Automated detection of cecal intubation with variable bowel preparation using a deep convolutional neural network

Background and study aims Colonoscopy completion reduces post-colonoscopy colorectal cancer. As a result, there have been attempts at implementing artificial intelligence to automate the detection of the appendiceal orifice (AO) for quality assurance. However, the utilization of these algorithms has...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Daniel J. Low, Zhuoqiao Hong, Rishad Khan, Rishi Bansal, Nikko Gimpaya, Samir C. Grover
Formato:	article
Lenguaje:	EN
Publicado:	Georg Thieme Verlag KG 2021
Materias:	Diseases of the digestive system. Gastroenterology RC799-869
Acceso en línea:	https://doaj.org/article/b66b9033877945069a43c412b5a810c6
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b66b9033877945069a43c412b5a810c6
record_format	dspace
spelling	oai:doaj.org-article:b66b9033877945069a43c412b5a810c62021-11-13T00:00:31ZAutomated detection of cecal intubation with variable bowel preparation using a deep convolutional neural network2364-37222196-973610.1055/a-1546-8266https://doaj.org/article/b66b9033877945069a43c412b5a810c62021-11-01T00:00:00Zhttp://www.thieme-connect.de/DOI/DOI?10.1055/a-1546-8266https://doaj.org/toc/2364-3722https://doaj.org/toc/2196-9736Background and study aims Colonoscopy completion reduces post-colonoscopy colorectal cancer. As a result, there have been attempts at implementing artificial intelligence to automate the detection of the appendiceal orifice (AO) for quality assurance. However, the utilization of these algorithms has not been demonstrated in suboptimal conditions, including variable bowel preparation. We present an automated computer-assisted method using a deep convolutional neural network to detect the AO irrespective of bowel preparation. Methods A total of 13,222 images (6,663 AO and 1,322 non-AO) were extracted from 35 colonoscopy videos recorded between 2015 and 2018. The images were labelled with Boston Bowel Preparation Scale scores. A total of 11,900 images were used for training/validation and 1,322 for testing. We developed a convolutional neural network (CNN) with a DenseNet architecture pre-trained on ImageNet as a feature extractor on our data and trained a classifier uniquely tailored for identification of AO and non-AO images using binary cross entropy loss. Results The deep convolutional neural network was able to correctly classify the AO and non-AO images with an accuracy of 94 %. The area under the receiver operating curve of this neural network was 0.98. The sensitivity, specificity, positive predictive value, and negative predictive value of the algorithm were 0.96, 0.92, 0.92 and 0.96, respectively. AO detection was > 95 % regardless of BBPS scores, while non-AO detection improved from BBPS 1 score (83.95 %) to BBPS 3 score (98.28 %). Conclusions A deep convolutional neural network was created demonstrating excellent discrimination between AO from non-AO images despite variable bowel preparation. This algorithm will require further testing to ascertain its effectiveness in real-time colonoscopy.Daniel J. LowZhuoqiao HongRishad KhanRishi BansalNikko GimpayaSamir C. GroverGeorg Thieme Verlag KGarticleDiseases of the digestive system. GastroenterologyRC799-869ENEndoscopy International Open, Vol 09, Iss 11, Pp E1778-E1784 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Diseases of the digestive system. Gastroenterology RC799-869
spellingShingle	Diseases of the digestive system. Gastroenterology RC799-869 Daniel J. Low Zhuoqiao Hong Rishad Khan Rishi Bansal Nikko Gimpaya Samir C. Grover Automated detection of cecal intubation with variable bowel preparation using a deep convolutional neural network
description	Background and study aims Colonoscopy completion reduces post-colonoscopy colorectal cancer. As a result, there have been attempts at implementing artificial intelligence to automate the detection of the appendiceal orifice (AO) for quality assurance. However, the utilization of these algorithms has not been demonstrated in suboptimal conditions, including variable bowel preparation. We present an automated computer-assisted method using a deep convolutional neural network to detect the AO irrespective of bowel preparation. Methods A total of 13,222 images (6,663 AO and 1,322 non-AO) were extracted from 35 colonoscopy videos recorded between 2015 and 2018. The images were labelled with Boston Bowel Preparation Scale scores. A total of 11,900 images were used for training/validation and 1,322 for testing. We developed a convolutional neural network (CNN) with a DenseNet architecture pre-trained on ImageNet as a feature extractor on our data and trained a classifier uniquely tailored for identification of AO and non-AO images using binary cross entropy loss. Results The deep convolutional neural network was able to correctly classify the AO and non-AO images with an accuracy of 94 %. The area under the receiver operating curve of this neural network was 0.98. The sensitivity, specificity, positive predictive value, and negative predictive value of the algorithm were 0.96, 0.92, 0.92 and 0.96, respectively. AO detection was > 95 % regardless of BBPS scores, while non-AO detection improved from BBPS 1 score (83.95 %) to BBPS 3 score (98.28 %). Conclusions A deep convolutional neural network was created demonstrating excellent discrimination between AO from non-AO images despite variable bowel preparation. This algorithm will require further testing to ascertain its effectiveness in real-time colonoscopy.
format	article
author	Daniel J. Low Zhuoqiao Hong Rishad Khan Rishi Bansal Nikko Gimpaya Samir C. Grover
author_facet	Daniel J. Low Zhuoqiao Hong Rishad Khan Rishi Bansal Nikko Gimpaya Samir C. Grover
author_sort	Daniel J. Low
title	Automated detection of cecal intubation with variable bowel preparation using a deep convolutional neural network
title_short	Automated detection of cecal intubation with variable bowel preparation using a deep convolutional neural network
title_full	Automated detection of cecal intubation with variable bowel preparation using a deep convolutional neural network
title_fullStr	Automated detection of cecal intubation with variable bowel preparation using a deep convolutional neural network
title_full_unstemmed	Automated detection of cecal intubation with variable bowel preparation using a deep convolutional neural network
title_sort	automated detection of cecal intubation with variable bowel preparation using a deep convolutional neural network
publisher	Georg Thieme Verlag KG
publishDate	2021
url	https://doaj.org/article/b66b9033877945069a43c412b5a810c6
work_keys_str_mv	AT danieljlow automateddetectionofcecalintubationwithvariablebowelpreparationusingadeepconvolutionalneuralnetwork AT zhuoqiaohong automateddetectionofcecalintubationwithvariablebowelpreparationusingadeepconvolutionalneuralnetwork AT rishadkhan automateddetectionofcecalintubationwithvariablebowelpreparationusingadeepconvolutionalneuralnetwork AT rishibansal automateddetectionofcecalintubationwithvariablebowelpreparationusingadeepconvolutionalneuralnetwork AT nikkogimpaya automateddetectionofcecalintubationwithvariablebowelpreparationusingadeepconvolutionalneuralnetwork AT samircgrover automateddetectionofcecalintubationwithvariablebowelpreparationusingadeepconvolutionalneuralnetwork
_version_	1718430338380726272

Automated detection of cecal intubation with variable bowel preparation using a deep convolutional neural network

Ejemplares similares