Cargando…

Artificial intelligence–based technology for semi-automated segmentation of rectal cancer using high-resolution MRI

AIM: Although MRI has a substantial role in directing treatment decisions for locally advanced rectal cancer, precise interpretation of the findings is not necessarily available at every institution. In this study, we aimed to develop artificial intelligence-based software for the segmentation of re...

Descripción completa

Detalles Bibliográficos
Autores principales: Hamabe, Atsushi, Ishii, Masayuki, Kamoda, Rena, Sasuga, Saeko, Okuya, Koichi, Okita, Kenji, Akizuki, Emi, Sato, Yu, Miura, Ryo, Onodera, Koichi, Hatakenaka, Masamitsu, Takemasa, Ichiro
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9205476/
https://www.ncbi.nlm.nih.gov/pubmed/35714069
http://dx.doi.org/10.1371/journal.pone.0269931
_version_ 1784729139938328576
author Hamabe, Atsushi
Ishii, Masayuki
Kamoda, Rena
Sasuga, Saeko
Okuya, Koichi
Okita, Kenji
Akizuki, Emi
Sato, Yu
Miura, Ryo
Onodera, Koichi
Hatakenaka, Masamitsu
Takemasa, Ichiro
author_facet Hamabe, Atsushi
Ishii, Masayuki
Kamoda, Rena
Sasuga, Saeko
Okuya, Koichi
Okita, Kenji
Akizuki, Emi
Sato, Yu
Miura, Ryo
Onodera, Koichi
Hatakenaka, Masamitsu
Takemasa, Ichiro
author_sort Hamabe, Atsushi
collection PubMed
description AIM: Although MRI has a substantial role in directing treatment decisions for locally advanced rectal cancer, precise interpretation of the findings is not necessarily available at every institution. In this study, we aimed to develop artificial intelligence-based software for the segmentation of rectal cancer that can be used for staging to optimize treatment strategy and for preoperative surgical simulation. METHOD: Images from a total of 201 patients who underwent preoperative MRI were analyzed for training data. The resected specimen was processed in a circular shape in 103 cases. Using these datasets, ground-truth labels were prepared by annotating MR images with ground-truth segmentation labels of tumor area based on pathologically confirmed lesions. In addition, the areas of rectum and mesorectum were also labeled. An automatic segmentation algorithm was developed using a U-net deep neural network. RESULTS: The developed algorithm could estimate the area of the tumor, rectum, and mesorectum. The Dice similarity coefficients between manual and automatic segmentation were 0.727, 0.930, and 0.917 for tumor, rectum, and mesorectum, respectively. The T2/T3 diagnostic sensitivity, specificity, and overall accuracy were 0.773, 0.768, and 0.771, respectively. CONCLUSION: This algorithm can provide objective analysis of MR images at any institution, and aid risk stratification in rectal cancer and the tailoring of individual treatments. Moreover, it can be used for surgical simulations.
format Online
Article
Text
id pubmed-9205476
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-92054762022-06-18 Artificial intelligence–based technology for semi-automated segmentation of rectal cancer using high-resolution MRI Hamabe, Atsushi Ishii, Masayuki Kamoda, Rena Sasuga, Saeko Okuya, Koichi Okita, Kenji Akizuki, Emi Sato, Yu Miura, Ryo Onodera, Koichi Hatakenaka, Masamitsu Takemasa, Ichiro PLoS One Research Article AIM: Although MRI has a substantial role in directing treatment decisions for locally advanced rectal cancer, precise interpretation of the findings is not necessarily available at every institution. In this study, we aimed to develop artificial intelligence-based software for the segmentation of rectal cancer that can be used for staging to optimize treatment strategy and for preoperative surgical simulation. METHOD: Images from a total of 201 patients who underwent preoperative MRI were analyzed for training data. The resected specimen was processed in a circular shape in 103 cases. Using these datasets, ground-truth labels were prepared by annotating MR images with ground-truth segmentation labels of tumor area based on pathologically confirmed lesions. In addition, the areas of rectum and mesorectum were also labeled. An automatic segmentation algorithm was developed using a U-net deep neural network. RESULTS: The developed algorithm could estimate the area of the tumor, rectum, and mesorectum. The Dice similarity coefficients between manual and automatic segmentation were 0.727, 0.930, and 0.917 for tumor, rectum, and mesorectum, respectively. The T2/T3 diagnostic sensitivity, specificity, and overall accuracy were 0.773, 0.768, and 0.771, respectively. CONCLUSION: This algorithm can provide objective analysis of MR images at any institution, and aid risk stratification in rectal cancer and the tailoring of individual treatments. Moreover, it can be used for surgical simulations. Public Library of Science 2022-06-17 /pmc/articles/PMC9205476/ /pubmed/35714069 http://dx.doi.org/10.1371/journal.pone.0269931 Text en © 2022 Hamabe et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Hamabe, Atsushi
Ishii, Masayuki
Kamoda, Rena
Sasuga, Saeko
Okuya, Koichi
Okita, Kenji
Akizuki, Emi
Sato, Yu
Miura, Ryo
Onodera, Koichi
Hatakenaka, Masamitsu
Takemasa, Ichiro
Artificial intelligence–based technology for semi-automated segmentation of rectal cancer using high-resolution MRI
title Artificial intelligence–based technology for semi-automated segmentation of rectal cancer using high-resolution MRI
title_full Artificial intelligence–based technology for semi-automated segmentation of rectal cancer using high-resolution MRI
title_fullStr Artificial intelligence–based technology for semi-automated segmentation of rectal cancer using high-resolution MRI
title_full_unstemmed Artificial intelligence–based technology for semi-automated segmentation of rectal cancer using high-resolution MRI
title_short Artificial intelligence–based technology for semi-automated segmentation of rectal cancer using high-resolution MRI
title_sort artificial intelligence–based technology for semi-automated segmentation of rectal cancer using high-resolution mri
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9205476/
https://www.ncbi.nlm.nih.gov/pubmed/35714069
http://dx.doi.org/10.1371/journal.pone.0269931
work_keys_str_mv AT hamabeatsushi artificialintelligencebasedtechnologyforsemiautomatedsegmentationofrectalcancerusinghighresolutionmri
AT ishiimasayuki artificialintelligencebasedtechnologyforsemiautomatedsegmentationofrectalcancerusinghighresolutionmri
AT kamodarena artificialintelligencebasedtechnologyforsemiautomatedsegmentationofrectalcancerusinghighresolutionmri
AT sasugasaeko artificialintelligencebasedtechnologyforsemiautomatedsegmentationofrectalcancerusinghighresolutionmri
AT okuyakoichi artificialintelligencebasedtechnologyforsemiautomatedsegmentationofrectalcancerusinghighresolutionmri
AT okitakenji artificialintelligencebasedtechnologyforsemiautomatedsegmentationofrectalcancerusinghighresolutionmri
AT akizukiemi artificialintelligencebasedtechnologyforsemiautomatedsegmentationofrectalcancerusinghighresolutionmri
AT satoyu artificialintelligencebasedtechnologyforsemiautomatedsegmentationofrectalcancerusinghighresolutionmri
AT miuraryo artificialintelligencebasedtechnologyforsemiautomatedsegmentationofrectalcancerusinghighresolutionmri
AT onoderakoichi artificialintelligencebasedtechnologyforsemiautomatedsegmentationofrectalcancerusinghighresolutionmri
AT hatakenakamasamitsu artificialintelligencebasedtechnologyforsemiautomatedsegmentationofrectalcancerusinghighresolutionmri
AT takemasaichiro artificialintelligencebasedtechnologyforsemiautomatedsegmentationofrectalcancerusinghighresolutionmri