{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:10:36Z","timestamp":1772907036349,"version":"3.50.1"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032049360","type":"print"},{"value":"9783032049377","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T00:00:00Z","timestamp":1758326400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T00:00:00Z","timestamp":1758326400000},"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\/978-3-032-04937-7_3","type":"book-chapter","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T05:40:09Z","timestamp":1758260409000},"page":"24-34","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Autoregressive Medical Image Segmentation via\u00a0Next-Scale Mask Prediction"],"prefix":"10.1007","author":[{"given":"Tao","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenhui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0604-3197","authenticated-orcid":false,"given":"Hongming","family":"Shan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,20]]},"reference":[{"key":"3_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106919","volume":"100","author":"H Aghapanah","year":"2025","unstructured":"Aghapanah, H., Rasti, R., Tabesh, F., Pouraliakbar, H., Sanei, H., Kermani, S.: MECardNet: a novel multi-scale convolutional ensemble model with adaptive deep supervision for precise cardiac MRI segmentation. Biomed. Signal Process. Control 100, 106919 (2025)","journal-title":"Biomed. Signal Process. Control"},{"key":"3_CR2","unstructured":"Amit, T., Shaharbany, T., Nachmani, E., Wolf, L.: SegDiff: image segmentation with diffusion probabilistic models. arXiv:2112.00390 (2021)"},{"key":"3_CR3","unstructured":"Baid, U., et\u00a0al.: The RSNA-ASNR-MICCAI BraTS 2021 benchmark on brain tumor segmentation and radiogenomic classification. arXiv:2107.02314 (2021)"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Cao, H., et\u00a0al.: Swin-Unet: Unet-like pure transformer for medical image segmentation. In: ECCV, pp. 205\u2013218 (2022)","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"3_CR5","unstructured":"Chen, J., et al.: TransUNet: transformers make strong encoders for medical image segmentation. arXiv:2102.04306 (2021)"},{"issue":"10","key":"3_CR6","doi-asserted-by":"publisher","first-page":"3570","DOI":"10.1109\/TMI.2024.3424471","volume":"43","author":"T Chen","year":"2024","unstructured":"Chen, T., Wang, C., Chen, Z., Lei, Y., Shan, H.: HiDiff: hybrid diffusion framework for medical image segmentation. IEEE Trans. Med. Imaging 43(10), 3570\u20133583 (2024)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Chen, T., Wang, C., Shan, H.: BerDiff: conditional bernoulli diffusion model for medical image segmentation. In: MICCAI (2023)","DOI":"10.1007\/978-3-031-43901-8_47"},{"issue":"6","key":"3_CR8","doi-asserted-by":"publisher","first-page":"1045","DOI":"10.1007\/s10278-013-9622-7","volume":"26","author":"K Clark","year":"2013","unstructured":"Clark, K., et al.: The cancer imaging archive (TCIA): maintaining and operating a public information repository. J. Digit. Imaging 26(6), 1045\u20131057 (2013)","journal-title":"J. Digit. Imaging"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: CVPR, pp. 12873\u201312883 (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"3_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2020.100297","volume":"18","author":"IRI Haque","year":"2020","unstructured":"Haque, I.R.I., Neubert, J.: Deep learning approaches to biomedical image segmentation. Inf. Med. Unlock. 18, 100297 (2020)","journal-title":"Inf. Med. Unlock."},{"issue":"2","key":"3_CR11","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":"3_CR12","doi-asserted-by":"crossref","unstructured":"Ji, W., et al.: Learning calibrated medical image segmentation via multi-rater agreement modeling. In: CVPR, pp. 12336\u201312346 (2021)","DOI":"10.1109\/CVPR46437.2021.01216"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: CVPR, pp. 4401\u20134410 (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Kassapis, E., Dikov, G., Gupta, D.K., Nugteren, C.: Calibrated adversarial refinement for stochastic semantic segmentation. In: ICCV, pp. 7037\u20137047 (2020)","DOI":"10.1109\/ICCV48922.2021.00697"},{"issue":"2","key":"3_CR15","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1109\/TAC.1980.1102314","volume":"25","author":"V Klema","year":"1980","unstructured":"Klema, V., Laub, A.: The singular value decomposition: its computation and some applications. IEEE Trans. Autom. Control 25(2), 164\u2013176 (1980)","journal-title":"IEEE Trans. Autom. Control"},{"key":"3_CR16","unstructured":"Kohl, S., et al.: A probabilistic U-Net for segmentation of ambiguous images. In: NIPS (2018)"},{"key":"3_CR17","unstructured":"Kohl, S.A., et al.: A hierarchical probabilistic U-Net for modeling multi-scale ambiguities. In: Medical Workshop of NIPS (2019)"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Lee, D., Kim, C., Kim, S., Cho, M., Han, W.S.: Autoregressive image generation using residual quantization. In: CVPR, pp. 11523\u201311532 (2022)","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"3_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.103028","volume":"92","author":"Z Liao","year":"2024","unstructured":"Liao, Z., Hu, S., Xie, Y., Xia, Y.: Modeling annotator preference and stochastic annotation error for medical image segmentation. Med. Image Anal. 92, 103028 (2024)","journal-title":"Med. Image Anal."},{"key":"3_CR20","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2017)"},{"key":"3_CR21","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","volume":"15","author":"J Ma","year":"2024","unstructured":"Ma, J., He, Y., Li, F., Han, L., You, C., Wang, B.: Segment anything in medical images. Nat. Commun. 15, 654 (2024)","journal-title":"Nat. Commun."},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., Ahmadi, S.A.: V-net: fully convolutional neural networks for volumetric medical image segmentation. In: 3DV, pp. 565\u2013571 (2016)","DOI":"10.1109\/3DV.2016.79"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Mostafijur\u00a0Rahman, M., Marculescu, R.: Multi-scale hierarchical vision transformer with cascaded attention decoding for medical image segmentation. In: MIDL (2023)","DOI":"10.1109\/WACV56688.2023.00616"},{"key":"3_CR24","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., et\u00a0al.: PyTorch: an imperative style, high-performance deep learning library. In: NIPS (2019)"},{"key":"3_CR25","unstructured":"Radford, A., Narasimhan, K.: Improving language understanding by generative pre-training (2018). https:\/\/api.semanticscholar.org\/CorpusID:49313245"},{"key":"3_CR26","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":"3_CR27","unstructured":"Tian, K., Jiang, Y., Yuan, Z., Peng, B., Wang, L.: Visual autoregressive modeling: scalable image generation via next-scale prediction. In: NIPS (2024)"},{"key":"3_CR28","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)"},{"key":"3_CR29","unstructured":"Wu, J., et al.: MedSegDiff: medical image segmentation with diffusion probabilistic model. In: MIDL, pp. 1623\u20131639 (2024)"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Wu, Y., et al.: Diversified and personalized multi-rater medical image segmentation. In: CVPR, pp. 11470\u201311479 (2024)","DOI":"10.1109\/CVPR52733.2024.01090"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, W., Zhang, X., Huang, S., Lu, Y., Wang, K.: PixelSeg: pixel-by-pixel stochastic semantic segmentation for ambiguous medical images. In: ACM MM, pp. 4742\u20134750 (2022)","DOI":"10.1145\/3503161.3548060"},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Chung, A.C.: Deep supervision with additional labels for retinal vessel segmentation task. In: MICCAI, pp. 83\u201391 (2018)","DOI":"10.1007\/978-3-030-00934-2_10"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04937-7_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T05:40:20Z","timestamp":1758260420000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04937-7_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,20]]},"ISBN":["9783032049360","9783032049377"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04937-7_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,20]]},"assertion":[{"value":"20 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"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":"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":"27 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}