基于EfficientNet的癌痛面部表情评估方法的研究
Study on Facial Expression Evaluation of Cancer Pain Based on EfficientNet
DOI: 10.12677/ACM.2023.1371672, PDF,   
作者: 陈小娇：西安医学院研究生院，陕西 西安；梁鹏科：中国电子科技集团公司第39研究所，陕西 西安；杨怡萍：陕西省肿瘤医院，陕西省放射治疗临床医学研究中心，陕西 西安
关键词: 癌痛；疼痛强度评估；面部表情；EfficientNet；Cancer Pain； Pain Intensity Assessment； Facial Expression； EfficientNet
摘要: 目的：搭建了一种基于EfficientNet的癌痛面部表情识别与强度分类的智能评估模型并评价模型准确性。方法：采集72位志愿者在6种不同疼痛强度状态下的面部表情图片，设计深度卷积神经网络并进行训练，使用特征级差异进行面部疼痛表情分类。在原网络基础上进行了以下两点优化：1) 将激活函数swish改为mish。2) 用inception v4代替网络中的mobile net模块。结果：优化后的网络与原网络相比，模型训练损失衰减更快，模型对于测试集的分类准确率有了显著的提升。结论：该方法在疼痛表情识别中准确有效，评分结果具有显著性。
Abstract: Objective: To establish an intelligent evaluation model for cancer pain facial expression recognition and intensity classification based on EfficientNet and evaluate the accuracy of the model. Methods: The facial expressions of 72 volunteers in 6 different pain intensity states were collected, deep con-volutional neural network was designed and trained, and facial pain expressions were classified using feature level difference. On the basis of the original network, the following two optimizations were performed: 1) The activation function swish was changed to mish. 2) Replace the mobile net module in the network with inception v4. Results: Compared with the original network, the training loss of the optimized network decreases faster, and the classification accuracy of the model for the test set is significantly improved. Conclusion: This method is accurate and effective in pain expres-sion recognition, and the score is significant.
文章引用：陈小娇, 梁鹏科, 杨怡萍. 基于EfficientNet的癌痛面部表情评估方法的研究[J]. 临床医学进展, 2023, 13(7): 11934-11942. https://doi.org/10.12677/ACM.2023.1371672

参考文献

[1] 世界卫生组织国际癌症研究机构(IARC)发布2020年全球最新癌症数据[Z].
[2] Williams, A.C. and Craig, K.D. (2016) Updating the Definition of Pain. Pain, 157, 2420-2423. [Google Scholar] [CrossRef] [PubMed]
[3] Allen, J.O., Zebrack, B., Wittman, D., et al. (2014) Ex-panding the NCCN Guidelines for Distress Management: A Model of Barriers to the Use of Coping Resources. Journal of Community and Supportive Oncology, 12, 271-277. [Google Scholar] [CrossRef] [PubMed]
[4] 癌症疼痛诊疗规范(2018年版) [J]. 临床肿瘤学杂志, 2018, 23(10): 937-944.
[5] 周娅楠, 李丽, 胡守紫. 癌症化疗病人症状负担与心理痛苦调查研究[J]. 全科护理, 2023, 21(3): 311-315.
[6] Bray, F., Ferlay, J., Soerjomataram, I., et al. (2018) Global Cancer Statistics 2018: GLOBOCAN Esti-mates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA: A Cancer Journal for Clinicians, 68, 394-424. [Google Scholar] [CrossRef] [PubMed]
[7] Ekman, P. and Friesen, W.V. (1978) Facial Action Coding System. Con-sulting Psychologists Press, Palo Alto. [Google Scholar] [CrossRef] 
[8] cPrkachin, K.M. and Solomon, P.E. (2008) The Structure, Reliability and Validity of Pain Expression: Evidence from Patients with Shoulder Pain. Pain, 139, 267-274. [Google Scholar] [CrossRef] [PubMed]
[9] Wang, M. and Deng, W.H. (2021) Deep Face Recognition: A Sur-vey. Neuro-Computing, 429, 215-244. [Google Scholar] [CrossRef] 
[10] 刘南艳, 魏鸿飞, 马圣祥. 融合局部动态特征的面部表情识别[J]. 计算机工程与科学, 2023, 45(5): 849-858.
[11] 杨瑞靖. 基于人脸视频图像的非接触式疼痛评估方法研究[D]: [博士学位论文]. 西安: 西北大学, 2021.[CrossRef] 
[12] 张敏. 基于深度学习的老年人疼痛表情识别[D]: [硕士学位论文]. 南京: 南京理工大学, 2021.[CrossRef] 
[13] 潘航. 基于局部情绪感知学习的面部微表情识别研究[D]: [博士学位论文]. 北京: 北京科技大学, 2023.[CrossRef] 
[14] Tan, M.X. and Le, Q.V. (2019) EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. ArXiv, abs/1905.11946.
[15] He, K., Zhang, X., Ren, S. and Sun, J. (2016) Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recog-nition (CVPR), Las Vegas, 27-30 June 2016, 770-778. [Google Scholar] [CrossRef] 
[16] Xie, S., Girshick, R., Dollar, P., Tu, Z. and He, K. (2017) Aggregated Residual Transformations for Deep Neural Networks. 2017 IEEE Conference on Computer Vision and Pattern Recogni-tion (CVPR), Honolulu, 21-26 July 2017, 5987-5995. [Google Scholar] [CrossRef] 
[17] Hu, J., Shen, L. and Sun, G. (2018) Squeeze-and-Excitation Networks. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-23 June 2018, 7132-7141. [Google Scholar] [CrossRef] 
[18] Zoph, B., Vasudevan, V., Shlens, J. and Le, Q.V. (2018) Learning Transferable Architectures for Scalable Image Recognition. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-23 June 2018, 8697-8710. [Google Scholar] [CrossRef] 
[19] Huang, Y., Cheng, Y., Chen, D., Lee, H., Ngiam, J., Le, Q.V. and Chen, Z. (2018) Gpipe: Efficient Training of Giant Neural Networks Using Pipeline Parallelism.
[20] Lucey, P., Cohn, J.F., Prkachin, K.M., et al. (2011) Painful Data: The UNBC-Mc Master Shoulder Pain Expression Archive Database. Proceedings of the 9th International Conference on Automatic Face & Gesture Recognition and Workshops (FG), Santa Barbara, 21-25 March 2011, 57-64. [Google Scholar] [CrossRef] 
[21] Werner, P., Al-Hamadi, A., Niese, R., et al. (2013) Towards Pain Monitoring: Facial Expression, Head Pose, a New Database, an Automatic System and Remaining Challenges. Proceedings of the British Machine Vision Conference (BMVC), Bristol, 9-13 September 2013, 1-13.
[22] Roy, S., Roy, C., Ethier-Majcher, C., et al. (2007) STOIC: A Database of Dynamic and Static Faces Expressing Highly Recognizable Emotions. Journal of Vision, 7, 944. [Google Scholar] [CrossRef] 
[23] Li, X., Lin, C., Li, C., et al. (2020) Improving One-Shot Nas By Suppressing the Posterior Fading. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, 13-19 June 2020, 13836-13845. [Google Scholar] [CrossRef] 
[24] 吴福彬, 卢浩然, 王统, 等. 基于CBAM YOLOv4-Mish的乳腺X线摄片肿块检测方法[J]. 中南民族大学学报(自然科学版), 2023, 42(2): 245-252. [Google Scholar] [CrossRef] 
[25] 马永刚, 曹永杰, 赵益花, 等. 基于深度学习实现成人坐骨耻骨支内侧缘的性别推断[J]. 法医学杂志, 2023, 39(2): 129-136+143.
[26] 孙常浩. 基于深度学习的舌面裂纹提取技术研究[D]: [硕士学位论文]. 北京: 北方工业大学, 2022.[CrossRef] 

为你推荐