Cargando…

Use of U-Net Convolutional Neural Networks for Automated Segmentation of Fecal Material for Objective Evaluation of Bowel Preparation Quality in Colonoscopy

Background: Adequate bowel cleansing is important for colonoscopy performance evaluation. Current bowel cleansing evaluation scales are subjective, with a wide variation in consistency among physicians and low reported rates of accuracy. We aim to use machine learning to develop a fully automatic se...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Yen-Po, Jheng, Ying-Chun, Sung, Kuang-Yi, Lin, Hung-En, Hsin, I-Fang, Chen, Ping-Hsien, Chu, Yuan-Chia, Lu, David, Wang, Yuan-Jen, Hou, Ming-Chih, Lee, Fa-Yauh, Lu, Ching-Liang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8947406/
https://www.ncbi.nlm.nih.gov/pubmed/35328166
http://dx.doi.org/10.3390/diagnostics12030613
_version_ 1784674431696633856
author Wang, Yen-Po
Jheng, Ying-Chun
Sung, Kuang-Yi
Lin, Hung-En
Hsin, I-Fang
Chen, Ping-Hsien
Chu, Yuan-Chia
Lu, David
Wang, Yuan-Jen
Hou, Ming-Chih
Lee, Fa-Yauh
Lu, Ching-Liang
author_facet Wang, Yen-Po
Jheng, Ying-Chun
Sung, Kuang-Yi
Lin, Hung-En
Hsin, I-Fang
Chen, Ping-Hsien
Chu, Yuan-Chia
Lu, David
Wang, Yuan-Jen
Hou, Ming-Chih
Lee, Fa-Yauh
Lu, Ching-Liang
author_sort Wang, Yen-Po
collection PubMed
description Background: Adequate bowel cleansing is important for colonoscopy performance evaluation. Current bowel cleansing evaluation scales are subjective, with a wide variation in consistency among physicians and low reported rates of accuracy. We aim to use machine learning to develop a fully automatic segmentation method for the objective evaluation of the adequacy of colon preparation. Methods: Colonoscopy videos were retrieved from a video data cohort and transferred to qualified images, which were randomly divided into training, validation, and verification datasets. The fecal residue was manually segmented. A deep learning model based on the U-Net convolutional network architecture was developed to perform automatic segmentation. The performance of the automatic segmentation was evaluated on the overlap area with the manual segmentation. Results: A total of 10,118 qualified images from 119 videos were obtained. The model averaged 0.3634 s to segmentate one image automatically. The models produced a strong high-overlap area with manual segmentation, with 94.7% ± 0.67% of that area predicted by our AI model, which correlated well with the area measured manually (r = 0.915, p < 0.001). The AI system can be applied in real-time qualitatively and quantitatively. Conclusions: We established a fully automatic segmentation method to rapidly and accurately mark the fecal residue-coated mucosa for the objective evaluation of colon preparation.
format Online
Article
Text
id pubmed-8947406
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-89474062022-03-25 Use of U-Net Convolutional Neural Networks for Automated Segmentation of Fecal Material for Objective Evaluation of Bowel Preparation Quality in Colonoscopy Wang, Yen-Po Jheng, Ying-Chun Sung, Kuang-Yi Lin, Hung-En Hsin, I-Fang Chen, Ping-Hsien Chu, Yuan-Chia Lu, David Wang, Yuan-Jen Hou, Ming-Chih Lee, Fa-Yauh Lu, Ching-Liang Diagnostics (Basel) Article Background: Adequate bowel cleansing is important for colonoscopy performance evaluation. Current bowel cleansing evaluation scales are subjective, with a wide variation in consistency among physicians and low reported rates of accuracy. We aim to use machine learning to develop a fully automatic segmentation method for the objective evaluation of the adequacy of colon preparation. Methods: Colonoscopy videos were retrieved from a video data cohort and transferred to qualified images, which were randomly divided into training, validation, and verification datasets. The fecal residue was manually segmented. A deep learning model based on the U-Net convolutional network architecture was developed to perform automatic segmentation. The performance of the automatic segmentation was evaluated on the overlap area with the manual segmentation. Results: A total of 10,118 qualified images from 119 videos were obtained. The model averaged 0.3634 s to segmentate one image automatically. The models produced a strong high-overlap area with manual segmentation, with 94.7% ± 0.67% of that area predicted by our AI model, which correlated well with the area measured manually (r = 0.915, p < 0.001). The AI system can be applied in real-time qualitatively and quantitatively. Conclusions: We established a fully automatic segmentation method to rapidly and accurately mark the fecal residue-coated mucosa for the objective evaluation of colon preparation. MDPI 2022-03-01 /pmc/articles/PMC8947406/ /pubmed/35328166 http://dx.doi.org/10.3390/diagnostics12030613 Text en © 2022 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
Wang, Yen-Po
Jheng, Ying-Chun
Sung, Kuang-Yi
Lin, Hung-En
Hsin, I-Fang
Chen, Ping-Hsien
Chu, Yuan-Chia
Lu, David
Wang, Yuan-Jen
Hou, Ming-Chih
Lee, Fa-Yauh
Lu, Ching-Liang
Use of U-Net Convolutional Neural Networks for Automated Segmentation of Fecal Material for Objective Evaluation of Bowel Preparation Quality in Colonoscopy
title Use of U-Net Convolutional Neural Networks for Automated Segmentation of Fecal Material for Objective Evaluation of Bowel Preparation Quality in Colonoscopy
title_full Use of U-Net Convolutional Neural Networks for Automated Segmentation of Fecal Material for Objective Evaluation of Bowel Preparation Quality in Colonoscopy
title_fullStr Use of U-Net Convolutional Neural Networks for Automated Segmentation of Fecal Material for Objective Evaluation of Bowel Preparation Quality in Colonoscopy
title_full_unstemmed Use of U-Net Convolutional Neural Networks for Automated Segmentation of Fecal Material for Objective Evaluation of Bowel Preparation Quality in Colonoscopy
title_short Use of U-Net Convolutional Neural Networks for Automated Segmentation of Fecal Material for Objective Evaluation of Bowel Preparation Quality in Colonoscopy
title_sort use of u-net convolutional neural networks for automated segmentation of fecal material for objective evaluation of bowel preparation quality in colonoscopy
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8947406/
https://www.ncbi.nlm.nih.gov/pubmed/35328166
http://dx.doi.org/10.3390/diagnostics12030613
work_keys_str_mv AT wangyenpo useofunetconvolutionalneuralnetworksforautomatedsegmentationoffecalmaterialforobjectiveevaluationofbowelpreparationqualityincolonoscopy
AT jhengyingchun useofunetconvolutionalneuralnetworksforautomatedsegmentationoffecalmaterialforobjectiveevaluationofbowelpreparationqualityincolonoscopy
AT sungkuangyi useofunetconvolutionalneuralnetworksforautomatedsegmentationoffecalmaterialforobjectiveevaluationofbowelpreparationqualityincolonoscopy
AT linhungen useofunetconvolutionalneuralnetworksforautomatedsegmentationoffecalmaterialforobjectiveevaluationofbowelpreparationqualityincolonoscopy
AT hsinifang useofunetconvolutionalneuralnetworksforautomatedsegmentationoffecalmaterialforobjectiveevaluationofbowelpreparationqualityincolonoscopy
AT chenpinghsien useofunetconvolutionalneuralnetworksforautomatedsegmentationoffecalmaterialforobjectiveevaluationofbowelpreparationqualityincolonoscopy
AT chuyuanchia useofunetconvolutionalneuralnetworksforautomatedsegmentationoffecalmaterialforobjectiveevaluationofbowelpreparationqualityincolonoscopy
AT ludavid useofunetconvolutionalneuralnetworksforautomatedsegmentationoffecalmaterialforobjectiveevaluationofbowelpreparationqualityincolonoscopy
AT wangyuanjen useofunetconvolutionalneuralnetworksforautomatedsegmentationoffecalmaterialforobjectiveevaluationofbowelpreparationqualityincolonoscopy
AT houmingchih useofunetconvolutionalneuralnetworksforautomatedsegmentationoffecalmaterialforobjectiveevaluationofbowelpreparationqualityincolonoscopy
AT leefayauh useofunetconvolutionalneuralnetworksforautomatedsegmentationoffecalmaterialforobjectiveevaluationofbowelpreparationqualityincolonoscopy
AT luchingliang useofunetconvolutionalneuralnetworksforautomatedsegmentationoffecalmaterialforobjectiveevaluationofbowelpreparationqualityincolonoscopy