[1]YANG Jie,GAO Yang,DUAN Zhengyu,et al.Facial acupoint localization algorithm based on the improved CycleGAN[J].CAAI Transactions on Intelligent Systems,2025,20(4):1024-1032.[doi:10.11992/tis.202410009]
Copy

Facial acupoint localization algorithm based on the improved CycleGAN

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 20 Number of periods: 2025 4 Page number: 1024-1032 Column: 学术论文—机器学习 Public date: 2025-08-05
Title:
Facial acupoint localization algorithm based on the improved CycleGAN
Author(s):
YANG Jie1; 2;  GAO Yang3;  DUAN Zhengyu1;  JI Bingxia1;  ZHANG Xiong3;  SHANGGUAN Hong3
1. School of Health Services and Management, Shanxi University of Chinese Medicine, Taiyuan 030619, China;
2. Shanxi Key Laboratory of Chinese Medicine Encephalopathy, Shanxi University of Chinese Medicine, Taiyuan 030619, China;
3. School of Electronic Information Engineering, Taiyuan University of Science and Technology, Taiyuan 030024, China
Keywords:
acupuncture; facial acupoint; automatic localization; cycle-consistent adversarial networks; generator; multiscale discriminator; alternating iteration; intelligent traditional Chinese medicine
CLC:
TP391.7
DOI:
10.11992/tis.202410009
Abstract:
The existing methods for automatic acupoint localization suffer from significant positioning errors, poor algorithm generalization, and operational complexity, making them insufficient for large-scale clinical applications in traditional Chinese medicine (TCM) acupuncture. Hence, an improved cycle-consistent generative adversarial network is proposed to address the issue of acupoint localization in TCM acupuncture. A dual-loop adversarial training mechanism is adopted to optimize network performance through alternating iterations of symmetric generative adversarial networks. A symmetric encoder-decoder generator embedded with acupoint information perception blocks and a multiscale block discriminator capable of processing features in different receptive fields are designed on the basis of the facial image characteristics. Multiple loss functions are used to constrain the acupoint localization network. The results show that the proposed algorithm achieves outcomes similar to those of manual localization, thus offering a novel perspective for the development of intelligent facial acupoint localization technology.
References:
[1] 张梦妮, 黄瑶, 张勤修. 面部穴位埋线对变应性鼻炎大鼠模型紧密连接蛋白Claudin-1和Occludin表达的影响[J]. 时珍国医国药, 2020, 31(5): 1279-1282.
ZHANG Mengni, HUANG Yao, ZHANG Qinxiu. Effects of catgut implantation at acupoint of face on expression of the Tight Junction Proteins Claudin-1 and Occludin of rats with allergic rhinitis[J]. Lishizhen medicine and materia medica research, 2020, 31(5): 1279-1282.
[2] 柳钶, 姜劲峰, 卢圣锋. 针灸调节自主神经研究的效应特点及其途径分析[J]. 针刺研究, 2021, 46(4): 335-341.
LIU Ke, JIANG Jinfeng, LU Shengfeng. Effect characteristics and mechanism of acupuncture in autonomic nerve regulation[J]. Acupuncture research, 2021, 46(4): 335-341.
[3] 胡艳美, 朱博畅. 张仁教授分期论治难治性面瘫经验[J]. 中国针灸, 2020, 40(8): 865-867,896.
HU Yanmei, ZHU Bochang. Professor ZHANG Ren’s experience of stage treatment for refractory facial paralysis[J]. Chinese acupuncture & moxibustion, 2020, 40(8): 865-867,896.
[4] 刘鑫, 李珊珊, 宓轶群. 超声在针刺治疗中的应用与研究进展[J]. 中国针灸, 2023, 43(1): 119-122.
LIU Xin, LI Shanshan, MI Yiqun. Application and research progress of ultrasound in acupuncture treatment[J]. Chinese acupuncture & moxibustion, 2023, 43(1): 119-122.
[5] 刘存志. 针灸治疗心血管疾病的循证医学证据与未来设计思路[J]. 中国中西医结合杂志, 2019, 39(11): 1306-1308.
LIU Cunzhi. Evidence-based medical proofs and future design thinking of acupuncture for treating cardiovascular diseases[J]. Chinese journal of integrated traditional and western medicine, 2019, 39(11): 1306-1308.
[6] 方智婷, 陈艳焦, 徐玉东, 等. 论针灸医学的传承、挑战及创新发展[J]. 上海中医药杂志, 2022, 56(6): 3-6.
FANG Zhiting, CHEN Yanjiao, XU Yudong, et al. On the inheritance, challenges and innovative development of acupuncture and moxibustion medicine[J]. Shanghai journal of traditional Chinese medicine, 2022, 56(6): 3-6.
[7] 谢依璇, 闫世艳, 陈波, 等. 新时代针灸的发展[J]. 科技导报, 2023, 41(14): 42-50.
XIE Yixuan, YAN Shiyan, CHEN Bo, et al. Development and prospect of acupuncture in the new era[J]. Science & technology review, 2023, 41(14): 42-50.
[8] 赵阳, 张涛, 练秋生. 红外面部图像的贝尔面瘫针灸穴位定位算法[J]. 小型微型计算机系统, 2012, 33(7): 1613-1619.
ZHAO Yang, ZHANG Tao, LIAN Qiusheng. Acupuncture points localization algorithm about Bell’s palsy on facial infrared images[J]. Journal of Chinese computer systems, 2012, 33(7): 1613-1619.
[9] CHANG Menglong, ZHU Qing. Automatic location of facial acupuncture-point based on facial feature points positioning[C]//Proceedings of the 2017 5th International Conference on Frontiers of Manufacturing Science and Measuring Technology. Taiyuan: Atlantis Press, 2017: 545-549.
[10] 杨旭明, 彭昊宇, 方琢, 等. 基于Web的针刺面部穴位定位、处方学习和虚拟仿真系统的研发[J]. 中华医学图书情报杂志, 2019, 28(10): 51-56.
YANG Xuming, PENG Haoyu, FANG Zhuo, et al. Web-based R & D of facial acupoint locating, prescription learning and virtual simulation system[J]. Chinese journal of medical library and information science, 2019, 28(10): 51-56.
[11] LIN Sheng, YI Pinqiao. Human acupoint positioning system based on binocular vision[J]. IOP conference series: materials science and engineering, 2019, 569(4): 042029.
[12] LAN Kunchan, HU Minchun, CHEN Yizhang, et al. The application of 3D morphable model (3DMM) for real-time visualization of acupoints on a smartphone[J]. IEEE sensors journal, 2021, 21(3): 3289-3300.
[13] 高东雯, 肖沪生, 徐智章, 等. 三维与二维高频超声技术应用于针灸穴位定位的可行性研究[J]. 中国中西医结合影像学杂志, 2013, 11(3): 231-234.
GAO Dongwen, XIAO Husheng, XU Zhizhang, et al. Study of locating acupuncture point by high frequency 3-dimensional and 2-dimensional ultrasonic technology[J]. Chinese imaging journal of integrated traditional and western medicine, 2013, 11(3): 231-234.
[14] 刘昳, 高渊, 刘小静, 等. 超声引导下精确定位针刺深度电针膈腧穴治疗顽固性呃逆[J]. 中国中医药现代远程教育, 2018, 16(10): 120-122.
LIU Yi, GAO Yuan, LIU Xiaojing, et al. Ultrasound guided precise positioning and depth of electroacupuncture at Ge Shu point in treating intractable hiccup[J]. Chinese medicine modern distance education of China, 2018, 16(10): 120-122.
[15] 严骄俊, 谯朗, 王政研, 等. 多模态超声成像对针刺温溜穴空间及生物力学特异度的研究[J]. 中国超声医学杂志, 2019, 35(3): 275-278.
YAN Jiaojun, QIAO Lang, WANG Zhengyan, et al. Study on spatial and biomechanical specificity of acupuncturing Wenliu point with multimodal ultrasound imaging[J]. Chinese journal of ultrasound in medicine, 2019, 35(3): 275-278.
[16] SUN Lingyao, SUN Shiying, FU Yuanbo, et al. Acupoint detection based on deep convolutional neural network[C]//2020 39th Chinese Control Conference. Shenyang: IEEE, 2020: 7418-7422.
[17] ZHU Junyan, PARK T, ISOLA P, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks[C]//2017 IEEE International Conference on Computer Vision. Venice: IEEE, 2017: 2242-2251.
[18] CRESWELL A, WHITE T, DUMOULIN V, et al. Generative adversarial networks: an overview[J]. IEEE signal processing magazine, 2018, 35(1): 53-65.
[19] ZHAO J, MATHIEU M, LECUN Y. Energy-based generative adversarial network[EB/OL]. (2016-09-11) [2024-10-09]. https://arxiv.org/abs/1609.03126.
[20] PEEBLES W, ZHU Junyan, ZHANG R, et al. GAN-supervised dense visual alignment[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022: 13460-13471.
[21] PAN Xingang, DAI Bo, LIU Ziwei, et al. Do 2D GANs know 3D shape? unsupervised 3D shape reconstruction from 2D image GANs[EB/OL]. (2020-11-02) [2024-10-09]. https://arxiv.org/abs/2011.00844.
[22] XU Lei, SKOULARIDOU M, CUESTA-INFANTE A, et al. Modeling tabular data using conditional GAN[EB/OL]. (2019-07-01)[2024-10-09]. https://arxiv.org/abs/1907.00503.
[23] GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial networks[J]. Communications of the acm, 2020, 63(11): 139-144.
[24] RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention. Cham: Springer International Publishing, 2015: 234-241.
[25] 张海川, 彭博, 许伟强. 基于UNet++及条件生成对抗网络的道路裂缝检测[J]. 计算机应用, 2020, 40(S2): 158-161.
ZHANG Haichuan, PENG Bo, XU Weiqiang. Road crack detection based on UNet++ and conditional generative adversarial nets[J]. Journal of computer applications, 2020, 40(S2): 158-161.
[26] MEI Yiqun, FAN Yuchen, ZHANG Yulun, et al. Pyramid attention network for image restoration[J]. International journal of computer vision, 2023, 131(12): 3207-3225.
[27] WANG Xiaolong, GIRSHICK R, GUPTA A, et al. Non-local neural networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 7794-7803.
[28] PAN Yue, PI Dechang, CHEN Junfu, et al. FDPPGAN: remote sensing image fusion based on deep perceptual patchGAN[J]. Neural computing and applications, 2021, 33(15): 9589-9605.
[29] FAN Tongle, WANG Guanglei, LI Yan, et al. MA-net: a multi-scale attention network for liver and tumor segmentation[J]. IEEE access, 2020, 8: 179656-179665.
[30] PUNN N S, AGARWAL S. Modality specific U-Net variants for biomedical image segmentation: a survey[J]. Artificial intelligence review, 2022, 55(7): 5845-5889.
[31] 李超波, 李洪均, 徐晨. 深度学习在图像识别中的应用[J]. 南通大学学报(自然科学版), 2018, 17(1): 1-9.
LI Chaobo, LI Hongjun, XU Chen. Application of deep learning in image recognition[J]. Journal of Nantong University (Natural Science Edition), 2018, 17(1): 1-9.
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems