{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T06:53:33Z","timestamp":1758351213360,"version":"3.44.0"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032051400"},{"type":"electronic","value":"9783032051417"}],"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\/978-3-032-05141-7_60","type":"book-chapter","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:16:58Z","timestamp":1758269818000},"page":"624-633","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["VAP-Diffusion: Enriching Descriptions with\u00a0MLLMs for\u00a0Enhanced Medical Image Generation"],"prefix":"10.1007","author":[{"given":"Peng","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junhu","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bowen","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeju","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanyuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,20]]},"reference":[{"key":"60_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.103046","volume":"92","author":"S Dayarathna","year":"2024","unstructured":"Dayarathna, S., Islam, K.T., Uribe, S., Yang, G., Hayat, M., Chen, Z.: Deep learning based synthesis of MRI, CT and PET: review and analysis. Med. Image Anal. 92, 103046 (2024)","journal-title":"Med. Image Anal."},{"issue":"11","key":"60_CR2","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., et al.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020)","journal-title":"Commun. ACM"},{"key":"60_CR3","unstructured":"Mirza, M.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)"},{"key":"60_CR4","doi-asserted-by":"crossref","unstructured":"Han, T., et al.: Breaking medical data sharing boundaries by using synthesized radiographs. Sci. Adv. 6(49), eabb7973 (2020)","DOI":"10.1126\/sciadv.abb7973"},{"key":"60_CR5","doi-asserted-by":"crossref","unstructured":"\u00d6zbey, M., et al.: Unsupervised medical image translation with adversarial diffusion models. TMI (2023)","DOI":"10.1109\/TMI.2023.3290149"},{"key":"60_CR6","unstructured":"Ktena, I., et al.: Generative models improve fairness of medical classifiers under distribution shifts. Nat. Med. 1\u20138 (2024)"},{"issue":"1","key":"60_CR7","doi-asserted-by":"publisher","first-page":"12098","DOI":"10.1038\/s41598-023-39278-0","volume":"13","author":"G M\u00fcller-Franzes","year":"2023","unstructured":"M\u00fcller-Franzes, G., et al.: A multimodal comparison of latent denoising diffusion probabilistic models and generative adversarial networks for medical image synthesis. Sci. Rep. 13(1), 12098 (2023)","journal-title":"Sci. Rep."},{"key":"60_CR8","doi-asserted-by":"crossref","unstructured":"Huang, P., et al.: Chest-diffusion: a light-weight text-to-image model for report-to-CXR generation. In: ISBI, pp. 1\u20135 (2024)","DOI":"10.1109\/ISBI56570.2024.10635417"},{"key":"60_CR9","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS, vol. 33, pp. 6840\u20136851 (2020)"},{"key":"60_CR10","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"60_CR11","doi-asserted-by":"crossref","unstructured":"Han, K., et al.: Medgen3D: a deep generative framework for paired 3D image and mask generation. In: MICCAI, pp. 759\u2013769 (2023)","DOI":"10.1007\/978-3-031-43907-0_72"},{"key":"60_CR12","doi-asserted-by":"crossref","unstructured":"Khader, F., et al.: Medical diffusion: denoising diffusion probabilistic models for 3D medical image generation. arXiv preprint arXiv:2211.03364 (2022)","DOI":"10.1038\/s41598-023-34341-2"},{"key":"60_CR13","unstructured":"Bluethgen, C., et al.: A vision\u2013language foundation model for the generation of realistic chest X-ray images. Nat. Biomed. Eng. 1\u201313 (2024)"},{"key":"60_CR14","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICML, pp. 12888\u201312900 (2022)"},{"key":"60_CR15","doi-asserted-by":"crossref","unstructured":"Chen, B., et al.: SpatialVLM: endowing vision-language models with spatial reasoning capabilities. In: CVPR, pp. 14455\u201314465 (2024)","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"60_CR16","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. In: NeurIPS, vol. 35, pp. 24824\u201324837 (2022)"},{"key":"60_CR17","unstructured":"Zhang, S., et al.: BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs. arXiv preprint arXiv:2303.00915 (2023)"},{"key":"60_CR18","unstructured":"Codella, N., et al.: Skin lesion analysis toward melanoma detection 2018: a challenge hosted by the International Skin Imaging Collaboration (ISIC). arXiv preprint arXiv:1902.03368 (2019)"},{"key":"60_CR19","unstructured":"Combalia, M., et al.: BCN20000: dermoscopic lesions in the wild. arXiv preprint arXiv:1908.02288 (2019)"},{"key":"60_CR20","doi-asserted-by":"crossref","unstructured":"Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., Summers, R.M.: ChestX-ray8: hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In: CVPR, pp. 2097\u20132106 (2017)","DOI":"10.1109\/CVPR.2017.369"},{"issue":"8","key":"60_CR21","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0255809","volume":"16","author":"K Li","year":"2021","unstructured":"Li, K., et al.: Colonoscopy polyp detection and classification: dataset creation and comparative evaluations. PLoS ONE 16(8), e0255809 (2021)","journal-title":"PLoS ONE"},{"issue":"4","key":"60_CR22","doi-asserted-by":"publisher","first-page":"960","DOI":"10.1016\/j.gie.2020.07.060","volume":"93","author":"M Misawa","year":"2021","unstructured":"Misawa, M., et al.: Development of a computer-aided detection system for colonoscopy and a publicly accessible large colonoscopy video database (with video). Gastrointest. Endosc. 93(4), 960\u2013967 (2021)","journal-title":"Gastrointest. Endosc."},{"issue":"9","key":"60_CR23","doi-asserted-by":"publisher","first-page":"2051","DOI":"10.1109\/TMI.2016.2547947","volume":"35","author":"P Mesejo","year":"2016","unstructured":"Mesejo, P., et al.: Computer-aided classification of gastrointestinal lesions in regular colonoscopy. IEEE Trans. Med. Imaging (TMI) 35(9), 2051\u20132063 (2016)","journal-title":"IEEE Trans. Med. Imaging (TMI)"},{"key":"60_CR24","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: NeurIPS, vol. 30 (2017)"},{"key":"60_CR25","unstructured":"Sajjadi, M.S.M., Bachem, O., Lucic, M., Bousquet, O., Gelly, S.: Assessing generative models via precision and recall. In: NeurIPS, vol. 31 (2018)"},{"key":"60_CR26","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: NeurIPS, vol. 29 (2016)"},{"key":"60_CR27","unstructured":"Karras, T., et al.: Alias-free generative adversarial networks. In: NeurIPS, vol. 34, pp. 852\u2013863 (2021)"},{"key":"60_CR28","doi-asserted-by":"crossref","unstructured":"Qin, Y., Zheng, H., Yao, J., Zhou, M., Zhang, Y.: Class-balancing diffusion models. In: CVPR, pp. 18434\u201318443 (2023)","DOI":"10.1109\/CVPR52729.2023.01768"},{"key":"60_CR29","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: CVPR, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"60_CR30","doi-asserted-by":"crossref","unstructured":"Bao, F., et al.: All are worth words: a ViT backbone for diffusion models. In: CVPR, pp. 22669\u201322679 (2023)","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"60_CR31","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: CVPR, pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"60_CR32","doi-asserted-by":"crossref","unstructured":"Tu, Z., et al.: MaxViT: multi-axis vision transformer. In: ECCV, pp. 459\u2013479 (2022)","DOI":"10.1007\/978-3-031-20053-3_27"}],"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\/978-3-032-05141-7_60","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:17:29Z","timestamp":1758269849000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-05141-7_60"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,20]]},"ISBN":["9783032051400","9783032051417"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-05141-7_60","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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"}}]}}