{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:07:09Z","timestamp":1784268429811,"version":"3.55.0"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031439001","type":"print"},{"value":"9783031439018","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-43901-8_40","type":"book-chapter","created":{"date-parts":[[2023,9,30]],"date-time":"2023-09-30T23:08:23Z","timestamp":1696115303000},"page":"416-426","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":119,"title":["SwinUNETR-V2: Stronger Swin Transformers with\u00a0Stagewise Convolutions for\u00a03D Medical Image Segmentation"],"prefix":"10.1007","author":[{"given":"Yufan","family":"He","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vishwesh","family":"Nath","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yucheng","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andriy","family":"Myronenko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daguang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,10,1]]},"reference":[{"issue":"1","key":"40_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-022-30695-9","volume":"13","author":"M Antonelli","year":"2022","unstructured":"Antonelli, M., et al.: The medical segmentation decathlon. Nat. Commun. 13(1), 1\u201313 (2022)","journal-title":"Nat. Commun."},{"key":"40_CR2","unstructured":"Cao, H., et al.: Swin-Unet: Unet-like pure transformer for medical image segmentation. arXiv preprint arXiv:2105.05537 (2021)"},{"key":"40_CR3","unstructured":"Chen, J., et al.: TransUNet: Transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306 (2021)"},{"key":"40_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Mobile-Former: Bridging mobileNet and transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5270\u20135279 (2022)","DOI":"10.1109\/CVPR52688.2022.00520"},{"key":"40_CR5","first-page":"3965","volume":"34","author":"Z Dai","year":"2021","unstructured":"Dai, Z., Liu, H., Le, Q.V., Tan, M.: CoAtNet: marrying convolution and attention for all data sizes. Adv. Neural Inf. Process. Syst. 34, 3965\u20133977 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"40_CR6","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"40_CR7","doi-asserted-by":"crossref","unstructured":"d\u2019Ascoli, S., Touvron, H., Leavitt, M.L., Morcos, A.S., Biroli, G., Sagun, L.: ConViT: improving vision transformers with soft convolutional inductive biases. In: International Conference on Machine Learning, pp. 2286\u20132296. PMLR (2021)","DOI":"10.1088\/1742-5468\/ac9830"},{"key":"40_CR8","doi-asserted-by":"crossref","unstructured":"Guo, J., et al.: CMT: convolutional neural networks meet vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12175\u201312185 (2022)","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"40_CR9","doi-asserted-by":"crossref","unstructured":"Hatamizadeh, A., et al.: UNETR: transformers for 3D medical image segmentation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 574\u2013584 (2022)","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"40_CR10","doi-asserted-by":"crossref","unstructured":"He, Y., Yang, D., Roth, H., Zhao, C., Xu, D.: DiNTS: differentiable neural network topology search for 3D medical image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5841\u20135850 (2021)","DOI":"10.1109\/CVPR46437.2021.00578"},{"key":"40_CR11","doi-asserted-by":"publisher","unstructured":"Huang, Z. et al.: Revisiting nnU-Net for iterative pseudo labeling and efficient sliding window inference. In: Ma, J., Wang, B. (eds.) Fast and Low-Resource Semi-supervised Abdominal Organ Segmentation. FLARE 2022. Lecture Notes in Computer Science. vol. 13816. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-23911-3_16","DOI":"10.1007\/978-3-031-23911-3_16"},{"issue":"2","key":"40_CR12","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","volume":"18","author":"F Isensee","year":"2021","unstructured":"Isensee, F., Jaeger, P.F., Kohl, S.A., Petersen, J., Maier-Hein, K.H.: nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18(2), 203\u2013211 (2021)","journal-title":"Nat. Methods"},{"key":"40_CR13","unstructured":"Ji, Y., et al.: AMOS: A large-scale abdominal multi-organ benchmark for versatile medical image segmentation. arXiv preprint arXiv:2206.08023 (2022)"},{"key":"40_CR14","unstructured":"Lee, H.H., Bao, S., Huo, Y., Landman, B.A.: 3D UX-Net: A large kernel volumetric convnet modernizing hierarchical transformer for medical image segmentation. arXiv (2022)"},{"key":"40_CR15","unstructured":"Li, X., et al.: The state-of-the-art 3d anisotropic intracranial hemorrhage segmentation on non-contrast head CT: the instance challenge. arXiv preprint arXiv:2301.03281 (2023)"},{"key":"40_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"40_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102642","volume":"82","author":"X Luo","year":"2022","unstructured":"Luo, X.: Word: a large scale dataset, benchmark and clinical applicable study for abdominal organ segmentation from CT image. Med. Image Anal. 82, 102642 (2022)","journal-title":"Med. Image Anal."},{"key":"40_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102616","volume":"82","author":"J Ma","year":"2022","unstructured":"Ma, J., et al.: Fast and low-GPU-memory abdomen CT organ segmentation: the flare challenge. Med. Image Anal. 82, 102616 (2022)","journal-title":"Med. Image Anal."},{"key":"40_CR19","unstructured":"Myronenko, A., Siddiquee, M.M.R., Yang, D., He, Y., Xu, D.: Automated head and neck tumor segmentation from 3D PET\/CT. arXiv preprint arXiv:2209.10809 (2022)"},{"key":"40_CR20","doi-asserted-by":"crossref","unstructured":"Peng, Z., et al.: Conformer: local features coupling global representations for visual recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 367\u2013376 (2021)","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"40_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"40_CR22","unstructured":"Siddiquee, M.M.R., Yang, D., He, Y., Xu, D., Myronenko, A.: Automated segmentation of intracranial hemorrhages from 3D CT. arXiv preprint arXiv:2209.10648 (2022)"},{"key":"40_CR23","doi-asserted-by":"crossref","unstructured":"Tang, Y., et al.: Self-supervised pre-training of swin transformers for 3D medical image analysis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20730\u201320740 (2022)","DOI":"10.1109\/CVPR52688.2022.02007"},{"key":"40_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1007\/978-3-030-87193-2_4","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"JMJ Valanarasu","year":"2021","unstructured":"Valanarasu, J.M.J., Oza, P., Hacihaliloglu, I., Patel, V.M.: Medical transformer: gated axial-attention for medical image segmentation. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12901, pp. 36\u201346. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87193-2_4"},{"key":"40_CR25","doi-asserted-by":"crossref","unstructured":"Vaswani, A., Ramachandran, P., Srinivas, A., Parmar, N., Hechtman, B., Shlens, J.: Scaling local self-attention for parameter efficient visual backbones. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12894\u201312904 (2021)","DOI":"10.1109\/CVPR46437.2021.01270"},{"key":"40_CR26","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"40_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/978-3-030-87193-2_11","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"W Wang","year":"2021","unstructured":"Wang, W., Chen, C., Ding, M., Yu, H., Zha, S., Li, J.: TransBTS: multimodal brain tumor segmentation using transformer. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12901, pp. 109\u2013119. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87193-2_11"},{"key":"40_CR28","doi-asserted-by":"crossref","unstructured":"Wu, H., et al.: CvT: introducing convolutions to vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22\u201331 (2021)","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"40_CR29","doi-asserted-by":"crossref","unstructured":"Xia, Z., Pan, X., Song, S., Li, L.E., Huang, G.: Vision transformer with deformable attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4794\u20134803 (2022)","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"40_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1007\/978-3-030-87199-4_16","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"Y Xie","year":"2021","unstructured":"Xie, Y., Zhang, J., Shen, C., Xia, Y.: CoTr: efficiently bridging CNN and transformer for 3D medical image segmentation. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12903, pp. 171\u2013180. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87199-4_16"},{"key":"40_CR31","unstructured":"Yang, C., et al.: MOAT: alternating mobile convolution and attention brings strong vision models. arXiv preprint arXiv:2210.01820 (2022)"},{"key":"40_CR32","doi-asserted-by":"crossref","unstructured":"Yang, D., et al.: T-AutoML: automated machine learning for lesion segmentation using transformers in 3d medical imaging. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3962\u20133974 (2021)","DOI":"10.1109\/ICCV48922.2021.00393"},{"key":"40_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1007\/978-3-030-87193-2_2","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Liu, H., Hu, Q.: TransFuse: fusing transformers and CNNs for medical image segmentation. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12901, pp. 14\u201324. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87193-2_2"},{"key":"40_CR34","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ADE20K dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 633\u2013641 (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"40_CR35","unstructured":"Zhou, H.Y., Guo, J., Zhang, Y., Yu, L., Wang, L., Yu, Y.: nnFormer: Interleaved transformer for volumetric segmentation. arXiv preprint arXiv:2109.03201 (2021)"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43901-8_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,11]],"date-time":"2024-03-11T15:22:55Z","timestamp":1710170575000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43901-8_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031439001","9783031439018"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43901-8_40","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"1 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Medical Image Computing and Computer-Assisted Intervention","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vancouver, BC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2023\/en\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2250","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"730","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"32% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}