{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T16:50:58Z","timestamp":1785516658640,"version":"3.56.0"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729850","type":"print"},{"value":"9783031729867","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T00:00:00Z","timestamp":1730505600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T00:00:00Z","timestamp":1730505600000},"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\/978-3-031-72986-7_8","type":"book-chapter","created":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T05:04:16Z","timestamp":1730437456000},"page":"126-143","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":32,"title":["GenerateCT: Text-Conditional Generation of\u00a03D Chest CT Volumes"],"prefix":"10.1007","author":[{"given":"Ibrahim Ethem","family":"Hamamci","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sezgin","family":"Er","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anjany","family":"Sekuboyina","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Enis","family":"Simsar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alperen","family":"Tezcan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ayse Gulnihan","family":"Simsek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sevval Nil","family":"Esirgun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Furkan","family":"Almas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Irem","family":"Do\u011fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammed Furkan","family":"Dasdelen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chinmay","family":"Prabhakar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hadrien","family":"Reynaud","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sarthak","family":"Pati","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Bluethgen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mehmet Kemal","family":"Ozdemir","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bjoern","family":"Menze","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,2]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: Vivit: a video vision transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6836\u20136846 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"8_CR2","unstructured":"Balaji, Y., et al.: eDiff-I: text-to-image diffusion models with an ensemble of expert denoisers. arXiv preprint arXiv:2211.01324 (2022)"},{"key":"8_CR3","unstructured":"Beltagy, I., Peters, M.E., Cohan, A.: Longformer: the long-document transformer. arXiv preprint arXiv:2004.05150 (2020)"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Blattmann, A., et al.: Align your latents: high-resolution video synthesis with latent diffusion models. arXiv preprint arXiv:2304.08818 (2023)","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"8_CR5","unstructured":"Chambon, P., et al.: Roentgen: vision-language foundation model for chest x-ray generation. arXiv preprint arXiv:2211.12737 (2022)"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Chang, H., Zhang, H., Jiang, L., Liu, C., Freeman, W.T.: Maskgit: masked generative image transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11315\u201311325 (2022)","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"8_CR7","unstructured":"Chen, W., Hu, H., Saharia, C., Cohen, W.W.: Re-imagen: retrieval-augmented text-to-image generator. arXiv preprint arXiv:2209.14491 (2022)"},{"key":"8_CR8","unstructured":"Clark, A., Donahue, J., Simonyan, K.: Adversarial video generation on complex datasets. arXiv preprint arXiv:1907.06571 (2019)"},{"key":"8_CR9","unstructured":"DenOtter, T.D., Schubert, J.: Hounsfield unit (2019)"},{"key":"8_CR10","unstructured":"Ding, M., et al.: Cogview: mastering text-to-image generation via transformers. In: Advances in Neural Information Processing Systems, vol. 34, pp. 19822\u201319835 (2021)"},{"key":"8_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101857","volume":"67","author":"RL Draelos","year":"2021","unstructured":"Draelos, R.L., et al.: Machine-learning-based multiple abnormality prediction with large-scale chest computed tomography volumes. Med. Image Anal. 67, 101857 (2021)","journal-title":"Med. Image Anal."},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Gu, S., et al.: Vector quantized diffusion model for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10696\u201310706 (2022)","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"8_CR13","unstructured":"Hamamci, I.E., et al.: A foundation model utilizing chest CT volumes and radiology reports for supervised-level zero-shot detection of abnormalities. arXiv preprint arXiv:2403.17834 (2024)"},{"key":"8_CR14","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1007\/978-3-031-43987-2_38","volume-title":"MICCAI 2023","author":"IE Hamamci","year":"2023","unstructured":"Hamamci, I.E., et al.: Diffusion-based hierarchical multi-label object detection to analyze panoramic dental X-rays. In: Greenspan, H., et al. (eds.) MICCAI 2023. LNCS, vol. 14225, pp. 389\u2013399. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-43987-2_38"},{"key":"8_CR15","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. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"8_CR16","unstructured":"Ho, J., et al.: Imagen video: high definition video generation with diffusion models. arXiv preprint arXiv:2210.02303 (2022)"},{"issue":"47","key":"8_CR17","first-page":"1","volume":"23","author":"J Ho","year":"2022","unstructured":"Ho, J., Saharia, C., Chan, W., Fleet, D.J., Norouzi, M., Salimans, T.: Cascaded diffusion models for high fidelity image generation. J. Mach. Learn. Res. 23(47), 1\u201333 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"8_CR18","unstructured":"Ho, J., Salimans, T., Gritsenko, A., Chan, W., Norouzi, M., Fleet, D.J.: Video diffusion models. arXiv preprint arXiv:2204.03458 (2022)"},{"key":"8_CR19","unstructured":"Hong, W., Ding, M., Zheng, W., Liu, X., Tang, J.: Cogvideo: large-scale pretraining for text-to-video generation via transformers. arXiv preprint arXiv:2205.15868 (2022)"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Johnson, A.E., et al.: MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports. Sci. Data 6(1), 317 (2019)","DOI":"10.1038\/s41597-019-0322-0"},{"key":"8_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1007\/978-3-319-46475-6_43","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Johnson","year":"2016","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694\u2013711. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_43"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of stylegan. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8110\u20138119 (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"issue":"4","key":"8_CR23","doi-asserted-by":"publisher","first-page":"81","DOI":"10.3390\/jimaging9040081","volume":"9","author":"A Kebaili","year":"2023","unstructured":"Kebaili, A., Lapuyade-Lahorgue, J., Ruan, S.: Deep learning approaches for data augmentation in medical imaging: a review. J. Imaging 9(4), 81 (2023)","journal-title":"J. Imaging"},{"key":"8_CR24","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"issue":"5","key":"8_CR25","doi-asserted-by":"publisher","first-page":"1013","DOI":"10.2214\/AJR.12.10037","volume":"203","author":"R Lamba","year":"2014","unstructured":"Lamba, R., et al.: CT hounsfield numbers of soft tissues on unenhanced abdominal CT scans: variability between two different manufacturers\u2019 MDCT scanners. AJR Am. J. Roentgenol. 203(5), 1013 (2014)","journal-title":"AJR Am. J. Roentgenol."},{"key":"8_CR26","unstructured":"Lee, H., et al.: Unified chest X-ray and radiology report generation model with multi-view chest X-rays. arXiv preprint arXiv:2302.12172 (2023)"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Linna, N., Kahn\u00a0Jr, C.E.: Applications of natural language processing in radiology: a systematic review. Int. J. Med. Inform. 104779 (2022)","DOI":"10.1016\/j.ijmedinf.2022.104779"},{"key":"8_CR28","unstructured":"Nichol, A., et al.: Glide: towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)"},{"key":"8_CR29","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"issue":"1","key":"8_CR30","first-page":"5485","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(1), 5485\u20135551 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"8_CR31","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"8_CR32","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"},{"key":"8_CR33","doi-asserted-by":"crossref","unstructured":"Saharia, C., et al.: Palette: image-to-image diffusion models. In: ACM SIGGRAPH 2022 Conference Proceedings, pp. 1\u201310 (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"8_CR34","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. In: Advances in Neural Information Processing Systems, vol. 35, pp.36479\u201336494 (2022)"},{"key":"8_CR35","unstructured":"Unterthiner, T., van Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., Gelly, S.: FVD: a new metric for video generation (2019)"},{"key":"8_CR36","unstructured":"Van Den\u00a0Oord, A., Vinyals, O., et\u00a0al.: Neural discrete representation learning. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"8_CR37","unstructured":"Villegas, R., et al.: Phenaki: variable length video generation from open domain textual description. arXiv preprint arXiv:2210.02399 (2022)"},{"key":"8_CR38","unstructured":"Voleti, V., Jolicoeur-Martineau, A., Pal, C.: Masked conditional video diffusion for prediction, generation, and interpolation. arXiv preprint arXiv:2205.09853 (2022)"},{"key":"8_CR39","doi-asserted-by":"publisher","first-page":"2185","DOI":"10.1007\/s00330-018-5810-7","volume":"29","author":"MJ Willemink","year":"2019","unstructured":"Willemink, M.J., No\u00ebl, P.B.: The evolution of image reconstruction for CT\u2013from filtered back projection to artificial intelligence. Eur. Radiol. 29, 2185\u20132195 (2019)","journal-title":"Eur. Radiol."},{"key":"8_CR40","unstructured":"Wu, C., et al.: Godiva: generating open-domain videos from natural descriptions. arXiv preprint arXiv:2104.14806 (2021)"},{"key":"8_CR41","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"720","DOI":"10.1007\/978-3-031-19787-1_41","volume-title":"ECCV 2022","author":"C Wu","year":"2022","unstructured":"Wu, C., et al.: N\u00fcwa: visual synthesis pre-training for neural visual world creation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13676, pp. 720\u2013736. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19787-1_41"},{"key":"8_CR42","unstructured":"Yan, W., Zhang, Y., Abbeel, P., Srinivas, A.: Videogpt: video generation using VQ-VAE and transformers. arXiv preprint arXiv:2104.10157 (2021)"},{"key":"8_CR43","doi-asserted-by":"crossref","unstructured":"Yang, R., Srivastava, P., Mandt, S.: Diffusion probabilistic modeling for video generation. arXiv preprint arXiv:2203.09481 (2022)","DOI":"10.3390\/e25101469"},{"key":"8_CR44","unstructured":"Yu, J., et al.: Vector-quantized image modeling with improved VQGAN. arXiv preprint arXiv:2110.04627 (2021)"},{"key":"8_CR45","unstructured":"Yu, J., et al.: Scaling autoregressive models for content-rich text-to-image generation. arXiv preprint arXiv:2206.10789 (2022)"},{"key":"8_CR46","unstructured":"Zhang, C., Zhang, C., Zhang, M., Kweon, I.S.: Text-to-image diffusion model in generative AI: a survey. arXiv preprint arXiv:2303.07909 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72986-7_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T05:07:21Z","timestamp":1730437641000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72986-7_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,2]]},"ISBN":["9783031729850","9783031729867"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72986-7_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,2]]},"assertion":[{"value":"2 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}