{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T17:30:12Z","timestamp":1790703012318,"version":"4.1.0"},"reference-count":57,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T00:00:00Z","timestamp":1783036800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002347","name":"Bundesministerium fur Forschung Technologie und Raumfahrt Informationstechnikzentrum Bund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"German Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100023863","name":"Munich Center for Machine Learning","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100023863","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001655","name":"DAAD","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001655","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100008672","name":"Wilhelm Sander Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008672","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010688","name":"Horizon 2020 European Innovation Council Fast Track to Innovation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010688","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Medical Image Analysis"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.media.2026.104195","type":"journal-article","created":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T06:59:49Z","timestamp":1783061989000},"page":"104195","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Progressive growing of patch size: Curriculum learning for accelerated and improved medical image segmentation"],"prefix":"10.1016","volume":"113","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7637-7183","authenticated-orcid":false,"given":"Stefan M.","family":"Fischer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9610-146X","authenticated-orcid":false,"given":"Johannes","family":"Kiechle","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4170-6168","authenticated-orcid":false,"given":"Laura","family":"Daza","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7695-2612","authenticated-orcid":false,"given":"Lina","family":"Felsner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1835-8564","authenticated-orcid":false,"given":"Richard","family":"Osuala","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0274-9069","authenticated-orcid":false,"given":"Daniel M.","family":"Lang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karim","family":"Lekadir","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jan C.","family":"Peeken","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6107-3009","authenticated-orcid":false,"given":"Julia A.","family":"Schnabel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.media.2026.104195_b1","doi-asserted-by":"crossref","first-page":"4128","DOI":"10.1038\/s41467-022-30695-9","article-title":"The medical segmentation decathlon","volume":"13","author":"Antonelli","year":"2022","journal-title":"Nat. Commun."},{"key":"10.1016\/j.media.2026.104195_b2","doi-asserted-by":"crossref","unstructured":"Arani, E., Marzban, S., Pata, A., Zonooz, B., 2021. Rgpnet: A real-time general purpose semantic segmentation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 3009\u20133018.","DOI":"10.1109\/WACV48630.2021.00305"},{"key":"10.1016\/j.media.2026.104195_b3","series-title":"V-jepa 2: Self-supervised video models enable understanding, prediction and planning","author":"Assran","year":"2025"},{"key":"10.1016\/j.media.2026.104195_b4","series-title":"Auto-nnU-Net: Towards automated medical image segmentation","author":"Becktepe","year":"2025"},{"key":"10.1016\/j.media.2026.104195_b5","series-title":"Proceedings of the International Conference on Machine Learning","first-page":"41","article-title":"Curriculum learning","author":"Bengio","year":"2009"},{"key":"10.1016\/j.media.2026.104195_b6","doi-asserted-by":"crossref","unstructured":"Bolelli, F., Marchesini, K., van Nistelrooij, N., Lumetti, L., Pipoli, V., Ficarra, E., Vinayahalingam, S., Grana, C., 2025. Segmenting Maxillofacial Structures in CBCT Volumes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 5238\u20135248.","DOI":"10.1109\/CVPR52734.2025.00494"},{"key":"10.1016\/j.media.2026.104195_b7","series-title":"Perception encoder: The best visual embeddings are not at the output of the network","author":"Bolya","year":"2025"},{"key":"10.1016\/j.media.2026.104195_b8","series-title":"Monai: An open-source framework for deep learning in healthcare","author":"Cardoso","year":"2022"},{"key":"10.1016\/j.media.2026.104195_b9","series-title":"International Conference on Information Processing in Medical Imaging","first-page":"715","article-title":"Is segmentation uncertainty useful?","author":"Czolbe","year":"2021"},{"key":"10.1016\/j.media.2026.104195_b10","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K., 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). pp. 4171\u20134186.","DOI":"10.18653\/v1\/N19-1423"},{"key":"10.1016\/j.media.2026.104195_b11","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al., 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In: International Conference on Learning Representations."},{"key":"10.1016\/j.media.2026.104195_b12","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"510","article-title":"Progressive growing of patch size: Resource-efficient curriculum learning for dense prediction tasks","author":"Fischer","year":"2024"},{"key":"10.1016\/j.media.2026.104195_b13","series-title":"Brainlesion Workshop At International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"272","article-title":"Swin UNETR: Swin transformers for semantic segmentation of brain tumors in MRI images","author":"Hatamizadeh","year":"2021"},{"key":"10.1016\/j.media.2026.104195_b14","doi-asserted-by":"crossref","unstructured":"Hatamizadeh, A., Tang, Y., Nath, V., Yang, D., Myronenko, A., Landman, B., Roth, H.R., Xu, D., 2022. UNETR: Transformers for 3D medical image segmentation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 574\u2013584.","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"10.1016\/j.media.2026.104195_b15","series-title":"Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"469","article-title":"HeMIS: Hetero-modal image segmentation","author":"Havaei","year":"2016"},{"key":"10.1016\/j.media.2026.104195_b16","series-title":"Kidney and Kidney Tumor Segmentation: MICCAI 2023 Challenge, KiTS 2023, Held in Conjunction with MICCAI 2023, Vancouver, BC, Canada, October 8, 2023, Proceedings","author":"Heller","year":"2024"},{"issue":"2","key":"10.1016\/j.media.2026.104195_b17","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nature Methods"},{"key":"10.1016\/j.media.2026.104195_b18","series-title":"nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation","author":"Isensee","year":"2024"},{"key":"10.1016\/j.media.2026.104195_b19","series-title":"Automated design of deep learning methods for biomedical image segmentation","author":"Isensee","year":"2019"},{"key":"10.1016\/j.media.2026.104195_b20","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"13","article-title":"Scaling nnU-Net for CBCT segmentation","author":"Isensee","year":"2024"},{"key":"10.1016\/j.media.2026.104195_b21","series-title":"BVM Workshop","first-page":"12","article-title":"Extending nnU-Net is all you need","author":"Isensee","year":"2023"},{"key":"10.1016\/j.media.2026.104195_b22","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"488","article-title":"Nnu-net revisited: A call for rigorous validation in 3d medical image segmentation","author":"Isensee","year":"2024"},{"key":"10.1016\/j.media.2026.104195_b23","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"376","article-title":"No more sliding window: Efficient 3D medical image segmentation with differentiable top-k patch sampling","author":"Jeon","year":"2025"},{"key":"10.1016\/j.media.2026.104195_b24","series-title":"Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"639","article-title":"CASED: Curriculum adaptive sampling for extreme data imbalance","author":"Jesson","year":"2017"},{"key":"10.1016\/j.media.2026.104195_b25","doi-asserted-by":"crossref","first-page":"36722","DOI":"10.52202\/068431-2661","article-title":"Amos: A large-scale abdominal multi-organ benchmark for versatile medical image segmentation","volume":"35","author":"Ji","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2026.104195_b26","series-title":"Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"694","article-title":"Medical-based deep curriculum learning for improved fracture classification","author":"Jim\u00e9nez-S\u00e1nchez","year":"2019"},{"key":"10.1016\/j.media.2026.104195_b27","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.media.2016.10.004","article-title":"Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation","volume":"36","author":"Kamnitsas","year":"2017","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2026.104195_b28","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J., 2018. Progressive Growing of GANs for Improved Quality, Stability, and Variation. In: International Conference on Learning Representations."},{"key":"10.1016\/j.media.2026.104195_b29","doi-asserted-by":"crossref","unstructured":"Ko\u00e7yi\u011fit, M.T., Hospedales, T.M., Bilen, H., 2023. Accelerating self-supervised learning via efficient training strategies. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 5654\u20135664.","DOI":"10.1109\/WACV56688.2023.00561"},{"key":"10.1016\/j.media.2026.104195_b30","doi-asserted-by":"crossref","unstructured":"Koehler, G., Wald, T., Ulrich, C., Zimmerer, D., Jaeger, P.F., Franke, J.K., Kohl, S., Isensee, F., Maier-Hein, K.H., 2024. Recyclenet: Latent feature recycling leads to iterative decision refinement. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 810\u2013818.","DOI":"10.1109\/WACV57701.2024.00086"},{"key":"10.1016\/j.media.2026.104195_b31","unstructured":"Landman, B., Xu, Z., Iglesias, J., Styner, M., Langerak, T., Klein, A., 2015. MICCAI Multi-Atlas Labeling Beyond the Cranial Vault\u2013Workshop and Challenge. In: Proceedings of the MICCAI Multi-Atlas Labeling beyond Cranial Vault Workshop Challenge."},{"key":"10.1016\/j.media.2026.104195_b32","series-title":"Vision transformer for small-size datasets","author":"Lee","year":"2021"},{"key":"10.1016\/j.media.2026.104195_b33","series-title":"RECLIP: Resource-efficient CLIP by training with small images, transactions on machine learning research","author":"Li","year":"2023"},{"key":"10.1016\/j.media.2026.104195_b34","doi-asserted-by":"crossref","unstructured":"Li, C., Yao, Z., Wu, X., Zhang, M., Holmes, C., Li, C., He, Y., 2024. Deepspeed data efficiency: Improving deep learning model quality and training efficiency via efficient data sampling and routing. In: Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 38, pp. 18490\u201318498.","DOI":"10.1609\/aaai.v38i16.29810"},{"key":"10.1016\/j.media.2026.104195_b35","doi-asserted-by":"crossref","first-page":"26736","DOI":"10.52202\/068431-1939","article-title":"The stability-efficiency dilemma: Investigating sequence length warmup for training GPT models","volume":"35","author":"Li","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2026.104195_b36","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B., 2021. Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10.1016\/j.media.2026.104195_b37","series-title":"U-mamba: Enhancing long-range dependency for biomedical image segmentation","author":"Ma","year":"2024"},{"key":"10.1016\/j.media.2026.104195_b38","series-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"10.1016\/j.media.2026.104195_b39","doi-asserted-by":"crossref","unstructured":"Press, O., Smith, N.A., Lewis, M., 2021. Shortformer: Better Language Modeling using Shorter Inputs. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). pp. 5493\u20135505.","DOI":"10.18653\/v1\/2021.acl-long.427"},{"key":"10.1016\/j.media.2026.104195_b40","series-title":"Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"10.1016\/j.media.2026.104195_b41","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"405","article-title":"Mednext: Transformer-driven scaling of convnets for medical image segmentation","author":"Roy","year":"2023"},{"key":"10.1016\/j.media.2026.104195_b42","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2024.103181","article-title":"Active learning using adaptable task-based prioritisation","volume":"95","author":"Saeed","year":"2024","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2026.104195_b43","series-title":"Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"506","article-title":"Carbon footprint of selecting and training deep learning models for medical image analysis","author":"Selvan","year":"2022"},{"issue":"3","key":"10.1016\/j.media.2026.104195_b44","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3700439","article-title":"On efficient training of large-scale deep learning models","volume":"57","author":"Shen","year":"2024","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.media.2026.104195_b45","doi-asserted-by":"crossref","unstructured":"Shrivastava, A., Gupta, A., Girshick, R., 2016. Training region-based object detectors with online hard example mining. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 761\u2013769.","DOI":"10.1109\/CVPR.2016.89"},{"key":"10.1016\/j.media.2026.104195_b46","series-title":"Dinov3","author":"Sim\u00e9oni","year":"2025"},{"key":"10.1016\/j.media.2026.104195_b47","series-title":"International Conference on Machine Learning","first-page":"10096","article-title":"Efficientnetv2: Smaller models and faster training","author":"Tan","year":"2021"},{"key":"10.1016\/j.media.2026.104195_b48","series-title":"International Conference on Machine Learning","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2021"},{"key":"10.1016\/j.media.2026.104195_b49","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"648","article-title":"Multitalent: A multi-dataset approach to medical image segmentation","author":"Ulrich","year":"2023"},{"key":"10.1016\/j.media.2026.104195_b50","series-title":"Comprehensive language-image pre-training for 3D medical image understanding","author":"Wald","year":"2025"},{"key":"10.1016\/j.media.2026.104195_b51","series-title":"Primus: Enforcing attention usage for 3d medical image segmentation","author":"Wald","year":"2025"},{"key":"10.1016\/j.media.2026.104195_b52","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2024.103201","article-title":"A comprehensive survey on deep active learning in medical image analysis","volume":"95","author":"Wang","year":"2024","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2026.104195_b53","article-title":"Efficienttrain++: Generalized curriculum learning for efficient visual backbone training","author":"Wang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"5","key":"10.1016\/j.media.2026.104195_b54","article-title":"TotalSegmentator: Robust segmentation of 104 anatomic structures in CT images","volume":"5","author":"Wasserthal","year":"2023","journal-title":"Radiol.: Artif. Intell."},{"key":"10.1016\/j.media.2026.104195_b55","doi-asserted-by":"crossref","unstructured":"Wei, J., Suriawinata, A., Ren, B., Liu, X., Lisovsky, M., Vaickus, L., Brown, C., Baker, M., Nasir-Moin, M., Tomita, N., Torresani, L., Wei, J., Hassanpour, S., 2021. Learn like a pathologist: Curriculum learning by annotator agreement for histopathology image classification. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 2473\u20132483.","DOI":"10.1109\/WACV48630.2021.00252"},{"key":"10.1016\/j.media.2026.104195_b56","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"399","article-title":"Suggestive annotation: A deep active learning framework for biomedical image segmentation","author":"Yang","year":"2017"},{"key":"10.1016\/j.media.2026.104195_b57","series-title":"Multiscale Multimodal Medical Imaging Workshop At International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"51","article-title":"PGU-net+: Progressive growing of U-net+ for automated cervical nuclei segmentation","author":"Zhao","year":"2020"}],"container-title":["Medical Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526002641?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526002641?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T06:57:20Z","timestamp":1785826640000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1361841526002641"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":57,"alternative-id":["S1361841526002641"],"URL":"https:\/\/doi.org\/10.1016\/j.media.2026.104195","relation":{},"ISSN":["1361-8415"],"issn-type":[{"value":"1361-8415","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Progressive growing of patch size: Curriculum learning for accelerated and improved medical image segmentation","name":"articletitle","label":"Article Title"},{"value":"Medical Image Analysis","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.media.2026.104195","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"104195"}}