Cargando…
Multiclass classification of whole‐body scintigraphic images using a self‐defined convolutional neural network with attention modules
PURPOSE: A self‐defined convolutional neural network is developed to automatically classify whole‐body scintigraphic images of concern (i.e., the normal, metastasis, arthritis, and thyroid carcinoma), automatically detecting diseases with whole‐body bone scintigraphy. METHODS: A set of parameter tra...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
John Wiley and Sons Inc.
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9135133/ https://www.ncbi.nlm.nih.gov/pubmed/34455613 http://dx.doi.org/10.1002/mp.15196 |
_version_ | 1784713897588031488 |
---|---|
author | Lin, Qiang Cao, Chuangui Li, Tongtong Cao, Yongchun Man, Zhengxing Wang, Haijun |
author_facet | Lin, Qiang Cao, Chuangui Li, Tongtong Cao, Yongchun Man, Zhengxing Wang, Haijun |
author_sort | Lin, Qiang |
collection | PubMed |
description | PURPOSE: A self‐defined convolutional neural network is developed to automatically classify whole‐body scintigraphic images of concern (i.e., the normal, metastasis, arthritis, and thyroid carcinoma), automatically detecting diseases with whole‐body bone scintigraphy. METHODS: A set of parameter transformation operations are first used to augment the original dataset of whole‐body bone scintigraphic images. A hybrid attention mechanism including the spatial and channel attention module is then introduced to develop a deep classification network, Dscint, which consists of eight weight layers, one hybrid attention module, two normalization modules, two fully connected layers, and one softmax layer. RESULTS: Experimental evaluations conducted on a set of whole‐body scintigraphic images show that the proposed deep classification network, Dscint, performs well for automated detection of diseases by classifying the images of concerns, achieving the accuracy, precision, recall, specificity, and F‐1 score of 0.9801, 0.9795, 0.9791, 0.9933, and 0.9792, respectively, on the test data in the augmented dataset. A comparative analysis of Dscint and several classical deep classification networks (i.e., AlexNet, ResNet, VGGNet, DenseNet, and Inception‐v4) reveals that our self‐defined network, Dscint, performs best on classifying whole‐body scintigraphic images on the same dataset. CONCLUSIONS: The self‐defined deep classification network, Dscint, can be utilized to automatically determine whether a whole‐body scintigraphic image is either normal or contains diseases of concern. Specifically, better performance of Dscint is obtained on images with lesions that are present in relatively fixed locations like thyroid carcinoma than those with lesions occurring in nonfixed locations of bone tissue. |
format | Online Article Text |
id | pubmed-9135133 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | John Wiley and Sons Inc. |
record_format | MEDLINE/PubMed |
spelling | pubmed-91351332022-06-04 Multiclass classification of whole‐body scintigraphic images using a self‐defined convolutional neural network with attention modules Lin, Qiang Cao, Chuangui Li, Tongtong Cao, Yongchun Man, Zhengxing Wang, Haijun Med Phys DIAGNOSTIC IMAGING (IONIZING AND NON‐IONIZING) PURPOSE: A self‐defined convolutional neural network is developed to automatically classify whole‐body scintigraphic images of concern (i.e., the normal, metastasis, arthritis, and thyroid carcinoma), automatically detecting diseases with whole‐body bone scintigraphy. METHODS: A set of parameter transformation operations are first used to augment the original dataset of whole‐body bone scintigraphic images. A hybrid attention mechanism including the spatial and channel attention module is then introduced to develop a deep classification network, Dscint, which consists of eight weight layers, one hybrid attention module, two normalization modules, two fully connected layers, and one softmax layer. RESULTS: Experimental evaluations conducted on a set of whole‐body scintigraphic images show that the proposed deep classification network, Dscint, performs well for automated detection of diseases by classifying the images of concerns, achieving the accuracy, precision, recall, specificity, and F‐1 score of 0.9801, 0.9795, 0.9791, 0.9933, and 0.9792, respectively, on the test data in the augmented dataset. A comparative analysis of Dscint and several classical deep classification networks (i.e., AlexNet, ResNet, VGGNet, DenseNet, and Inception‐v4) reveals that our self‐defined network, Dscint, performs best on classifying whole‐body scintigraphic images on the same dataset. CONCLUSIONS: The self‐defined deep classification network, Dscint, can be utilized to automatically determine whether a whole‐body scintigraphic image is either normal or contains diseases of concern. Specifically, better performance of Dscint is obtained on images with lesions that are present in relatively fixed locations like thyroid carcinoma than those with lesions occurring in nonfixed locations of bone tissue. John Wiley and Sons Inc. 2021-09-14 2021-10 /pmc/articles/PMC9135133/ /pubmed/34455613 http://dx.doi.org/10.1002/mp.15196 Text en © 2021 The Authors. Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine https://creativecommons.org/licenses/by/4.0/This is an open access article under the terms of the http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited. |
spellingShingle | DIAGNOSTIC IMAGING (IONIZING AND NON‐IONIZING) Lin, Qiang Cao, Chuangui Li, Tongtong Cao, Yongchun Man, Zhengxing Wang, Haijun Multiclass classification of whole‐body scintigraphic images using a self‐defined convolutional neural network with attention modules |
title | Multiclass classification of whole‐body scintigraphic images using a self‐defined convolutional neural network with attention modules |
title_full | Multiclass classification of whole‐body scintigraphic images using a self‐defined convolutional neural network with attention modules |
title_fullStr | Multiclass classification of whole‐body scintigraphic images using a self‐defined convolutional neural network with attention modules |
title_full_unstemmed | Multiclass classification of whole‐body scintigraphic images using a self‐defined convolutional neural network with attention modules |
title_short | Multiclass classification of whole‐body scintigraphic images using a self‐defined convolutional neural network with attention modules |
title_sort | multiclass classification of whole‐body scintigraphic images using a self‐defined convolutional neural network with attention modules |
topic | DIAGNOSTIC IMAGING (IONIZING AND NON‐IONIZING) |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9135133/ https://www.ncbi.nlm.nih.gov/pubmed/34455613 http://dx.doi.org/10.1002/mp.15196 |
work_keys_str_mv | AT linqiang multiclassclassificationofwholebodyscintigraphicimagesusingaselfdefinedconvolutionalneuralnetworkwithattentionmodules AT caochuangui multiclassclassificationofwholebodyscintigraphicimagesusingaselfdefinedconvolutionalneuralnetworkwithattentionmodules AT litongtong multiclassclassificationofwholebodyscintigraphicimagesusingaselfdefinedconvolutionalneuralnetworkwithattentionmodules AT caoyongchun multiclassclassificationofwholebodyscintigraphicimagesusingaselfdefinedconvolutionalneuralnetworkwithattentionmodules AT manzhengxing multiclassclassificationofwholebodyscintigraphicimagesusingaselfdefinedconvolutionalneuralnetworkwithattentionmodules AT wanghaijun multiclassclassificationofwholebodyscintigraphicimagesusingaselfdefinedconvolutionalneuralnetworkwithattentionmodules |