{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T10:54:46Z","timestamp":1773658486517,"version":"3.50.1"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772319, 62002200, 62202268 and 61972235"],"award-info":[{"award-number":["61772319, 62002200, 62202268 and 61972235"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s13042-025-02983-5","type":"journal-article","created":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T06:19:25Z","timestamp":1770013165000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Diffusion U-Net coupled with text-attention guided block for medical image segmentation"],"prefix":"10.1007","volume":"17","author":[{"given":"Jianjun","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengming","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Duan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinjiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,2]]},"reference":[{"key":"2983_CR1","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, pp 234\u2013241. Springer","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2983_CR2","doi-asserted-by":"crossref","unstructured":"Zhou Z, Mahfuzur Rahman\u00a0Siddiquee Md, Tajbakhsh N, Liang J (2018) Unet++: a nested u-net architecture for medical image segmentation. In: Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 20, 2018, Proceedings 4, pp 3\u201311. Springer","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"2983_CR3","unstructured":"Oktay O, Schlemper J, Folgoc LL, Lee M, Heinrich M, Misawa K, Mori K, McDonagh S, Hammerla NY, Kainz B et\u00a0al (2018) Attention u-net: learning where to look for the pancreas. arXiv:1804.03999"},{"key":"2983_CR4","doi-asserted-by":"crossref","unstructured":"\u00c7i\u00e7ek, \u00d6, Abdulkadir A, Lienkamp SS, Brox T, Ronneberger O (2016) 3d u-net: learning dense volumetric segmentation from sparse annotation. In: Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2016: 19th International Conference, Athens, Greece, October 17-21, 2016, Proceedings, Part II 19, pp 424\u2013432. Springer","DOI":"10.1007\/978-3-319-46723-8_49"},{"key":"2983_CR5","doi-asserted-by":"crossref","unstructured":"Milletari F, Navab N, Ahmadi S-A (2016). V-net: fully convolutional neural networks for volumetric medical image segmentation. IEEE, pp 565\u2013571","DOI":"10.1109\/3DV.2016.79"},{"key":"2983_CR6","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"2983_CR7","doi-asserted-by":"crossref","unstructured":"Pang Y, Liang J, Huang T, Chen H, Li Y, Li D, Huang L, Wang Q (2023) Slim unetr: scale hybrid transformers to efficient 3d medical image segmentation under limited computational resources. IEEE Trans Med Imaging","DOI":"10.1109\/TMI.2023.3326188"},{"key":"2983_CR8","doi-asserted-by":"crossref","unstructured":"Jain S, Atale R, Gupta A, Mishra U, Seal A, Ojha A, Kuncewicz J, Krejcar O (2023) Coinnet: a convolution-involution network with a novel statistical attention for automatic polyp segmentation. IEEE Trans Med Imaging","DOI":"10.1109\/TMI.2023.3320151"},{"key":"2983_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105154","volume":"148","author":"B Asheghi","year":"2024","unstructured":"Asheghi B, Salehpour P, Moallemi Khiavi A, Hashemzadeh M, Monajemi A (2024) Dasod: detail-aware salient object detection. Image Vis Comput 148:105154","journal-title":"Image Vis Comput"},{"key":"2983_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2022.108496","volume":"195","author":"B Asheghi","year":"2022","unstructured":"Asheghi B, Salehpour P, Khiavi AM, Hashemzadeh M (2022) A comprehensive review on content-aware image retargeting: from classical to state-of-the-art methods. Signal Process 195:108496","journal-title":"Signal Process"},{"key":"2983_CR11","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1016\/j.sigpro.2018.09.037","volume":"155","author":"M Hashemzadeh","year":"2019","unstructured":"Hashemzadeh M, Asheghi B, Farajzadeh N (2019) Content-aware image resizing: an improved and shadow-preserving seam carving method. Signal Process 155:233\u2013246","journal-title":"Signal Process"},{"key":"2983_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102075","volume":"103","author":"S Umirzakova","year":"2024","unstructured":"Umirzakova S, Ahmad S, Khan LU, Whangbo T (2024) Medical image super-resolution for smart healthcare applications: a comprehensive survey. Inf Fusion 103:102075","journal-title":"Inf Fusion"},{"key":"2983_CR13","first-page":"29582","volume":"35","author":"C You","year":"2022","unstructured":"You C, Zhao R, Liu F, Dong S, Chinchali S, Topcu U, Staib L, Duncan J (2022) Class-aware adversarial transformers for medical image segmentation. Adv Neural Inf Process Syst 35:29582\u201329596","journal-title":"Adv Neural Inf Process Syst"},{"key":"2983_CR14","doi-asserted-by":"crossref","unstructured":"You C, Zhao R, Staib LH, Duncan JS (2022). Momentum contrastive voxel-wise representation learning for semi-supervised volumetric medical image segmentation. Springer, pp 639\u2013652","DOI":"10.1007\/978-3-031-16440-8_61"},{"issue":"9","key":"2983_CR15","doi-asserted-by":"publisher","first-page":"2228","DOI":"10.1109\/TMI.2022.3161829","volume":"41","author":"C You","year":"2022","unstructured":"You C, Zhou Y, Zhao R, Staib L, Duncan JS (2022) Simcvd: simple contrastive voxel-wise representation distillation for semi-supervised medical image segmentation. IEEE Trans Med Imaging 41(9):2228\u20132237","journal-title":"IEEE Trans Med Imaging"},{"key":"2983_CR16","doi-asserted-by":"crossref","unstructured":"You C, Yang J, Chapiro J, Duncan JS (2020) Unsupervised wasserstein distance guided domain adaptation for 3d multi-domain liver segmentation. Interpretable and Annotation-Efficient Learning for Medical Image Computing: Third International Workshop, iMIMIC 2020, Second International Workshop, MIL3ID edn. Springer, pp 155\u2013163","DOI":"10.1007\/978-3-030-61166-8_17"},{"key":"2983_CR17","doi-asserted-by":"crossref","unstructured":"You C, Dai W, Min Y, Staib L, Sekhon J, Duncan JS (2023). Action++: Improving semi-supervised medical image segmentation with adaptive anatomical contrast. Springer, pp 194\u2013205","DOI":"10.1007\/978-3-031-43901-8_19"},{"key":"2983_CR18","doi-asserted-by":"crossref","unstructured":"Yu X, Ma Q, Ling T, Zhu J, Shi Y (2024) Enhancing semi-supervised medical image segmentation with bidirectional copy-paste and masked image reconstruction. Int J Mach Learn Cybern 1\u201311","DOI":"10.1007\/s13042-024-02410-1"},{"key":"2983_CR19","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho J, Jain A, Abbeel P (2020) Denoising diffusion probabilistic models. Adv Neural Inf Process Syst 33:6840\u20136851","journal-title":"Adv Neural Inf Process Syst"},{"key":"2983_CR20","unstructured":"Nichol AQ, Dhariwal P (2021) Improved denoising diffusion probabilistic models. In: International Conference on Machine Learning, pp 8162\u20138171. PMLR"},{"key":"2983_CR21","unstructured":"Song J, Meng C, Ermon S (2020) Denoising diffusion implicit models. arXiv:2010.02502"},{"key":"2983_CR22","doi-asserted-by":"crossref","unstructured":"Gao Q, Li Z, Zhang J, Zhang J, Shan H (2023) Corediff: contextual error-modulated generalized diffusion model for low-dose ct denoising and generalization. arXiv:2304.01814","DOI":"10.1109\/TMI.2023.3320812"},{"key":"2983_CR23","doi-asserted-by":"publisher","unstructured":"Zhang F, Kevin Cho KIk, Seitz-Holland J, Ning L, Legarreta JH, Rathi Y, Westin C-F, O\u2019Donnell LJ, Pasternak O (2023) Ddparcel: deep learning anatomical brain parcellation from diffusion mri. IEEE Transactions on Medical Imaging, pages 1\u20131. https:\/\/doi.org\/10.1109\/TMI.2023.3331691","DOI":"10.1109\/TMI.2023.3331691"},{"key":"2983_CR24","unstructured":"Kohl S, Romera-Paredes B, Meyer C, De\u00a0Fauw J, Ledsam JR, Maier-Hein K, Eslami SM, Jimenez\u00a0Rezende D, Ronneberger O (2018) A probabilistic u-net for segmentation of ambiguous images. Adv Neural Inf Process Syst 31"},{"key":"2983_CR25","first-page":"12438","volume":"33","author":"Y Song","year":"2020","unstructured":"Song Y, Ermon S (2020) Improved techniques for training score-based generative models. Adv Neural Inf Process Syst 33:12438\u201312448","journal-title":"Adv Neural Inf Process Syst"},{"key":"2983_CR26","doi-asserted-by":"crossref","unstructured":"Choi J, Kim S, Jeong Y, Gwon Y, Yoon S (2021) Ilvr: conditioning method for denoising diffusion probabilistic models. arXiv:2108.02938","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"2983_CR27","doi-asserted-by":"crossref","unstructured":"Lugmayr A, Danelljan M, Romero A, Yu F, Timofte R, Van Gool L (2022) Repaint: inpainting using denoising diffusion probabilistic models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 11461\u201311471","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"2983_CR28","unstructured":"Wolleb J, Sandk\u00fchler R, Bieder F, Valmaggia P, Cattin PC (2022) Diffusion models for implicit image segmentation ensembles. pp 1336\u20131348"},{"key":"2983_CR29","unstructured":"Baranchuk D, Rubachev I, Voynov A, Khrulkov V, Babenko A (2021) Label-efficient semantic segmentation with diffusion models. arXiv:2112.03126"},{"key":"2983_CR30","unstructured":"Xing Z, Wan L, Fu H, Yang G, Zhu (2023) Diff-unet: a diffusion embedded network for volumetric segmentation. arXiv:2303.10326"},{"key":"2983_CR31","unstructured":"Wu J, Fang H, Zhang Y, Yang Y, Xu Y (2022) Medsegdiff: medical image segmentation with diffusion probabilistic model. arXiv:2211.00611"},{"key":"2983_CR32","doi-asserted-by":"crossref","unstructured":"Wu J, Fu R, Fang H, Zhang Y, Xu Y (2023) Medsegdiff-v2: diffusion based medical image segmentation with transformer. arXiv:2301.11798","DOI":"10.1609\/aaai.v38i6.28418"},{"key":"2983_CR33","unstructured":"Zhao Y, Li J, Liu Y Dynamic weight hilo attention network for medical image multiple organ segmentation. Int J Imaging Syst Technol"},{"key":"2983_CR34","doi-asserted-by":"crossref","unstructured":"Fan D-P, Ji G-P, Zhou T, Chen G, Fu H, Shen J, Shao L (2020) Pranet: parallel reverse attention network for polyp segmentation. In: International conference on medical image computing and computer-assisted intervention, pp 263\u2013273. Springer","DOI":"10.1007\/978-3-030-59725-2_26"},{"key":"2983_CR35","doi-asserted-by":"crossref","unstructured":"Wang J, Chen F, Ma Y, Wang L, Fei Z, Shuai J, Tang X, Zhou Q, Qin J (2023) Toward cross-scale boundary modeling in transformers. IEEE Trans Med Imaging Xbound-former","DOI":"10.1109\/TMI.2023.3236037"},{"key":"2983_CR36","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.106626","volume":"154","author":"X Qing","year":"2023","unstructured":"Qing X, Ma Z, Na HE, Duan W (2023) Dcsau-net: a deeper and more compact split-attention u-net for medical image segmentation. Comput Biol Med 154:106626","journal-title":"Comput Biol Med"},{"key":"2983_CR37","doi-asserted-by":"crossref","unstructured":"Tomar NK, Jha D, Bagci U, Ali S (2022) Tganet: text-guided attention for improved polyp segmentation. Springer, pp 151\u2013160","DOI":"10.1007\/978-3-031-16437-8_15"},{"key":"2983_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/JTEHM.2022.3210047","volume":"10","author":"Y Zhao","year":"2022","unstructured":"Zhao Y, Li J, Hua Z (2022) Mpsht: multiple progressive sampling hybrid model multi-organ segmentation. IEEE J Transl Eng Health Med 10:1\u20139","journal-title":"IEEE J Transl Eng Health Med"},{"key":"2983_CR39","unstructured":"Amit T, Shaharbany T, Nachmani E, Wolf L (2021) Segdiff: image segmentation with diffusion probabilistic models. arXiv:2112.00390"},{"key":"2983_CR40","unstructured":"Bandara WGC, Nair NG, Patel VM (2022) Ddpm-cd: remote sensing change detection using denoising diffusion probabilistic models. arXiv:2206.11892"},{"key":"2983_CR41","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal P, Nichol A (2021) Diffusion models beat gans on image synthesis. Adv Neural Inf Process Syst 34:8780\u20138794","journal-title":"Adv Neural Inf Process Syst"},{"key":"2983_CR42","doi-asserted-by":"crossref","unstructured":"Guo X, Yang Y, Ye C, Lu S, Peng B, Huang H, Xiang Y, Ma T (2023) Accelerating diffusion models via pre-segmentation diffusion sampling for medical image segmentation. In: 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), pp 1\u20135. IEEE","DOI":"10.1109\/ISBI53787.2023.10230524"},{"key":"2983_CR43","unstructured":"Kim B, Oh Y, Chul Ye J (2022) Diffusion adversarial representation learning for self-supervised vessel segmentation. arXiv:2209.14566"},{"key":"2983_CR44","doi-asserted-by":"crossref","unstructured":"Rahman A, Valanarasu JMJ, Hacihaliloglu I and Patel VM (2023) Ambiguous medical image segmentation using diffusion models. pp 11536\u201311546","DOI":"10.1109\/CVPR52729.2023.01110"},{"key":"2983_CR45","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. Adv Neural Inf Process Syst 30"},{"key":"2983_CR46","doi-asserted-by":"crossref","unstructured":"Sennrich R, Haddow B, Birch A (2015) Neural machine translation of rare words with subword units. arXiv:1508.07909","DOI":"10.18653\/v1\/P16-1162"},{"key":"2983_CR47","unstructured":"Xu K, Ba J, Kiros R, Cho K, Courville A, Salakhudinov R, Zemel R, Bengio Y (2015) Show, attend and tell: neural image caption generation with visual attention. In: International conference on machine learning, pp 2048\u20132057. PMLR"},{"issue":"4","key":"2983_CR48","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1177\/0272989X8300300403","volume":"3","author":"J Robert Beck","year":"1983","unstructured":"Robert Beck J, Pauker SG (1983) The Markov process in medical prognosis. Med Decis Making 3(4):419\u2013458","journal-title":"Med Decis Making"},{"key":"2983_CR49","first-page":"17981","volume":"34","author":"J Austin","year":"2021","unstructured":"Austin J, Johnson DD, Ho J, Tarlow D, Van Den Berg R (2021) Structured denoising diffusion models in discrete state-spaces. Adv Neural Inf Process Syst 34:17981\u201317993","journal-title":"Adv Neural Inf Process Syst"},{"key":"2983_CR50","doi-asserted-by":"crossref","unstructured":"Qian X, Yanwei F, Jiang Y-G, Xiang T and Xue X (2017) Multi-scale deep learning architectures for person re-identification. pp 5399\u20135408","DOI":"10.1109\/ICCV.2017.577"},{"key":"2983_CR51","doi-asserted-by":"crossref","unstructured":"Zhao H, Shi J, Qi X, Wang X, Jia J (2017) Pyramid scene parsing network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2881\u20132890","DOI":"10.1109\/CVPR.2017.660"},{"key":"2983_CR52","doi-asserted-by":"crossref","unstructured":"Jha D, Smedsrud PH, Riegler MA, Halvorsen P, de\u00a0Lange T, Johansen D, Johansen HD (2020) Kvasir-seg: a segmented polyp dataset. In: MultiMedia Modeling: 26th International Conference, MMM 2020, Daejeon, South Korea, January 5\u20138, 2020, Proceedings, Part II 26, pp 451\u2013462. Springer","DOI":"10.1007\/978-3-030-37734-2_37"},{"issue":"6","key":"2983_CR53","doi-asserted-by":"publisher","first-page":"2029","DOI":"10.1109\/JBHI.2021.3049304","volume":"25","author":"D Jha","year":"2021","unstructured":"Jha D, Smedsrud PH, Johansen D, de Lange T, Johansen HD, Halvorsen P, Riegler MA (2021) A comprehensive study on colorectal polyp segmentation with resunet++, conditional random field and test-time augmentation. IEEE J Biomed Health Inform 25(6):2029\u20132040","journal-title":"IEEE J Biomed Health Inform"},{"key":"2983_CR54","doi-asserted-by":"crossref","unstructured":"Mendon\u00e7a T, Ferreira PM, Marques JS, Marcal ARS, Rozeira J (2013) Ph 2-a dermoscopic image database for research and benchmarking. pp 5437\u20135440","DOI":"10.1109\/EMBC.2013.6610779"},{"issue":"12","key":"2983_CR55","doi-asserted-by":"publisher","first-page":"1247","DOI":"10.1038\/s41592-019-0612-7","volume":"16","author":"JC Caicedo","year":"2019","unstructured":"Caicedo JC, Goodman A, Karhohs KW, Cimini BA, Ackerman J, Haghighi M, Heng CK, Becker T, Doan M, McQuin C et al (2019) Nucleus segmentation across imaging experiments: the 2018 data science bowl. Nat Methods 16(12):1247\u20131253","journal-title":"Nat Methods"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02983-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-025-02983-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02983-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T09:55:55Z","timestamp":1773654955000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-025-02983-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":55,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["2983"],"URL":"https:\/\/doi.org\/10.1007\/s13042-025-02983-5","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"value":"1868-8071","type":"print"},{"value":"1868-808X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]},"assertion":[{"value":"15 December 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 February 2026","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 declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"74"}}