{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T23:03:38Z","timestamp":1778281418000,"version":"3.51.4"},"reference-count":21,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2023,5,3]],"date-time":"2023-05-03T00:00:00Z","timestamp":1683072000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,5,3]],"date-time":"2023-05-03T00:00:00Z","timestamp":1683072000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100013297","name":"Eurostars","doi-asserted-by":"publisher","award":["114442"],"award-info":[{"award-number":["114442"]}],"id":[{"id":"10.13039\/100013297","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007601","name":"Horizon 2020","doi-asserted-by":"publisher","award":["GEYEDANCE"],"award-info":[{"award-number":["GEYEDANCE"]}],"id":[{"id":"10.13039\/501100007601","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J CARS"],"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Purpose<\/jats:title>\n                <jats:p>A fundamental problem in designing safe machine learning systems is identifying when samples presented to a deployed model differ from those observed at training time. Detecting so-called out-of-distribution (OoD) samples is crucial in safety-critical applications such as robotically guided retinal microsurgery, where distances between the instrument and the retina are derived from sequences of 1D images that are acquired by an instrument-integrated optical coherence tomography (iiOCT) probe.\n<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>This work investigates the feasibility of using an OoD detector to identify when images from the iiOCT probe are inappropriate for subsequent machine learning-based distance estimation. We show how a simple OoD detector based on the Mahalanobis distance can successfully reject corrupted samples coming from real-world ex vivo porcine eyes.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>Our results demonstrate that the proposed approach can successfully detect OoD samples and help maintain the performance of the downstream task within reasonable levels. MahaAD outperformed a supervised approach trained on the same kind of corruptions and achieved the best performance in detecting OoD cases from a collection of iiOCT samples with real-world corruptions.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusion<\/jats:title>\n                <jats:p>The results indicate that detecting corrupted iiOCT data through OoD detection is feasible and does not need prior knowledge of possible corruptions. Consequently, MahaAD could aid in ensuring patient safety during robotically guided microsurgery by preventing deployed prediction models from estimating distances that put the patient at risk.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1007\/s11548-023-02909-y","type":"journal-article","created":{"date-parts":[[2023,5,3]],"date-time":"2023-05-03T11:01:48Z","timestamp":1683111708000},"page":"1085-1091","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Unsupervised out-of-distribution detection for safer robotically guided retinal microsurgery"],"prefix":"10.1007","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8327-4653","authenticated-orcid":false,"given":"Alain","family":"Jungo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lars","family":"Doorenbos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tommaso","family":"Da Col","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maarten","family":"Beelen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"Zinkernagel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pablo","family":"M\u00e1rquez-Neila","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raphael","family":"Sznitman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,5,3]]},"reference":[{"key":"2909_CR1","unstructured":"Yang J, Zhou K, Li Y, Liu Z (2021) Generalized out-of-distribution detection: a survey. arXiv preprint arXiv:2110.11334"},{"key":"2909_CR2","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1007\/978-3-030-32251-9_36","volume":"2019","author":"P M\u00e1rquez-Neila","year":"2019","unstructured":"M\u00e1rquez-Neila P, Sznitman R (2019) Image data validation for medical systems. MICCAI 2019:329\u2013337. https:\/\/doi.org\/10.1007\/978-3-030-32251-9_36","journal-title":"MICCAI"},{"key":"2909_CR3","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1007\/978-3-030-32251-9_32","volume":"2019","author":"D Zimmerer","year":"2019","unstructured":"Zimmerer D, Isensee F, Petersen J, Kohl S, Maier-Hein K (2019) Unsupervised anomaly localization using variational auto-encoders. MICCAI 2019:289\u2013297. https:\/\/doi.org\/10.1007\/978-3-030-32251-9_32","journal-title":"MICCAI"},{"key":"2909_CR4","unstructured":"Jungo A, Meier R, Ermis E, Herrmann E, Reyes M (2018) Uncertainty-driven sanity check: application to postoperative brain tumor cavity segmentation. MIDL 2018"},{"issue":"10","key":"2909_CR5","doi-asserted-by":"publisher","first-page":"2728","DOI":"10.1109\/TMI.2022.3170077","volume":"41","author":"D Zimmerer","year":"2022","unstructured":"Zimmerer D, Full PM, Isensee F, J\u00e4ger P, Adler T, Petersen J, K\u00f6hler G, Ross T, Reinke A, Kascenas A, Jensen BS, O\u2019Neil AQ, Tan J, Hou B, Batten J, Qiu H, Kainz B, Shvetsova N, Fedulova I, Dylov DV, Yu B, Zhai J, Hu J, Si R, Zhou S, Wang S, Li X, Chen X, Zhao Y, Marimont SN, Tarroni G, Saase V, Maier-Hein L, Maier-Hein K (2022) Mood 2020: a public benchmark for out-of-distribution detection and localization on medical images. IEEE Trans Med Imag 41(10):2728\u20132738. https:\/\/doi.org\/10.1109\/TMI.2022.3170077","journal-title":"IEEE Trans Med Imag"},{"key":"2909_CR6","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1007\/978-3-319-59050-9_12","volume":"2017","author":"T Schlegl","year":"2017","unstructured":"Schlegl T, Seeb\u00f6ck P, Waldstein SM, Schmidt-Erfurth U, Langs G (2017) Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. MICCAI 2017:146\u2013157. https:\/\/doi.org\/10.1007\/978-3-319-59050-9_12","journal-title":"MICCAI"},{"key":"2909_CR7","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1007\/978-3-030-87735-4_12","volume":"2021","author":"C Berger","year":"2021","unstructured":"Berger C, Paschali M, Glocker B, Kamnitsas K (2021) Confidence-based out-of-distribution detection: a comparative study and analysis. UNSURE 2021:122\u2013132. https:\/\/doi.org\/10.1007\/978-3-030-87735-4_12","journal-title":"UNSURE"},{"key":"2909_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102596","volume":"82","author":"C Gonz\u00e1lez","year":"2022","unstructured":"Gonz\u00e1lez C, Gotkowski K, Fuchs M, Bucher A, Dadras A, Fischbach R, Kaltenborn IJ, Mukhopadhyay A (2022) Distance-based detection of out-of-distribution silent failures for covid-19 lung lesion segmentation. Med Image Anal 82:102596. https:\/\/doi.org\/10.1016\/j.media.2022.102596","journal-title":"Med Image Anal"},{"key":"2909_CR9","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1007\/978-3-642-04268-3_14","volume":"2009","author":"M Balicki","year":"2009","unstructured":"Balicki M, Han J-H, Iordachita I, Gehlbach P, Handa J, Taylor R, Kang J (2009) Single fiber optical coherence tomography microsurgical instruments for computer and robot-assisted retinal surgery. MICCAI 2009:108\u2013115. https:\/\/doi.org\/10.1007\/978-3-642-04268-3_14","journal-title":"MICCAI"},{"key":"2909_CR10","doi-asserted-by":"publisher","first-page":"814","DOI":"10.1109\/BIOROB.2010.5625991","volume":"2010","author":"A \u00dcneri","year":"2010","unstructured":"\u00dcneri A, Balicki MA, Handa J, Gehlbach P, Taylor RH, Iordachita I (2010) New steady-hand eye robot with micro-force sensing for vitreoretinal surgery. BioRob 2010:814\u2013819. https:\/\/doi.org\/10.1109\/BIOROB.2010.5625991","journal-title":"BioRob"},{"key":"2909_CR11","doi-asserted-by":"publisher","unstructured":"Vander\u00a0Poorten E, Riviere CN, Abbott JJ, Bergeles C, Nasseri MA, Kang JU, Sznitman R, Faridpooya K, Iordachita I (2020) Robotic retinal surgery. In: Handbook of robotic and image-guided surgery, pp. 627\u2013672 https:\/\/doi.org\/10.1016\/B978-0-12-814245-5.00036-0","DOI":"10.1016\/B978-0-12-814245-5.00036-0"},{"issue":"4","key":"2909_CR12","doi-asserted-by":"publisher","first-page":"100085","DOI":"10.1016\/j.xops.2021.100085","volume":"1","author":"MG Cereda","year":"2021","unstructured":"Cereda MG, Parrulli S, Douven YGM, Faridpooya K, van Romunde S, H\u00fcttmann G, Eixmann T, Schulz-Hildebrandt H, Kronreif G, Beelen M, de Smet MD (2021) Clinical evaluation of an instrument-integrated oct-based distance sensor for robotic vitreoretinal surgery. Ophthalmol Sci 1(4):100085. https:\/\/doi.org\/10.1016\/j.xops.2021.100085","journal-title":"Ophthalmol Sci"},{"issue":"6","key":"2909_CR13","doi-asserted-by":"publisher","first-page":"787","DOI":"10.1007\/s11548-018-1751-5","volume":"13","author":"J Weiss","year":"2018","unstructured":"Weiss J, Rieke N, Nasseri MA, Maier M, Eslami A, Navab N (2018) Fast 5dof needle tracking in ioct. IJCARS 13(6):787\u2013796. https:\/\/doi.org\/10.1007\/s11548-018-1751-5","journal-title":"IJCARS"},{"key":"2909_CR14","doi-asserted-by":"publisher","first-page":"6726","DOI":"10.1109\/ICPR48806.2021.9412109","volume":"2020","author":"O Rippel","year":"2021","unstructured":"Rippel O, Mertens P, Merhof D (2021) Modeling the distribution of normal data in pre-trained deep features for anomaly detection. ICPR 2020:6726\u20136733. https:\/\/doi.org\/10.1109\/ICPR48806.2021.9412109","journal-title":"ICPR"},{"issue":"6","key":"2909_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1117\/1.JBO.26.6.068001","volume":"26","author":"S Lee","year":"2021","unstructured":"Lee S, Kang JU (2021) CNN-based CP-OCT sensor integrated with a subretinal injector for retinal boundary tracking and injection guidance. J Biomed Optics 26(6):1\u201314. https:\/\/doi.org\/10.1117\/1.JBO.26.6.068001","journal-title":"J Biomed Optics"},{"key":"2909_CR16","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1007\/978-3-031-19821-2_8","volume":"2022","author":"L Doorenbos","year":"2022","unstructured":"Doorenbos L, Sznitman R, M\u00e1rquez-Neila P (2022) Data invariants to understand unsupervised out-of-distribution detection. ECCV 2022:133\u2013150. https:\/\/doi.org\/10.1007\/978-3-031-19821-2_8","journal-title":"ECCV"},{"key":"2909_CR17","unstructured":"Tan M, Le Q (2019) EfficientNet: Rethinking model scaling for convolutional neural networks. In: ICML 2019, vol. 97, pp. 6105\u20136114"},{"key":"2909_CR18","unstructured":"Kingma DP, Dhariwal P (2018) Glow: Generative flow with invertible 1x1 convolutions. In: NeurIPS 2018, vol. 31"},{"key":"2909_CR19","unstructured":"Amersfoort Jv (2022) Glow https:\/\/github.com\/y0ast\/Glow-PyTorch Accessed 08 Nov 2022"},{"key":"2909_CR20","unstructured":"Hendrycks D, Gimpel K (2017) A baseline for detecting misclassified and out-of-distribution examples in neural networks. ICLR 2017"},{"key":"2909_CR21","doi-asserted-by":"publisher","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. MICCAI 2015:234\u2013241. https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28","DOI":"10.1007\/978-3-319-24574-4_28"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-023-02909-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-023-02909-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-023-02909-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,12]],"date-time":"2023-07-12T16:26:26Z","timestamp":1689179186000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-023-02909-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,3]]},"references-count":21,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2023,6]]}},"alternative-id":["2909"],"URL":"https:\/\/doi.org\/10.1007\/s11548-023-02909-y","relation":{},"ISSN":["1861-6429"],"issn-type":[{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,3]]},"assertion":[{"value":"8 February 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 April 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 May 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 July 2023","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Update","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"End period has been placed outside the hyperlink at the end of data availability section","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent"}}]}}