Cargando…
Unsupervised Monocular Depth Estimation for Colonoscope System Using Feedback Network
A colonoscopy is a medical examination used to check disease or abnormalities in the large intestine. If necessary, polyps or adenomas would be removed through the scope during a colonoscopy. Colorectal cancer can be prevented through this. However, the polyp detection rate differs depending on the...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8069522/ https://www.ncbi.nlm.nih.gov/pubmed/33920357 http://dx.doi.org/10.3390/s21082691 |
_version_ | 1783683256993972224 |
---|---|
author | Hwang, Seung-Jun Park, Sung-Jun Kim, Gyu-Min Baek, Joong-Hwan |
author_facet | Hwang, Seung-Jun Park, Sung-Jun Kim, Gyu-Min Baek, Joong-Hwan |
author_sort | Hwang, Seung-Jun |
collection | PubMed |
description | A colonoscopy is a medical examination used to check disease or abnormalities in the large intestine. If necessary, polyps or adenomas would be removed through the scope during a colonoscopy. Colorectal cancer can be prevented through this. However, the polyp detection rate differs depending on the condition and skill level of the endoscopist. Even some endoscopists have a 90% chance of missing an adenoma. Artificial intelligence and robot technologies for colonoscopy are being studied to compensate for these problems. In this study, we propose a self-supervised monocular depth estimation using spatiotemporal consistency in the colon environment. It is our contribution to propose a loss function for reconstruction errors between adjacent predicted depths and a depth feedback network that uses predicted depth information of the previous frame to predict the depth of the next frame. We performed quantitative and qualitative evaluation of our approach, and the proposed FBNet (depth FeedBack Network) outperformed state-of-the-art results for unsupervised depth estimation on the UCL datasets. |
format | Online Article Text |
id | pubmed-8069522 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-80695222021-04-26 Unsupervised Monocular Depth Estimation for Colonoscope System Using Feedback Network Hwang, Seung-Jun Park, Sung-Jun Kim, Gyu-Min Baek, Joong-Hwan Sensors (Basel) Article A colonoscopy is a medical examination used to check disease or abnormalities in the large intestine. If necessary, polyps or adenomas would be removed through the scope during a colonoscopy. Colorectal cancer can be prevented through this. However, the polyp detection rate differs depending on the condition and skill level of the endoscopist. Even some endoscopists have a 90% chance of missing an adenoma. Artificial intelligence and robot technologies for colonoscopy are being studied to compensate for these problems. In this study, we propose a self-supervised monocular depth estimation using spatiotemporal consistency in the colon environment. It is our contribution to propose a loss function for reconstruction errors between adjacent predicted depths and a depth feedback network that uses predicted depth information of the previous frame to predict the depth of the next frame. We performed quantitative and qualitative evaluation of our approach, and the proposed FBNet (depth FeedBack Network) outperformed state-of-the-art results for unsupervised depth estimation on the UCL datasets. MDPI 2021-04-11 /pmc/articles/PMC8069522/ /pubmed/33920357 http://dx.doi.org/10.3390/s21082691 Text en © 2021 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 Hwang, Seung-Jun Park, Sung-Jun Kim, Gyu-Min Baek, Joong-Hwan Unsupervised Monocular Depth Estimation for Colonoscope System Using Feedback Network |
title | Unsupervised Monocular Depth Estimation for Colonoscope System Using Feedback Network |
title_full | Unsupervised Monocular Depth Estimation for Colonoscope System Using Feedback Network |
title_fullStr | Unsupervised Monocular Depth Estimation for Colonoscope System Using Feedback Network |
title_full_unstemmed | Unsupervised Monocular Depth Estimation for Colonoscope System Using Feedback Network |
title_short | Unsupervised Monocular Depth Estimation for Colonoscope System Using Feedback Network |
title_sort | unsupervised monocular depth estimation for colonoscope system using feedback network |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8069522/ https://www.ncbi.nlm.nih.gov/pubmed/33920357 http://dx.doi.org/10.3390/s21082691 |
work_keys_str_mv | AT hwangseungjun unsupervisedmonoculardepthestimationforcolonoscopesystemusingfeedbacknetwork AT parksungjun unsupervisedmonoculardepthestimationforcolonoscopesystemusingfeedbacknetwork AT kimgyumin unsupervisedmonoculardepthestimationforcolonoscopesystemusingfeedbacknetwork AT baekjoonghwan unsupervisedmonoculardepthestimationforcolonoscopesystemusingfeedbacknetwork |