{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T13:13:16Z","timestamp":1788873196910,"version":"build-2803163510"},"reference-count":15,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T00:00:00Z","timestamp":1779840000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T00:00:00Z","timestamp":1779840000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000070","name":"National Institute of Biomedical Imaging and Bioengineering","doi-asserted-by":"publisher","award":["K25EB035166"],"award-info":[{"award-number":["K25EB035166"]}],"id":[{"id":"10.13039\/100000070","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>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Keypoint-based tracking and navigation are central to many image-guided surgical systems, yet their reliability degrades significantly in the presence of soft-tissue deformation, as commonly observed in procedures such as liver surgery. Existing keypoint descriptors often fail to remain stable under large affine and non-rigid transformations. This work introduces Stretcher, a framework designed to improve the deformation robustness of keypoint descriptors for surgical tracking and navigation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Instead of directly matching keypoint descriptors across deformed images, Stretcher learns a neural model that explicitly captures the effect of affine deformations on descriptor representations. At inference time, a grid of affine transformations is simulated, and keypoint descriptors are efficiently adjusted using the learned model, avoiding redundant descriptor recomputation. This enables robust descriptor adaptation under deformation while maintaining computational efficiency.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Stretcher is evaluated on liver surgery images exhibiting large tissue deformation. Experimental results show that the proposed approach improves keypoint matching robustness in highly deformed regions. Across all evaluated scenarios, Stretcher maintains state-of-the-art precision while providing higher matching accuracy compared to existing descriptor-based methods, particularly where deformation is severe.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>\n                      By explicitly modeling the impact of affine deformations on keypoint descriptors, Stretcher enables reliable keypoint matching under complex tissue motion. The proposed framework improves robustness in challenging surgical scenarios without sacrificing efficiency, making it well suited for deformation-prone intraoperative tracking and navigation tasks. Code is available at\n                      <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/constiwitzleben\/Stretchers\" ext-link-type=\"uri\">https:\/\/github.com\/constiwitzleben\/Stretchers<\/jats:ext-link>\n                      .\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s11548-026-03698-w","type":"journal-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T04:46:23Z","timestamp":1779857183000},"page":"1657-1663","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Stretcher: a learning-based framework for deformation-robust keypoint descriptors"],"prefix":"10.1007","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7611-2160","authenticated-orcid":false,"given":"Constantin","family":"von Witzleben","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nazim","family":"Haouchine","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,27]]},"reference":[{"key":"3698_CR1","doi-asserted-by":"publisher","unstructured":"Bojanic D, Bartol K, Pribanic T, Petkovic T, Donoso YD, Mas JS (2019) On the comparison of classic and deep keypoint detector and descriptor methods. In: 2019 11th International symposium on image and signal processing and analysis (ISPA), p 64\u201369. https:\/\/doi.org\/10.1109\/ISPA.2019.8868792 . ISSN: 1849-2266","DOI":"10.1109\/ISPA.2019.8868792"},{"issue":"10","key":"3698_CR2","doi-asserted-by":"publisher","first-page":"1771","DOI":"10.1016\/j.neucom.2007.11.032","volume":"71","author":"J Li","year":"2008","unstructured":"Li J, Allinson NM (2008) A comprehensive review of current local features for computer vision. Neurocomputing 71(10):1771\u20131787. https:\/\/doi.org\/10.1016\/j.neucom.2007.11.032","journal-title":"Neurocomputing"},{"key":"3698_CR3","doi-asserted-by":"publisher","unstructured":"Mikolajczyk K, Schmid C (2005) A performance evaluation of local descriptors. IEEE transactions on pattern analysis and machine intelligence 27(10): 1615\u20131630 https:\/\/doi.org\/10.1109\/TPAMI.2005.188 . Conference name: IEEE transactions on pattern analysis and machine intelligence","DOI":"10.1109\/TPAMI.2005.188"},{"key":"3698_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118696","volume":"213","author":"M Farhat","year":"2023","unstructured":"Farhat M, Chaabouni-Chouayakh H, Ben-Hamadou A (2023) Self-supervised endoscopic image key-points matching. Expert Syst Appl 213:118696. https:\/\/doi.org\/10.1016\/j.eswa.2022.118696","journal-title":"Expert Syst Appl"},{"issue":"8","key":"3698_CR5","doi-asserted-by":"publisher","first-page":"1746","DOI":"10.1109\/TMI.2017.2691259","volume":"36","author":"J R\u00fchaak","year":"2017","unstructured":"R\u00fchaak J, Polzin T, Heldmann S, Simpson IJA, Handels H, Modersitzki J, Heinrich MP (2017) Estimation of large motion in lung CT by integrating regularized keypoint correspondences into dense deformable registration. IEEE Trans Med Imaging 36(8):1746\u20131757. https:\/\/doi.org\/10.1109\/TMI.2017.2691259","journal-title":"IEEE Trans Med Imaging"},{"key":"3698_CR6","unstructured":"Yu EM, Wang AQ, Dalca AV, Sabuncu MR (2022) Keymorph: robust multi-modal affine registration via unsupervised keypoint detection. In: proceedings of The 5th International conference on medical imaging with deep learning. Proceedings of machine learning research, PMLR, Virtual, vol. 172, p 1482\u20131503"},{"issue":"2","key":"3698_CR7","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vision 60(2):91\u2013110. https:\/\/doi.org\/10.1023\/B:VISI.0000029664.99615.94","journal-title":"Int J Comput Vision"},{"key":"3698_CR8","doi-asserted-by":"crossref","unstructured":"DeTone D, Malisiewicz T, Rabinovich A (2018) SuperPoint: self-supervised interest point detection and description. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition workshops (CVPRW), IEEE, Salt Lake City, p 337\u201333712.DOIurlhttps:\/\/doi.org\/10.1109\/CVPRW.2018.00060","DOI":"10.1109\/CVPRW.2018.00060"},{"key":"3698_CR9","unstructured":"Tyszkiewicz M, Fua P, Trulls E (2020) Disk: learning local features with policy gradient. Adv Neural Inf Process Syst 33:14254\u201314265"},{"key":"3698_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2023.3271000","volume":"72","author":"X Zhao","year":"2023","unstructured":"Zhao X, Wu X, Chen W, Chen PCY, Xu Q, Li Z (2023) Aliked: a lighter keypoint and descriptor extraction network via deformable transformation. IEEE Trans Instrumen Meas 72:1\u201316. https:\/\/doi.org\/10.1109\/TIM.2023.3271000","journal-title":"IEEE Trans Instrumen Meas"},{"key":"3698_CR11","doi-asserted-by":"crossref","unstructured":"B\u00f6kman G, Edstedt J, Felsberg M, Kahl F (2024) Affine steerers for structured keypoint description. In: European conference on computer vision, p 449\u2013468","DOI":"10.1007\/978-3-031-73016-0_26"},{"key":"3698_CR12","doi-asserted-by":"publisher","unstructured":"B\u00f6kman G, Edstedt J, Felsberg M, Kahl F (2024) Steerers: a framework for rotation equivariant keypoint descriptors. In: 2024 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), IEEE, Seattle, p 4885\u20134895. https:\/\/doi.org\/10.1109\/CVPR52733.2024.00467","DOI":"10.1109\/CVPR52733.2024.00467"},{"key":"3698_CR13","doi-asserted-by":"crossref","unstructured":"Lindenberger P, Sarlin P-E, Pollefeys M (2023) Lightglue: Local feature matching at light speed. In: proceedings of the IEEE\/CVF international conference on computer vision, p 17627\u201317638","DOI":"10.1109\/ICCV51070.2023.01616"},{"key":"3698_CR14","doi-asserted-by":"crossref","unstructured":"Haouchine N, Stoyanov D, Roy F, Cotin S (2017) Dejavu: intra-operative simulation for surgical gesture rehearsal. In: medical image computing and computer-assisted intervention- MICCAI 2017: 20th International conference, Quebec City, 11-13 Sept 2017, Proceedings, Part II 20, Springer, p 523\u2013531","DOI":"10.1007\/978-3-319-66185-8_59"},{"key":"3698_CR15","unstructured":"Hong W-Y, Kao C-L, Kuo Y-H, Wang J-R, Chang W-L, Shih C-S (2020) Cholecseg8k: a semantic segmentation dataset for laparoscopic cholecystectomy based on cholec80. arXiv:2012.12453"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-026-03698-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-026-03698-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-026-03698-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T13:03:45Z","timestamp":1788872625000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-026-03698-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,27]]},"references-count":15,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["3698"],"URL":"https:\/\/doi.org\/10.1007\/s11548-026-03698-w","relation":{},"ISSN":["1861-6429"],"issn-type":[{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,27]]},"assertion":[{"value":"20 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This work has no conflict of interest to declare.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}}]}}