Cargando…

Deep Convolutional Neural Network for Nasopharyngeal Carcinoma Discrimination on MRI by Comparison of Hierarchical and Simple Layered Convolutional Neural Networks

Nasopharyngeal carcinoma (NPC) is one of the most common head and neck cancers. Early diagnosis plays a critical role in the treatment of NPC. To aid diagnosis, deep learning methods can provide interpretable clues for identifying NPC from magnetic resonance images (MRI). To identify the optimal mod...

Descripción completa

Detalles Bibliográficos
Autores principales: Ji, Li, Mao, Rongzhi, Wu, Jian, Ge, Cheng, Xiao, Feng, Xu, Xiaojun, Xie, Liangxu, Gu, Xiaofeng
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9601165/
https://www.ncbi.nlm.nih.gov/pubmed/36292167
http://dx.doi.org/10.3390/diagnostics12102478
_version_ 1784816990112710656
author Ji, Li
Mao, Rongzhi
Wu, Jian
Ge, Cheng
Xiao, Feng
Xu, Xiaojun
Xie, Liangxu
Gu, Xiaofeng
author_facet Ji, Li
Mao, Rongzhi
Wu, Jian
Ge, Cheng
Xiao, Feng
Xu, Xiaojun
Xie, Liangxu
Gu, Xiaofeng
author_sort Ji, Li
collection PubMed
description Nasopharyngeal carcinoma (NPC) is one of the most common head and neck cancers. Early diagnosis plays a critical role in the treatment of NPC. To aid diagnosis, deep learning methods can provide interpretable clues for identifying NPC from magnetic resonance images (MRI). To identify the optimal models, we compared the discrimination performance of hierarchical and simple layered convolutional neural networks (CNN). Retrospectively, we collected the MRI images of patients and manually built the tailored NPC image dataset. We examined the performance of the representative CNN models including shallow CNN, ResNet50, ResNet101, and EfficientNet-B7. By fine-tuning, shallow CNN, ResNet50, ResNet101, and EfficientNet-B7 achieved the precision of 72.2%, 94.4%, 92.6%, and 88.4%, displaying the superiority of deep hierarchical neural networks. Among the examined models, ResNet50 with pre-trained weights demonstrated the best classification performance over other types of CNN with accuracy, precision, and an F1-score of 0.93, 0.94, and 0.93, respectively. The fine-tuned ResNet50 achieved the highest prediction performance and can be used as a potential tool for aiding the diagnosis of NPC tumors.
format Online
Article
Text
id pubmed-9601165
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-96011652022-10-27 Deep Convolutional Neural Network for Nasopharyngeal Carcinoma Discrimination on MRI by Comparison of Hierarchical and Simple Layered Convolutional Neural Networks Ji, Li Mao, Rongzhi Wu, Jian Ge, Cheng Xiao, Feng Xu, Xiaojun Xie, Liangxu Gu, Xiaofeng Diagnostics (Basel) Article Nasopharyngeal carcinoma (NPC) is one of the most common head and neck cancers. Early diagnosis plays a critical role in the treatment of NPC. To aid diagnosis, deep learning methods can provide interpretable clues for identifying NPC from magnetic resonance images (MRI). To identify the optimal models, we compared the discrimination performance of hierarchical and simple layered convolutional neural networks (CNN). Retrospectively, we collected the MRI images of patients and manually built the tailored NPC image dataset. We examined the performance of the representative CNN models including shallow CNN, ResNet50, ResNet101, and EfficientNet-B7. By fine-tuning, shallow CNN, ResNet50, ResNet101, and EfficientNet-B7 achieved the precision of 72.2%, 94.4%, 92.6%, and 88.4%, displaying the superiority of deep hierarchical neural networks. Among the examined models, ResNet50 with pre-trained weights demonstrated the best classification performance over other types of CNN with accuracy, precision, and an F1-score of 0.93, 0.94, and 0.93, respectively. The fine-tuned ResNet50 achieved the highest prediction performance and can be used as a potential tool for aiding the diagnosis of NPC tumors. MDPI 2022-10-13 /pmc/articles/PMC9601165/ /pubmed/36292167 http://dx.doi.org/10.3390/diagnostics12102478 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
Ji, Li
Mao, Rongzhi
Wu, Jian
Ge, Cheng
Xiao, Feng
Xu, Xiaojun
Xie, Liangxu
Gu, Xiaofeng
Deep Convolutional Neural Network for Nasopharyngeal Carcinoma Discrimination on MRI by Comparison of Hierarchical and Simple Layered Convolutional Neural Networks
title Deep Convolutional Neural Network for Nasopharyngeal Carcinoma Discrimination on MRI by Comparison of Hierarchical and Simple Layered Convolutional Neural Networks
title_full Deep Convolutional Neural Network for Nasopharyngeal Carcinoma Discrimination on MRI by Comparison of Hierarchical and Simple Layered Convolutional Neural Networks
title_fullStr Deep Convolutional Neural Network for Nasopharyngeal Carcinoma Discrimination on MRI by Comparison of Hierarchical and Simple Layered Convolutional Neural Networks
title_full_unstemmed Deep Convolutional Neural Network for Nasopharyngeal Carcinoma Discrimination on MRI by Comparison of Hierarchical and Simple Layered Convolutional Neural Networks
title_short Deep Convolutional Neural Network for Nasopharyngeal Carcinoma Discrimination on MRI by Comparison of Hierarchical and Simple Layered Convolutional Neural Networks
title_sort deep convolutional neural network for nasopharyngeal carcinoma discrimination on mri by comparison of hierarchical and simple layered convolutional neural networks
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9601165/
https://www.ncbi.nlm.nih.gov/pubmed/36292167
http://dx.doi.org/10.3390/diagnostics12102478
work_keys_str_mv AT jili deepconvolutionalneuralnetworkfornasopharyngealcarcinomadiscriminationonmribycomparisonofhierarchicalandsimplelayeredconvolutionalneuralnetworks
AT maorongzhi deepconvolutionalneuralnetworkfornasopharyngealcarcinomadiscriminationonmribycomparisonofhierarchicalandsimplelayeredconvolutionalneuralnetworks
AT wujian deepconvolutionalneuralnetworkfornasopharyngealcarcinomadiscriminationonmribycomparisonofhierarchicalandsimplelayeredconvolutionalneuralnetworks
AT gecheng deepconvolutionalneuralnetworkfornasopharyngealcarcinomadiscriminationonmribycomparisonofhierarchicalandsimplelayeredconvolutionalneuralnetworks
AT xiaofeng deepconvolutionalneuralnetworkfornasopharyngealcarcinomadiscriminationonmribycomparisonofhierarchicalandsimplelayeredconvolutionalneuralnetworks
AT xuxiaojun deepconvolutionalneuralnetworkfornasopharyngealcarcinomadiscriminationonmribycomparisonofhierarchicalandsimplelayeredconvolutionalneuralnetworks
AT xieliangxu deepconvolutionalneuralnetworkfornasopharyngealcarcinomadiscriminationonmribycomparisonofhierarchicalandsimplelayeredconvolutionalneuralnetworks
AT guxiaofeng deepconvolutionalneuralnetworkfornasopharyngealcarcinomadiscriminationonmribycomparisonofhierarchicalandsimplelayeredconvolutionalneuralnetworks