{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:19:45Z","timestamp":1792790385105,"version":"4.5.0"},"posted":{"date-parts":[[2026,9,12]]},"group-title":"Bioengineering","reference-count":56,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T00:00:00Z","timestamp":1789171200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.biorxiv.org\/about\/FAQ#license"}],"funder":[{"name":"NIH"},{"name":"Department of Bioengineering, University of Washington Seattle US","id":[{"id":"https:\/\/ror.org\/00cvxb145","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,9,12]]},"abstract":"<jats:p>Noncontact dynamic optical coherence elastography (OCE) can measure the elastic properties of anterior soft tissues. However, applying OCE to skin requires tracking mechanical waves propagating in multiple directions to reconstruct mechanical anisotropy. Robotic scanning is well suited to this task but requires accurate probe positioning, alignment to the surface normal, and precise, repeatable rotation. To ensure phase and polarization stability, polarization-maintaining (PM) fibers can be used, although they introduce stripe and ghost artifacts that can destabilize surface detection. We present DINOCT, a DINO-based method to localize the skin surface from optical coherence tomography (OCT) images that combines self-supervised pretraining with DINO (self-DIstillation with NO labels) and iBOT (image BERT pre-training with Online Tokenizer) objectives, low-rank adaptation, and a lightweight curve decoder. Compared with classical and supervised learning baselines, DINOCT achieved competitive localization accuracy on clean test data with a near-zero spike rate. Among the learned methods, DINOCT achieved the lowest average and maximum values of mean absolute error (MAE) for severe synthetic stress conditions and the lowest catastrophic failure rates on a separate recording with strong PM-fiber artifacts.<\/jats:p>","DOI":"10.64898\/2026.09.05.749536","type":"posted-content","created":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T06:00:11Z","timestamp":1789279211000},"source":"Crossref","is-referenced-by-count":0,"title":["DINOCT: robust skin surface localization for robotic noncontact dynamic optical coherence elastography"],"prefix":"10.64898","author":[{"given":"Raveeroj","family":"Bawornkitchaikul","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering, University of Washington, Seattle, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruikang K.","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Bioengineering, University of Washington, Seattle, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew","family":"O\u2019donnell","sequence":"additional","affiliation":[{"name":"Department of Bioengineering, University of Washington, Seattle, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ivan","family":"Pelivanov","sequence":"additional","affiliation":[{"name":"Department of Bioengineering, University of Washington, Seattle, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026091609300493000_2026.09.05.749536v1.1","first-page":"3963","article-title":"Probing elastic anisotropy of human skin in vivo with light using non-contact acoustic micro-tapping OCE and polarization sensitive OCT","volume":"12","year":"2022","journal-title":"Sci. Reports"},{"key":"2026091609300493000_2026.09.05.749536v1.2","doi-asserted-by":"publisher","DOI":"10.1002\/jbio.201400108"},{"key":"2026091609300493000_2026.09.05.749536v1.3","first-page":"38967","article-title":"Acoustic micro-tapping for non-contact 4D imaging of tissue elasticity","volume":"6","year":"2016","journal-title":"Sci. Reports"},{"key":"2026091609300493000_2026.09.05.749536v1.4","first-page":"124503","article-title":"Reconstruction of tensile and shear elastic moduli in anisotropic nearly incompressible media using Rayleigh wave phase and group velocities","volume":"30","year":"2025","journal-title":"J. Biomed. Opt"},{"key":"2026091609300493000_2026.09.05.749536v1.5","doi-asserted-by":"crossref","first-page":"3993","DOI":"10.1364\/BOE.525524","article-title":"Large area robotically assisted optical coherence tomography (LARA-OCT)","volume":"15","year":"2024","journal-title":"Biomed. Opt. Express"},{"key":"2026091609300493000_2026.09.05.749536v1.6","doi-asserted-by":"publisher","DOI":"10.1016\/j.optlastec.2023.110145"},{"key":"2026091609300493000_2026.09.05.749536v1.7","doi-asserted-by":"crossref","first-page":"1014","DOI":"10.1111\/bjd.19553","article-title":"Applications and future directions for optical coherence tomography in dermatology","volume":"184","year":"2021","journal-title":"Br. J. Dermatol"},{"key":"2026091609300493000_2026.09.05.749536v1.8","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1021\/cbmi.5c00066","article-title":"From optical to molecular imaging on human skin: A review","volume":"4","year":"2026","journal-title":"Chem. Biomed. Imaging"},{"key":"2026091609300493000_2026.09.05.749536v1.9","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1111\/srt.12255","article-title":"Potential use of OCT-based microangiography in clinical dermatology","volume":"22","year":"2016","journal-title":"Ski. Res. Technol"},{"key":"2026091609300493000_2026.09.05.749536v1.10","doi-asserted-by":"publisher","DOI":"10.1111\/dsu.12093"},{"key":"2026091609300493000_2026.09.05.749536v1.11","first-page":"8900","article-title":"Using optical coherence tomography to optimize Mohs micrographic surgery","volume":"14","year":"2024","journal-title":"Sci. Reports"},{"key":"2026091609300493000_2026.09.05.749536v1.12","doi-asserted-by":"crossref","first-page":"100015","DOI":"10.1016\/j.ejcskn.2023.100015","article-title":"Preoperative evaluation of high-risk basal cell carcinoma with line-field confocal optical coherence tomography (LC-OCT) reduces Mohs micrographic surgery stage number: A case-control study","volume":"2","year":"2024","journal-title":"EJC Ski. Cancer"},{"key":"2026091609300493000_2026.09.05.749536v1.13","doi-asserted-by":"crossref","first-page":"54","DOI":"10.3390\/ebj6040054","article-title":"Assessment of attenuation coefficient and blood flow at depth in pediatric thermal hand injuries using optical coherence tomography: A clinical study","volume":"6","year":"2025","journal-title":"Eur. Burn. J"},{"key":"2026091609300493000_2026.09.05.749536v1.14","doi-asserted-by":"crossref","first-page":"731","DOI":"10.21037\/qims.2019.04.19","article-title":"Optical coherence tomography correlates multiple measures of tissue damage following acute burn injury","volume":"9","year":"2019","journal-title":"Quant. Imaging Med. Surg"},{"key":"2026091609300493000_2026.09.05.749536v1.15","doi-asserted-by":"crossref","first-page":"155","DOI":"10.3390\/ebj5020013","article-title":"An optical tomography-based score to assess pediatric hand burns","volume":"5","year":"2024","journal-title":"Eur. Burn. J"},{"key":"2026091609300493000_2026.09.05.749536v1.16","doi-asserted-by":"crossref","first-page":"699","DOI":"10.1002\/lsm.23219","article-title":"Use of optical coherence tomography (OCT) in aesthetic skin assessment\u2014a short review","volume":"52","year":"2020","journal-title":"Lasers Surg. Med"},{"key":"2026091609300493000_2026.09.05.749536v1.17","first-page":"2","article-title":"LC-OCT imaging for studying the variation of morphological properties of human skin In Vivo according to age and body area: The forearm and the thigh","volume":"2","year":"2022","journal-title":"Dermis"},{"key":"2026091609300493000_2026.09.05.749536v1.18","doi-asserted-by":"crossref","first-page":"126014","DOI":"10.1117\/1.JBO.19.12.126014","article-title":"Imaging of skin birefringence for human scar assessment using polarization-sensitive optical coherence tomography aided by vascular masking","volume":"19","year":"2014","journal-title":"J. Biomed. Opt"},{"key":"2026091609300493000_2026.09.05.749536v1.19","first-page":"30","article-title":"An atlas of Optical Coherence Tomography (OCT): Elucidating In Vivo differences of scar types using OCT in order to guide laser treatment parameters","volume":"15","year":"2022","journal-title":"The J. Clin. Aesthetic Dermatol"},{"key":"2026091609300493000_2026.09.05.749536v1.20","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1038\/s41377-021-00679-3","article-title":"Polarization sensitive optical coherence tomography with single input for imaging depth-resolved collagen organizations","volume":"10","year":"2021","journal-title":"Light. Sci. & Appl"},{"key":"2026091609300493000_2026.09.05.749536v1.21","first-page":"036003","article-title":"Skin characterization of diabetes mellitus revealed by polarization-sensitive optical coherence tomography imaging","volume":"29","year":"2024","journal-title":"J. Biomed. Opt"},{"key":"2026091609300493000_2026.09.05.749536v1.22","doi-asserted-by":"crossref","first-page":"6379","DOI":"10.1364\/BOE.403933","article-title":"Polarization sensitive optical coherence tomography for imaging microvascular information within living tissue without polarization-induced artifacts","volume":"11","year":"2020","journal-title":"Biomed. Opt. Express"},{"key":"2026091609300493000_2026.09.05.749536v1.23","doi-asserted-by":"publisher","DOI":"10.1007\/s00403-013-1417-7"},{"key":"2026091609300493000_2026.09.05.749536v1.24","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1002\/lsm.22788","article-title":"Optical coherence tomography angiography of normal skin and inflammatory dermatologic conditions","volume":"50","year":"2018","journal-title":"Lasers Surg. Med"},{"key":"2026091609300493000_2026.09.05.749536v1.25","doi-asserted-by":"crossref","first-page":"849","DOI":"10.1002\/lsm.23367","article-title":"OCT-based angiography and surface topography in burn-damaged skin","volume":"53","year":"2021","journal-title":"Lasers Surg. Med"},{"key":"2026091609300493000_2026.09.05.749536v1.26","first-page":"116009","article-title":"Stable fiber-based polarization-sensitive optical coherence tomography using polarization maintaining common-path interferometer","volume":"25","year":"2020","journal-title":"J. Biomed. Opt"},{"key":"2026091609300493000_2026.09.05.749536v1.27","doi-asserted-by":"publisher","DOI":"10.1364\/OE.17.022704"},{"key":"2026091609300493000_2026.09.05.749536v1.28","doi-asserted-by":"publisher","DOI":"10.1364\/BOE.10.004179"},{"key":"2026091609300493000_2026.09.05.749536v1.29","doi-asserted-by":"crossref","first-page":"3116","DOI":"10.1364\/AO.56.003116","article-title":"Semi-automated localization of dermal epidermal junction in optical coherence tomography images of skin","volume":"56","year":"2017","journal-title":"Appl. Opt"},{"key":"2026091609300493000_2026.09.05.749536v1.30","doi-asserted-by":"crossref","unstructured":"A. Li , J. Cheng , A. P. Yow , et al., \u201cEpidermal segmentation in high-definition optical coherence tomography,\u201d in 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), (IEEE, 2015), pp. 3045\u20133048.","DOI":"10.1109\/EMBC.2015.7319034"},{"key":"2026091609300493000_2026.09.05.749536v1.31","doi-asserted-by":"crossref","first-page":"220","DOI":"10.3389\/fmed.2020.00220","article-title":"Automatic segmentation of epidermis and hair follicles in optical coherence tomography images of normal skin by convolutional neural networks","volume":"7","year":"2020","journal-title":"Front. Med"},{"key":"2026091609300493000_2026.09.05.749536v1.32","first-page":"2230","article-title":"Rapid measurement of epidermal thickness in OCT images of skin","volume":"14","year":"2024","journal-title":"Sci. Reports"},{"key":"2026091609300493000_2026.09.05.749536v1.33","doi-asserted-by":"publisher","DOI":"10.1364\/BOE.492670"},{"key":"2026091609300493000_2026.09.05.749536v1.34","doi-asserted-by":"crossref","first-page":"1381758","DOI":"10.3389\/fmed.2024.1381758","article-title":"Robust and accurate corneal interfaces segmentation in 2D and 3D OCT images","volume":"11","year":"2024","journal-title":"Front. Med"},{"key":"2026091609300493000_2026.09.05.749536v1.35","article-title":"Are large-scale datasets necessary for self-supervised pre-training?","year":"2021","journal-title":"arXiv preprint"},{"key":"2026091609300493000_2026.09.05.749536v1.36","doi-asserted-by":"crossref","first-page":"129199","DOI":"10.1016\/j.neucom.2024.129199","article-title":"Self-supervised visual learning in the low-data regime: A comparative evaluation","volume":"620","year":"2025","journal-title":"Neurocomputing"},{"key":"2026091609300493000_2026.09.05.749536v1.37","doi-asserted-by":"crossref","first-page":"5025","DOI":"10.1364\/BOE.524603","article-title":"Pretraining of 3D image segmentation models for retinal OCT using denoising-based self-supervised learning","volume":"15","year":"2024","journal-title":"Biomed. Opt. Express"},{"key":"2026091609300493000_2026.09.05.749536v1.38","doi-asserted-by":"crossref","unstructured":"Z. Liu , H. Mao , C. Wu , et al., \u201cA ConvNet for the 2020s,\u201d CoRR abs\/2201.03545 (2022).","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"2026091609300493000_2026.09.05.749536v1.39","article-title":"iBOT: Image BERT pre-training with online tokenizer","year":"2022","journal-title":"arXiv preprint"},{"key":"2026091609300493000_2026.09.05.749536v1.40","article-title":"Emerging properties in self-supervised vision transformers","year":"2021","journal-title":"arXiv preprint"},{"key":"2026091609300493000_2026.09.05.749536v1.41","article-title":"DINOv2: Learning robust visual features without supervision","year":"2024","journal-title":"arXiv preprint"},{"key":"2026091609300493000_2026.09.05.749536v1.42","article-title":"DINOv3","year":"2025","journal-title":"arXiv preprint"},{"key":"2026091609300493000_2026.09.05.749536v1.43","article-title":"LoRA: Low-rank adaptation of large language models","year":"2021","journal-title":"arXiv preprint"},{"key":"2026091609300493000_2026.09.05.749536v1.44","article-title":"Numerical coordinate regression with convolutional neural networks","year":"2018","journal-title":"arXiv preprint"},{"key":"2026091609300493000_2026.09.05.749536v1.45","unstructured":"R. Bawornkitchaikul , \u201cDINOCT: Code and evaluation pipeline,\u201d GitHub repository, https:\/\/github.com\/rjbaw\/dinoct (2026)."},{"key":"2026091609300493000_2026.09.05.749536v1.46","unstructured":"P. Foret , A. Kleiner , H. Mobahi , and B. Neyshabur , \u201cSharpness-aware minimization for efficiently improving generalization,\u201d CoRR abs\/2010.01412 (2020)."},{"key":"2026091609300493000_2026.09.05.749536v1.47","doi-asserted-by":"publisher","DOI":"10.1007\/BF00991005"},{"key":"2026091609300493000_2026.09.05.749536v1.48","article-title":"Open3D: A modern library for 3D data processing","year":"2018","journal-title":"arXiv preprint"},{"key":"2026091609300493000_2026.09.05.749536v1.49","doi-asserted-by":"publisher","DOI":"10.5860\/CHOICE.189890"},{"key":"2026091609300493000_2026.09.05.749536v1.50","doi-asserted-by":"crossref","unstructured":"Y. He , A. Carass , Y. Liu , et al., \u201cFully convolutional boundary regression for retina OCT segmentation,\u201d in Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2019, vol. 11764 of Lecture Notes in Computer Science (Springer, 2019), pp. 120\u2013128.","DOI":"10.1007\/978-3-030-32239-7_14"},{"key":"2026091609300493000_2026.09.05.749536v1.51","unstructured":"J. Bai , F. Lu , K. Zhang et al., \u201cONNX: Open neural network exchange,\u201d https:\/\/github.com\/onnx\/onnx (2019)."},{"key":"2026091609300493000_2026.09.05.749536v1.52","article-title":"LeJEPA: Provable and scalable self-supervised learning without the heuristics","year":"2025","journal-title":"arXiv preprint"},{"key":"2026091609300493000_2026.09.05.749536v1.53","unstructured":"J. Schulman and Thinking Machines Lab , \u201cLoRA Without Regret,\u201d Think. Mach. Lab: Connect. (2025)."},{"key":"2026091609300493000_2026.09.05.749536v1.54","article-title":"Robustness may be at odds with accuracy","year":"2019","journal-title":"arXiv preprint"},{"key":"2026091609300493000_2026.09.05.749536v1.55","unstructured":"R. Bawornkitchaikul , \u201cOCT surface-localization dataset,\u201d Hugging Face dataset, https:\/\/huggingface.co\/datasets\/rjbaw\/oct (2026)."},{"key":"2026091609300493000_2026.09.05.749536v1.56","unstructured":"R. Bawornkitchaikul , \u201cPS-OCTA-OCE-Robot: Robot platform code,\u201d GitHub repository, https:\/\/github.com\/rjbaw\/PS-OCTA-OCE-Robot (2026)."}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.09.05.749536","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T16:30:21Z","timestamp":1789576221000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.09.05.749536"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,12]]},"references-count":56,"URL":"https:\/\/doi.org\/10.64898\/2026.09.05.749536","relation":{},"subject":[],"published":{"date-parts":[[2026,9,12]]},"subtype":"preprint"}}