{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T04:12:22Z","timestamp":1727928742662},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031723834","type":"print"},{"value":"9783031723841","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-72384-1_6","type":"book-chapter","created":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T11:02:53Z","timestamp":1727866973000},"page":"56-66","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Advancing Text-Driven Chest X-Ray Generation with\u00a0Policy-Based Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Woojung","family":"Han","sequence":"first","affiliation":[]},{"given":"Chanyoung","family":"Kim","sequence":"additional","affiliation":[]},{"given":"Dayun","family":"Ju","sequence":"additional","affiliation":[]},{"given":"Yumin","family":"Shim","sequence":"additional","affiliation":[]},{"given":"Seong Jae","family":"Hwang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,3]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Alsentzer, E., Murphy, J., Boag, W., Weng, W.H., Jin, D., Naumann, T., McDermott, M.: Publicly available clinical BERT embeddings. In: Proceedings of the 2nd Clinical Natural Language Processing Workshop. pp. 72\u201378. Association for Computational Linguistics, Minneapolis, Minnesota, USA (Jun 2019)","DOI":"10.18653\/v1\/W19-1909"},{"key":"6_CR2","unstructured":"Black, K., Janner, M., Du, Y., Kostrikov, I., Levine, S.: Training diffusion models with reinforcement learning. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"6_CR3","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":"6_CR4","unstructured":"Cohen, J.P., Viviano, J.D., Bertin, P., Morrison, P., Torabian, P., Guarrera, M., Lungren, M.P., Chaudhari, A., Brooks, R., Hashir, M., et\u00a0al.: Torchxrayvision: A library of chest x-ray datasets and models. In: International Conference on Medical Imaging with Deep Learning. pp. 231\u2013249. PMLR (2022)"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Du, Y., Jiang, Y., Tan, S., Wu, X., Dou, Q., Li, Z., Li, G., Wan, X.: Arsdm: colonoscopy images synthesis with adaptive refinement semantic diffusion models. In: International conference on medical image computing and computer-assisted intervention. pp. 339\u2013349. Springer (2023)","DOI":"10.1007\/978-3-031-43895-0_32"},{"key":"6_CR6","unstructured":"Fan, Y., Watkins, O., Du, Y., Liu, H., Ryu, M., Boutilier, C., Abbeel, P., Ghavamzadeh, M., Lee, K., Lee, K.: Reinforcement learning for fine-tuning text-to-image diffusion models. In: Thirty-seventh Conference on Neural Information Processing Systems (2023)"},{"key":"6_CR7","unstructured":"Hao, Y., Chi, Z., Dong, L., Wei, F.: Optimizing prompts for text-to-image generation. In: Thirty-seventh Conference on Neural Information Processing Systems (2023)"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"6_CR9","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Advances in neural information processing systems 33, 6840\u20136851 (2020)","journal-title":"Advances in neural information processing systems"},{"key":"6_CR10","unstructured":"Hu, E.J., yelong shen, Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., Chen, W.: LoRA: Low-rank adaptation of large language models. In: International Conference on Learning Representations (2022)"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der\u00a0Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Jiang, L., Mao, Y., Wang, X., Chen, X., Li, C.: Cola-diff: Conditional latent diffusion model for multi-modal mri synthesis. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. pp. 398\u2013408. Springer (2023)","DOI":"10.1007\/978-3-031-43999-5_38"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Johnson, A.E., Pollard, T.J., Greenbaum, N.R., Lungren, M.P., Deng, C.y., Peng, Y., Lu, Z., Mark, R.G., Berkowitz, S.J., Horng, S.: Mimic-cxr-jpg, a large publicly available database of labeled chest radiographs. arXiv preprint arXiv:1901.07042 (2019)","DOI":"10.1038\/s41597-019-0322-0"},{"key":"6_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102846","volume":"88","author":"A Kazerouni","year":"2023","unstructured":"Kazerouni, A., Aghdam, E.K., Heidari, M., Azad, R., Fayyaz, M., Ilker: Diffusion models in medical imaging: A comprehensive survey. Medical Image Analysis 88, 102846 (2023)","journal-title":"Medical Image Analysis"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Ke, J., Ye, K., Yu, J., Wu, Y., Milanfar, P., Yang, F.: Vila: Learning image aesthetics from user comments with vision-language pretraining. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10041\u201310051 (2023)","DOI":"10.1109\/CVPR52729.2023.00968"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Khader, F., Mueller-Franzes, G., Arasteh, S.T., Han, T., Haarburger, C., Schulze-Hagen, M., Schad, P., Engelhardt, S., Baessler, B., Foersch, S., et\u00a0al.: Medical diffusion\u2013denoising diffusion probabilistic models for 3d medical image generation. arXiv preprint arXiv:2211.03364 (2022)","DOI":"10.1038\/s41598-023-34341-2"},{"key":"6_CR17","unstructured":"Kirstain, Y., Polyak, A., Singer, U., Matiana, S., Penna, J., Levy, O.: Pick-a-pic: An open dataset of user preferences for text-to-image generation. In: Thirty-seventh Conference on Neural Information Processing Systems (2023)"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Lee, S.H., Li, Y., Ke, J., Yoo, I., Zhang, H., Yu, J., Wang, Q., Deng, F., Entis, G., He, J., et\u00a0al.: Parrot: Pareto-optimal multi-reward reinforcement learning framework for text-to-image generation. In: European Conference on Computer Vision. Springer (2024)","DOI":"10.1007\/978-3-031-72920-1_26"},{"key":"6_CR19","unstructured":"Lee, S., Kim, W.J., Chang, J., Ye, J.C.: LLM-CXR: Instruction-finetuned LLM for CXR image understanding and generation. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Lester, B., Al-Rfou, R., Constant, N.: The power of scale for parameter-efficient prompt tuning. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. pp. 3045\u20133059. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic (Nov 2021)","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Liu, J., Zhao, G., Fei, Y., Zhang, M., Wang, Y., Yu, Y.: Align, attend and locate: Chest x-ray diagnosis via contrast induced attention network with limited supervision. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (October 2019)","DOI":"10.1109\/ICCV.2019.01073"},{"issue":"4","key":"6_CR22","doi-asserted-by":"publisher","first-page":"805","DOI":"10.1002\/jmri.23718","volume":"36","author":"HL Margaret Cheng","year":"2012","unstructured":"Margaret\u00a0Cheng, H.L., Stikov, N., Ghugre, N.R., Wright, G.A.: Practical medical applications of quantitative mr relaxometry. Journal of Magnetic Resonance Imaging 36(4), 805\u2013824 (2012)","journal-title":"Journal of Magnetic Resonance Imaging"},{"issue":"2","key":"6_CR23","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1016\/j.cognition.2011.10.005","volume":"122","author":"T Mussweiler","year":"2012","unstructured":"Mussweiler, T., Posten, A.C.: Relatively certain! comparative thinking reduces uncertainty. Cognition 122(2), 236\u2013240 (2012)","journal-title":"Cognition"},{"key":"6_CR24","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. In: International conference on medical image computing and computer-assisted intervention. Springer (2023)","DOI":"10.1007\/978-3-031-43993-3_2"},{"key":"6_CR25","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":"6_CR26","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":"6_CR27","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1016\/j.neuroimage.2017.12.059","volume":"169","author":"AF Rosen","year":"2018","unstructured":"Rosen, A.F., Roalf, D.R., Ruparel, K., Blake, J., Seelaus, K., Villa, L.P., Ciric, R., Cook, P.A., Davatzikos, C., Elliott, M.A., et\u00a0al.: Quantitative assessment of structural image quality. Neuroimage 169, 407\u2013418 (2018)","journal-title":"Neuroimage"},{"key":"6_CR28","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representations (2021)"},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"You, K., Gu, J., Ham, J., Park, B., Kim, J., Hong, E.K., Baek, W., Roh, B.: Cxr-clip: Toward large scale chest x-ray language-image pre-training. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. pp. 101\u2013111. Springer (2023)","DOI":"10.1007\/978-3-031-43895-0_10"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72384-1_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T11:13:01Z","timestamp":1727867581000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72384-1_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031723834","9783031723841"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72384-1_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"3 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests.","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":"Marrakesh","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Morocco","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":"7 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2024\/en\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}