.publisher.placeGermany-
dc.identifier.issnl2196-9736-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats