Year 2023 / Volume 115 / Number 2
Original
Artificial intelligence and capsule endoscopy: automatic detection of enteric protruding lesions using a convolutional neural network

75-79

DOI: 10.17235/reed.2021.7979/2021

Miguel Mascarenhas Saraiva, João Afonso, Tiago Ribeiro, João Ferreira, Hélder Cardoso, Patricia Andrade, Raquel Gonçalves, Pedro Cardoso, Marco Parente, Renato Jorge, Guilherme Macedo,

Abstract
Background and aims: capsule endoscopy (CE) revolutionized the study of the small intestine. Nevertheless, reviewing CE images is time-consuming and prone to error. Artificial intelligence algorithms, particularly convolutional neural networks (CNN), are expected to overcome these drawbacks. Protruding lesions of the small intestine exhibit enormous morphological diversity in CE images. This study aimed to develop a CNN-based algorithm for the automatic detection small bowel protruding lesions. Methods: a CNN was developed using a pool of CE images containing protruding lesions or normal mucosa from 1,229 patients. A training dataset was used for the development of the model. The performance of the network was evaluated using an independent dataset, by calculating its sensitivity, specificity, accuracy, positive and negative predictive values. Results: a total of 18,625 CE images (2,830 showing protruding lesions and 15,795 normal mucosa) were included. Training and validation datasets were built with an 80 %/20 % distribution, respectively. After optimizing the architecture of the network, our model automatically detected small-bowel protruding lesions with an accuracy of 92.5 %. CNN had a sensitivity and specificity of 96.8 % and 96.5 %, respectively. The CNN analyzed the validation dataset in 53 seconds, at a rate of approximately 70 frames per second. Conclusions: we developed an accurate CNN for the automatic detection of enteric protruding lesions with a wide range of morphologies. The development of these tools may enhance the diagnostic efficiency of CE.
Share Button
New comment
Comments
No comments for this article
References
1. Pennazio M, Spada C, Eliakim R, et al. Small-bowel capsule endoscopy and device-assisted enteroscopy for diagnosis and treatment of small-bowel disorders: European Society of Gastrointestinal Endoscopy (ESGE) Clinical Guideline. Endoscopy 2015;47(4):352-76. 10.1055/s-0034-1391855
2. Teshima CW, Kuipers EJ, van Zanten SV, et al. Double balloon enteroscopy and capsule endoscopy for obscure gastrointestinal bleeding: an updated meta-analysis. J Gastroenterol Hepatol 2011;26(5):796-801. 10.1111/j.1440-1746.2010.06530.x
3. Le Berre C, Trang-Poisson C, Bourreille A. Small bowel capsule endoscopy and treat-to-target in Crohn's disease: A systematic review. World J Gastroenterol 2019;25(31):4534-54. 10.3748/wjg.v25.i31.4534
4. Korman LY, Delvaux M, Gay G, et al. Capsule endoscopy structured terminology (CEST): proposal of a standardized and structured terminology for reporting capsule endoscopy procedures. Endoscopy 2005;37(10):951-9. 10.1055/s-2005-870329
5. Schwartz GD, Barkin JS. Small-bowel tumors detected by wireless capsule endoscopy. Dig Dis Sci 2007;52(4):1026-30. 10.1007/s10620-006-9483-8
6. Saurin JC, Delvaux M, Gaudin JL, et al. Diagnostic value of endoscopic capsule in patients with obscure digestive bleeding: blinded comparison with video push-enteroscopy. Endoscopy 2003;35(7):576-84. 10.1055/s-2003-40244
7. Leenhardt R, Vasseur P, Li C, et al. A neural network algorithm for detection of GI angiectasia during small-bowel capsule endoscopy. Gastrointest Endosc 2019;89(1):189-94. 10.1016/j.gie.2018.06.036
8. Yasaka K, Akai H, Abe O, et al. Deep Learning with Convolutional Neural Network for Differentiation of Liver Masses at Dynamic Contrast-enhanced CT: A Preliminary Study. Radiology 2018;286(3):887-96. 10.1148/radiol.2017170706
9. Esteva A, Kuprel B, Novoa RA, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature 2017;542(7639):115-8. 10.1038/nature21056
10. Gargeya R, Leng T. Automated Identification of Diabetic Retinopathy Using Deep Learning. Ophthalmology 2017;124(7):962-9. 10.1016/j.ophtha.2017.02.008
11. Aoki T, Yamada A, Kato Y, et al. Automatic detection of blood content in capsule endoscopy images based on a deep convolutional neural network. J Gastroenterol Hepatol 2020;35(7):1196-200. 10.1111/jgh.14941
12. Tsuboi A, Oka S, Aoyama K, et al. Artificial intelligence using a convolutional neural network for automatic detection of small-bowel angioectasia in capsule endoscopy images. Dig Endosc 2020;32(3):382-90. 10.1111/den.13507
13. Rondonotti E, Spada C, Adler S, et al. Small-bowel capsule endoscopy and device-assisted enteroscopy for diagnosis and treatment of small-bowel disorders: European Society of Gastrointestinal Endoscopy (ESGE) Technical Review. Endoscopy 2018;50(4):423-46. 10.1055/a-0576-0566
14. Saito H, Aoki T, Aoyama K, et al. Automatic detection and classification of protruding lesions in wireless capsule endoscopy images based on a deep convolutional neural network. Gastrointestinal Endoscopy 2020;92(1):144-51.e1. 10.1016/j.gie.2020.01.054
Related articles

Letter

Blue rubber bleb nevus syndrome

DOI: 10.17235/reed.2023.9913/2023

Letter

Capsule endoscopy diagnosis of gastrointestinal melanoma

DOI: 10.17235/reed.2023.9803/2023

Letter

Isolated Jejunal Crohn's Disease: a challenging diagnosis

DOI: 10.17235/reed.2022.9423/2022

Digestive Diseases Image

Whipple’s disease – A typical endoscopic finding of a rare disease

DOI: 10.17235/reed.2022.9338/2022

Letter

Primary intestinal melanoma?

DOI: 10.17235/reed.2022.8944/2022

Digestive Diseases Image

Colonic Kaposi’s sarcoma as the first clinical manifestation of undiagnosed HIV

DOI: 10.17235/reed.2022.8717/2022

Letter

A rare gastrointestinal tumor: primary gastric melanoma

DOI: 10.17235/reed.2022.8715/2022

Digestive Diseases Image

Ileal neuroendocrine tumor as an uncommon cause of obscure gastrointestinal bleeding

DOI: 10.17235/reed.2022.8641/2022

Digestive Diseases Image

Duodenal-type follicular lymphoma: a silent tumor

DOI: 10.17235/reed.2021.8149/2021

Letter

Bochdalek hernia: use of capsule endoscopy

DOI: 10.17235/reed.2021.7760/2020

Letter

Colonic adenocarcinoma arising from traditional serrated adenoma

DOI: 10.17235/reed.2020.6818/2019

Letter

Gastric ulcer due to mucormycosis in a critical patient

DOI: 10.17235/reed.2020.6636/2019

Digestive Diseases Image

Jejunal schwannoma detected by video capsule endoscopy

DOI: 10.17235/reed.2020.6474/2019

Digestive Diseases Image

Capsule endoscopy, a useful tool for the diagnosis of a tapeworm infection

DOI: 10.17235/reed.2019.6346/2019

Letter

Gastric serrated adenoma

DOI: 10.17235/reed.2019.6145/2018

Letter

Use of patency capsule in daily practice

DOI: 10.17235/reed.2019.5952/2018

Digestive Diseases Image

Metastasis of dermatofibrosarcoma diagnosed by capsule endoscopy

DOI: 10.17235/reed.2018.4900/2017

Letter to the Editor

Symptomatic retention of the Agile® patency capsule

DOI: 10.17235/reed.2017.4691/2016

Letter to the Editor

Whipple’s disease under the vision of capsule endoscopy

DOI: 10.17235/reed.2016.4362/2016

Letter to the Editor

Asymptomatic bronchial aspiration of capsule endoscope: a significant complication

DOI: 10.17235/reed.2016.4363/2016

Review

Serrated lesions and serrated polyposis syndrome

DOI: 10.17235/reed.2017.4065/2015

Case Report

Appendicular bleeding: an excepcional cause of lower hemorrhage

DOI: 10.17235/reed.2015.3828/2015

Case Report

Atypical diagnosis diagnosis by endoscopic capsule: Whipple´s disease

DOI: 10.17235/reed.2015.3718/2015

Citation tools
Mascarenhas Saraiva M, Afonso J, Ribeiro T, Ferreira J, Cardoso H, Andrade P, et all. Artificial intelligence and capsule endoscopy: automatic detection of enteric protruding lesions using a convolutional neural network. 7979/2021


Download to a citation manager

Download the citation for this article by clicking on one of the following citation managers:

Metrics
This article has received 2133 visits.
This article has been downloaded 112 times.

Statistics from Dimensions


Statistics from Plum Analytics

Publication history

Received: 17/03/2021

Accepted: 08/09/2021

Online First: 14/09/2021

Published: 07/02/2023

Article revision time: 169 days

Article Online First time: 181 days

Article editing time: 692 days


Share
This article hasn't been rated yet.
Reader rating:
Valora este artículo:




Asociación Española de Ecografía Digestiva Sociedad Española de Endoscopia Digestiva Sociedad Española de Patología Digestiva
The Spanish Journal of Gastroenterology is the official organ of the Sociedad Española de Patología Digestiva, the Sociedad Española de Endoscopia Digestiva and the Asociación Española de Ecografía Digestiva
Cookie policy Privacy Policy Legal Notice © Copyright 2023 y Creative Commons. The Spanish Journal of Gastroenterology