{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:54:22Z","timestamp":1781589262846,"version":"3.54.5"},"reference-count":35,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T00:00:00Z","timestamp":1781568000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Bioeng. Biotechnol."],"abstract":"<jats:p>Precise anatomical landmark localization is critical for the therapeutic efficacy of Traditional Eastern Medicine, yet manual localization methods show inter-practitioner variability exceeding 5\u00a0mm. Deep learning can automate this process, but data scarcity limits model development. MetaHuman-rendered synthetic images offer a scalable alternative, though their texture fidelity and architecture-specific training effects remain underexplored. Six landmark localization models (HRNet-W32\/W48; YOLO26-pose: small\/medium\/large\/extra-large) were trained for five anatomical landmarks on the distal upper limb under two configurations: real-only (2,963 images) and real\u2013synthetic mixed (3,863 images). Synthetic image quality was assessed via Local Binary Pattern (LBP) chi-squared distances and Gray-Level Co-occurrence Matrix (GLCM) features. All models were evaluated on 50 held-out real images from 18 participants using localization error (mm) and mean Average Precision (mAP). Real-to-synthetic LBP chi-squared distances (0.0155 \u00b1 0.0042) fell within natural real-image variation (0.0107 \u00b1 0.0117), confirming sufficient texture fidelity. Mixed training reduced the mean localization error across all six models. Under subject-level clustered bootstrap analysis (n = 18 participant clusters, 10,000 iterations), statistically significant improvements were observed in YOLO26x-pose (17.8%; p = 0.002), YOLO26s-pose (14.5%; p = 0.001), and HRNet-W48 (6.3%; p = 0.020). However, because the mixed training set contains approximately 30% more images and gradient updates than the real-only set, contributions from increased training volume, optimization steps, and synthetic data content cannot be fully disentangled. Detection confidence remained stable across conditions. All models achieved sub-3.1\u00a0mm accuracy under mixed training, approaching expert-level consistency. These findings offer practical guidance for integrating MetaHuman-rendered synthetic images into deep learning pipelines for Traditional Eastern Medicine applications when real data is scarce.<\/jats:p>","DOI":"10.3389\/fbioe.2026.1852405","type":"journal-article","created":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:39:41Z","timestamp":1781588381000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Synthetic data augmentation for improving performance in deep learning models for anatomical landmark localization on the distal upper limb"],"prefix":"10.3389","volume":"14","author":[{"given":"Prathiksha","family":"Padmanabha","sequence":"first","affiliation":[{"name":"Industry 4.0 Convergence Bionics Engineering, Pukyong National University","place":["Busan, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kasunika","family":"Guruge","sequence":"additional","affiliation":[{"name":"Industry 4.0 Convergence Bionics Engineering, Pukyong National University","place":["Busan, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"H. M. K. K. M. B.","family":"Herath","sequence":"additional","affiliation":[{"name":"Industry 4.0 Convergence Bionics Engineering, Pukyong National University","place":["Busan, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seongeun","family":"Lee","sequence":"additional","affiliation":[{"name":"Division of Smart Healthcare, College of Information Technology and Convergence, Pukyong National University","place":["Busan, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nuwan","family":"Madusanka","sequence":"additional","affiliation":[{"name":"Digital Healthcare Research Center, Pukyong National University","place":["Busan, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hi-Joon","family":"Park","sequence":"additional","affiliation":[{"name":"College of Korean Medicine, Kyung Hee University","place":["Seoul, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang-Su","family":"Na","sequence":"additional","affiliation":[{"name":"College of Korean Medicine, Dongshin University","place":["Naju-si, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Myunggi","family":"Yi","sequence":"additional","affiliation":[{"name":"Industry 4.0 Convergence Bionics Engineering, Pukyong National University","place":["Busan, Republic of Korea"]},{"name":"Division of Smart Healthcare, College of Information Technology and Convergence, Pukyong National University","place":["Busan, Republic of Korea"]},{"name":"Digital Healthcare Research Center, Pukyong National University","place":["Busan, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Byeong-il","family":"Lee","sequence":"additional","affiliation":[{"name":"Industry 4.0 Convergence Bionics Engineering, Pukyong National University","place":["Busan, Republic of Korea"]},{"name":"Division of Smart Healthcare, College of Information Technology and Convergence, Pukyong National University","place":["Busan, Republic of Korea"]},{"name":"Digital Healthcare Research Center, Pukyong National University","place":["Busan, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,16]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"23","DOI":"10.3390\/S23073440","article-title":"Evaluating synthetic medical images using artificial intelligence with the GAN algorithm","volume":"23","author":"Abdusalomov","year":"2023","journal-title":"Sensors"},{"key":"B2","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1159\/000335825","article-title":"Acupuncture point localization varies among acupuncturists","volume":"19","author":"B\u00e4umler","year":"2012","journal-title":"Forschende Komplement\u00e4rmedizin\/Res. Complementary Med."},{"key":"B3","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"Esteva","year":"2017","journal-title":"Nature"},{"key":"B4","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1038\/s41746-023-00927-3","article-title":"Harnessing the power of synthetic data in healthcare: innovation, application, and privacy","volume":"6","author":"Giuffr\u00e8","year":"2023","journal-title":"Npj Digit. Med."},{"key":"B5","doi-asserted-by":"publisher","first-page":"52","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":"B6","doi-asserted-by":"publisher","first-page":"13","DOI":"10.3390\/HEALTHCARE13233093","article-title":"MetaAcuPoint: metahuman-generated synthetic data for hand acupoint localization","volume":"13","author":"Guruge","year":"2025","journal-title":"Healthcare"},{"key":"B7","doi-asserted-by":"publisher","first-page":"610","DOI":"10.1109\/TSMC.1973.4309314","article-title":"Textural features for image classification","author":"Haralick","year":"1973","journal-title":"IEEE Trans. Syst. Man. Cybern."},{"key":"B8","unstructured":"Hi5: synthetic data for inclusive, robust, hand pose estimation\n          \n          \n            \n              Hasan\n              M.\n            \n            \n              Ozel\n              C.\n            \n            \n              Long\n              N.\n            \n            \n              Martin\n              A.\n            \n            \n              Potter\n              S.\n            \n            \n              Adnan\n              T.\n            \n          \n          \n          2024"},{"key":"B9","doi-asserted-by":"publisher","first-page":"704","DOI":"10.1007\/3-540-59496-5_337","article-title":"Noise and the reality gap: the use of simulation in evolutionary robotics","volume":"929","author":"Jakobi","year":"1995","journal-title":"Lect. Notes Comput. Sci. Incl. Subseries Lect. Notes Artif. Intell. Lect. Notes Bioinforma."},{"key":"B10","doi-asserted-by":"publisher","first-page":"101759","DOI":"10.1016\/J.MEDIA.2020.101759","article-title":"Deep learning with noisy labels: exploring techniques and remedies in medical image analysis","volume":"65","author":"Karimi","year":"2020","journal-title":"Med. Image Anal."},{"key":"B11","doi-asserted-by":"publisher","first-page":"105174","DOI":"10.1016\/J.EBIOM.2024.105174","article-title":"Synthetically enhanced: unveiling synthetic data\u2019s potential in medical imaging research","volume":"104","author":"Khosravi","year":"2024","journal-title":"EBioMedicine"},{"key":"B12","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"B13","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/NATURE14539","article-title":"Deep learning","volume":"521","author":"Lecun","year":"2015","journal-title":"Nature"},{"key":"B14","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1093\/ECAM\/NEP006","article-title":"WHO standard acupuncture point locations","volume":"7","author":"Lim","year":"2010","journal-title":"Evidence-Based Complementary Altern. Med."},{"key":"B15","first-page":"740","article-title":"Microsoft COCO: common objects in context","author":"Lin","year":"2014"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1484038","DOI":"10.3389\/FNBOT.2024.1484038\/TEXT","article-title":"Real-time location of acupuncture points based on anatomical landmarks and pose estimation models","volume":"18","author":"Malekroodi","year":"2024","journal-title":"Front. Neurorobot."},{"key":"B17","article-title":"OpenMMLab pose estimation toolbox and benchmark","year":"2020"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-030-75178-4_1","article-title":"Synthetic data for deep learning","volume":"174","author":"Nikolenko","year":"2019","journal-title":"Springer Optim. Its Appl."},{"key":"B19","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1109\/TPAMI.2002.1017623","article-title":"Multiresolution gray-scale and rotation invariant texture classification with local binary patterns","volume":"24","author":"Ojala","year":"2002","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"B20","volume-title":"REGEN: Real-Time Photorealism Enhancement in Games via a Dual-Stage Generative Network Framework","author":"Pasios","year":"2025"},{"key":"B21","doi-asserted-by":"publisher","first-page":"e1002686","DOI":"10.1371\/JOURNAL.PMED.1002686","article-title":"Deep learning for chest radiograph diagnosis: a retrospective comparison of the CheXNeXt algorithm to practicing radiologists","volume":"15","author":"Rajpurkar","year":"2018","journal-title":"PLoS Med."},{"key":"B22","doi-asserted-by":"publisher","first-page":"779","DOI":"10.1109\/CVPR.2016.91","article-title":"You only look once: unified, real-time object detection, \u201d in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Redmon","year":"2016","journal-title":"Cvpr"},{"key":"B23","first-page":"658","article-title":"Generalized intersection over union: a metric and a loss for bounding box regression","author":"Rezatofighi","year":"2019"},{"key":"B24","unstructured":"YOLO26: key architectural enhancements and performance benchmarking for real-time object detection\n          \n          \n            \n              Sapkota\n              R.\n            \n            \n              Cheppally\n              R. H.\n            \n            \n              Sharda\n              A.\n            \n            \n              Karkee\n              M.\n            \n          \n          \n          2025"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2174\/0115734056315235240820080406","article-title":"Accurate acupoint localization in 2D hand images: evaluating HRNet and ResNet architectures for enhanced detection performance","volume":"20","author":"Seo","year":"2024","journal-title":"Curr. Med. Imaging"},{"key":"B26","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1370\/AFM.248","article-title":"The practice of acupuncture: who are the providers and what do they do?","volume":"3","author":"Sherman","year":"2005","journal-title":"Ann. Fam. Med."},{"key":"B27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-030-00536-8_1","article-title":"Medical image synthesis for data augmentation and anonymization using generative adversarial networks","author":"Shin","year":"2018","journal-title":"Lect. Notes in Comput. Sci. Incl. Subseries Lect. Notes in Artif. Intell. Lect. Notes in Bioinforma."},{"key":"B28","first-page":"5686","article-title":"Deep high-resolution representation learning for human pose estimation","author":"Sun","year":"2019"},{"key":"B29","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1038\/s41597-025-04934-9","article-title":"AcuSim: a synthetic dataset for cervicocranial acupuncture points localisation","volume":"12","author":"Sun","year":"2025","journal-title":"Sci. Data"},{"key":"B30","first-page":"23","article-title":"Domain randomization for transferring deep neural networks from simulation to the real world","author":"Tobin","year":"2017"},{"key":"B31","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1016\/J.JPAIN.2017.11.005","article-title":"Acupuncture for chronic pain: update of an individual patient data meta-analysis","volume":"19","author":"Vickers","year":"2018","journal-title":"J. Pain"},{"key":"B32","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: from error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"B33","doi-asserted-by":"publisher","first-page":"662","DOI":"10.1093\/RHEUMATOLOGY\/KEG005","article-title":"A brief history of acupuncture","volume":"43","author":"White","year":"2004","journal-title":"Rheumatology"},{"key":"B34","doi-asserted-by":"publisher","first-page":"4599","DOI":"10.1109\/JBHI.2024.3511128","article-title":"Exploring an innovative deep learning solution for acupuncture point localization on the weak feature body surface of the human back","volume":"29","author":"Yang","year":"2025","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"B35","doi-asserted-by":"publisher","first-page":"482","DOI":"10.1097\/ALN.0000000000000101","article-title":"Mechanisms of acupuncture-electroacupuncture on persistent pain","volume":"120","author":"Zhang","year":"2014","journal-title":"Anesthesiology"}],"container-title":["Frontiers in Bioengineering and Biotechnology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbioe.2026.1852405\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:39:45Z","timestamp":1781588385000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbioe.2026.1852405\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,16]]},"references-count":35,"alternative-id":["10.3389\/fbioe.2026.1852405"],"URL":"https:\/\/doi.org\/10.3389\/fbioe.2026.1852405","relation":{},"ISSN":["2296-4185"],"issn-type":[{"value":"2296-4185","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,16]]},"article-number":"1852405"}}