Real-Time Use of Artificial Intelligence in Identification of Diminutive Polyps During Colonoscopy

There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

Abstract

Computer-aided diagnosis (CAD) for colonoscopy may help endoscopists distinguish neoplastic polyps (adenomas) requiring resection from nonneoplastic polyps not requiring resection, potentially reducing cost.

Related collections

Most cited references 15

Record: found
Abstract: found
Article: not found

The American Society for Gastrointestinal Endoscopy PIVI (Preservation and Incorporation of Valuable Endoscopic Innovations) on real-time endoscopic assessment of the histology of diminutive colorectal polyps.

Douglas Rex, Charles Kahi, Michael V O'brien … (2011)

The PIVI (Preservation and Incorporation of Valuable endoscopic Innovations) initiative is an ASGE program whose objectives are to identify important clinical questions related to endoscopy and to establish a priori diagnostic and/or therapeutic thresholds for endoscopic technologies designed to resolve these clinical questions. Additionally, PIVIs may also outline the data and or the research study design required for proving an established threshold is met. Once endoscopic technologies meet an established PIVI threshold, those technologies are appropriate to incorporate into clinical practice presuming the appropriate training in that endoscopic technology has been achieved. The ASGE encourages and supports the appropriate use of technologies that meet its established PIVI thresholds. The PIVI initiative was developed primarily to direct endoscopic technology development toward resolving important clinical issues in endoscopy. The PIVI initiative is also designed to minimize the possibility that potentially valuable innovations are prematurely abandoned due to lack of utilization and to avoid widespread use of an endoscopic technology before clinical studies documenting their effectiveness have been performed. The following document, or PIVI, is one of a series of statements defining the diagnostic or therapeutic threshold that must be met for a technique or device to become considered appropriate for incorporation into clinical practice. It is also meant to serve as a guide for researchers or those seeking to develop technologies that are designed to improve digestive health outcomes. An ad hoc committee under the auspices of the existing ASGE Technology and Standards of Practice Committees Chairs develops PIVIs. An expert in the subject area chairs the PIVI, with additional committee members chosen for their individual expertise. In preparing this document, evidence-based methodology was employed, using a MEDLINE and PubMed literature search to identify pertinent clinical studies on the topic. PIVIs are ultimately submitted to the ASGE Governing Board for approval, as is done for all Technology and Standards of Practice documents. This document is provided solely for educational and informational purposes and to support incorporating these endoscopic technologies into clinical practice. It should not be construed as establishing a legal standard of care. Copyright © 2011. Published by Mosby, Inc.

0 comments Cited 160 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: not found

Variation in the detection of serrated polyps in an average risk colorectal cancer screening cohort.

Shi Yang, David Huang, J Hetzel … (2010)

Serrated polyps are precursors in an alternative pathway to colon cancer. These polyps are frequently sessile or flat, located in the proximal colon, and may be overlooked during colonoscopy. Histological criteria to classify these polyps have only recently been described. This study assessed the variation of serrated polyp detection among endoscopists and pathologists in an average risk-screening cohort and trends in detection over time. Endoscopy and pathology reports were reviewed from all average risk-screening colonoscopies at an urban academic medical center from 2006 through 2008. Polyps were classified as adenoma (tubular, tubulovillous, or villous), serrated polyp (hyperplastic polyp (HP), sessile serrated adenoma (SSA), or dysplastic serrated polyp (DSP)), adenocarcinoma, or other. Differences in polyp detection among endoscopists and pathologists were tested with χ(2)-tests. Potential predictors of polyp detection were modeled with Poisson regression. Included in the study were 4,335 polyps from 7,192 colonoscopies. Detection prevalence (patients with at least one polyp per 100 colonoscopies) was 22.2 for adenomas, 11.7 for HP, 0.6 for SSA, and 0.2 for DSP. Detection prevalence of proximal SSAs increased from 0.2 in 2006 to 4.4 in 2008 (P<0.001). Detection prevalences among endoscopists differed significantly for adenomas, HP, and SSA. Classification rates among pathologists differed significantly for HP and SSA, but not for adenoma or DSP. On multivariate analysis, endoscopist was a significant predictor of adenoma, HP, and SSA. Pathologist was a significant predictor of HP, SSA, and DSP, but not adenoma. This study describes the detection of colorectal polyps in an average risk-screening cohort at an urban academic medical center. Detection of proximal SSAs increased during the study period. Detection of adenoma, HP, and SSA differed significantly by endoscopist. Classification of HP and SSA differed significantly by pathologist. Endoscopy and pathology practices should consider educational interventions to improve serrated polyp detection and standardize classification.

0 comments Cited 84 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: not found

Real-time optical biopsy of colon polyps with narrow band imaging in community practice does not yet meet key thresholds for clinical decisions.

URI LADABAUM, ANN FIORITTO, AYA MITANI … (2013)

Accurate optical analysis of colorectal polyps (optical biopsy) could prevent unnecessary polypectomies or allow a "resect and discard" strategy with surveillance intervals determined based on the results of the optical biopsy; this could be less expensive than histopathologic analysis of polyps. We prospectively evaluated real-time optical biopsy analysis of polyps with narrow band imaging (NBI) by community-based gastroenterologists. We first analyzed a computerized module to train gastroenterologists (N = 13) in optical biopsy skills using photographs of polyps. Then we evaluated a practice-based learning program for these gastroenterologists (n = 12) that included real-time optical analysis of polyps in vivo, comparison of optical biopsy predictions to histopathologic analysis, and ongoing feedback on performance. Twelve of 13 subjects identified adenomas with >90% accuracy at the end of the computer study, and 3 of 12 subjects did so with accuracy ≥90% in the in vivo study. Learning curves showed considerable variation among batches of polyps. For diminutive rectosigmoid polyps assessed with high confidence at the end of the study, adenomas were identified with mean (95% confidence interval [CI]) accuracy, sensitivity, specificity, and negative predictive values of 81% (73%-89%), 85% (74%-96%), 78% (66%-92%), and 91% (86%-97%), respectively. The adjusted odds ratio for high confidence as a predictor of accuracy was 1.8 (95% CI, 1.3-2.5). The agreement between surveillance recommendations informed by high-confidence NBI analysis of diminutive polyps and results from histopathologic analysis of all polyps was 80% (95% CI, 77%-82%). In an evaluation of real-time optical biopsy analysis of polyps with NBI, only 25% of gastroenterologists assessed polyps with ≥90% accuracy. The negative predictive value for identification of adenomas, but not the surveillance interval agreement, met the American Society for Gastrointestinal Endoscopy-recommended thresholds for optical biopsy. Better results in community practice must be achieved before NBI-based optical biopsy methods can be used routinely to evaluate polyps; ClinicalTrials.gov number, NCT01638091. Copyright © 2013 AGA Institute. Published by Elsevier Inc. All rights reserved.

0 comments Cited 65 times – based on 0 reviews      Review now

Bookmark

All references

Author and article information

Journal

Title: Annals of Internal Medicine

Abbreviated Title: Ann Intern Med

Publisher: American College of Physicians

ISSN (Print): 0003-4819

Publication date (Electronic): August 14 2018

Affiliations

[1 ]Showa University Northern Yokohama Hospital, Yokohama, Japan (Y.M., S.K., M.M., F.U., S.K., Y.O., Y.M., K.T., H.N., K.I., T.K., T.H., K.W., F.I.)

[2 ]National Cancer Center Hospital, Tokyo, Japan (Y.S.)

[3 ]National Cancer Center Hospital East, Kashiwa, Japan (H.I.)

[4 ]Shizuoka Cancer Center, Shizuoka, Japan (K.H.)

[5 ]Tokyo Medical and Dental University, Tokyo, Japan (K.O.)

[6 ]Showa University Koto-Toyosu Hospital, Tokyo, Japan (H.I.)

[7 ]Nagoya University, Nagoya, Japan (H.I., M.O., K.M.)

Article

DOI: 10.7326/M18-0249

PubMed ID: 30105375

SO-VID: 8ebfc220-81ae-4e02-8e98-b90cd613c2bf

History

Data availability:

Comments

Comment on this article

scite_

Cited by 158

See all cited by

Most referenced authors 339

See all reference authors

- Version 1

Real-Time Use of Artificial Intelligence in Identification of Diminutive Polyps During Colonoscopy : A Prospective Study

Read this article at

Abstract

Related collections

Artificial Intelligence in Medicine

Most cited references 15

The American Society for Gastrointestinal Endoscopy PIVI (Preservation and Incorporation of Valuable Endoscopic Innovations) on real-time endoscopic assessment of the histology of diminutive colorectal polyps.

Variation in the detection of serrated polyps in an average risk colorectal cancer screening cohort.

Real-time optical biopsy of colon polyps with narrow band imaging in community practice does not yet meet key thresholds for clinical decisions.

Author and article information

Journal

Affiliations

Article

History

Comments

Comment on this article

Similar content 5,302

Cited by 158

Most referenced authors 339