Computer-Aided Detection Improves Adenomas per Colonoscopy for Screening and Surveillance Colonoscopy: A Randomized Trial

SKOUT™ Registration Study Team

doi:10.1053/j.gastro.2022.05.028

Computer-Aided Detection Improves Adenomas per Colonoscopy for Screening and Surveillance Colonoscopy: A Randomized Trial

SKOUT™ Registration Study Team

Research output: Contribution to journal › Article › peer-review

56 Scopus citations

Abstract

BACKGROUND & AIMS: Colonoscopy for colorectal cancer screening is endoscopist dependent, and colonoscopy quality improvement programs aim to improve efficacy. This study evaluated the clinical benefit and safety of using a computer-aided detection (CADe) device in colonoscopy procedures.

METHODS: This randomized study prospectively evaluated the use of a CADe device at 5 academic and community centers by US board-certified gastroenterologists (n = 22). Participants aged ≥40 scheduled for screening or surveillance (≥3 years) colonoscopy were included; exclusion criteria included incomplete procedure, diagnostic indication, inflammatory bowel disease, and familial adenomatous polyposis. Patients were randomized by endoscopist to the standard or CADe colonoscopy arm using computer-generated, random-block method. The 2 primary endpoints were adenomas per colonoscopy (APC), the total number of adenomas resected divided by the total number of colonoscopies; and true histology rate (THR), the proportion of resections with clinically significant histology divided by the total number of polyp resections. The primary analysis used a modified intention-to-treat approach.

RESULTS: Between January and September 2021, 1440 participants were enrolled to be randomized. After exclusion of participants who did not meet the eligibility criteria, 677 in the standard arm and 682 in the CADe arm were included in a modified intention-to-treat analysis. APC increased significantly with use of the CADe device (standard vs CADe: 0.83 vs 1.05, P = .002; total number of adenomas, 562 vs 719). There was no decrease in THR with use of the CADe device (standard vs CADe: 71.7% vs 67.4%, P for noninferiority < .001; total number of non-neoplastic lesions, 284 vs 375). Adenoma detection rate was 43.9% and 47.8% in the standard and CADe arms, respectively (P = .065).

CONCLUSIONS: For experienced endoscopists performing screening and surveillance colonoscopies in the United States, the CADe device statistically improved overall adenoma detection (APC) without a concomitant increase in resection of non-neoplastic lesions (THR).

CLINICALTRIALS: gov registration: NCT04754347.

Original language	English (US)
Pages (from-to)	732-741
Number of pages	10
Journal	Gastroenterology
Volume	163
Issue number	3
DOIs	https://doi.org/10.1053/j.gastro.2022.05.028
State	Published - Sep 2022

Bibliographical note

Funding Information:
Funding Support for this study was provided by Iterative Scopes, Inc., Cambridge, Massachusetts.

Funding Information:
Conflict of interest These authors disclose the following: Aasma Shaukat reports research funding to her institution for the current manuscript from Iterative Scopes and consulting fees from Freenome Inc and Medtronic. David Lichtenstein has received consulting fees from Ambu and Olympus America Inc and reports research funding to his institution for the current manuscript and unremunerated participation in an advisory board from Iterative Scopes. Samuel C. Somers reports research funding to his institution for the current manuscript from Iterative Scopes, participation on an advisory board for Iterative Scopes, and honoraria from Harvard Medical School for a clinical teaching conference. Daniel C. Chung reports research funding to his institution for the current manuscript from Iterative Scopes. Murali Gopal, Daniel R. Colucci, and Sloane A. Phillips are employees of Iterative Scopes and hold stock or stock options in Iterative Scopes. Timothy R. Church reports research funding to his institution for the current manuscript from Iterative Scopes and has received consulting fees from Iterative Scopes. William Brugge reports unremunerated participation on an advisory board for Iterative Scopes. The remaining authors disclose no conflicts. Funding Support for this study was provided by Iterative Scopes, Inc., Cambridge, Massachusetts.

Publisher Copyright:
© 2022 The Authors

Keywords

Adenomas
Artificial Intelligence
Colonoscopy
Histology
Colonic Polyps/diagnostic imaging
Computers
Early Detection of Cancer/methods
Colorectal Neoplasms/diagnostic imaging
Adenoma/diagnostic imaging
Humans
Colonoscopy/methods

PubMed: MeSH publication types

Randomized Controlled Trial
Journal Article

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Publisher link

10.1053/j.gastro.2022.05.028

Find It

Find It at U of M Libraries

Cite this

@article{6968a3d17f0b407aa11811c075fe038a,

title = "Computer-Aided Detection Improves Adenomas per Colonoscopy for Screening and Surveillance Colonoscopy: A Randomized Trial",

abstract = "BACKGROUND & AIMS: Colonoscopy for colorectal cancer screening is endoscopist dependent, and colonoscopy quality improvement programs aim to improve efficacy. This study evaluated the clinical benefit and safety of using a computer-aided detection (CADe) device in colonoscopy procedures.METHODS: This randomized study prospectively evaluated the use of a CADe device at 5 academic and community centers by US board-certified gastroenterologists (n = 22). Participants aged ≥40 scheduled for screening or surveillance (≥3 years) colonoscopy were included; exclusion criteria included incomplete procedure, diagnostic indication, inflammatory bowel disease, and familial adenomatous polyposis. Patients were randomized by endoscopist to the standard or CADe colonoscopy arm using computer-generated, random-block method. The 2 primary endpoints were adenomas per colonoscopy (APC), the total number of adenomas resected divided by the total number of colonoscopies; and true histology rate (THR), the proportion of resections with clinically significant histology divided by the total number of polyp resections. The primary analysis used a modified intention-to-treat approach.RESULTS: Between January and September 2021, 1440 participants were enrolled to be randomized. After exclusion of participants who did not meet the eligibility criteria, 677 in the standard arm and 682 in the CADe arm were included in a modified intention-to-treat analysis. APC increased significantly with use of the CADe device (standard vs CADe: 0.83 vs 1.05, P = .002; total number of adenomas, 562 vs 719). There was no decrease in THR with use of the CADe device (standard vs CADe: 71.7% vs 67.4%, P for noninferiority < .001; total number of non-neoplastic lesions, 284 vs 375). Adenoma detection rate was 43.9% and 47.8% in the standard and CADe arms, respectively (P = .065).CONCLUSIONS: For experienced endoscopists performing screening and surveillance colonoscopies in the United States, the CADe device statistically improved overall adenoma detection (APC) without a concomitant increase in resection of non-neoplastic lesions (THR).CLINICALTRIALS: gov registration: NCT04754347.",

keywords = "Adenomas, Artificial Intelligence, Colonoscopy, Histology, Colonic Polyps/diagnostic imaging, Computers, Early Detection of Cancer/methods, Colorectal Neoplasms/diagnostic imaging, Adenoma/diagnostic imaging, Humans, Colonoscopy/methods",

author = "{SKOUT{\texttrademark} Registration Study Team} and Aasma Shaukat and Lichtenstein, {David R.} and Somers, {Samuel C.} and Chung, {Daniel C.} and Perdue, {David G.} and Murali Gopal and Colucci, {Daniel R.} and Phillips, {Sloane A.} and Marka, {Nicholas A.} and Church, {Timothy R} and Brugge, {William R.} and Robert Thompson and Robert Chehade and Burr Loew and Jackie Downing and James Vermillion and Lawrence Borges and Ruma Rajbhandari and Theodore Schafer and Sahin Coban and James Richter and Peter Carolan and Francis Colizzo and Tiffany Jeong and Marisa DelSignore and Shreya Asher and Robert McCabe and {Van Handel}, Daniel and Birtukan Cinnor and Benjamin Mitlyng and Cynthia Sherman and Feldshon, {S. David} and Amy Lounsbury and Ana Thompson and Anusha Duggirala and Irena Davies and Christopher Huang and Charles Bliss and Arpan Mohanty and Oltion Sina and Jean Mendez and Allison Iwan and Jennifer Stromberg and Jonathan Ng and Lavi Erisson and Polina Golland and Daniel Wang and Evan Wlodkowski and Joseph Carlin and Perikumar Javia",

note = "Funding Information: Funding Support for this study was provided by Iterative Scopes, Inc., Cambridge, Massachusetts. Funding Information: Conflict of interest These authors disclose the following: Aasma Shaukat reports research funding to her institution for the current manuscript from Iterative Scopes and consulting fees from Freenome Inc and Medtronic. David Lichtenstein has received consulting fees from Ambu and Olympus America Inc and reports research funding to his institution for the current manuscript and unremunerated participation in an advisory board from Iterative Scopes. Samuel C. Somers reports research funding to his institution for the current manuscript from Iterative Scopes, participation on an advisory board for Iterative Scopes, and honoraria from Harvard Medical School for a clinical teaching conference. Daniel C. Chung reports research funding to his institution for the current manuscript from Iterative Scopes. Murali Gopal, Daniel R. Colucci, and Sloane A. Phillips are employees of Iterative Scopes and hold stock or stock options in Iterative Scopes. Timothy R. Church reports research funding to his institution for the current manuscript from Iterative Scopes and has received consulting fees from Iterative Scopes. William Brugge reports unremunerated participation on an advisory board for Iterative Scopes. The remaining authors disclose no conflicts. Funding Support for this study was provided by Iterative Scopes, Inc., Cambridge, Massachusetts. Publisher Copyright: {\textcopyright} 2022 The Authors",

year = "2022",

month = sep,

doi = "10.1053/j.gastro.2022.05.028",

language = "English (US)",

volume = "163",

pages = "732--741",

journal = "Gastroenterology",

issn = "0016-5085",

publisher = "W.B. Saunders",

number = "3",

}

TY - JOUR

T1 - Computer-Aided Detection Improves Adenomas per Colonoscopy for Screening and Surveillance Colonoscopy

T2 - A Randomized Trial

AU - SKOUT™ Registration Study Team

AU - Shaukat, Aasma

AU - Lichtenstein, David R.

AU - Somers, Samuel C.

AU - Chung, Daniel C.

AU - Perdue, David G.

AU - Gopal, Murali

AU - Colucci, Daniel R.

AU - Phillips, Sloane A.

AU - Marka, Nicholas A.

AU - Church, Timothy R

AU - Brugge, William R.

AU - Thompson, Robert

AU - Chehade, Robert

AU - Loew, Burr

AU - Downing, Jackie

AU - Vermillion, James

AU - Borges, Lawrence

AU - Rajbhandari, Ruma

AU - Schafer, Theodore

AU - Coban, Sahin

AU - Richter, James

AU - Carolan, Peter

AU - Colizzo, Francis

AU - Jeong, Tiffany

AU - DelSignore, Marisa

AU - Asher, Shreya

AU - McCabe, Robert

AU - Van Handel, Daniel

AU - Cinnor, Birtukan

AU - Mitlyng, Benjamin

AU - Sherman, Cynthia

AU - Feldshon, S. David

AU - Lounsbury, Amy

AU - Thompson, Ana

AU - Duggirala, Anusha

AU - Davies, Irena

AU - Huang, Christopher

AU - Bliss, Charles

AU - Mohanty, Arpan

AU - Sina, Oltion

AU - Mendez, Jean

AU - Iwan, Allison

AU - Stromberg, Jennifer

AU - Ng, Jonathan

AU - Erisson, Lavi

AU - Golland, Polina

AU - Wang, Daniel

AU - Wlodkowski, Evan

AU - Carlin, Joseph

AU - Javia, Perikumar

N1 - Funding Information: Funding Support for this study was provided by Iterative Scopes, Inc., Cambridge, Massachusetts. Funding Information: Conflict of interest These authors disclose the following: Aasma Shaukat reports research funding to her institution for the current manuscript from Iterative Scopes and consulting fees from Freenome Inc and Medtronic. David Lichtenstein has received consulting fees from Ambu and Olympus America Inc and reports research funding to his institution for the current manuscript and unremunerated participation in an advisory board from Iterative Scopes. Samuel C. Somers reports research funding to his institution for the current manuscript from Iterative Scopes, participation on an advisory board for Iterative Scopes, and honoraria from Harvard Medical School for a clinical teaching conference. Daniel C. Chung reports research funding to his institution for the current manuscript from Iterative Scopes. Murali Gopal, Daniel R. Colucci, and Sloane A. Phillips are employees of Iterative Scopes and hold stock or stock options in Iterative Scopes. Timothy R. Church reports research funding to his institution for the current manuscript from Iterative Scopes and has received consulting fees from Iterative Scopes. William Brugge reports unremunerated participation on an advisory board for Iterative Scopes. The remaining authors disclose no conflicts. Funding Support for this study was provided by Iterative Scopes, Inc., Cambridge, Massachusetts. Publisher Copyright: © 2022 The Authors

PY - 2022/9

Y1 - 2022/9

N2 - BACKGROUND & AIMS: Colonoscopy for colorectal cancer screening is endoscopist dependent, and colonoscopy quality improvement programs aim to improve efficacy. This study evaluated the clinical benefit and safety of using a computer-aided detection (CADe) device in colonoscopy procedures.METHODS: This randomized study prospectively evaluated the use of a CADe device at 5 academic and community centers by US board-certified gastroenterologists (n = 22). Participants aged ≥40 scheduled for screening or surveillance (≥3 years) colonoscopy were included; exclusion criteria included incomplete procedure, diagnostic indication, inflammatory bowel disease, and familial adenomatous polyposis. Patients were randomized by endoscopist to the standard or CADe colonoscopy arm using computer-generated, random-block method. The 2 primary endpoints were adenomas per colonoscopy (APC), the total number of adenomas resected divided by the total number of colonoscopies; and true histology rate (THR), the proportion of resections with clinically significant histology divided by the total number of polyp resections. The primary analysis used a modified intention-to-treat approach.RESULTS: Between January and September 2021, 1440 participants were enrolled to be randomized. After exclusion of participants who did not meet the eligibility criteria, 677 in the standard arm and 682 in the CADe arm were included in a modified intention-to-treat analysis. APC increased significantly with use of the CADe device (standard vs CADe: 0.83 vs 1.05, P = .002; total number of adenomas, 562 vs 719). There was no decrease in THR with use of the CADe device (standard vs CADe: 71.7% vs 67.4%, P for noninferiority < .001; total number of non-neoplastic lesions, 284 vs 375). Adenoma detection rate was 43.9% and 47.8% in the standard and CADe arms, respectively (P = .065).CONCLUSIONS: For experienced endoscopists performing screening and surveillance colonoscopies in the United States, the CADe device statistically improved overall adenoma detection (APC) without a concomitant increase in resection of non-neoplastic lesions (THR).CLINICALTRIALS: gov registration: NCT04754347.

AB - BACKGROUND & AIMS: Colonoscopy for colorectal cancer screening is endoscopist dependent, and colonoscopy quality improvement programs aim to improve efficacy. This study evaluated the clinical benefit and safety of using a computer-aided detection (CADe) device in colonoscopy procedures.METHODS: This randomized study prospectively evaluated the use of a CADe device at 5 academic and community centers by US board-certified gastroenterologists (n = 22). Participants aged ≥40 scheduled for screening or surveillance (≥3 years) colonoscopy were included; exclusion criteria included incomplete procedure, diagnostic indication, inflammatory bowel disease, and familial adenomatous polyposis. Patients were randomized by endoscopist to the standard or CADe colonoscopy arm using computer-generated, random-block method. The 2 primary endpoints were adenomas per colonoscopy (APC), the total number of adenomas resected divided by the total number of colonoscopies; and true histology rate (THR), the proportion of resections with clinically significant histology divided by the total number of polyp resections. The primary analysis used a modified intention-to-treat approach.RESULTS: Between January and September 2021, 1440 participants were enrolled to be randomized. After exclusion of participants who did not meet the eligibility criteria, 677 in the standard arm and 682 in the CADe arm were included in a modified intention-to-treat analysis. APC increased significantly with use of the CADe device (standard vs CADe: 0.83 vs 1.05, P = .002; total number of adenomas, 562 vs 719). There was no decrease in THR with use of the CADe device (standard vs CADe: 71.7% vs 67.4%, P for noninferiority < .001; total number of non-neoplastic lesions, 284 vs 375). Adenoma detection rate was 43.9% and 47.8% in the standard and CADe arms, respectively (P = .065).CONCLUSIONS: For experienced endoscopists performing screening and surveillance colonoscopies in the United States, the CADe device statistically improved overall adenoma detection (APC) without a concomitant increase in resection of non-neoplastic lesions (THR).CLINICALTRIALS: gov registration: NCT04754347.

KW - Adenomas

KW - Artificial Intelligence

KW - Colonoscopy

KW - Histology

KW - Colonic Polyps/diagnostic imaging

KW - Computers

KW - Early Detection of Cancer/methods

KW - Colorectal Neoplasms/diagnostic imaging

KW - Adenoma/diagnostic imaging

KW - Humans

KW - Colonoscopy/methods

UR - http://www.scopus.com/inward/record.url?scp=85134769975&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85134769975&partnerID=8YFLogxK

U2 - 10.1053/j.gastro.2022.05.028

DO - 10.1053/j.gastro.2022.05.028

M3 - Article

C2 - 35643173

AN - SCOPUS:85134769975

SN - 0016-5085

VL - 163

SP - 732

EP - 741

JO - Gastroenterology

JF - Gastroenterology

IS - 3

ER -

Computer-Aided Detection Improves Adenomas per Colonoscopy for Screening and Surveillance Colonoscopy: A Randomized Trial

Abstract

Bibliographical note

Keywords

PubMed: MeSH publication types

UN SDGs

Publisher link

Find It

Other files and links

Fingerprint

Cite this