Cargando…

Automatic segmentation of nasopharyngeal carcinoma on CT images using efficient UNet‐2.5D ensemble with semi‐supervised pretext task pretraining

Nasopharyngeal carcinoma (NPC) is primarily treated with radiation therapy. Accurate delineation of target volumes and organs at risk is important. However, manual delineation is time-consuming, variable, and subjective depending on the experience of the radiation oncologist. This work explores the...

Descripción completa

Detalles Bibliográficos
Autores principales: Domoguen, Jansen Keith L., Manuel, Jen-Jen A., Cañal, Johanna Patricia A., Naval, Prospero C.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9691832/
https://www.ncbi.nlm.nih.gov/pubmed/36439414
http://dx.doi.org/10.3389/fonc.2022.980312
_version_ 1784837115992866816
author Domoguen, Jansen Keith L.
Manuel, Jen-Jen A.
Cañal, Johanna Patricia A.
Naval, Prospero C.
author_facet Domoguen, Jansen Keith L.
Manuel, Jen-Jen A.
Cañal, Johanna Patricia A.
Naval, Prospero C.
author_sort Domoguen, Jansen Keith L.
collection PubMed
description Nasopharyngeal carcinoma (NPC) is primarily treated with radiation therapy. Accurate delineation of target volumes and organs at risk is important. However, manual delineation is time-consuming, variable, and subjective depending on the experience of the radiation oncologist. This work explores the use of deep learning methods to automate the segmentation of NPC primary gross tumor volume (GTVp) in planning computer tomography (CT) images. A total of sixty-three (63) patients diagnosed with NPC were included in this study. Although a number of studies applied have shown the effectiveness of deep learning methods in medical imaging, their high performance has mainly been due to the wide availability of data. In contrast, the data for NPC is scarce and inaccessible. To tackle this problem, we propose two sequential approaches. First we propose a much simpler architecture which follows the UNet design but using 2D convolutional network for 3D segmentation. We find that this specific architecture is much more effective in the segmentation of GTV in NPC. We highlight its efficacy over other more popular and modern architecture by achieving significantly higher performance. Moreover to further improve performance, we trained the model using multi-scale dataset to create an ensemble of models. However, the performance of the model is ultimately dependent on the availability of labelled data. Hence building on top of this proposed architecture, we employ the use of semi-supervised learning by proposing the use of a combined pre-text tasks. Specifically we use the combination of 3D rotation and 3D relative-patch location pre-texts tasks to pretrain the feature extractor. We use an additional 50 CT images of healthy patients which have no annotation or labels. By semi-supervised pretraining the feature extractor can be frozen after pretraining which essentially makes it much more efficient in terms of the number of parameters since only the decoder is trained. Finally it is not only efficient in terms of parameters but also data, which is shown when the pretrained model with only portion of the labelled training data was able to achieve very close performance to the model trained with the full labelled data.
format Online
Article
Text
id pubmed-9691832
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-96918322022-11-26 Automatic segmentation of nasopharyngeal carcinoma on CT images using efficient UNet‐2.5D ensemble with semi‐supervised pretext task pretraining Domoguen, Jansen Keith L. Manuel, Jen-Jen A. Cañal, Johanna Patricia A. Naval, Prospero C. Front Oncol Oncology Nasopharyngeal carcinoma (NPC) is primarily treated with radiation therapy. Accurate delineation of target volumes and organs at risk is important. However, manual delineation is time-consuming, variable, and subjective depending on the experience of the radiation oncologist. This work explores the use of deep learning methods to automate the segmentation of NPC primary gross tumor volume (GTVp) in planning computer tomography (CT) images. A total of sixty-three (63) patients diagnosed with NPC were included in this study. Although a number of studies applied have shown the effectiveness of deep learning methods in medical imaging, their high performance has mainly been due to the wide availability of data. In contrast, the data for NPC is scarce and inaccessible. To tackle this problem, we propose two sequential approaches. First we propose a much simpler architecture which follows the UNet design but using 2D convolutional network for 3D segmentation. We find that this specific architecture is much more effective in the segmentation of GTV in NPC. We highlight its efficacy over other more popular and modern architecture by achieving significantly higher performance. Moreover to further improve performance, we trained the model using multi-scale dataset to create an ensemble of models. However, the performance of the model is ultimately dependent on the availability of labelled data. Hence building on top of this proposed architecture, we employ the use of semi-supervised learning by proposing the use of a combined pre-text tasks. Specifically we use the combination of 3D rotation and 3D relative-patch location pre-texts tasks to pretrain the feature extractor. We use an additional 50 CT images of healthy patients which have no annotation or labels. By semi-supervised pretraining the feature extractor can be frozen after pretraining which essentially makes it much more efficient in terms of the number of parameters since only the decoder is trained. Finally it is not only efficient in terms of parameters but also data, which is shown when the pretrained model with only portion of the labelled training data was able to achieve very close performance to the model trained with the full labelled data. Frontiers Media S.A. 2022-11-11 /pmc/articles/PMC9691832/ /pubmed/36439414 http://dx.doi.org/10.3389/fonc.2022.980312 Text en Copyright © 2022 Domoguen, Manuel, Cañal and Naval https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Oncology
Domoguen, Jansen Keith L.
Manuel, Jen-Jen A.
Cañal, Johanna Patricia A.
Naval, Prospero C.
Automatic segmentation of nasopharyngeal carcinoma on CT images using efficient UNet‐2.5D ensemble with semi‐supervised pretext task pretraining
title Automatic segmentation of nasopharyngeal carcinoma on CT images using efficient UNet‐2.5D ensemble with semi‐supervised pretext task pretraining
title_full Automatic segmentation of nasopharyngeal carcinoma on CT images using efficient UNet‐2.5D ensemble with semi‐supervised pretext task pretraining
title_fullStr Automatic segmentation of nasopharyngeal carcinoma on CT images using efficient UNet‐2.5D ensemble with semi‐supervised pretext task pretraining
title_full_unstemmed Automatic segmentation of nasopharyngeal carcinoma on CT images using efficient UNet‐2.5D ensemble with semi‐supervised pretext task pretraining
title_short Automatic segmentation of nasopharyngeal carcinoma on CT images using efficient UNet‐2.5D ensemble with semi‐supervised pretext task pretraining
title_sort automatic segmentation of nasopharyngeal carcinoma on ct images using efficient unet‐2.5d ensemble with semi‐supervised pretext task pretraining
topic Oncology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9691832/
https://www.ncbi.nlm.nih.gov/pubmed/36439414
http://dx.doi.org/10.3389/fonc.2022.980312
work_keys_str_mv AT domoguenjansenkeithl automaticsegmentationofnasopharyngealcarcinomaonctimagesusingefficientunet25densemblewithsemisupervisedpretexttaskpretraining
AT manueljenjena automaticsegmentationofnasopharyngealcarcinomaonctimagesusingefficientunet25densemblewithsemisupervisedpretexttaskpretraining
AT canaljohannapatriciaa automaticsegmentationofnasopharyngealcarcinomaonctimagesusingefficientunet25densemblewithsemisupervisedpretexttaskpretraining
AT navalprosperoc automaticsegmentationofnasopharyngealcarcinomaonctimagesusingefficientunet25densemblewithsemisupervisedpretexttaskpretraining