Cargando…

Design of a Convolutional Neural Network as a Deep Learning Tool for the Automatic Classification of Small-Bowel Cleansing in Capsule Endoscopy

Background and objectives: Capsule endoscopy (CE) is a non-invasive method to inspect the small bowel that, like other enteroscopy methods, requires adequate small-bowel cleansing to obtain conclusive results. Artificial intelligence (AI) algorithms have been seen to offer important benefits in the...

Descripción completa

Detalles Bibliográficos
Autores principales: Ribeiro, Tiago, Mascarenhas Saraiva, Miguel José, Afonso, João, Cardoso, Pedro, Mendes, Francisco, Martins, Miguel, Andrade, Ana Patrícia, Cardoso, Hélder, Mascarenhas Saraiva, Miguel, Ferreira, João, Macedo, Guilherme
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10145655/
https://www.ncbi.nlm.nih.gov/pubmed/37109768
http://dx.doi.org/10.3390/medicina59040810
_version_ 1785034389062680576
author Ribeiro, Tiago
Mascarenhas Saraiva, Miguel José
Afonso, João
Cardoso, Pedro
Mendes, Francisco
Martins, Miguel
Andrade, Ana Patrícia
Cardoso, Hélder
Mascarenhas Saraiva, Miguel
Ferreira, João
Macedo, Guilherme
author_facet Ribeiro, Tiago
Mascarenhas Saraiva, Miguel José
Afonso, João
Cardoso, Pedro
Mendes, Francisco
Martins, Miguel
Andrade, Ana Patrícia
Cardoso, Hélder
Mascarenhas Saraiva, Miguel
Ferreira, João
Macedo, Guilherme
author_sort Ribeiro, Tiago
collection PubMed
description Background and objectives: Capsule endoscopy (CE) is a non-invasive method to inspect the small bowel that, like other enteroscopy methods, requires adequate small-bowel cleansing to obtain conclusive results. Artificial intelligence (AI) algorithms have been seen to offer important benefits in the field of medical imaging over recent years, particularly through the adaptation of convolutional neural networks (CNNs) to achieve more efficient image analysis. Here, we aimed to develop a deep learning model that uses a CNN to automatically classify the quality of intestinal preparation in CE. Methods: A CNN was designed based on 12,950 CE images obtained at two clinical centers in Porto (Portugal). The quality of the intestinal preparation was classified for each image as: excellent, ≥90% of the image surface with visible mucosa; satisfactory, 50–90% of the mucosa visible; and unsatisfactory, <50% of the mucosa visible. The total set of images was divided in an 80:20 ratio to establish training and validation datasets, respectively. The CNN prediction was compared with the classification established by consensus of a group of three experts in CE, currently considered the gold standard to evaluate cleanliness. Subsequently, how the CNN performed in diagnostic terms was evaluated using an independent validation dataset. Results: Among the images obtained, 3633 were designated as unsatisfactory preparation, 6005 satisfactory preparation, and 3312 with excellent preparation. When differentiating the classes of small-bowel preparation, the algorithm developed here achieved an overall accuracy of 92.1%, with a sensitivity of 88.4%, a specificity of 93.6%, a positive predictive value of 88.5%, and a negative predictive value of 93.4%. The area under the curve for the detection of excellent, satisfactory, and unsatisfactory classes was 0.98, 0.95, and 0.99, respectively. Conclusions: A CNN-based tool was developed to automatically classify small-bowel preparation for CE, and it was seen to accurately classify intestinal preparation for CE. The development of such a system could enhance the reproducibility of the scales used for such purposes.
format Online
Article
Text
id pubmed-10145655
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-101456552023-04-29 Design of a Convolutional Neural Network as a Deep Learning Tool for the Automatic Classification of Small-Bowel Cleansing in Capsule Endoscopy Ribeiro, Tiago Mascarenhas Saraiva, Miguel José Afonso, João Cardoso, Pedro Mendes, Francisco Martins, Miguel Andrade, Ana Patrícia Cardoso, Hélder Mascarenhas Saraiva, Miguel Ferreira, João Macedo, Guilherme Medicina (Kaunas) Article Background and objectives: Capsule endoscopy (CE) is a non-invasive method to inspect the small bowel that, like other enteroscopy methods, requires adequate small-bowel cleansing to obtain conclusive results. Artificial intelligence (AI) algorithms have been seen to offer important benefits in the field of medical imaging over recent years, particularly through the adaptation of convolutional neural networks (CNNs) to achieve more efficient image analysis. Here, we aimed to develop a deep learning model that uses a CNN to automatically classify the quality of intestinal preparation in CE. Methods: A CNN was designed based on 12,950 CE images obtained at two clinical centers in Porto (Portugal). The quality of the intestinal preparation was classified for each image as: excellent, ≥90% of the image surface with visible mucosa; satisfactory, 50–90% of the mucosa visible; and unsatisfactory, <50% of the mucosa visible. The total set of images was divided in an 80:20 ratio to establish training and validation datasets, respectively. The CNN prediction was compared with the classification established by consensus of a group of three experts in CE, currently considered the gold standard to evaluate cleanliness. Subsequently, how the CNN performed in diagnostic terms was evaluated using an independent validation dataset. Results: Among the images obtained, 3633 were designated as unsatisfactory preparation, 6005 satisfactory preparation, and 3312 with excellent preparation. When differentiating the classes of small-bowel preparation, the algorithm developed here achieved an overall accuracy of 92.1%, with a sensitivity of 88.4%, a specificity of 93.6%, a positive predictive value of 88.5%, and a negative predictive value of 93.4%. The area under the curve for the detection of excellent, satisfactory, and unsatisfactory classes was 0.98, 0.95, and 0.99, respectively. Conclusions: A CNN-based tool was developed to automatically classify small-bowel preparation for CE, and it was seen to accurately classify intestinal preparation for CE. The development of such a system could enhance the reproducibility of the scales used for such purposes. MDPI 2023-04-21 /pmc/articles/PMC10145655/ /pubmed/37109768 http://dx.doi.org/10.3390/medicina59040810 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Ribeiro, Tiago
Mascarenhas Saraiva, Miguel José
Afonso, João
Cardoso, Pedro
Mendes, Francisco
Martins, Miguel
Andrade, Ana Patrícia
Cardoso, Hélder
Mascarenhas Saraiva, Miguel
Ferreira, João
Macedo, Guilherme
Design of a Convolutional Neural Network as a Deep Learning Tool for the Automatic Classification of Small-Bowel Cleansing in Capsule Endoscopy
title Design of a Convolutional Neural Network as a Deep Learning Tool for the Automatic Classification of Small-Bowel Cleansing in Capsule Endoscopy
title_full Design of a Convolutional Neural Network as a Deep Learning Tool for the Automatic Classification of Small-Bowel Cleansing in Capsule Endoscopy
title_fullStr Design of a Convolutional Neural Network as a Deep Learning Tool for the Automatic Classification of Small-Bowel Cleansing in Capsule Endoscopy
title_full_unstemmed Design of a Convolutional Neural Network as a Deep Learning Tool for the Automatic Classification of Small-Bowel Cleansing in Capsule Endoscopy
title_short Design of a Convolutional Neural Network as a Deep Learning Tool for the Automatic Classification of Small-Bowel Cleansing in Capsule Endoscopy
title_sort design of a convolutional neural network as a deep learning tool for the automatic classification of small-bowel cleansing in capsule endoscopy
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10145655/
https://www.ncbi.nlm.nih.gov/pubmed/37109768
http://dx.doi.org/10.3390/medicina59040810
work_keys_str_mv AT ribeirotiago designofaconvolutionalneuralnetworkasadeeplearningtoolfortheautomaticclassificationofsmallbowelcleansingincapsuleendoscopy
AT mascarenhassaraivamigueljose designofaconvolutionalneuralnetworkasadeeplearningtoolfortheautomaticclassificationofsmallbowelcleansingincapsuleendoscopy
AT afonsojoao designofaconvolutionalneuralnetworkasadeeplearningtoolfortheautomaticclassificationofsmallbowelcleansingincapsuleendoscopy
AT cardosopedro designofaconvolutionalneuralnetworkasadeeplearningtoolfortheautomaticclassificationofsmallbowelcleansingincapsuleendoscopy
AT mendesfrancisco designofaconvolutionalneuralnetworkasadeeplearningtoolfortheautomaticclassificationofsmallbowelcleansingincapsuleendoscopy
AT martinsmiguel designofaconvolutionalneuralnetworkasadeeplearningtoolfortheautomaticclassificationofsmallbowelcleansingincapsuleendoscopy
AT andradeanapatricia designofaconvolutionalneuralnetworkasadeeplearningtoolfortheautomaticclassificationofsmallbowelcleansingincapsuleendoscopy
AT cardosohelder designofaconvolutionalneuralnetworkasadeeplearningtoolfortheautomaticclassificationofsmallbowelcleansingincapsuleendoscopy
AT mascarenhassaraivamiguel designofaconvolutionalneuralnetworkasadeeplearningtoolfortheautomaticclassificationofsmallbowelcleansingincapsuleendoscopy
AT ferreirajoao designofaconvolutionalneuralnetworkasadeeplearningtoolfortheautomaticclassificationofsmallbowelcleansingincapsuleendoscopy
AT macedoguilherme designofaconvolutionalneuralnetworkasadeeplearningtoolfortheautomaticclassificationofsmallbowelcleansingincapsuleendoscopy