Wang
[2]
等人新开发的深度学习放射组学(DLRE)前体层摄影术在评估肝纤维化分期方面显著优于其他方法。Yasaka K.
[3]
等人证明,使用卷积神经网络(CNN)深度学习方法在动态对比增强计算机断层扫描(CT)中区分肝脏肿块的诊断性能优于传统方法。Wu
[4]
等人将3层DBN应用于从造影剂增强超声(CEUS)视频序列中提取的时间强度曲线(TIC),实现了局灶性肝脏病变的良恶性分类,获得了86.36%的最高准确率。Sato M.
[5]
通过对B型超声图像以及病历和血液数据中的其他信息进行联合训练,提出了一种用于良恶性肿瘤识别的人工智能模型,其准确率为96.3%,AUROC为0.994。Tarek M.
[6]
等人提出了一种基于深度学习技术的堆叠稀疏自动编码器特征表示,其整体分类准确率达到97.2%,优于(多重支持向量机、K-最近邻和Naive Bayes)等技术。然而,这些机器学习方法大多使用浅层架构。鉴于深度神经网络强大的特征和学习能力,基于特征提取的深度卷积神经网络用于肝脏超声图像分类是一个值得深入研究的课题。本文提出了一种基于特征提取的深度残差神经网络(ResNet),用于肝脏病变的超声图像分类,提高了肝脏病灶分类的准确性。
<xref></xref>Table 1. Comparison of training effectiveness of different network modelsTable 1. Comparison of training effectiveness of different network models 表1. 不同网络模型的训练效能比较
References
Rumgay, H., Arnold, M., Ferlay, J., Lesi, O., Cabasag, C.J., Vignat, J., et al. (2022) Global Burden of Primary Liver Cancer in 2020 and Predictions to 2040. Journal of Hepatology, 77, 1598-1606. >https://doi.org/10.1016/j.jhep.2022.08.021
Wang, K., Lu, X., Zhou, H., Gao, Y., Zheng, J., Tong, M., et al. (2018) Deep Learning Radiomics of Shear Wave Elastography Significantly Improved Diagnostic Performance for Assessing Liver Fibrosis in Chronic Hepatitis B: A Prospective Multicentre Study. Gut, 68, 729-741. >https://doi.org/10.1136/gutjnl-2018-316204
Yasaka, K., Akai, H., Abe, O. and Kiryu, S. (2018) Deep Learning with Convolutional Neural Network for Differentiation of Liver Masses at Dynamic Contrast-Enhanced CT: A Preliminary Study. Radiology, 286, 887-896. >https://doi.org/10.1148/radiol.2017170706
Wu, K., Chen, X. and Ding, M. (2014) Deep Learning Based Classification of Focal Liver Lesions with Contrast-Enhanced Ultrasound. Optik, 125, 4057-4063. >https://doi.org/10.1016/j.ijleo.2014.01.114
Sato, M., Kobayashi, T., Soroida, Y., Tanaka, T., Nakatsuka, T., Nakagawa, H., et al. (2022) Development of Novel Deep Multimodal Representation Learning‐based Model for the Differentiation of Liver Tumors on B‐mode Ultrasound Images. Journal of Gastroenterology and Hepatology, 37, 678-684. >https://doi.org/10.1111/jgh.15763
Hassan, T.M., Elmogy, M. and Sallam, E. (2017) Diagnosis of Focal Liver Diseases Based on Deep Learning Technique for Ultrasound Images. Arabian Journal for Science and Engineering, 42, 3127-3140. >https://doi.org/10.1007/s13369-016-2387-9
Dogo, E.M., Afolabi, O.J., Nwulu, N.I., Twala, B. and Aigbavboa, C.O. (2018) A Comparative Analysis of Gradient Descent-Based Optimization Algorithms on Convolutional Neural Networks. 2018 International Conference on Computational Techniques, Electronics and Mechanical Systems (CTEMS), Belgaum, 21-22 December 2018, 92-99. >https://doi.org/10.1109/ctems.2018.8769211
Simonyan, K. and Zisserman, A. (2014) Two-Stream Convolutional Networks for Action Recognition in Videos. NIPS’14: Proceedings of the 28th International Conference on Neural Information Processing Systems, Volume 1, 568-576.
Lee, C. and Le, T. (2021) Identifying Faults of Rolling Element Based on Persistence Spectrum and Convolutional Neural Network with Resnet Structure. IEEE Access, 9, 78241-78252. >https://doi.org/10.1109/access.2021.3083646
Krizhevsky, A., Sutskever, I. and Hinton, G.E. (2017) Imagenet Classification with Deep Convolutional Neural Networks. Communications of the ACM, 60, 84-90. >https://doi.org/10.1145/3065386