Computer-aided detection of colorectal polyps using a newly generated deep convolutional neural network : from development to first clinical experience
Copyright © 2021 The Author(s). Published by Wolters Kluwer Health, Inc..
AIM: The use of artificial intelligence represents an objective approach to increase endoscopist's adenoma detection rate (ADR) and limit interoperator variability. In this study, we evaluated a newly developed deep convolutional neural network (DCNN) for automated detection of colorectal polyps ex vivo as well as in a first in-human trial.
METHODS: For training of the DCNN, 116 529 colonoscopy images from 278 patients with 788 different polyps were collected. A subset of 10 467 images containing 504 different polyps were manually annotated and treated as the gold standard. An independent set of 45 videos consisting of 15 534 single frames was used for ex vivo performance testing. In vivo real-time detection of colorectal polyps during routine colonoscopy by the DCNN was tested in 42 patients in a back-to-back approach.
RESULTS: When analyzing the test set of 15 534 single frames, the DCNN's sensitivity and specificity for polyp detection and localization within the frame was 90% and 80%, respectively, with an area under the curve of 0.92. In vivo, baseline polyp detection rate and ADR were 38% and 26% and significantly increased to 50% (P = 0.023) and 36% (P = 0.044), respectively, with the use of the DCNN. Of the 13 additionally with the DCNN detected lesions, the majority were diminutive and flat, among them three sessile serrated adenomas.
CONCLUSION: This newly developed DCNN enables highly sensitive automated detection of colorectal polyps both ex vivo and during first in-human clinical testing and could potentially increase the detection of colorectal polyps during colonoscopy.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2021 |
|---|---|
| Erschienen: |
2021 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:33 |
|---|---|
| Enthalten in: |
European journal of gastroenterology & hepatology - 33(2021), 1S Suppl 1 vom: 01. Dez., Seite e662-e669 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Pfeifer, Lukas [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| Anmerkungen: |
Date Completed 11.04.2022 Date Revised 05.10.2022 published: Print ClinicalTrials.gov: NCT04359355 Citation Status MEDLINE |
|---|
| doi: |
10.1097/MEG.0000000000002209 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM325833052 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM325833052 | ||
| 003 | DE-627 | ||
| 005 | 20231225193301.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231225s2021 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1097/MEG.0000000000002209 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1086.xml |
| 035 | |a (DE-627)NLM325833052 | ||
| 035 | |a (NLM)34034272 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Pfeifer, Lukas |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Computer-aided detection of colorectal polyps using a newly generated deep convolutional neural network |b from development to first clinical experience |
| 264 | 1 | |c 2021 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 11.04.2022 | ||
| 500 | |a Date Revised 05.10.2022 | ||
| 500 | |a published: Print | ||
| 500 | |a ClinicalTrials.gov: NCT04359355 | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Copyright © 2021 The Author(s). Published by Wolters Kluwer Health, Inc. | ||
| 520 | |a AIM: The use of artificial intelligence represents an objective approach to increase endoscopist's adenoma detection rate (ADR) and limit interoperator variability. In this study, we evaluated a newly developed deep convolutional neural network (DCNN) for automated detection of colorectal polyps ex vivo as well as in a first in-human trial | ||
| 520 | |a METHODS: For training of the DCNN, 116 529 colonoscopy images from 278 patients with 788 different polyps were collected. A subset of 10 467 images containing 504 different polyps were manually annotated and treated as the gold standard. An independent set of 45 videos consisting of 15 534 single frames was used for ex vivo performance testing. In vivo real-time detection of colorectal polyps during routine colonoscopy by the DCNN was tested in 42 patients in a back-to-back approach | ||
| 520 | |a RESULTS: When analyzing the test set of 15 534 single frames, the DCNN's sensitivity and specificity for polyp detection and localization within the frame was 90% and 80%, respectively, with an area under the curve of 0.92. In vivo, baseline polyp detection rate and ADR were 38% and 26% and significantly increased to 50% (P = 0.023) and 36% (P = 0.044), respectively, with the use of the DCNN. Of the 13 additionally with the DCNN detected lesions, the majority were diminutive and flat, among them three sessile serrated adenomas | ||
| 520 | |a CONCLUSION: This newly developed DCNN enables highly sensitive automated detection of colorectal polyps both ex vivo and during first in-human clinical testing and could potentially increase the detection of colorectal polyps during colonoscopy | ||
| 650 | 4 | |a Journal Article | |
| 700 | 1 | |a Neufert, Clemens |e verfasserin |4 aut | |
| 700 | 1 | |a Leppkes, Moritz |e verfasserin |4 aut | |
| 700 | 1 | |a Waldner, Maximilian J |e verfasserin |4 aut | |
| 700 | 1 | |a Häfner, Michael |e verfasserin |4 aut | |
| 700 | 1 | |a Beyer, Albert |e verfasserin |4 aut | |
| 700 | 1 | |a Hoffman, Arthur |e verfasserin |4 aut | |
| 700 | 1 | |a Siersema, Peter D |e verfasserin |4 aut | |
| 700 | 1 | |a Neurath, Markus F |e verfasserin |4 aut | |
| 700 | 1 | |a Rath, Timo |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t European journal of gastroenterology & hepatology |d 1996 |g 33(2021), 1S Suppl 1 vom: 01. Dez., Seite e662-e669 |w (DE-627)NLM074735322 |x 1473-5687 |7 nnns |
| 773 | 1 | 8 | |g volume:33 |g year:2021 |g number:1S Suppl 1 |g day:01 |g month:12 |g pages:e662-e669 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1097/MEG.0000000000002209 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 33 |j 2021 |e 1S Suppl 1 |b 01 |c 12 |h e662-e669 | ||