{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T13:38:13Z","timestamp":1760189893234,"version":"3.44.0"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032049643","type":"print"},{"value":"9783032049650","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T00:00:00Z","timestamp":1758240000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T00:00:00Z","timestamp":1758240000000},"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\/978-3-032-04965-0_45","type":"book-chapter","created":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T08:07:56Z","timestamp":1758182876000},"page":"478-488","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["RL4Med-DDPO: Reinforcement Learning for\u00a0Controlled Guidance Towards Diverse Medical Image Generation Using Vision-Language Foundation Models"],"prefix":"10.1007","author":[{"given":"Parham","family":"Saremi","sequence":"first","affiliation":[]},{"given":"Amar","family":"Kumar","sequence":"additional","affiliation":[]},{"given":"Mohamed","family":"Mohamed","sequence":"additional","affiliation":[]},{"given":"Zahra","family":"TehraniNasab","sequence":"additional","affiliation":[]},{"given":"Tal","family":"Arbel","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,19]]},"reference":[{"key":"45_CR1","doi-asserted-by":"crossref","unstructured":"Bansal, H., Yin, D., et\u00a0al.: How well can text-to-image generative models understand ethical natural language interventions? arXiv preprint arXiv:2210.15230 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.88"},{"key":"45_CR2","doi-asserted-by":"crossref","unstructured":"Bissoto, A., Valle, E., Avila, S.: Debiasing skin lesion datasets and models? Not so fast. In: 2020 IEEE CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 3192\u20133201 (2020)","DOI":"10.1109\/CVPRW50498.2020.00378"},{"key":"45_CR3","unstructured":"Black, K., Janner, M., et\u00a0al.: Training diffusion models with reinforcement learning. arXiv preprint arXiv:2305.13301 (2023)"},{"key":"45_CR4","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. arXiv preprint arXiv:1809.11096 (2018)"},{"key":"45_CR5","doi-asserted-by":"crossref","unstructured":"Codella, N.C., Gutman, D., et\u00a0al.: Skin lesion analysis toward melanoma detection: a challenge at the 2017 international symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC). In: 2018 IEEE 15th international symposium on biomedical imaging (ISBI 2018), pp. 168\u2013172. IEEE (2018)","DOI":"10.1109\/ISBI.2018.8363547"},{"key":"45_CR6","unstructured":"Combalia, M., Codella, N.C., et\u00a0al.: BCN20000: dermoscopic lesions in the wild. arXiv preprint arXiv:1908.02288 (2019)"},{"issue":"42","key":"45_CR7","doi-asserted-by":"publisher","first-page":"5771","DOI":"10.1038\/onc.2017.189","volume":"36","author":"WE Damsky","year":"2017","unstructured":"Damsky, W.E., Bosenberg, M.: Melanocytic nevi and melanoma: unraveling a complex relationship. Oncogene 36(42), 5771\u20135792 (2017)","journal-title":"Oncogene"},{"key":"45_CR8","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"45_CR9","doi-asserted-by":"publisher","first-page":"S4","DOI":"10.1038\/modpathol.3800515","volume":"19","author":"DE Elder","year":"2006","unstructured":"Elder, D.E.: Precursors to melanoma and their mimics: nevi of special sites. Mod. Pathol. 19, S4\u2013S20 (2006)","journal-title":"Mod. Pathol."},{"key":"45_CR10","first-page":"79858","volume":"36","author":"Y Fan","year":"2023","unstructured":"Fan, Y., Watkins, O., et al.: DPOK: reinforcement learning for fine-tuning text-to-image diffusion models. Adv. Neural. Inf. Process. Syst. 36, 79858\u201379885 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"45_CR11","unstructured":"Favero, G.M., Saremi, P., et\u00a0al.: Conditional diffusion models are medical image classifiers that provide explainability and uncertainty for free (2025). https:\/\/arxiv.org\/abs\/2502.03687"},{"issue":"4","key":"45_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530164","volume":"41","author":"R Gal","year":"2022","unstructured":"Gal, R., Patashnik, O., et al.: StyleGAN-nada: CLIP-guided domain adaptation of image generators. ACM Trans. Graphics (TOG) 41(4), 1\u201313 (2022)","journal-title":"ACM Trans. Graphics (TOG)"},{"issue":"11","key":"45_CR13","doi-asserted-by":"publisher","first-page":"12561","DOI":"10.1007\/s10462-023-10453-z","volume":"56","author":"E Goceri","year":"2023","unstructured":"Goceri, E.: Medical image data augmentation: techniques, comparisons and interpretations. Artif. Intell. Rev. 56(11), 12561\u201312605 (2023)","journal-title":"Artif. Intell. Rev."},{"key":"45_CR14","unstructured":"Heusel, M., Ramsauer, H., et\u00a0al.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"45_CR15","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"45_CR16","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"45_CR17","unstructured":"Kakade, S., Langford, J.: Approximately optimal approximate reinforcement learning. In: Proceedings of the Nineteenth International Conference on Machine Learning, pp. 267\u2013274 (2002)"},{"issue":"4","key":"45_CR18","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":"45_CR19","doi-asserted-by":"crossref","unstructured":"Kumar, A., Fathi, N., et\u00a0al.: Debiasing counterfactuals in the presence of spurious correlations. In: Workshop on Clinical Image-Based Procedures, pp. 276\u2013286. Springer (2023)","DOI":"10.1007\/978-3-031-45249-9_27"},{"key":"45_CR20","doi-asserted-by":"crossref","unstructured":"Kumar, A., Hu, A., et\u00a0al.: Counterfactual image synthesis for discovery of personalized predictive image markers. In: MICCAI Workshop on Medical Image Assisted Blomarkers\u2019 Discovery, pp. 113\u2013124. Springer (2022)","DOI":"10.1007\/978-3-031-19660-7_11"},{"key":"45_CR21","unstructured":"Kumar, A., Kriz, A., et\u00a0al.: PRISM: high-resolution & precise counterfactual medical image generation using language-guided stable diffusion. MIDL (2025)"},{"key":"45_CR22","doi-asserted-by":"crossref","unstructured":"Miao, Z., Wang, J., et\u00a0al.: Training diffusion models towards diverse image generation with reinforcement learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10844\u201310853 (2024)","DOI":"10.1109\/CVPR52733.2024.01031"},{"key":"45_CR23","unstructured":"Pawlowski, N., Coelho de Castro, D., Glocker, B.: Deep structural causal models for tractable counterfactual inference. Adv. Neural. Inf. Process. Syst. 33, 857\u2013869 (2020)"},{"key":"45_CR24","doi-asserted-by":"crossref","unstructured":"Perera, M.V., Patel, V.M.: Analyzing bias in diffusion-based face generation models. In: 2023 IEEE International Joint Conference on Biometrics (IJCB), pp. 1\u201310. IEEE (2023)","DOI":"10.1109\/IJCB57857.2023.10449200"},{"key":"45_CR25","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., et\u00a0al.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"45_CR26","unstructured":"Schulman, J., Levine, S., et\u00a0al.: Trust region policy optimization. In: International Conference on Machine Learning, pp. 1889\u20131897. PMLR (2015)"},{"key":"45_CR27","unstructured":"Schulman, J., Wolski, F., et\u00a0al.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"issue":"7","key":"45_CR28","doi-asserted-by":"crossref","first-page":"P07019","DOI":"10.1088\/1742-5468\/2015\/07\/P07019","volume":"2015","author":"J Sohl-Dickstein","year":"2015","unstructured":"Sohl-Dickstein, J., Weiss, E.A., et al.: Deep unsupervised learning using nonequilibrium thermodynamics. J. Stat. Mech: Theory Exp. 2015(7), P07019 (2015)","journal-title":"J. Stat. Mech: Theory Exp."},{"issue":"1","key":"45_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4103\/tcmj.tcmj_158_20","volume":"34","author":"WW Sung","year":"2022","unstructured":"Sung, W.W., Chang, C.H.: Nevi, dysplastic nevi, and melanoma: molecular and immune mechanisms involving the progression. Tzu Chi Med. J. 34(1), 1\u20137 (2022)","journal-title":"Tzu Chi Med. J."},{"key":"45_CR30","unstructured":"Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114. PMLR (2019)"},{"issue":"1","key":"45_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2018.161","volume":"5","author":"P Tschandl","year":"2018","unstructured":"Tschandl, P., Rosendahl, C., Kittler, H.: The ham10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Sci. Data 5(1), 1\u20139 (2018)","journal-title":"Sci. Data"},{"key":"45_CR32","doi-asserted-by":"crossref","unstructured":"Yan, S., Yu, Z., et\u00a0al.: Towards trustable skin cancer diagnosis via rewriting model\u2019s decision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11568\u201311577 (2023)","DOI":"10.1109\/CVPR52729.2023.01113"},{"key":"45_CR33","unstructured":"Zhang, C., Tavanapong, W., et\u00a0al.: Real data augmentation for medical image classification. In: 6th Joint International Workshops, CVII-STENT 2017 and 2nd International Workshop, LABELS 2017, Held in Conjunction with MICCAI 2017, Qu\u00e9bec City, QC, Canada, 10\u201314 September 2017, Proceedings 2, pp. 67\u201376. Springer (2017)"},{"key":"45_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., et\u00a0al.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"45_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Tzeng, E., et\u00a0al.: Large-scale reinforcement learning for diffusion models. In: European Conference on Computer Vision, pp. 1\u201317. Springer (2024)","DOI":"10.1007\/978-3-031-73036-8_1"}],"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\/978-3-032-04965-0_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T22:03:57Z","timestamp":1758233037000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04965-0_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,19]]},"ISBN":["9783032049643","9783032049650"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04965-0_45","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,19]]},"assertion":[{"value":"19 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"}}]}}