|
|
基于深度迁移学习的乳腺癌图像分类方法
|
Abstract:
针对乳腺癌病理图像样本数量少、设计特征费时、检测分类的准确性不高等问题，提出一种基于深度学习和迁移学习结合的乳腺癌图像分类模型算法，本算法基于深度神经网络DenseNet结构，通过引入注意力机制构建网络模型，对增强后的数据集使用多级迁移学习进行训练。实验结果表明，在测试集中该算法检测的有效率在83.5%以上，分类的准确率较先前的模型有大幅提升，可以应用到医疗乳腺癌检测任务中。
Aiming at the problem of small sample size, time-consuming design features and low accuracy of detection and classification, a breast cancer image classification algorithm based on deep learning and transfer learning is proposed. The algorithm is based on the deep neural network DenseNet structure, and constructs the network model by introducing attention mechanism. The enhanced data set is trained by multilevel transfer learning. The experimental results show that the efficiency of the algorithm is over 83.5% in the test set, and the accuracy of classification is much higher than that of the previous model, which can be applied to the medical breast cancer detection task.
| [1] | Spanhol, F.A., Oliveira, L.S., Petitjean, C., et al. (2015) A Dataset for Breast Cancer Histopathological Image Classifica-tion. IEEE Transactions on Bio-Medical Engineering, 63, 1455-1462.
https://doi.org/10.1109/TBME.2015.2496264 |
| [2] | Ojala, T., Pietik？inen, M. and Harwood, D. (1996) Comparative Study of Texture Measures with Classification Based on Feature Distrubution. Pattern Recognition, 29, 51-59. https://doi.org/10.1016/0031-3203(95)00067-4 |
| [3] | 李慧, 焦雄. 基于影像组学的乳腺钼靶图像机器学习分类模型研究[J/OL]. 太原理工大学学报.
http://kns.cnki.net/kcms/detail/14.1220.n.20220401.1053.002.html, 2022-04-08. |
| [4] | Rezazadeh, A., Jafarian, Y. and Kord, A. (2201) Explainable Ensemble Machine Learning for Breast Cancer Diagnosis Based on Ultrasound Image Tex-ture Features. arXiv: 2201.07227, 2, 22. |
| [5] | Pawer, M.M., Pujari, S.D., Pawar, S.P., et al. (2022) MuSCF-Net: Mul-ti-Scale, Multi-Channel Feature Network Using Resnet-Based Attention Mechanism for Breast Histopathological Image Classification. Machine Learning and Deep Learning Techniques for Medical Science, CRC Press, 243-261. https://doi.org/10.1201/9781003217497-14 |
| [6] | Kavitha, T., Mathai, P.P., Karthikeyan, C., et al. (2022) Deep Learning Based Capsule Neural Network Model for Breast Cancer Diagnosis Using Mammogram Images. Interdiscipli-nary Sciences: Computational Life Sciences, 14, 113-129. https://doi.org/10.1007/s12539-021-00467-y |
| [7] | 李赵旭, 宋涛, 葛梦飞, 刘嘉欣, 王宏伟, 王佳. 基于改进Inception模型的乳腺癌病理学图像分类[J]. 激光与光电子学进展, 2021, 58(8): 396-402. |
| [8] | Sahiner, B., Chan, H.P., Petrick, N., et al. (1996) Classification of Mass and Nor-mal Breast Tissue: A Convolution Neural Network Classifier with Spatial Domain and Texture Images. IEEE Transac-tions on Medical Imaging, 15, 598-610. https://doi.org/10.1109/42.538937 |
| [9] | Doi, K. (2007) Computer-Aided Diagnosisin Medical Imaging: Historical Review, Current Status and Future Potential. Computerized Medical Imaging & Graphics, 31, 198-211. https://doi.org/10.1016/j.compmedimag.2007.02.002 |
| [10] | Karssemeijer, N., Giger, M.L. and Karssemeijer, N. (2000) Computer-Aided Diagnosis of Breast Lesions in Medical Images. Computing in Science & Engineering, 2, 39-45. https://doi.org/10.1109/5992.877391 |
| [11] | Pan, S.J. and Yang, Q. (2010) A Survey on Transfer Leatring. IEEE Transactions on Knowledge and Data Engineer, 22, 1345-1359. https://doi.org/10.1109/TKDE.2009.191 |
| [12] | Dawud, A.M., Yurtkan, K. and Oztoprak, H. (2019) Application of Deep Learning in Neuroradiology: Brain Haemorrhage Classification Using Transfer Learning. Computational Intelli-gence and Neuroscience, 2019, Article ID: 4629859. https://doi.org/10.1155/2019/4629859 |
| [13] | Byra, M., Styczynski, G., Szmigielski, C., Kalinowski, P., Micha？owski, ？., Paluszkiewicz, R., Ziarkiewicz-Wróblewska, B., Zieniewicz, K., Sobieraj, P. and Nowicki, A. (2018) Transfer Learning with Deep Convolutional Neural Network for Liver Steatosis Assessment in Ultrasound Images. International Journal of Computer Assisted Radiology and Surgery, 13, 1895-1903. https://doi.org/10.1007/s11548-018-1843-2 |
| [14] | Qu, A.P., Chen, J.M., Wang, L.W., et al. (2015) Segmentation of Hematoxylin-Eosin Stained Breast Cancer Histopathological Images Based on Pixel-Wise SVM Classi-fier. Science China Information Sciences, 58, 1-13.
https://doi.org/10.1007/s11432-014-5277-3 |
| [15] | Huang, G., Liu, Z., Van Der Maaten, L., et al. (2017) Densely Connected Convolutional Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, 21-26 July 2017, 4700-4708.
https://doi.org/10.1109/CVPR.2017.243 |
| [16] | 郝旭政, 柴争义. 一种改进的深度残差网络行人检测方法[J]. 计算机应用研究, 2019, 36(6): 1-3. |
| [17] | Simonyan, K. and Zisserman, A. (2015) Very Deep Convolutional Networks Forlarge-Scale Image Recognition. Proceedings of International Conference on Learning Representations, San Diego, April 2015, 1-14. |
| [18] | Li, J., Wang, P., Li, Y.Z., Zhou, Y., Liu, X.L. and Luan, K. (2018) Transfer Learning of Pre-trained Inception-V3 Model for Colorectal Cancer Lymph Node Metastasis Classification. 2018 IEEE International Con-ference on Mechatronics and Automation, Changchun, 5-8 August 2018, 1650-1654. https://doi.org/10.1109/ICMA.2018.8484405 |
