Cargando…

Accurate classification of lung nodules on CT images using the TransUnet

BACKGROUND: Computed tomography (CT) is an effective way to scan for lung cancer. The classification of lung nodules in CT screening is completely doctor dependent, which has drawbacks, including difficulty classifying tiny nodules, subjectivity, and high false-positive rates. In recent years, deep...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Hongfeng, Zhu, Hai, Ding, Lihua
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9760709/
https://www.ncbi.nlm.nih.gov/pubmed/36544802
http://dx.doi.org/10.3389/fpubh.2022.1060798
_version_ 1784852537826869248
author Wang, Hongfeng
Zhu, Hai
Ding, Lihua
author_facet Wang, Hongfeng
Zhu, Hai
Ding, Lihua
author_sort Wang, Hongfeng
collection PubMed
description BACKGROUND: Computed tomography (CT) is an effective way to scan for lung cancer. The classification of lung nodules in CT screening is completely doctor dependent, which has drawbacks, including difficulty classifying tiny nodules, subjectivity, and high false-positive rates. In recent years, deep convolutional neural networks, a deep learning technology, have been shown to be effective in medical imaging diagnosis. Herein, we propose a deep convolutional neural network technique (TransUnet) to automatically classify lung nodules accurately. METHODS: TransUnet consists of three parts: the transformer, the Unet, and global average pooling (GAP). The transformer encodes discriminative features via global self-attention modeling on CT image patches. The Unet, which collects context by constricting route, enables exact lunge nodule localization. The GAP categorizes CT images, assigning each sample a score. Python was employed to pre-process all CT images in the LIDI-IDRI, and the obtained 8,474 images (3,259 benign and 5,215 lung nodules) were used to evaluate the method's performance. RESULTS: The accuracies of TransUnet in the training and testing sets were 87.90 and 84.62%. The sensitivity, specificity, and AUC of the proposed TransUnet on the testing dataset were 70.92, 93.17, and 0.862%, respectively (0.844–0.879). We also compared TransUnet to three well-known methods, which outperformed these methods. CONCLUSION: The experimental results on LIDI-IDRI demonstrated that the proposed TransUnet has a great performance in classifying lung nodules and has a great potential application in diagnosing lung cancer.
format Online
Article
Text
id pubmed-9760709
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-97607092022-12-20 Accurate classification of lung nodules on CT images using the TransUnet Wang, Hongfeng Zhu, Hai Ding, Lihua Front Public Health Public Health BACKGROUND: Computed tomography (CT) is an effective way to scan for lung cancer. The classification of lung nodules in CT screening is completely doctor dependent, which has drawbacks, including difficulty classifying tiny nodules, subjectivity, and high false-positive rates. In recent years, deep convolutional neural networks, a deep learning technology, have been shown to be effective in medical imaging diagnosis. Herein, we propose a deep convolutional neural network technique (TransUnet) to automatically classify lung nodules accurately. METHODS: TransUnet consists of three parts: the transformer, the Unet, and global average pooling (GAP). The transformer encodes discriminative features via global self-attention modeling on CT image patches. The Unet, which collects context by constricting route, enables exact lunge nodule localization. The GAP categorizes CT images, assigning each sample a score. Python was employed to pre-process all CT images in the LIDI-IDRI, and the obtained 8,474 images (3,259 benign and 5,215 lung nodules) were used to evaluate the method's performance. RESULTS: The accuracies of TransUnet in the training and testing sets were 87.90 and 84.62%. The sensitivity, specificity, and AUC of the proposed TransUnet on the testing dataset were 70.92, 93.17, and 0.862%, respectively (0.844–0.879). We also compared TransUnet to three well-known methods, which outperformed these methods. CONCLUSION: The experimental results on LIDI-IDRI demonstrated that the proposed TransUnet has a great performance in classifying lung nodules and has a great potential application in diagnosing lung cancer. Frontiers Media S.A. 2022-12-05 /pmc/articles/PMC9760709/ /pubmed/36544802 http://dx.doi.org/10.3389/fpubh.2022.1060798 Text en Copyright © 2022 Wang, Zhu and Ding. 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 Public Health
Wang, Hongfeng
Zhu, Hai
Ding, Lihua
Accurate classification of lung nodules on CT images using the TransUnet
title Accurate classification of lung nodules on CT images using the TransUnet
title_full Accurate classification of lung nodules on CT images using the TransUnet
title_fullStr Accurate classification of lung nodules on CT images using the TransUnet
title_full_unstemmed Accurate classification of lung nodules on CT images using the TransUnet
title_short Accurate classification of lung nodules on CT images using the TransUnet
title_sort accurate classification of lung nodules on ct images using the transunet
topic Public Health
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9760709/
https://www.ncbi.nlm.nih.gov/pubmed/36544802
http://dx.doi.org/10.3389/fpubh.2022.1060798
work_keys_str_mv AT wanghongfeng accurateclassificationoflungnodulesonctimagesusingthetransunet
AT zhuhai accurateclassificationoflungnodulesonctimagesusingthetransunet
AT dinglihua accurateclassificationoflungnodulesonctimagesusingthetransunet