{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T07:33:40Z","timestamp":1774164820146,"version":"3.50.1"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032095121","type":"print"},{"value":"9783032095138","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-09513-8_5","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T02:14:58Z","timestamp":1767320098000},"page":"41-51","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["VIViT: Variable-Input Vision Transformer Framework for\u00a03D MR Image Segmentation"],"prefix":"10.1007","author":[{"given":"Badhan Kumar","family":"Das","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ajay","family":"Singh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gengyan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thmoas J.","family":"Re","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dorin","family":"Comaniciu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eli","family":"Gibson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreas","family":"Maier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"5_CR1","unstructured":"Azad, R., Khosravi, N., Dehghanmanshadi, M., Cohen-Adad, J., Merhof, D.: Medical image segmentation on MRI images with missing modalities: a review. arXiv preprint arXiv:2203.06217 (2022)"},{"key":"5_CR2","unstructured":"Baid, U., et\u00a0al.: The RSNA-ASNR-MICCAI BraTS 2021 benchmark on brain tumor segmentation and radiogenomic classification. arXiv preprint arXiv:2107.02314 (2021)"},{"key":"5_CR3","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F.: BEiT: BERT pre-training of image transformers. arXiv preprint arXiv:2106.08254 (2021)"},{"key":"5_CR4","unstructured":"Cardoso, M.J., et\u00a0al.: MONAI: an open-source framework for deep learning in healthcare. arXiv preprint arXiv:2211.02701 (2022)"},{"issue":"8","key":"5_CR5","doi-asserted-by":"publisher","first-page":"1384","DOI":"10.3390\/diagnostics11081384","volume":"11","author":"Y Dai","year":"2021","unstructured":"Dai, Y., Gao, Y., Liu, F.: TransMed: transformers advance multi-modal medical image classification. Diagnostics 11(8), 1384 (2021)","journal-title":"Diagnostics"},{"issue":"1","key":"5_CR6","doi-asserted-by":"publisher","first-page":"9380","DOI":"10.1038\/s41598-024-59813-x","volume":"14","author":"BK Das","year":"2024","unstructured":"Das, B.K., et al.: Co-ordinate-based positional embedding that captures resolution to enhance transformer performance in medical image analysis. Sci. Rep. 14(1), 9380 (2024)","journal-title":"Sci. Rep."},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Das, B.K., et al.: Self pre-training with adaptive mask autoencoders for variable-contrast 3D medical imaging. arXiv preprint arXiv:2501.09096 (2025)","DOI":"10.1109\/ISBI60581.2025.10981097"},{"key":"5_CR8","unstructured":"Dosovitskiy, A.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"issue":"2","key":"5_CR9","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1002\/hbm.21440","volume":"34","author":"X Hao","year":"2013","unstructured":"Hao, X., et al.: Multimodal magnetic resonance imaging: the coordinated use of multiple, mutually informative probes to understand brain structure and function. Hum. Brain Mapp. 34(2), 253\u2013271 (2013)","journal-title":"Hum. Brain Mapp."},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Hatamizadeh, A., Nath, V., Tang, Y., Yang, D., Roth, H.R., Xu, D.: Swin UNETR: swin transformers for semantic segmentation of brain tumors in MRI images. In: International MICCAI Brainlesion Workshop, pp. 272\u2013284. Springer (2021)","DOI":"10.1007\/978-3-031-08999-2_22"},{"key":"5_CR11","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":"5_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"issue":"1","key":"5_CR13","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1109\/TMI.2022.3210133","volume":"42","author":"S Hu","year":"2022","unstructured":"Hu, S., Liao, Z., Zhang, J., Xia, Y.: Domain and content adaptive convolution based multi-source domain generalization for medical image segmentation. IEEE Trans. Med. Imaging 42(1), 233\u2013244 (2022)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"5_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 preprint arXiv:2209.15076 (2022)"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Liu, H., et al.: ModDrop++: a dynamic filter network with intra-subject co-training for multiple sclerosis lesion segmentation with missing modalities. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 444\u2013453. Springer (2022)","DOI":"10.1007\/978-3-031-16443-9_43"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Luo, P., Xiao, G., Gao, X., Wu, S.: LKD-Net: large kernel convolution network for single image dehazing. In: 2023 IEEE International Conference on Multimedia and Expo (ICME), pp. 1601\u20131606. IEEE (2023)","DOI":"10.1109\/ICME55011.2023.00276"},{"issue":"1","key":"5_CR17","first-page":"9580991","volume":"2022","author":"P Malhotra","year":"2022","unstructured":"Malhotra, P., Gupta, S., Koundal, D., Zaguia, A., Enbeyle, W.: [Retracted] deep neural networks for medical image segmentation. J. Healthcare Eng. 2022(1), 9580991 (2022)","journal-title":"J. Healthcare Eng."},{"key":"5_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.106791","volume":"157","author":"ON Manzari","year":"2023","unstructured":"Manzari, O.N., Ahmadabadi, H., Kashiani, H., Shokouhi, S.B., Ayatollahi, A.: MedViT: a robust vision transformer for generalized medical image classification. Comput. Biol. Med. 157, 106791 (2023)","journal-title":"Comput. Biol. Med."},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., Ahmadi, S.A.: V-Net: fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D Vision (3DV), pp. 565\u2013571. IEEE (2016)","DOI":"10.1109\/3DV.2016.79"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Myronenko, A.: 3D MRI brain tumor segmentation using autoencoder regularization. In: Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries: 4th International Workshop, BrainLes 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, 16 September 2018, Revised Selected Papers, Part II 4, pp. 311\u2013320. Springer (2019)","DOI":"10.1007\/978-3-030-11726-9_28"},{"issue":"1","key":"5_CR21","doi-asserted-by":"publisher","first-page":"6876","DOI":"10.1038\/s41598-021-86022-7","volume":"11","author":"K Nael","year":"2021","unstructured":"Nael, K., et al.: Automated detection of critical findings in multi-parametric brain MRI using a system of 3D neural networks. Sci. Rep. 11(1), 6876 (2021)","journal-title":"Sci. Rep."},{"key":"5_CR22","unstructured":"Oquab, M., et\u00a0al.: DINOv2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"5_CR23","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 \u2014 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"},{"issue":"2","key":"5_CR24","first-page":"63","volume":"36","author":"HR Roth","year":"2018","unstructured":"Roth, H.R., et al.: Deep learning and its application to medical image segmentation. Med. Imaging Technol. 36(2), 63\u201371 (2018)","journal-title":"Med. Imaging Technol."},{"key":"5_CR25","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":"5_CR26","unstructured":"Vaswani, A.: Attention is all you need. In: Advances in Neural Information Processing Systems (2017)"},{"key":"5_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1007\/978-3-030-87199-4_12","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"H Yang","year":"2021","unstructured":"Yang, H., Sun, J., Yang, L., Xu, Z.: A unified hyper-GAN model for unpaired multi-contrast MR image translation. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12903, pp. 127\u2013137. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87199-4_12"},{"key":"5_CR28","unstructured":"Zhang, H., et al.: DINO: DETR with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605 (2022)"},{"key":"5_CR29","doi-asserted-by":"crossref","unstructured":"Zhou, L., Liu, H., Bae, J., He, J., Samaras, D., Prasanna, P.: Self pre-training with masked autoencoders for medical image classification and segmentation. In: 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), pp.\u00a01\u20136. IEEE (2023)","DOI":"10.1109\/ISBI53787.2023.10230477"}],"container-title":["Lecture Notes in Computer Science","Machine Learning in Medical Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-09513-8_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T02:15:00Z","timestamp":1767320100000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-09513-8_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032095121","9783032095138"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-09513-8_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MLMI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Machine Learning in Medical Imaging","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mlmi-med2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/sites.google.com\/view\/mlmi2025\/home","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}