{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T04:04:34Z","timestamp":1784174674965,"version":"3.55.0"},"reference-count":53,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T00:00:00Z","timestamp":1784073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Infrared thermal imaging offers objective physiological insights for Traditional Chinese Medicine (TCM), yet automated acupoint localization struggles with low texture and extreme pose variations. To address this, we constructed a multi-pose thermal facial dataset using digitized bone-proportional measurements and TCM anatomical rules. We propose T2FAL, a two-stage cascaded regression framework explicitly decoupling macroscopic face detection from fine-grained acupoint localization. Stage 1 utilizes an improved YOLOv12m-based Thermal-Aware Face Detector\u2014integrating ICAN_C2f, MixNeck, and TAF-IoU\u2014to mitigate domain shifts and thermal noise. Stage 2 deploys pose-specific regressors incorporating Gated Feature-Conditioned Cascade Refinement (FCCR) and a Selective GeoDeriv module, mathematically translating anatomical rules into geometric constraints. Under the stated experimental protocol, Stage 1 processed images at 87.3 frames per second on an NVIDIA RTX 4090. For Stage 2, the final frontal- and profile-view configurations achieved mAP@50\u201395 values of 73.19% and 86.92%, with mean pixel errors of 1.986 and 3.109 pixels, respectively. These results support the feasibility of automated reference-coordinate localization on the datasets used. However, given the partial reliance of the annotations on image registration and geometric rules, the use of the cross-domain set for model selection, and the lack of clinical or diagnostic evaluation, further validation using independently generated expert annotations, a strictly held-out external test set, and clinically labeled data is required before clinical or diagnostic use.<\/jats:p>","DOI":"10.3390\/s26144498","type":"journal-article","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T03:34:23Z","timestamp":1784172863000},"page":"4498","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Two-Stage Cascaded Regression Framework for Automatic Facial Acupoint Localization in Infrared Thermal Images"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1818-8721","authenticated-orcid":false,"given":"Jiahao","family":"Li","sequence":"first","affiliation":[{"name":"Systems Engineering Institute, Academy of Military Sciences, PLA, Beijing 100091, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingcheng","family":"Ming","sequence":"additional","affiliation":[{"name":"Systems Engineering Institute, Academy of Military Sciences, PLA, Beijing 100091, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Zeng","sequence":"additional","affiliation":[{"name":"Systems Engineering Institute, Academy of Military Sciences, PLA, Beijing 100091, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruifeng","family":"Yang","sequence":"additional","affiliation":[{"name":"Systems Engineering Institute, Academy of Military Sciences, PLA, Beijing 100091, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Tian","sequence":"additional","affiliation":[{"name":"Systems Engineering Institute, Academy of Military Sciences, PLA, Beijing 100091, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fu","family":"Niu","sequence":"additional","affiliation":[{"name":"Systems Engineering Institute, Academy of Military Sciences, PLA, Beijing 100091, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Freihat, O., Sipos, D., Aamir, M., and Kovacs, A. (2025). Global Burden and Future Projections of Non-Communicable Diseases (2000\u20132050): Progress toward SDG 3.4 and Disparities across Regions and Risk Factors. PLoS ONE, 20.","DOI":"10.1371\/journal.pone.0336036"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1007\/s13167-020-00200-7","article-title":"Population-Based Case-Control Study Revealed Metabolomic Biomarkers of Suboptimal Health Status in Chinese Population\u2014Potential Utility for Innovative Approach by Predictive, Preventive, and Personalized Medicine","volume":"11","author":"Wang","year":"2020","journal-title":"EPMA J."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Ren, J., Hao, J., Jia, Z.-Q., Zheng, C.-X., Zheng, Y.-Z., Wu, Z.-X., Zhou, X.-N., Wu, H., Ye, X.-T., and Ma, X.-C. (2026). The Utilization, Characteristics, and Influencing Factors of Non-Therapeutic Traditional Chinese Medicine Services among Middle-Aged and Older Population in Guangzhou, China: A Cross-Sectional Study. Front. Public Health, 14.","DOI":"10.3389\/fpubh.2026.1772557"},{"key":"ref_4","first-page":"15","article-title":"Design of TCM Chronic Disease Management System Based on Cloud Computing Platform","volume":"10","author":"Zhang","year":"2020","journal-title":"Comput. Sci. Appl."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1097\/HM9.0000000000000018","article-title":"Trigger Points and Sensitized Acupoints: Same Book, Different Covers?","volume":"1","author":"Sun","year":"2021","journal-title":"Acupunct. Herb. Med."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/j.jams.2018.10.009","article-title":"Accuracy and Precision in Acupuncture Point Location: A Critical Systematic Review","volume":"12","author":"Godson","year":"2019","journal-title":"J. Acupunct. Meridian Stud."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Guruge, K., Padmanabha, P., Herath, H.M.K.K.M.B., Madusanka, N., Park, H.-J., Na, C.-S., Yi, M., and Lee, B.-I. (2025). MetaAcuPoint: MetaHuman-Generated Synthetic Data for Hand Acupoint Localization. Healthcare, 13.","DOI":"10.3390\/healthcare13233093"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Malekroodi, H.S., Seo, S.-D., Choi, J., Na, C.-S., Lee, B.-I., and Yi, M. (2024). Real-Time Location of Acupuncture Points Based on Anatomical Landmarks and Pose Estimation Models. Front. Neurorobot., 18.","DOI":"10.3389\/fnbot.2024.1484038"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"181889","DOI":"10.1109\/ACCESS.2024.3509026","article-title":"Research on Human Acupoint Detection by Integrating Key Point Information and Acupoint Theory","volume":"12","author":"Zhang","year":"2024","journal-title":"IEEE Access"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2217","DOI":"10.1007\/s00530-023-01104-y","article-title":"An Acupoint Health Care System with Real-Time Acupoint Localization and Visualization in Augmented Reality","volume":"29","author":"Su","year":"2023","journal-title":"Multimed. Syst."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Lee, Y.-T., Sun, C.-H., Chiu, C.-S., and Chen, Y.-T. (2023, January 27\u201328). Design of a Hand Back Acupoint Massage Aid. Proceedings of the 2023 International Conference on System Science and Engineering (ICSSE), Ho Chi Minh City, Vietnam.","DOI":"10.1109\/ICSSE58758.2023.10227180"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Hu, W.-K., Sheng, Q., and Sheng, X.-J. (2021, January 26\u201328). A Novel Real-Time Vision-Based Acupoint Estimation for TCM Massage Robot. Proceedings of the 2021 27th International Conference on Mechatronics and Machine Vision in Practice (M2VIP), Shanghai, China.","DOI":"10.1109\/M2VIP49856.2021.9665080"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Wei, C.-Y., Xu, B.-Y., and Zhao, Y.-X. (November, January 31). Design of Interactive System for Acupoint Analysis Based on Augmented Reality. Proceedings of the 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Taipei, Taiwan.","DOI":"10.1109\/APSIPAASC58517.2023.10317347"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"4455","DOI":"10.1007\/s11760-023-02679-9","article-title":"Facial Acupoint Location Method Based on Faster PFLD","volume":"17","author":"Liu","year":"2023","journal-title":"Signal Image Video Process."},{"key":"ref_15","first-page":"24","article-title":"A Vision Based Acupoint Localization Method for Traditional Chinese Medicine Tongluo Robot in the Lumbar and Back","volume":"44","author":"Fei","year":"2023","journal-title":"Mod. Tradit. Chin. Med."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Sun, L.-Y., Sun, S.-Y., Fu, Y.-B., and Zhao, X.-G. (2020, January 27\u201329). Acupoint Detection Based on Deep Convolutional Neural Network. Proceedings of the 2020 40th Chinese Control Conference (CCC), Shenyang, China.","DOI":"10.23919\/CCC50068.2020.9188367"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"5965","DOI":"10.1364\/BOE.501663","article-title":"Hand Acupuncture Point Localization Method Based on a Dual-Attention Mechanism and Cascade Network Model","volume":"14","author":"Wang","year":"2023","journal-title":"Biomed. Opt. Express"},{"key":"ref_18","first-page":"1893","article-title":"Research on Hand Acupoint Location Based on Deep Learning","volume":"38","author":"Chang","year":"2024","journal-title":"Chin. J. Sens. Actuators"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"102743","DOI":"10.1016\/j.displa.2024.102743","article-title":"AIR-Net: Acupoint Image Registration Network for Automatic Acupoint Recognition and Localization","volume":"83","author":"Li","year":"2024","journal-title":"Displays"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Yuan, Z.-J., Shao, P.-W., Li, J.-R., Wang, Y.-N., Zhu, Z.-X., Qiu, W.-J., Chen, B.-Q., Tang, Y., and Han, A.-Q. (2024). YOLOv8-ACU: Improved YOLOv8-Pose for Facial Acupoint Detection. Front. Neurorobot., 18.","DOI":"10.3389\/fnbot.2024.1355857"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Fu, Z., Wei, Q.-S., Liu, J., and Zhang, W.-J. (2022, January 16\u201319). Application Research of Automatic Acupoint Finding Based on Binocular Vision Positioning and Skeleton Recognition. Proceedings of the 2022 8th Annual International Conference on Network and Information Systems for Computers (ICNISC), Hangzhou, China.","DOI":"10.1109\/ICNISC57059.2022.00121"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1016\/j.infrared.2012.03.007","article-title":"Medical Applications of Infrared Thermography: A Review","volume":"55","author":"Lahiri","year":"2012","journal-title":"Infrared Phys. Technol."},{"key":"ref_23","first-page":"937","article-title":"Research Progress on the Application of Infrared Thermal Imaging Technology to Assist Traditional Chinese Medicine Diagnosis and Treatment Based on the Theory of Acupoint Sensitization","volume":"44","author":"Liao","year":"2025","journal-title":"Shandong J. Tradit. Chin. Med."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Villa, E., Arteaga-Marrero, N., and Ruiz-Alzola, J. (2020). Performance Assessment of Low-Cost Thermal Cameras for Medical Applications. Sensors, 20.","DOI":"10.3390\/s20051321"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"104201","DOI":"10.1016\/j.infrared.2022.104201","article-title":"Low-Cost Thermal Imaging with Machine Learning for Non-Invasive Diagnosis and Therapeutic Monitoring of Pneumonia","volume":"123","author":"Qu","year":"2022","journal-title":"Infrared Phys. Technol."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zhao, Y.-F., Zhang, D., and Wang, Y.-X. (2010, January 24\u201327). Automatic Location of Facial Acupuncture-Point Based on Content of Infrared Thermal Image. Proceedings of the 2010 5th International Conference on Computer Science & Education (ICCSE), Hefei, China.","DOI":"10.1109\/ICCSE.2010.5593668"},{"key":"ref_27","first-page":"1613","article-title":"Acupuncture Points Localization Algorithm about Bell\u2019s Palsy on Facial Infrared Images","volume":"34","author":"Zhao","year":"2012","journal-title":"J. Chin. Comput. Syst."},{"key":"ref_28","unstructured":"Liu, X.-L. (2013). A Method of Objective Assessment and Selecting Acupoints for Acupuncture Treatment of Facial Paralysis Using Infrared Thermography. [Ph.D. Dissertation, Yanshan University]."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"355","DOI":"10.18280\/ts.390137","article-title":"Acupoint Selection for Autonomous Massage Based on Infrared Thermography","volume":"40","author":"Shu","year":"2022","journal-title":"Trait. Signal"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Lian, Y.-Y., Wang, Z.-H., Yuan, H.-Q., Gao, L.-F., Yu, Z.-Z., Chen, W.-W., Xing, Y.-F., Xu, S.-Y., and Feng, L. (2020, January 15\u201319). Partial Occlusion Face Recognition Method Based on Acupoints Locating Through Infrared Thermal Imaging. Proceedings of the 2020 International Wireless Communications and Mobile Computing (IWCMC), Limassol, Cyprus.","DOI":"10.1109\/IWCMC48107.2020.9148064"},{"key":"ref_31","unstructured":"Xia, Y. (2023). Design of Non-Contact Infrared Thermometer Based on Raspberry Pi. [Master\u2019s Thesis, Qingdao University of Science and Technology]."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Yang, F., Zhang, Q., Wang, M.-H., and Qiu, G.-P. (2018, January 20\u201324). Quality Classified Image Analysis with Application to Face Detection and Recognition. Proceedings of the 2018 24th International Conference on Pattern Recognition (ICPR), Beijing, China.","DOI":"10.1109\/ICPR.2018.8545476"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., and Wang, J.-D. (2019, January 15\u201320). Deep high-resolution representation learning for human pose estimation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref_34","unstructured":"Jiang, T., Wu, P., Ji, W.-K., Li, J.-H., Luo, P., and Wang, X.-G. (2023). RTMPose: Real-time multi-person pose estimation based on MMPose. arXiv."},{"key":"ref_35","first-page":"38571","article-title":"ViTPose: Simple vision transformer baselines for human pose estimation","volume":"Volume 36","author":"Koyejo","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref_36","first-page":"509","article-title":"A comprehensive database for benchmarking imaging systems","volume":"43","author":"Panetta","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"104209","DOI":"10.1016\/j.infrared.2022.104209","article-title":"Charlotte-ThermalFace: A fully annotated thermal infrared face dataset with various environmental conditions and distances","volume":"124","author":"Ashrafi","year":"2022","journal-title":"Infrared Phys. Technol."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1007\/s11263-007-0090-8","article-title":"LabelMe: A database and web-based tool for image annotation","volume":"77","author":"Russell","year":"2008","journal-title":"Int. J. Comput. Vis."},{"key":"ref_39","unstructured":"Heckbert, P.S. (1994). Contrast limited adaptive histogram equalization. Graphics Gems IV, Academic Press Professional, Inc."},{"key":"ref_40","unstructured":"(2021). Name and Location of Acupoints. State Administration for Market Regulation. Standardization Administration of China (Standard No. GB\/T 12346-2021)."},{"key":"ref_41","unstructured":"(2021). Name and Location of Extra Points. Standardization Administration of China (Standard No. GB\/T 40997-2021)."},{"key":"ref_42","unstructured":"World Health Organization (2008). WHO Standard Acupuncture Point Locations in the Western Pacific Region, World Health Organization, Regional Office for the Western Pacific."},{"key":"ref_43","unstructured":"(2008). Standard Acupuncture Point Locations in Human Body. General Administration of Quality Supervision, Inspection and Quarantine. Standardization Administration of China (Standard No. GB\/T 22163-2008)."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1159","DOI":"10.1002\/ca.23556","article-title":"Location of the infraorbital foramen with reference to soft tissue landmarks for regional nerve blocks during midface surgery","volume":"34","author":"Shin","year":"2020","journal-title":"Clin. Anat."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"e45454","DOI":"10.1097\/MD.0000000000045454","article-title":"Electroacupuncture for oxaliplatin-induced facial numbness: A CARE-compliant case report","volume":"104","author":"Ying","year":"2025","journal-title":"Medicine"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Edstedt, J., Sun, Q., B\u00f6kman, G., Wadenb\u00e4ck, M., and Felsberg, M. (2024, January 17\u201321). RoMa: Revisiting Robust Losses for Dense Feature Matching. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.01871"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Sun, J.-M., Shen, Z.-H., Wang, Y.-A., Bao, H.-J., and Zhou, X.-W. (2021, January 20\u201325). LoFTR: Detector-free local feature matching with transformers. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00881"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Pan, X.-G., Luo, P., Shi, J.-P., and Tang, X.-O. (2018, January 8\u201314). Two at once: Enhancing learning and generalization capacities via IBN-Net. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01225-0_29"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Cai, X.-H., Lai, Q.-X., Wang, Y.-W., Wang, W.-G., Sun, Z.-R., and Yao, Y.-Z. (2024, January 17\u201321). Poly Kernel Inception Network for Remote Sensing Detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.02617"},{"key":"ref_50","unstructured":"Zheng, Z.-H., Wang, P., Liu, W., Li, J.-Z., Ye, R.-G., and Ren, D.-W. (2020, January 7\u201312). Distance-IoU loss: Faster and better learning for bounding box regression. Proceedings of the 35th AAAI Conference on Artificial Intelligence, New York, NY, USA."},{"key":"ref_51","unstructured":"Tong, Z.-J., Chen, Y.-H., Xu, Z.-W., and Yu, R.-W. (2023). Wise-IoU: Bounding box regression loss with dynamic focusing mechanism. arXiv."},{"key":"ref_52","unstructured":"Loshchilov, I., and Hutter, F. (2017, January 24\u201326). SGDR: Stochastic gradient descent with warm restarts. Proceedings of the 5th International Conference on Learning Representations (ICLR), Toulon, France."},{"key":"ref_53","unstructured":"Xia, S., Shao, J., Ding, Y.-G., and Ji, R.-R. (2019). PFLD: A practical facial landmark detector. arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/14\/4498\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T03:38:39Z","timestamp":1784173119000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/14\/4498"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,15]]},"references-count":53,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["s26144498"],"URL":"https:\/\/doi.org\/10.3390\/s26144498","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,15]]}}}