{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T19:13:24Z","timestamp":1770750804179,"version":"3.50.0"},"reference-count":15,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T00:00:00Z","timestamp":1750809600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T00:00:00Z","timestamp":1750809600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100003483","name":"Hebrew University of Jerusalem","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100003483","id-type":"DOI","asserted-by":"crossref"}]}],"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>Radiologist\u2019s manual annotations limit robust deep learning in volumetric medical imaging. While supervised methods excel with large annotated datasets, few-shot learning performs well for large structures but struggles with small ones, such as lesions. This paper describes a novel method that leverages the advantages of both few-shot learning models and fully supervised models while reducing the cost of manual annotation.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Methods<\/jats:title>\n            <jats:p>Our method inputs a small dataset of labeled scans and a large dataset of unlabeled scans and outputs a validated labeled dataset used to train a supervised model (nnU-Net). The estimated correction effort is reduced by having the radiologist correct a subset of the scan labels computed by a few-shot learning model (UniverSeg). The method uses an optimized support set of scan slice patches and prioritizes the resulting labeled scans that require the least correction. This process is repeated for the remaining unannotated scans until satisfactory performance is obtained.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Results<\/jats:title>\n            <jats:p>We validated our method on liver, lung, and brain lesions on CT and MRI scans (375 scans, 5933 lesions). It significantly reduces the estimated lesion detection correction effort by 34% for missed lesions, 387% for wrongly identified lesions, with 130% fewer lesion contour corrections, and 424% fewer pixels to correct in the lesion contours with respect to manual annotation from scratch.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Conclusion<\/jats:title>\n            <jats:p>Our method effectively reduces the radiologist\u2019s annotation effort of small structures to produce sufficient high-quality annotated datasets to train deep learning models. The method is generic and can be applied to a variety of lesions in various organs imaged by different modalities.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1007\/s11548-025-03457-3","type":"journal-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T15:37:15Z","timestamp":1750865835000},"page":"1863-1873","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Streamlining the annotation process by radiologists of volumetric medical images with few-shot learning"],"prefix":"10.1007","volume":"20","author":[{"given":"Alina","family":"Ryabtsev","sequence":"first","affiliation":[]},{"given":"Richard","family":"Lederman","sequence":"additional","affiliation":[]},{"given":"Jacob","family":"Sosna","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3010-4770","authenticated-orcid":false,"given":"Leo","family":"Joskowicz","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,6,25]]},"reference":[{"key":"3457_CR1","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T. (2015). U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W., Frangi, A. (eds) Medical image computing and computer-assisted intervention. Lecture Notes in Computer Science 9351. Springer, Cham","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"12","key":"3457_CR2","doi-asserted-by":"publisher","first-page":"10076","DOI":"10.1109\/TPAMI.2024.3435571","volume":"46","author":"R Azad","year":"2024","unstructured":"Azad R, Aghdam EK, Rauland A, Jia Y, Haddadi A (2024) Medical image segmentation review: the success of U-Net. IEEE Trans Pattern Anal Mach Intell 46(12):10076\u201310095","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3457_CR3","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","volume":"18","author":"F Isensee","year":"2020","unstructured":"Isensee F, Jaeger PF, Kohl SA, Petersen J, Maier-Hein K (2020) nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods 18:203\u2013211","journal-title":"Nat Methods"},{"key":"3457_CR4","doi-asserted-by":"crossref","unstructured":"Isensee F, Wald T, Ulrich C, Baumgartner M, Roy S, Maier-Hein K, Jaeger PF. (2024). nnU-Net revisited: a call for\u00a0rigorous validation in\u00a03D medical image segmentation. In: Linguraru, M.G., et al. Medical image computing and computer assisted intervention. Lecture notes in computer science 15003. Springer","DOI":"10.1007\/978-3-031-72114-4_47"},{"issue":"3","key":"3457_CR5","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1007\/s12194-021-00630-6","volume":"14","author":"T Nemoto","year":"2021","unstructured":"Nemoto T, Futakami N, Kunieda E, Yagi M, Takeda A, Akiba T, Mutu E, Shigematsu N (2021) Effects of sample size and data augmentation on U-Net-based automatic segmentation of various organs. Radiol Phys Technol 14(3):318\u2013327","journal-title":"Radiol Phys Technol"},{"key":"3457_CR6","doi-asserted-by":"publisher","DOI":"10.3389\/fradi.2021.748968","volume":"1","author":"P Bangert","year":"2021","unstructured":"Bangert P, Moon H, Woo JO, Didari S, Hao H (2021) Active learning performance in labeling radiology images is 90% effective. Front Radiol 1:748968","journal-title":"Front Radiol"},{"key":"3457_CR7","doi-asserted-by":"crossref","unstructured":"Zhang Y, Zhou T, Liang P, Chen D. (2023). Input augmentation with SAM: boosting medical image segmentation with segmentation foundation model. In: Medical image computing and computer assisted intervention. Lecture notes in computer science 14393. Springer","DOI":"10.1007\/978-3-031-47401-9_13"},{"key":"3457_CR8","unstructured":"Hu C, Xia T, Ju S, Li X. (2023). When SAM meets medical images: an investigation of Segment Anything Model (SAM) on multi-phase liver tumor segmentation. ArXiv: 2304.08506"},{"issue":"3","key":"3457_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3386252","volume":"53","author":"Y Wang","year":"2020","unstructured":"Wang Y, Yao Q, Kwok JT, Ni LM (2020) Generalizing from a few examples: a survey on few-shot learning. ACM Comput Surv 53(3):1\u201334","journal-title":"ACM Comput Surv"},{"key":"3457_CR10","doi-asserted-by":"crossref","unstructured":"Wang K, Liew JH, Zou Y, Zhou D, Feng J. (2019). PANet: few-shot image semantic segmentation with prototype alignment. In: Proc. IEEE Int. Conf. Computer Vision, pp. 9196\u20139205","DOI":"10.1109\/ICCV.2019.00929"},{"key":"3457_CR11","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham M, Eslami SMA, Van Gool L et al (2015) The PASCAL visual object classes challenge: a retrospective. Int J Computer Vision 111:98\u2013136","journal-title":"Int J Computer Vision"},{"key":"3457_CR12","doi-asserted-by":"publisher","first-page":"1837","DOI":"10.1109\/TMI.2022.3150682","volume":"41","author":"C Ouyang","year":"2022","unstructured":"Ouyang C, Biffi C, Chen C, Kart T, Qiu H, Rueckert D (2022) Self-supervised learning for few-shot medical image segmentation. IEEE Trans Med Imag 41:1837\u20131848","journal-title":"IEEE Trans Med Imag"},{"key":"3457_CR13","doi-asserted-by":"crossref","unstructured":"Butoi VI, Ortiz JJG, Ma T, Sabuncu MR, Guttag JV, Dalca AV (2023). UniverSeg: universal medical image segmentation. In: Proc. Int. Conf. Computer Vision, pp. 21381\u201321394","DOI":"10.1109\/ICCV51070.2023.01960"},{"key":"3457_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102675","volume":"83","author":"A Szeskin","year":"2023","unstructured":"Szeskin A, Rochman S, Weis S, Lederman R, Sosna J, Joskowicz L (2023) Liver lesion changes analysis in longitudinal CECT scans by simultaneous deep learning voxel classification with SimU-Net. Med Image Anal 83:102675","journal-title":"Med Image Anal"},{"issue":"3","key":"3457_CR15","doi-asserted-by":"publisher","first-page":"1391","DOI":"10.1007\/s00330-018-5695-5","volume":"29","author":"L Joskowicz","year":"2019","unstructured":"Joskowicz L, Cohen D, Caplan N, Sosna J (2019) Inter-observer variability of manual contour delineation of structures in CT. Eur Radiol 29(3):1391\u20131399","journal-title":"Eur Radiol"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-025-03457-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-025-03457-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-025-03457-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T11:22:03Z","timestamp":1758972123000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-025-03457-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,25]]},"references-count":15,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["3457"],"URL":"https:\/\/doi.org\/10.1007\/s11548-025-03457-3","relation":{},"ISSN":["1861-6429"],"issn-type":[{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,25]]},"assertion":[{"value":"10 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 June 2025","order":3,"name":"first_online","label":"First Online","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":"All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and\/or national research committee and with the 1964 Helsinki Declaration and its later amendments.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"There was no need for informed consent.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}