Bone scintigraphic classification method based on ACGAN and transfer learning

YU Hong; LUO Renze; CHEN Chunmeng; TANG Xiang; LUO Renquan

doi:10.37188/OPE.20233106.0936

您当前的位置：

首页 >

文章列表页 >

Bone scintigraphic classification method based on ACGAN and transfer learning

Information Sciences | 更新时间：2023-03-25

- Bone scintigraphic classification method based on ACGAN and transfer learning
- Optics and Precision Engineering Vol. 31, Issue 6, Pages: 936-949(2023)
- 作者机构：
  
  1.西南石油大学电气信息学院，四川成都 610500
  2.宜宾市第二人民医院核医学科，四川宜宾 644000
  3.西南石油大学计算机科学学院，四川成都 610500
- 作者简介：
- 基金信息：
- DOI：10.37188/OPE.20233106.0936
  CLC： TP391
- Received：19 July 2022，
  
  Revised：22 August 2022，
  
  Published：25 March 2023
- 稿件说明：
移动端阅览
余泓,罗仁泽,陈春梦等.基于ACGAN和迁移学习的骨显像分类方法[J].光学精密工程,2023,31(06):936-949.

YU Hong,LUO Renze,CHEN Chunmeng,et al.Bone scintigraphic classification method based on ACGAN and transfer learning[J].Optics and Precision Engineering,2023,31(06):936-949.
余泓,罗仁泽,陈春梦等.基于ACGAN和迁移学习的骨显像分类方法[J].光学精密工程,2023,31(06):936-949. DOI： 10.37188/OPE.20233106.0936.

YU Hong,LUO Renze,CHEN Chunmeng,et al.Bone scintigraphic classification method based on ACGAN and transfer learning[J].Optics and Precision Engineering,2023,31(06):936-949. DOI： 10.37188/OPE.20233106.0936.

摘要

由于骨显像存在样本数量有限、类别不平衡的问题，导致骨显像分类存在较大困难。为提升骨显像的分类准确率，本文提出了一种基于结合辅助分类器的生成对抗网络（ACGAN）数据生成和迁移学习的骨显像分类方法。首先，为解决骨显像类别不平衡的问题，设计了一种MU-ACGAN模型。该模型以U-Net为生成器框架，同时结合密集残差连接和通道-空间注意力机制结构来提升骨显像细节特征生成，判别器通过密集残差注意力卷积块提取骨显像特征进行判别；然后，结合传统数据增强方式进一步扩充数据量；最后，设计了一种多尺度卷积神经网络提取骨显像不同尺度的特征，提升分类效果。在模型训练过程中，采用两阶段迁移学习方式，优化模型的初始化参数、解决过拟合的问题。实验结果表明，本文提出方法分类准确率达到了85.71%，有效缓解了小样本骨显像数据集分类准确率不高的问题。

Abstract

Owing to the limited availability of samples and unbalanced categories of bone images， it is difficult to classify these images. To improve the classification accuracy of bone images， this study developed a bone-image classification method based on auxiliary classifier generative adversarial network （ACGAN） data generation and transfer learning. First， an multi-attention U-Net-based ACGAN （MU-ACGAN） model was designed to address the imbalance of bone-image categories. The model uses U-Net as the generator framework and combines dense residual connection and channel-spatial attention mechanism to improve the generation of bone-image detail features. The discriminator extracts bone-image features by using a dense residual attention convolution block for discrimination. Next， the amount of data was further expanded via combination with traditional data enhancement methods. Finally， a multi-scale convolutional neural network was designed to extract the features at different scales of bone imaging so as to improve the classification effect. In the model training process， a two-stage transfer learning method was adopted to optimize the initialization parameters of the model and address the problem of overfitting. Experimental results indicate that the classification accuracy of the proposed method reaches 85.71%， effectively alleviating the problem of low classification accuracy on small sample bone-image datasets.

关键词

Keywords

references

FENG J X ， JIANG J . Deep learning-based chest CT image features in diagnosis of lung cancer ［J］. Computational and Mathematical Methods in Medicine ， 2022 ， 2022 ： 4153211 . doi: 10.1155/2022/4153211 http://dx.doi.org/10.1155/2022/4153211

张永平，兰朋训，周兆霞 . MRI和骨显像诊断骨转移瘤的临床价值分析［J］. 医学影像学杂志， 2017 ， 27 （ 10 ）： 2040 - 2042 .

ZHANG Y P ， LAN P X ， ZHOU ZH X . Clinical value of MRI and bone scintigraphy in the diagnosis of bone metastases ［J］. Journal of Medical Imaging ， 2017 ， 27 （ 10 ）： 2040 - 2042 . （in Chinese）

MADSEN M T . Recent advances in SPECT imaging ［J］. Journal of Nuclear Medicine： Official Publication ， Society of Nuclear Medicine， 2007 ， 48 （ 4 ）： 661 - 673 . doi: 10.2967/jnumed.106.032680 http://dx.doi.org/10.2967/jnumed.106.032680

SADIK M ， HAMADEH I ， NORDBLOM P ， et al . Computer-assisted interpretation of planar whole-body bone scans ［J］. J Nucl Med ， 2008 ， 49 （ 12 ）： 1958 - 1965 . doi: 10.2967/jnumed.108.055061 http://dx.doi.org/10.2967/jnumed.108.055061

ASLANTAS A ， DANDIL E ， SAǦLAM S ， et al . CADBOSS： a computer-aided diagnosis system for whole-body bone scintigraphy scans ［J］. Journal of Cancer Research and Therapeutics ， 2016 ， 12 （ 2 ）： 787 - 792 . doi: 10.4103/0973-1482.150422 http://dx.doi.org/10.4103/0973-1482.150422

ANTONINA M ， CALIN . Object-oriented classification approach for bone metastasis mapping from whole-body bone scintigraphy ［J］. Physica Medica ， 2021 ， 84 ： 141 - 148 . doi: 10.1016/j.ejmp.2021.03.040 http://dx.doi.org/10.1016/j.ejmp.2021.03.040

ELFARRA F G ， CALIN M A ， PARASCA S V . Computer-aided detection of bone metastasis in bone scintigraphy images using parallelepiped classification method ［J］. Annals of Nuclear Medicine ， 2019 ， 33 （ 11 ）： 866 - 874 . doi: 10.1007/s12149-019-01399-w http://dx.doi.org/10.1007/s12149-019-01399-w

WANG Z Y ， WEN X T ， LU Y H ， et al . Exploiting machine learning for predicting skeletal-related events in cancer patients with bone metastases ［J］. Oncotarget ， 2016 ， 7 （ 11 ）： 12612 - 12622 . doi: 10.18632/oncotarget.7278 http://dx.doi.org/10.18632/oncotarget.7278

LU L M ， ZHANG C L ， CAO K ， et al . A multichannel CNN-GRU model for human activity recognition ［J］. IEEE Access ， 2022 ， 10 ： 66797 - 66810 . doi: 10.1109/access.2022.3185112 http://dx.doi.org/10.1109/access.2022.3185112

ZHENG Z W ， LIU L X ， CHEN X Y ， et al . Construction of Bisection Model of SPECT Bone Scan Image Based on VGGNet ［C］. 2021 IEEE International Conference on Artificial Intelligence and Industrial Design （AIID）. 2830，2021 ， Guangzhou， China. IEEE ， 2021 ： 150 - 154 . doi: 10.1109/aiid51893.2021.9456458 http://dx.doi.org/10.1109/aiid51893.2021.9456458

PAPANDRIANOS N ， PAPAGEORGIOU E ， ANAGNOSTIS A ， et al . Bone metastasis classification using whole body images from prostate cancer patients based on convolutional neural networks application ［J］. PLoS One ， 2020 ， 15 （ 8 ）： e0237213 . doi: 10.1371/journal.pone.0237213 http://dx.doi.org/10.1371/journal.pone.0237213

NTAKOLIA C ， DIAMANTIS D E ， PAPANDRIANOS N ， et al . A lightweight convolutional neural network architecture applied for bone metastasis classification in nuclear medicine： a case study on prostate cancer patients ［J］. Healthcare ， 2020 ， 8 （ 4 ）： 493 . doi: 10.3390/healthcare8040493 http://dx.doi.org/10.3390/healthcare8040493

LIN Q ， CAO C G ， LI T T ， et al . dSPIC： a deep SPECT image classification network for automated multi-disease， multi-lesion diagnosis ［J］. BMC Medical Imaging ， 2021 ， 21 （ 1 ）： 122 . doi: 10.1186/s12880-021-00653-w http://dx.doi.org/10.1186/s12880-021-00653-w

ABDOLLAHI B ， TOMITA N ， HASSANPOUR S . Data augmentation in training deep learning models for medical image analysis ［J］. Intelligent Systems Reference Library ， 2020 ： 167 - 180 . doi: 10.1007/978-3-030-42750-4_6 http://dx.doi.org/10.1007/978-3-030-42750-4_6

PADMAVATHI KORA . Transfer learning techniques for medical image analysis： a review ［J］. Biocybernetics and Biomedical Engineering ， 2022 ， 42 （ 1 ）： 79 - 107 . doi: 10.1016/j.bbe.2021.11.004 http://dx.doi.org/10.1016/j.bbe.2021.11.004

TEHSEEN ZIA . VANT-GAN： adversarial learning for discrepancy-based visual attribution in medical imaging ［J］. Pattern Recognition Letters ， 2022 ， 156 ： 112 - 118 . doi: 10.1016/j.patrec.2022.02.005 http://dx.doi.org/10.1016/j.patrec.2022.02.005

WU C M ， ZENG Z . A fault diagnosis method based on Auxiliary Classifier Generative Adversarial Network for rolling bearing ［J］. PLoS One ， 2021 ， 16 （ 3 ）： e0246905 . doi: 10.1371/journal.pone.0246905 http://dx.doi.org/10.1371/journal.pone.0246905

RONNEBERGER O ， FISCHER P ， BROX T . U-net： convolutional networks for biomedical image segmentation ［J］. Lecture Notes in Computer Science ， 2015 ： 234 - 241 . doi: 10.1007/978-3-319-24574-4_28 http://dx.doi.org/10.1007/978-3-319-24574-4_28

HOU Q B ， ZHOU D Q ， FENG J S . Coordinate Attention for Efficient Mobile Network Design ［C］. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. 2025，2021 ， Nashville， TN， USA. IEEE ， 2021 ： 13708 - 13717 . doi: 10.1109/cvpr46437.2021.01350 http://dx.doi.org/10.1109/cvpr46437.2021.01350

XU J ， WANG J ， XU X ， et al . Image recognition for different developmental stages of rice by RAdam deep convolutional neural networks ［J］. Nongye Gongcheng Xuebao/Transactions of the Chinese Society of Agricultural Engineering ， 2021 ， 37 （ 8 ）： 143 - 150 .

HOWARD A ， SANDLER M ， CHEN B ， et al . Searching for MobileNetV3 ［C］. 2019 IEEE/CVF International Conference on Computer Vision （ICCV）. 272，2019 ， Seoul， Korea （South）. IEEE ， 2020 ： 1314 - 1324 . doi: 10.1109/iccv.2019.00140 http://dx.doi.org/10.1109/iccv.2019.00140

LIU K ， YU S T ， LIU S D . An improved InceptionV3 network for obscured ship classification in remote sensing images ［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing ， 2020 ， 13 ： 4738 - 4747 . doi: 10.1109/jstars.2020.3017676 http://dx.doi.org/10.1109/jstars.2020.3017676

TAN M ， LE Q V . EfficientNet： Rethinking Model Scaling for Convolution Neural Networks ［C］. 36th International Conference on Machine Learning（ICML 2019 ）， Los Angeles， USA ： Proceedings of Machine Learning Research ， 2019： 6105 - 6114 .

Views

619

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Underwater image enhancement based on multi-branch residual attention network

End-to-end recognition of nighttime wildlife based on semi-supervised learning

Pseudo-label confidence regulates semi-supervised semantic segmentation of pathological images of colorectal cancer

Real-time deblurring of wideband small target based on attention mechanism

Integrating global information and dual-domain attention mechanism for optical remote sensing aircraft target detection

Related Author

CHENG Zhuming

LI Jiaxuan

HUANG San'ao

HAN Lichao

WANG Peizhen

LU Han

CUI Bolun

WAN Huayang

Related Institution

School of Electrical and Information Engineering， Anhui University of Technology， Maanshan

School of Mechatronic Engineering and Automation，Shanghai University

Beijing Institute of Space Mechanics & Electricity

Faculty of Mechanical and Electrical Engineering， Kunming University of Science and Technology

Department of Radiology， Yunnan Cancer Hospital

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰