Endoscopy 2020; 52(S 01): S235-S236
DOI: 10.1055/s-0040-1704737
ESGE Days 2020 ePoster Podium presentations
Saturday, April 25, 2020 15:00 – 15:30 Artificial Intelligence for colonoscopy and ePoster Podium 4 small: Bowel endoscopy
© Georg Thieme Verlag KG Stuttgart · New York

ARTIFICIAL INTELLIGENCE ALLEVIATES THE TEDIOUS TASK OF READING SMALL BOWEL CAPSULE ENDOSCOPY RECORDINGS

R Leenhardt
1   Sorbonne University, APHP, Saint Antoine Hospital, Paris, France
,
M Souchaud
2   University of Cergy Pontoise, ENSEA, ETIS, Cergy Pontoise, France
,
A Becq
1   Sorbonne University, APHP, Saint Antoine Hospital, Paris, France
,
A Histace
2   University of Cergy Pontoise, ENSEA, ETIS, Cergy Pontoise, France
,
X Dray
1   Sorbonne University, APHP, Saint Antoine Hospital, Paris, France
,
CAD-CAP Database Working Group › Author Affiliations
Further Information

Publication History

Publication Date:
23 April 2020 (online)

Also available at
 

Artificial intelligence (AI) is a disruptive technology that has the potential of alleviating the tedious and time-consuming task of reading small bowel (SB) capsule endoscopy (CE) videos. This videocase illustrates the concept of automated SB reading of CE recordings. Two SB-CE (Pillcam SB3, Medtronic, USA) recordings are presented, one with angiectasias, one with superficial ulcerations. All lesions identified by CE expert readers were detected, segmented and characterized as well by a neural network-based software (Augmented Endoscopy, France), with significant decreases of the reading times (30 vs 5 minutes).