UEGJournal Abstracts 2021 - 810

Endoscopy and imaging
The overall ADR was numerically higher in the intervention group (75.0%
vs 53.8%, p= 0.119). The differential ADR for 5-10mm adenomas was significantly
higher in the intervention group (66.7% vs 38.5%, p= 0.046). The
mean number of adenomas was comparable between two groups (1.58 vs
1.69, p= 0.653). The advanced adenoma detection rate was similar (8.3%
vs 11.5%, p= 0.706). The SSL (8.3% vs 0%, p= 0.225) and cancer (4.2% vs
0%, p= 0.480) detection rates were numerically higher in the intervention
group. The mean number of non-neoplastic resection was similar (0.83 vs
0.85, p= 0.435).
Conclusion: We observed a potential benefit of the new CADe system
(ENDO-AID) in enhancing the performance of junior endoscopists to detect
neoplasms during colonoscopies, especially for 5-10mm adenomas. It
warrants further investigation in a large-scale randomized controlled trial.
References:
1. Munroe CA, Lee P, Copland A, et al. A tandem colonoscopy study of adenoma
miss rates during endoscopic training: a venture into uncharted
territory. Gastrointest Endosc. 2012 Mar;75(3):561-7.
2. Pohl H, Robertson DJ. Colorectal cancers detected after colonoscopy
frequently result from missed lesions. Clin Gastroenterol Hepatol. 2010
Oct;8(10):858-64.
3. Wang P, Berzin TM, Glissen Brown JR, et al. Real-time automatic detection
system increases colonoscopic polyp and adenoma detection rates:
a prospective randomised controlled study. Gut. 2019 Oct;68(10):18131819.
4.
Wang P, Liu X, Berzin TM, et al. Effect of a deep-learning computer-aided
detection system on adenoma detection during colonoscopy (CADe-DB
trial): a double-blind randomised study. Lancet Gastroenterol Hepatol.
2020 Apr;5(4):343-351.
5. Repici A, Badalamenti M, Maselli R, et al. Efficacy of Real-Time Computer-Aided
Detection of Colorectal Neoplasia in a Randomized Trial. Gastroenterology.
2020 Aug;159(2):512-520.e7.
6. Wang P, Liu P, Glissen Brown JR, et al. Lower Adenoma Miss Rate of
Computer-Aided Detection-Assisted Colonoscopy vs Routine White-Light
Colonoscopy in a Prospective Tandem Study. Gastroenterology. 2020
Oct;159(4):1252-1261.e5.
7. Hassan C, Spadaccini M, Iannone A, et al. Performance of artificial intelligence
in colonoscopy for adenoma and polyp detection: a systematic
review and meta-analysis. Gastrointest Endosc. 2021 Jan;93(1):77-85.e6.
Disclosure: Philip WY Chiu has served as a speaker for Olympus and an
advisory committee member for EndoMASTER and Aptorum.
The other authors do not have any conflict of interest to declare.
The study was not directly supported by any research grant or industry.
Essential equipment including the computer-aided polyp detection and
endoscopy systems (ENDO-AID; Olympus EVIS X1 CV-1500; Olympus Co.,
Tokyo, Japan) were loaned from Olympus Corporation with no extra funding.
P0943
ENDOSCOPIC
MEASUREMENT FUNDAMENTALS - FIRST IN HUMAN
STUDY FOR SAFETY AND USABILITY
S. Odeh1
, O. Goldstein1,2
T. Rainis1,2
1
2
, A. Partoush Abbou1
, M. Carlebach1
,
Bnai Zion Medical Center, Gastroenterology Unit, Haifa, Israel,
Technion, Ruth and Bruce Rappaport Faculty of Medicine, Haida,
Israel
Contact E-Mail Address: safwatod@gmail.com
Introduction: Assessing the size of polyps during colonoscopy is part of
the guidelines1
. It is traditionally done by visual assessment which has
been proven to be inaccurate. According to a previous study, approximate810
UEG
Journal | Abstract Book
ly 1 of 3 polypectomies yielded inappropriate surveillance recommendations
because of clinical mis-sizing2
proof-of-concept ex-vivo study for endoscopic measurement3
. The current work follows a previous
.
Aims & Methods: The aim of this study was to assess the applicability of
a novel endoscopic system (AccuMeasure™, by VTM Technologies Ltd.)
for measuring polyp size during colonoscopy. This study addressed the
safety and usability aspects of the system. It was not intended to provide
quantitative data on size and accuracy, which was validated separately in
a phantom model.
The system is composed of two separate units: a through-the-scope
probe emitting a laser line (similar to a barcode reader) referred to as a
Virtual Tape Measure (VTM), and a medical grade PC for conducting the
measurement on screen. The measurements were performed by aligning
the VTM across the polyp to be measured, freezing the endoscope image,
and designating two points along the VTM between which the 3D
Euclidean distance is to be displayed. The system was used in 30 colonoscopies.
For each polyp detected during a procedure, the physician and
the supporting staff handled the device and system to obtain on-screen
measurements while noting their own qualitative assessment of the various
usability aspects (score of 1-5). The time to obtain a measurement
was also recorded.
Results: A total of 71 patients were enrolled in the study, of whom 9 were
excluded due to poor preparation, 30 had no findings and 2 more patients
were excluded due to an endoscope fault unrelated to the device. The remaining
30 patients had one or more polyps. Four physicians participated,
measuring a total of 43 polyps. It was noted that in regions of sub-optimal
preparation, cases of partial visibility of the polyp or exaggerated peristalsis,
measurements could not be made. This was the case in 12/43 of the
polyps. Of the remaining 31 polyps, the physicians successfully measured
size of 28 polyps. In-vivo cleaning was routinely required for clear visualisation
of the VTM and probe tip markers and obtained a score of 4.5/5 (SD
0.8). The probe was found to respond adequately to rotation to allow measurement,
with a score of 4.9/5 (SD 0.3). The software was straightforward
and intuitive to operate, scoring 5/5 in all usability aspects, aside for two
incidents of software freeze (of all 71 cases).
In some cases, the system required recurrent capture of images to enable
measurement. Even though the study did not focus on speed of operation,
it was noted that 16 of 28 polyps were measured within 2 minutes or
less. Four measurements were achieved in 60 seconds or less. No adverse
events were reported.
Conclusion: The AccuMeasure™ endoscopic measurement system was
found to be safe and easy to use while providing good user experience.
Further multi-center trials are scheduled in the near future, which will focus
on the correlation between the duration for obtaining measurements
and experience gained, and on comparing the assessment of size made by
physicians to the reference measurement obtained by the system.
References:
1. Hassan C, Antonelli G, Dumonceau JM, et al. Post-polypectomy colonoscopy
surveillance: European Society of Gastrointestinal Endoscopy
(ESGE) Guideline - Update 2020. Endoscopy. 2020 Aug;52(8):687-700. doi:
10.1055/a-1185-3109. Epub 2020 Jun 22. PMID: 32572858.
2. Eichenseer PJ, Dhanekula R, Jakate S, et al. Endoscopic mis-sizing of
polyps changes colorectal cancer surveillance recommendations. Dis Colon
Rectum. 2013 Mar;56(3):315-21. doi: 10.1097/DCR.0b013e31826dd138.
PMID: 23392145.
3. Goldstein O, Segol O, Gross SA, et al. Novel device for measuring polyp
size: an ex vivo animal study. Gut 2018;67:1755-1756
Disclosure: Nothing to disclose.
UEGJournal Abstracts 2021

Table of Contents for the Digital Edition of UEGJournal Abstracts 2021
