Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

AI-assisted capsule endoscopy reading in suspected small bowel bleeding : a multicentre prospective study

Spada, Cristiano ; Piccirelli, Stefania ; Hassan, Cesare ; Ferrari, Clarissa ; Toth, Ervin LU ; González-Suárez, Begoña ; Keuchel, Martin ; McAlindon, Marc ; Finta, Ádám and Rosztóczy, András , et al. (2024) In The Lancet Digital Health 6(5). p.345-353
Abstract

Background: Capsule endoscopy reading is time consuming, and readers are required to maintain attention so as not to miss significant findings. Deep convolutional neural networks can recognise relevant findings, possibly exceeding human performances and reducing the reading time of capsule endoscopy. Our primary aim was to assess the non-inferiority of artificial intelligence (AI)-assisted reading versus standard reading for potentially small bowel bleeding lesions (high P2, moderate P1; Saurin classification) at per-patient analysis. The mean reading time in both reading modalities was evaluated among the secondary endpoints. Methods: Patients aged 18 years or older with suspected small bowel bleeding (with anaemia with or without... (More)

Background: Capsule endoscopy reading is time consuming, and readers are required to maintain attention so as not to miss significant findings. Deep convolutional neural networks can recognise relevant findings, possibly exceeding human performances and reducing the reading time of capsule endoscopy. Our primary aim was to assess the non-inferiority of artificial intelligence (AI)-assisted reading versus standard reading for potentially small bowel bleeding lesions (high P2, moderate P1; Saurin classification) at per-patient analysis. The mean reading time in both reading modalities was evaluated among the secondary endpoints. Methods: Patients aged 18 years or older with suspected small bowel bleeding (with anaemia with or without melena or haematochezia, and negative bidirectional endoscopy) were prospectively enrolled at 14 European centres. Patients underwent small bowel capsule endoscopy with the Navicam SB system (Ankon, China), which is provided with a deep neural network-based AI system (ProScan) for automatic detection of lesions. Initial reading was performed in standard reading mode. Second blinded reading was performed with AI assistance (the AI operated a first-automated reading, and only AI-selected images were assessed by human readers). The primary endpoint was to assess the non-inferiority of AI-assisted reading versus standard reading in the detection (diagnostic yield) of potentially small bowel bleeding P1 and P2 lesions in a per-patient analysis. This study is registered with ClinicalTrials.gov, NCT04821349. Findings: From Feb 17, 2021 to Dec 29, 2021, 137 patients were prospectively enrolled. 133 patients were included in the final analysis (73 [55%] female, mean age 66·5 years [SD 14·4]; 112 [84%] completed capsule endoscopy). At per-patient analysis, the diagnostic yield of P1 and P2 lesions in AI-assisted reading (98 [73·7%] of 133 lesions) was non-inferior (p<0·0001) and superior (p=0·0213) to standard reading (82 [62·4%] of 133; 95% CI 3·6–19·0). Mean small bowel reading time was 33·7 min (SD 22·9) in standard reading and 3·8 min (3·3) in AI-assisted reading (p<0·0001). Interpretation: AI-assisted reading might provide more accurate and faster detection of clinically relevant small bowel bleeding lesions than standard reading. Funding: ANKON Technologies, China and AnX Robotica, USA provided the NaviCam SB system.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; ; and , et al. (More)
; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; and (Less)
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
The Lancet Digital Health
volume
6
issue
5
pages
345 - 353
publisher
Elsevier
external identifiers
  • pmid:38670743
  • scopus:85190944020
ISSN
2589-7500
DOI
10.1016/S2589-7500(24)00048-7
language
English
LU publication?
yes
id
3cde1f60-d798-41dd-bc1a-158b83416935
date added to LUP
2024-05-06 11:06:52
date last changed
2024-05-20 13:21:05
@article{3cde1f60-d798-41dd-bc1a-158b83416935,
  abstract     = {{<p>Background: Capsule endoscopy reading is time consuming, and readers are required to maintain attention so as not to miss significant findings. Deep convolutional neural networks can recognise relevant findings, possibly exceeding human performances and reducing the reading time of capsule endoscopy. Our primary aim was to assess the non-inferiority of artificial intelligence (AI)-assisted reading versus standard reading for potentially small bowel bleeding lesions (high P2, moderate P1; Saurin classification) at per-patient analysis. The mean reading time in both reading modalities was evaluated among the secondary endpoints. Methods: Patients aged 18 years or older with suspected small bowel bleeding (with anaemia with or without melena or haematochezia, and negative bidirectional endoscopy) were prospectively enrolled at 14 European centres. Patients underwent small bowel capsule endoscopy with the Navicam SB system (Ankon, China), which is provided with a deep neural network-based AI system (ProScan) for automatic detection of lesions. Initial reading was performed in standard reading mode. Second blinded reading was performed with AI assistance (the AI operated a first-automated reading, and only AI-selected images were assessed by human readers). The primary endpoint was to assess the non-inferiority of AI-assisted reading versus standard reading in the detection (diagnostic yield) of potentially small bowel bleeding P1 and P2 lesions in a per-patient analysis. This study is registered with ClinicalTrials.gov, NCT04821349. Findings: From Feb 17, 2021 to Dec 29, 2021, 137 patients were prospectively enrolled. 133 patients were included in the final analysis (73 [55%] female, mean age 66·5 years [SD 14·4]; 112 [84%] completed capsule endoscopy). At per-patient analysis, the diagnostic yield of P1 and P2 lesions in AI-assisted reading (98 [73·7%] of 133 lesions) was non-inferior (p&lt;0·0001) and superior (p=0·0213) to standard reading (82 [62·4%] of 133; 95% CI 3·6–19·0). Mean small bowel reading time was 33·7 min (SD 22·9) in standard reading and 3·8 min (3·3) in AI-assisted reading (p&lt;0·0001). Interpretation: AI-assisted reading might provide more accurate and faster detection of clinically relevant small bowel bleeding lesions than standard reading. Funding: ANKON Technologies, China and AnX Robotica, USA provided the NaviCam SB system.</p>}},
  author       = {{Spada, Cristiano and Piccirelli, Stefania and Hassan, Cesare and Ferrari, Clarissa and Toth, Ervin and González-Suárez, Begoña and Keuchel, Martin and McAlindon, Marc and Finta, Ádám and Rosztóczy, András and Dray, Xavier and Salvi, Daniele and Riccioni, Maria Elena and Benamouzig, Robert and Chattree, Amit and Humphries, Adam and Saurin, Jean Christophe and Despott, Edward J. and Murino, Alberto and Johansson, Gabriele Wurm and Giordano, Antonio and Baltes, Peter and Sidhu, Reena and Szalai, Milan and Helle, Krisztina and Nemeth, Artur and Nowak, Tanja and Lin, Rong and Costamagna, Guido}},
  issn         = {{2589-7500}},
  language     = {{eng}},
  number       = {{5}},
  pages        = {{345--353}},
  publisher    = {{Elsevier}},
  series       = {{The Lancet Digital Health}},
  title        = {{AI-assisted capsule endoscopy reading in suspected small bowel bleeding : a multicentre prospective study}},
  url          = {{http://dx.doi.org/10.1016/S2589-7500(24)00048-7}},
  doi          = {{10.1016/S2589-7500(24)00048-7}},
  volume       = {{6}},
  year         = {{2024}},
}