{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:51:21Z","timestamp":1767340281997,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":41,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819609000"},{"type":"electronic","value":"9789819609017"}],"license":[{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-0901-7_12","type":"book-chapter","created":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T07:55:50Z","timestamp":1733558150000},"page":"191-208","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["TexDC: Text-Driven Disease-Aware 4D Cardiac Cine MRI Images Generation"],"prefix":"10.1007","author":[{"given":"Cong","family":"Liu","sequence":"first","affiliation":[]},{"given":"Xiaohan","family":"Yuan","sequence":"additional","affiliation":[]},{"given":"ZhiPeng","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Yangang","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,8]]},"reference":[{"key":"12_CR1","unstructured":"Second annual data science bowl. https:\/\/kaggle.com\/competitions\/second-annual-data-science-bowl"},{"issue":"11","key":"12_CR2","doi-asserted-by":"publisher","first-page":"2514","DOI":"10.1109\/TMI.2018.2837502","volume":"37","author":"O Bernard","year":"2018","unstructured":"Bernard, O., Lalande, A., Zotti, C., Cervenansky, F., Yang, X., Heng, P.A., Cetin, I., Lekadir, K., Camara, O., Ballester, M.A.G., et al.: Deep learning techniques for automatic mri cardiac multi-structures segmentation and diagnosis: is the problem solved? IEEE Trans. Med. Imaging 37(11), 2514\u20132525 (2018)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Blattmann, A., Rombach, R., Ling, H., Dockhorn, T., Kim, S.W., Fidler, S., Kreis, K.: Align your latents: High-resolution video synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 22563\u201322575 (2023)","DOI":"10.1109\/CVPR52729.2023.02161"},{"issue":"12","key":"12_CR4","doi-asserted-by":"publisher","first-page":"3543","DOI":"10.1109\/TMI.2021.3090082","volume":"40","author":"VM Campello","year":"2021","unstructured":"Campello, V.M., Gkontra, P., Izquierdo, C., Martin-Isla, C., Sojoudi, A., Full, P.M., Maier-Hein, K., Zhang, Y., He, Z., Ma, J., et al.: Multi-centre, multi-vendor and multi-disease cardiac segmentation: the m &ms challenge. IEEE Trans. Med. Imaging 40(12), 3543\u20133554 (2021)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"12_CR5","unstructured":"Chambon, P., Bluethgen, C., Delbrouck, J.B., Van\u00a0der Sluijs, R., Po\u0142acin, M., Chaves, J.M.Z., Abraham, T.M., Purohit, S., Langlotz, C.P., Chaudhari, A.: Roentgen: vision-language foundation model for chest x-ray generation. arXiv preprint arXiv:2211.12737 (2022)"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S., Wolf, L.: Generic attention-model explainability for interpreting bi-modal and encoder-decoder transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 397\u2013406 (2021)","DOI":"10.1109\/ICCV48922.2021.00045"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y.C., Li, L., Yu, L., El\u00a0Kholy, A., Ahmed, F., Gan, Z., Cheng, Y., Liu, J.: Uniter: Learning universal image-text representations (2019)","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"12_CR8","unstructured":"Dorjsembe, Z., Odonchimed, S., Xiao, F.: Three-dimensional medical image synthesis with denoising diffusion probabilistic models. In: Medical Imaging with Deep Learning (2022)"},{"key":"12_CR9","unstructured":"Hamamci, I.E., Er, S., Simsar, E., Tezcan, A., Simsek, A.G., Almas, F., Esirgun, S.N., Reynaud, H., Pati, S., Bluethgen, C., et\u00a0al.: Generatect: Text-guided 3d chest ct generation. arXiv preprint arXiv:2305.16037 (2023)"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Han, K., Xiong, Y., You, C., Khosravi, P., Sun, S., Yan, X., Duncan, J.S., Xie, X.: Medgen3d: A deep generative framework for paired 3d image and mask generation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. pp. 759\u2013769. Springer (2023)","DOI":"10.1007\/978-3-031-43907-0_72"},{"key":"12_CR11","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems 30 (2017)"},{"key":"12_CR12","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Hong, S., Marinescu, R., Dalca, A.V., Bonkhoff, A.K., Bretzner, M., Rost, N.S., Golland, P.: 3d-stylegan: A style-based generative adversarial network for generative modeling of three-dimensional medical images. In: Deep Generative Models, and Data Augmentation, Labelling, and Imperfections: First Workshop, DGM4MICCAI 2021, and First Workshop, DALI 2021, Held in Conjunction with MICCAI 2021, Strasbourg, France, October 1, 2021, Proceedings 1. pp. 24\u201334. Springer (2021)","DOI":"10.1007\/978-3-030-88210-5_3"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Huang, S.C., Shen, L., Lungren, M.P., Yeung, S.: Gloria: A multimodal global-local representation learning framework for label-efficient medical image recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 3942\u20133951 (2021)","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Jang, S.I., Lois, C., Thibault, E., Becker, J.A., Dong, Y., Normandin, M.D., Price, J.C., Johnson, K.A., Fakhri, G.E., Gong, K.: Taupetgen: Text-conditional tau pet image synthesis based on latent diffusion models. arXiv preprint arXiv:2306.11984 (2023)","DOI":"10.1109\/NSSMICRTSD49126.2023.10338710"},{"issue":"1","key":"12_CR16","doi-asserted-by":"publisher","first-page":"7303","DOI":"10.1038\/s41598-023-34341-2","volume":"13","author":"F Khader","year":"2023","unstructured":"Khader, F., M\u00fcller-Franzes, G., Tayebi Arasteh, S., Han, T., Haarburger, C., Schulze-Hagen, M., Schad, P., Engelhardt, S., Bae\u00dfler, B., Foersch, S., et al.: Denoising diffusion probabilistic models for 3d medical image generation. Sci. Rep. 13(1), 7303 (2023)","journal-title":"Sci. Rep."},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Kim, B., Ye, J.C.: Diffusion deformable model for 4d temporal medical image generation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. pp. 539\u2013548. Springer (2022)","DOI":"10.1007\/978-3-031-16431-6_51"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Kwon, G., Han, C., Kim, D.s.: Generation of 3d brain mri using auto-encoding generative adversarial networks. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. pp. 118\u2013126. Springer (2019)","DOI":"10.1007\/978-3-030-32248-9_14"},{"key":"12_CR19","unstructured":"Lee, H., Kim, W., Kim, J.H., Kim, T., Kim, J., Sunwoo, L., Choi, E.: Unified chest x-ray and radiology report generation model with multi-view chest x-rays. arXiv preprint arXiv:2302.12172 (2023)"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Y., Dwivedi, G., Boussaid, F., Sanfilippo, F., Yamada, M., Bennamoun, M.: Inflating 2d convolution weights for efficient generation of 3d medical images. Computer Methods and Programs in Biomedicine p. 107685 (2023)","DOI":"10.1016\/j.cmpb.2023.107685"},{"issue":"11","key":"12_CR21","first-page":"2579","volume":"9","author":"L Van der Maaten","year":"2008","unstructured":"Van der Maaten, L., Hinton, G.: Visualizing data using t-sne. J. Mach. Learn. Res. 9(11), 2579\u20132605 (2008)","journal-title":"J. Mach. Learn. Res."},{"key":"12_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13244-019-0754-2","volume":"10","author":"RM Mench\u00f3n-Lara","year":"2019","unstructured":"Mench\u00f3n-Lara, R.M., Simmross-Wattenberg, F., Casaseca-de-la Higuera, P., Mart\u00edn-Fern\u00e1ndez, M., Alberola-L\u00f3pez, C.: Reconstruction techniques for cardiac cine mri. Insights Imaging 10, 1\u201316 (2019)","journal-title":"Insights Imaging"},{"key":"12_CR23","unstructured":"M\u00fcller-Franzes, G., Niehues, J.M., Khader, F., Arasteh, S.T., Haarburger, C., Kuhl, C., Wang, T., Han, T., Nebelung, S., Kather, J.N., et\u00a0al.: Diffusion probabilistic models beat gans on medical images. arXiv preprint arXiv:2212.07501 (2022)"},{"key":"12_CR24","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Peng, W., Adeli, E., Bosschieter, T., Park, S.H., Zhao, Q., Pohl, K.M.: Generating realistic brain mris via a conditional diffusion probabilistic model. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. pp. 14\u201324. Springer (2023)","DOI":"10.1007\/978-3-031-43993-3_2"},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Peng, W., Adeli, E., Zhao, Q., Pohl, K.M.: Generating realistic 3d brain mris using a conditional diffusion probabilistic model. arXiv preprint arXiv:2212.08034 (2022)","DOI":"10.1007\/978-3-031-43993-3_2"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Pinaya, W.H., Tudosiu, P.D., Dafflon, J., Da\u00a0Costa, P.F., Fernandez, V., Nachev, P., Ourselin, S., Cardoso, M.J.: Brain imaging generation with latent diffusion models. In: MICCAI Workshop on Deep Generative Models. pp. 117\u2013126. Springer (2022)","DOI":"10.1007\/978-3-031-18576-2_12"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"issue":"8","key":"12_CR29","doi-asserted-by":"publisher","first-page":"3966","DOI":"10.1109\/JBHI.2022.3172976","volume":"26","author":"L Sun","year":"2022","unstructured":"Sun, L., Chen, J., Xu, Y., Gong, M., Yu, K., Batmanghelich, K.: Hierarchical amortized gan for 3d high resolution medical image synthesis. IEEE J. Biomed. Health Inform. 26(8), 3966\u20133975 (2022)","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"12_CR30","unstructured":"Unterthiner, T., Van\u00a0Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., Gelly, S.: Towards accurate generative models of video: A new metric & challenges. arXiv preprint arXiv:1812.01717 (2018)"},{"key":"12_CR31","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Advances in neural information processing systems 30 (2017)"},{"key":"12_CR32","first-page":"33536","volume":"35","author":"F Wang","year":"2022","unstructured":"Wang, F., Zhou, Y., Wang, S., Vardhanabhuti, V., Yu, L.: Multi-granularity cross-modal alignment for generalized medical visual representation learning. Adv. Neural. Inf. Process. Syst. 35, 33536\u201333549 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"12_CR33","unstructured":"Wu, C., Huang, L., Zhang, Q., Li, B., Ji, L., Yang, F., Sapiro, G., Duan, N.: Godiva: Generating open-domain videos from natural descriptions. arXiv preprint arXiv:2104.14806 (2021)"},{"key":"12_CR34","unstructured":"Xing, S., Sinha, H., Hwang, S.J.: Cycle consistent embedding of 3d brains with auto-encoding generative adversarial networks. In: Medical Imaging with Deep Learning (2021)"},{"key":"12_CR35","doi-asserted-by":"crossref","unstructured":"Xu, Y., Sun, L., Peng, W., Visweswaran, S., Batmanghelich, K.: Medsyn: Text-guided anatomy-aware synthesis of high-fidelity 3d ct images. arXiv preprint arXiv:2310.03559 (2023)","DOI":"10.1109\/TMI.2024.3415032"},{"key":"12_CR36","doi-asserted-by":"crossref","unstructured":"Yoon, J.S., Zhang, C., Suk, H.I., Guo, J., Li, X.: Sadm: Sequence-aware diffusion model for longitudinal medical image generation. In: International Conference on Information Processing in Medical Imaging. pp. 388\u2013400. Springer (2023)","DOI":"10.1007\/978-3-031-34048-2_30"},{"key":"12_CR37","unstructured":"\u017belaszczyk, M., Ma\u0144dziuk, J.: Text-to-image cross-modal generation: A systematic review. arXiv preprint arXiv:2401.11631 (2024)"},{"issue":"2","key":"12_CR38","doi-asserted-by":"publisher","first-page":"905","DOI":"10.3390\/tomography8020073","volume":"8","author":"K Zhang","year":"2022","unstructured":"Zhang, K., Hu, H., Philbrick, K., Conte, G.M., Sobek, J.D., Rouzrokh, P., Erickson, B.J.: Soup-gan: Super-resolution mri using generative adversarial networks. Tomography 8(2), 905\u2013919 (2022)","journal-title":"Tomography"},{"key":"12_CR39","unstructured":"Zhang, S., Xu, Y., Usuyama, N., Bagga, J., Tinn, R., Preston, S., Rao, R., Wei, M., Valluri, N., Wong, C., et\u00a0al.: Large-scale domain-specific pretraining for biomedical vision-language processing. arXiv preprint arXiv:2303.00915 (2023)"},{"issue":"9","key":"12_CR40","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. Int. J. Comput. Vision 130(9), 2337\u20132348 (2022)","journal-title":"Int. J. Comput. Vision"},{"key":"12_CR41","doi-asserted-by":"crossref","unstructured":"Zhu, L., Xue, Z., Jin, Z., Liu, X., He, J., Liu, Z., Yu, L.: Make-a-volume: Leveraging latent diffusion models for cross-modality 3d brain mri synthesis. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. pp. 592\u2013601. Springer (2023)","DOI":"10.1007\/978-3-031-43999-5_56"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0901-7_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T08:09:04Z","timestamp":1733558944000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0901-7_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,8]]},"ISBN":["9789819609000","9789819609017"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0901-7_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,8]]},"assertion":[{"value":"8 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}