Deep learning based automated diagnosis of bone metastases with SPECT thoracic bone images
Abstract SPECT nuclear medicine imaging is widely used for treating, diagnosing, evaluating and preventing various serious diseases. The automated classification of medical images is becoming increasingly important in developing computer-aided diagnosis systems. Deep learning, particularly for the c...
Guardado en:
Autores principales: | , , , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Nature Portfolio
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/afc5c4313ac74df1930818e5cc5bd931 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:afc5c4313ac74df1930818e5cc5bd931 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:afc5c4313ac74df1930818e5cc5bd9312021-12-02T12:11:12ZDeep learning based automated diagnosis of bone metastases with SPECT thoracic bone images10.1038/s41598-021-83083-62045-2322https://doaj.org/article/afc5c4313ac74df1930818e5cc5bd9312021-02-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-83083-6https://doaj.org/toc/2045-2322Abstract SPECT nuclear medicine imaging is widely used for treating, diagnosing, evaluating and preventing various serious diseases. The automated classification of medical images is becoming increasingly important in developing computer-aided diagnosis systems. Deep learning, particularly for the convolutional neural networks, has been widely applied to the classification of medical images. In order to reliably classify SPECT bone images for the automated diagnosis of metastasis on which the SPECT imaging solely focuses, in this paper, we present several deep classifiers based on the deep networks. Specifically, original SPECT images are cropped to extract the thoracic region, followed by a geometric transformation that contributes to augment the original data. We then construct deep classifiers based on the widely used deep networks including VGG, ResNet and DenseNet by fine-tuning their parameters and structures or self-defining new network structures. Experiments on a set of real-world SPECT bone images show that the proposed classifiers perform well in identifying bone metastasis with SPECT imaging. It achieves 0.9807, 0.9900, 0.9830, 0.9890, 0.9802 and 0.9933 for accuracy, precision, recall, specificity, F-1 score and AUC, respectively, on the test samples from the augmented dataset without normalization.Qiang LinTongtong LiChuangui CaoYongchun CaoZhengxing ManHaijun WangNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-15 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Medicine R Science Q |
spellingShingle |
Medicine R Science Q Qiang Lin Tongtong Li Chuangui Cao Yongchun Cao Zhengxing Man Haijun Wang Deep learning based automated diagnosis of bone metastases with SPECT thoracic bone images |
description |
Abstract SPECT nuclear medicine imaging is widely used for treating, diagnosing, evaluating and preventing various serious diseases. The automated classification of medical images is becoming increasingly important in developing computer-aided diagnosis systems. Deep learning, particularly for the convolutional neural networks, has been widely applied to the classification of medical images. In order to reliably classify SPECT bone images for the automated diagnosis of metastasis on which the SPECT imaging solely focuses, in this paper, we present several deep classifiers based on the deep networks. Specifically, original SPECT images are cropped to extract the thoracic region, followed by a geometric transformation that contributes to augment the original data. We then construct deep classifiers based on the widely used deep networks including VGG, ResNet and DenseNet by fine-tuning their parameters and structures or self-defining new network structures. Experiments on a set of real-world SPECT bone images show that the proposed classifiers perform well in identifying bone metastasis with SPECT imaging. It achieves 0.9807, 0.9900, 0.9830, 0.9890, 0.9802 and 0.9933 for accuracy, precision, recall, specificity, F-1 score and AUC, respectively, on the test samples from the augmented dataset without normalization. |
format |
article |
author |
Qiang Lin Tongtong Li Chuangui Cao Yongchun Cao Zhengxing Man Haijun Wang |
author_facet |
Qiang Lin Tongtong Li Chuangui Cao Yongchun Cao Zhengxing Man Haijun Wang |
author_sort |
Qiang Lin |
title |
Deep learning based automated diagnosis of bone metastases with SPECT thoracic bone images |
title_short |
Deep learning based automated diagnosis of bone metastases with SPECT thoracic bone images |
title_full |
Deep learning based automated diagnosis of bone metastases with SPECT thoracic bone images |
title_fullStr |
Deep learning based automated diagnosis of bone metastases with SPECT thoracic bone images |
title_full_unstemmed |
Deep learning based automated diagnosis of bone metastases with SPECT thoracic bone images |
title_sort |
deep learning based automated diagnosis of bone metastases with spect thoracic bone images |
publisher |
Nature Portfolio |
publishDate |
2021 |
url |
https://doaj.org/article/afc5c4313ac74df1930818e5cc5bd931 |
work_keys_str_mv |
AT qianglin deeplearningbasedautomateddiagnosisofbonemetastaseswithspectthoracicboneimages AT tongtongli deeplearningbasedautomateddiagnosisofbonemetastaseswithspectthoracicboneimages AT chuanguicao deeplearningbasedautomateddiagnosisofbonemetastaseswithspectthoracicboneimages AT yongchuncao deeplearningbasedautomateddiagnosisofbonemetastaseswithspectthoracicboneimages AT zhengxingman deeplearningbasedautomateddiagnosisofbonemetastaseswithspectthoracicboneimages AT haijunwang deeplearningbasedautomateddiagnosisofbonemetastaseswithspectthoracicboneimages |
_version_ |
1718394649498877952 |