{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T07:45:46Z","timestamp":1785829546519,"version":"3.56.0"},"reference-count":102,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T00:00:00Z","timestamp":1783468800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Medical Image Analysis"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.media.2026.104191","type":"journal-article","created":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:46:23Z","timestamp":1783529183000},"page":"104191","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Controllable synthesis of dermoscopic images using diffusion models for enhanced computer aided diagnosis and detection"],"prefix":"10.1016","volume":"113","author":[{"given":"Junjie","family":"Shentu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6375-3905","authenticated-orcid":false,"given":"Matthew","family":"Watson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Noura Al","family":"Moubayed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.media.2026.104191_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2020.113922","article-title":"Data augmentation for skin lesion using self-attention based progressive generative adversarial network","volume":"165","author":"Abdelhalim","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.media.2026.104191_b2","series-title":"Phi-4 Technical Report","author":"Abdin","year":"2024"},{"key":"10.1016\/j.media.2026.104191_b3","series-title":"International Workshop on Simulation and Synthesis in Medical Imaging, Lecture Notes in Computer Science, Vol. 11827","first-page":"71","article-title":"Mask2Lesion: Mask-constrained adversarial skin lesion image synthesis","author":"Abhishek","year":"2019"},{"key":"10.1016\/j.media.2026.104191_b4","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention, Lecture Notes in Computer Science, Vol. 14533","first-page":"99","article-title":"Diffusion-based data augmentation for skin disease classification: Impact across original medical datasets to fully synthetic images","author":"Akrout","year":"2023"},{"issue":"1","key":"10.1016\/j.media.2026.104191_b5","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1186\/s12859-022-04818-4","article-title":"CAD systems for COVID-19 diagnosis and disease stage classification by segmentation of infected regions from CT images","volume":"23","author":"Alshayeji","year":"2022","journal-title":"BMC Bioinformatics"},{"issue":"4","key":"10.1016\/j.media.2026.104191_b6","doi-asserted-by":"crossref","first-page":"1239","DOI":"10.1007\/s00530-021-00840-3","article-title":"Automatic segmentation of melanoma skin cancer using transfer learning and fine-tuning","volume":"28","author":"Ara\u00fajo","year":"2022","journal-title":"Multimedia Syst."},{"issue":"1","key":"10.1016\/j.media.2026.104191_b7","doi-asserted-by":"crossref","first-page":"3948","DOI":"10.1038\/s41598-022-07885-y","article-title":"Melanoma segmentation using deep learning with test-time augmentations and conditional random fields","volume":"12","author":"Ashraf","year":"2022","journal-title":"Sci. Rep."},{"issue":"9","key":"10.1016\/j.media.2026.104191_b8","doi-asserted-by":"crossref","first-page":"6713","DOI":"10.1007\/s00521-022-08053-z","article-title":"Multiclass skin lesion classification in dermoscopic images using SWIN transformer model","volume":"35","author":"Ayas","year":"2023","journal-title":"Neural Comput. Appl."},{"key":"10.1016\/j.media.2026.104191_b9","doi-asserted-by":"crossref","DOI":"10.1016\/j.displa.2022.102267","article-title":"DSB-GAN: Generation of deep learning based synthetic biometric data","volume":"74","author":"Bamoriya","year":"2022","journal-title":"Displays"},{"key":"10.1016\/j.media.2026.104191_b10","series-title":"OR 2.0 Context-Aware Operating Theaters, Computer Assisted Robotic Endoscopy, Clinical Image-Based Procedures, and Skin Image Analysis, Lecture Notes in Computer Science, Vol. 11041","first-page":"260","article-title":"Generating highly realistic images of skin lesions with GANs","author":"Baur","year":"2018"},{"key":"10.1016\/j.media.2026.104191_b11","doi-asserted-by":"crossref","DOI":"10.1016\/j.cmpb.2024.108044","article-title":"Understanding skin color bias in deep learning-based skin lesion segmentation","volume":"245","author":"Ben\u010devi\u0107","year":"2024","journal-title":"Comput. Methods Programs Biomed."},{"key":"10.1016\/j.media.2026.104191_b12","doi-asserted-by":"crossref","unstructured":"Bisla, D., Choromanska, A., Berman, R.S., Stein, J.A., Polsky, D., 2019. Towards automated melanoma detection with deep learning: Data purification and augmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops.","DOI":"10.1109\/CVPRW.2019.00330"},{"key":"10.1016\/j.media.2026.104191_b13","series-title":"OR 2.0 Context-Aware Operating Theaters, Computer Assisted Robotic Endoscopy, Clinical Image-Based Procedures, and Skin Image Analysis, Lecture Notes in Computer Science, Vol. 11041","first-page":"294","article-title":"Skin lesion synthesis with generative adversarial networks","author":"Bissoto","year":"2018"},{"issue":"4","key":"10.1016\/j.media.2026.104191_b14","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1038\/s41551-024-01246-y","article-title":"A vision\u2013language foundation model for the generation of realistic chest x-ray images","volume":"9","author":"Bluethgen","year":"2025","journal-title":"Nat. Biomed. Eng."},{"issue":"4","key":"10.1016\/j.media.2026.104191_b15","doi-asserted-by":"crossref","first-page":"4771","DOI":"10.1109\/TPAMI.2025.3646548","article-title":"Controllable generation with text-to-image diffusion models: A survey","volume":"48","author":"Cao","year":"2026","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"39","key":"10.1016\/j.media.2026.104191_b16","doi-asserted-by":"crossref","first-page":"28477","DOI":"10.1007\/s11042-020-09388-2","article-title":"A multi-class skin cancer classification using deep convolutional neural networks","volume":"79","author":"Chaturvedi","year":"2020","journal-title":"Multimedia Tools Appl."},{"issue":"4","key":"10.1016\/j.media.2026.104191_b17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3592116","article-title":"Attend-and-excite: Attention-based semantic guidance for text-to-image diffusion models","volume":"42","author":"Chefer","year":"2023","journal-title":"ACM Trans. Graph."},{"key":"10.1016\/j.media.2026.104191_b18","doi-asserted-by":"crossref","unstructured":"Chen, M., Laina, I., Vedaldi, A., 2024. Training-free layout control with cross-attention guidance. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 5343\u20135353.","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"10.1016\/j.media.2026.104191_b19","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2024.103280","article-title":"TransUNet: Rethinking the U-Net architecture design for medical image segmentation through the lens of transformers","volume":"97","author":"Chen","year":"2024","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2026.104191_b20","doi-asserted-by":"crossref","unstructured":"Couairon, G., Careil, M., Cord, M., Lathuiliere, S., Verbeek, J., 2023. Zero-shot spatial layout conditioning for text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 2174\u20132183.","DOI":"10.1109\/ICCV51070.2023.00207"},{"key":"10.1016\/j.media.2026.104191_b21","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"4\u20135","key":"10.1016\/j.media.2026.104191_b22","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1016\/j.compmedimag.2007.02.002","article-title":"Computer-aided diagnosis in medical imaging: historical review, current status and future potential","volume":"31","author":"Doi","year":"2007","journal-title":"Comput. Med. Imaging Graph."},{"issue":"2","key":"10.1016\/j.media.2026.104191_b23","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1016\/j.jacr.2023.11.011","article-title":"Economic and environmental costs of cloud technologies for medical imaging and radiology artificial intelligence","volume":"21","author":"Doo","year":"2024","journal-title":"J. Am. Coll. Radiol."},{"key":"10.1016\/j.media.2026.104191_b24","series-title":"2024 IEEE International Symposium on Biomedical Imaging","first-page":"1","article-title":"Boosting dermatoscopic lesion segmentation via diffusion models with visual and textual prompts","author":"Du","year":"2024"},{"issue":"7639","key":"10.1016\/j.media.2026.104191_b25","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"Esteva","year":"2017","journal-title":"Nature"},{"key":"10.1016\/j.media.2026.104191_b26","series-title":"2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society","first-page":"1","article-title":"Derm-t2im: Harnessing synthetic skin lesion data via stable diffusion models for enhanced skin disease classification using ViT and CNN","author":"Farooq","year":"2024"},{"key":"10.1016\/j.media.2026.104191_b27","unstructured":"Feng, W., He, X., Fu, T.-J., Jampani, V., Akula, A.R., Narayana, P., Basu, S., Wang, X.E., Wang, W.Y., 2023. Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis. In: The Eleventh International Conference on Learning Representations."},{"issue":"1","key":"10.1016\/j.media.2026.104191_b28","doi-asserted-by":"crossref","first-page":"3","DOI":"10.25259\/IJDVL_1361_2023","article-title":"Global health dermatology: An emerging field addressing the access to care crisis","volume":"90","author":"Freeman","year":"2023","journal-title":"Indian J. Dermatol. Venereol. Leprol."},{"key":"10.1016\/j.media.2026.104191_b29","unstructured":"Gal, R., Alaluf, Y., Atzmon, Y., Patashnik, O., Bermano, A.H., Chechik, G., Cohen-or, D., 2023. An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion. In: The Eleventh International Conference on Learning Representations."},{"issue":"12","key":"10.1016\/j.media.2026.104191_b30","doi-asserted-by":"crossref","first-page":"5799","DOI":"10.1118\/1.3013555","article-title":"Anniversary paper: history and status of CAD and quantitative image analysis: the role of medical physics and AAPM","volume":"35","author":"Giger","year":"2008","journal-title":"Med. Phys."},{"key":"10.1016\/j.media.2026.104191_b31","doi-asserted-by":"crossref","unstructured":"Groh, M., Harris, C., Soenksen, L., Lau, F., Han, R., Kim, A., Koochek, A., Badri, O., 2021. Evaluating deep neural networks trained on clinical images in dermatology with the fitzpatrick 17k dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 1820\u20131828.","DOI":"10.1109\/CVPRW53098.2021.00201"},{"key":"10.1016\/j.media.2026.104191_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.compmedimag.2021.101911","article-title":"A multiparametric MRI-based CAD system for accurate diagnosis of bladder cancer staging","volume":"90","author":"Hammouda","year":"2021","journal-title":"Comput. Med. Imaging Graph."},{"key":"10.1016\/j.media.2026.104191_b33","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2023.106624","article-title":"A survey, review, and future trends of skin lesion segmentation and classification","volume":"155","author":"Hasan","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.media.2026.104191_b34","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-or, D., 2023. Prompt-to-Prompt Image Editing with Cross-Attention Control. In: The Eleventh International Conference on Learning Representations."},{"key":"10.1016\/j.media.2026.104191_b35","doi-asserted-by":"crossref","unstructured":"Hertz, A., Voynov, A., Fruchter, S., Cohen-Or, D., 2024. Style aligned image generation via shared attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 4775\u20134785.","DOI":"10.1109\/CVPR52733.2024.00457"},{"key":"10.1016\/j.media.2026.104191_b36","series-title":"ISIC 2018: Skin lesion analysis towards melanoma detection","author":"International Skin Imaging Collaboration","year":"2018"},{"issue":"1","key":"10.1016\/j.media.2026.104191_b37","doi-asserted-by":"crossref","first-page":"19130","DOI":"10.1038\/s41598-022-21841-w","article-title":"Development of a multipotent diagnostic tool for chest X-rays by multi-object detection method","volume":"12","author":"Kang","year":"2022","journal-title":"Sci. Rep."},{"issue":"2","key":"10.1016\/j.media.2026.104191_b38","doi-asserted-by":"crossref","first-page":"538","DOI":"10.1109\/JBHI.2018.2824327","article-title":"Seven-point checklist and skin lesion classification using multitask multimodal neural nets","volume":"23","author":"Kawahara","year":"2018","journal-title":"IEEE J. Biomed. Health Informatics"},{"key":"10.1016\/j.media.2026.104191_b39","unstructured":"Khani, A., Taghanaki, S.A., Sanghi, A., Amiri, A.M., Hamarneh, G., 2024. Slime: Segment like me. In: The Twelfth International Conference on Learning Representations."},{"key":"10.1016\/j.media.2026.104191_b40","doi-asserted-by":"crossref","unstructured":"Kim, Y., Lee, J., Kim, J.-H., Ha, J.-W., Zhu, J.-Y., 2023. Dense text-to-image generation with attention modulation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 7701\u20137711.","DOI":"10.1109\/ICCV51070.2023.00708"},{"issue":"3","key":"10.1016\/j.media.2026.104191_b41","doi-asserted-by":"crossref","first-page":"143","DOI":"10.4258\/hir.2011.17.3.143","article-title":"The recent progress in quantitative medical image analysis for computer aided diagnosis systems","volume":"17","author":"Kim","year":"2011","journal-title":"Heal. Inform. Res."},{"key":"10.1016\/j.media.2026.104191_b42","series-title":"European Conference on Computer Vision","first-page":"381","article-title":"Bk-sdm: A lightweight, fast, and cheap version of stable diffusion","author":"Kim","year":"2024"},{"key":"10.1016\/j.media.2026.104191_b43","unstructured":"Kingma, D.P., Welling, M., 2014. Auto-encoding variational bayes. In: International Conference on Learning Representations. pp. 1\u201314."},{"key":"10.1016\/j.media.2026.104191_b44","doi-asserted-by":"crossref","unstructured":"Lin, B., Xu, Y., Bao, X., Zhao, Z., Wang, Z., Yin, J., 2025. SkinGEN: an explainable dermatology diagnosis-to-generation framework with interactive vision-language models. In: Proceedings of the 30th International Conference on Intelligent User Interfaces. pp. 1287\u20131296.","DOI":"10.1145\/3708359.3712098"},{"key":"10.1016\/j.media.2026.104191_b45","doi-asserted-by":"crossref","first-page":"34892","DOI":"10.52202\/075280-1516","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2026.104191_b46","series-title":"The llama 3 herd of models","author":"Llama Team, AI at Meta","year":"2024"},{"key":"10.1016\/j.media.2026.104191_b47","series-title":"International Conference on Artificial Neural Networks, Lecture Notes in Computer Science, Vol. 14254","first-page":"268","article-title":"SkinDistilViT: Lightweight vision transformer for skin lesion classification","author":"Lungu-Stan","year":"2023"},{"key":"10.1016\/j.media.2026.104191_b48","doi-asserted-by":"crossref","unstructured":"Mao, J., Wang, Y., Tang, Y., Xu, D., Wang, K., Yang, Y., Zhou, Z., Zhou, Y., 2025. Medsegfactory: Text-guided generation of medical image-mask pairs. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 21525\u201321535.","DOI":"10.1109\/ICCV51701.2025.01999"},{"key":"10.1016\/j.media.2026.104191_b49","series-title":"2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society","first-page":"5437","article-title":"PH 2-a dermoscopic image database for research and benchmarking","author":"Mendon\u00e7a","year":"2013"},{"key":"10.1016\/j.media.2026.104191_b50","doi-asserted-by":"crossref","unstructured":"Mokady, R., Hertz, A., Aberman, K., Pritch, Y., Cohen-Or, D., 2023. Null-text inversion for editing real images using guided diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 6038\u20136047.","DOI":"10.1109\/CVPR52729.2023.00585"},{"issue":"6","key":"10.1016\/j.media.2026.104191_b51","doi-asserted-by":"crossref","first-page":"2137","DOI":"10.1002\/ima.22750","article-title":"Melanoma segmentation: A framework of improved DenseNet77 and UNET convolutional neural network","volume":"32","author":"Nawaz","year":"2022","journal-title":"Int. J. Imaging Syst. Technol."},{"key":"10.1016\/j.media.2026.104191_b52","doi-asserted-by":"crossref","unstructured":"Nguyen, T.-T., Nguyen, Q., Nguyen, K., Tran, A., Pham, C., 2025. Swiftedit: Lightning fast text-guided image editing via one-step diffusion. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 21492\u201321501.","DOI":"10.1109\/CVPR52734.2025.02002"},{"key":"10.1016\/j.media.2026.104191_b53","doi-asserted-by":"crossref","first-page":"76872","DOI":"10.52202\/075280-3359","article-title":"Dataset diffusion: Diffusion-based synthetic data generation for pixel-level semantic segmentation","volume":"36","author":"Nguyen","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2026.104191_b54","series-title":"Medical Imaging with Deep Learning","article-title":"Attention U-Net: Learning where to look for the pancreas","author":"Oktay","year":"2018"},{"key":"10.1016\/j.media.2026.104191_b55","doi-asserted-by":"crossref","first-page":"613","DOI":"10.1007\/s00521-016-2482-6","article-title":"Computational methods for pigmented skin lesion classification in images: review and future trends","volume":"29","author":"Oliveira","year":"2018","journal-title":"Neural Comput. Appl."},{"issue":"285\u2013296","key":"10.1016\/j.media.2026.104191_b56","first-page":"23","article-title":"A threshold selection method from gray-level histograms","volume":"11","author":"Otsu","year":"1975","journal-title":"Automatica"},{"key":"10.1016\/j.media.2026.104191_b57","doi-asserted-by":"crossref","unstructured":"Phung, Q., Ge, S., Huang, J.-B., 2024. Grounded text-to-image synthesis with attention refocusing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 7932\u20137942.","DOI":"10.1109\/CVPR52733.2024.00758"},{"issue":"21","key":"10.1016\/j.media.2026.104191_b58","doi-asserted-by":"crossref","first-page":"15575","DOI":"10.1007\/s11042-019-7717-y","article-title":"Augmenting data with GANs to segment melanoma skin lesions","volume":"79","author":"Pollastri","year":"2020","journal-title":"Multimedia Tools Appl."},{"key":"10.1016\/j.media.2026.104191_b59","doi-asserted-by":"crossref","DOI":"10.1016\/j.cmpb.2020.105568","article-title":"A GAN-based image synthesis method for skin lesion classification","volume":"195","author":"Qin","year":"2020","journal-title":"Comput. Methods Programs Biomed."},{"key":"10.1016\/j.media.2026.104191_b60","doi-asserted-by":"crossref","unstructured":"Rahman, A., Valanarasu, J.M.J., Hacihaliloglu, I., Patel, V.M., 2023. Ambiguous medical image segmentation using diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 11536\u201311546.","DOI":"10.1109\/CVPR52729.2023.01110"},{"key":"10.1016\/j.media.2026.104191_b61","doi-asserted-by":"crossref","first-page":"3536","DOI":"10.52202\/075280-0157","article-title":"Linguistic binding in diffusion models: Enhancing attribute correspondence through attention map alignment","volume":"36","author":"Rassin","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2026.104191_b62","series-title":"2021 IEEE\/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies","first-page":"23","article-title":"Improve image-based skin cancer diagnosis with generative self-supervised learning","author":"Ren","year":"2021"},{"key":"10.1016\/j.media.2026.104191_b63","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B., 2022. High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10684\u201310695.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"10.1016\/j.media.2026.104191_b64","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention, Lecture Notes in Computer Science, Vol. 9351","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"10.1016\/j.media.2026.104191_b65","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K., 2023. Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 22500\u201322510.","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"10.1016\/j.media.2026.104191_b66","series-title":"International Conference on Learning Representations","first-page":"38384","article-title":"Lightning-fast image inversion and editing for text-to-image diffusion models","volume":"Vol. 2025","author":"Samuel","year":"2025"},{"key":"10.1016\/j.media.2026.104191_b67","doi-asserted-by":"crossref","first-page":"25278","DOI":"10.52202\/068431-1833","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2026.104191_b68","doi-asserted-by":"crossref","DOI":"10.1016\/j.imu.2021.100628","article-title":"Proposing a novel cascade ensemble super resolution generative adversarial network (CESR-GAN) method for the reconstruction of super-resolution skin lesion images","volume":"24","author":"Shahsavari","year":"2021","journal-title":"Informatics Med. Unlocked"},{"key":"10.1016\/j.media.2026.104191_b69","doi-asserted-by":"crossref","DOI":"10.3389\/fmed.2023.1231436","article-title":"Finetuning of GLIDE stable diffusion model for AI-based text-conditional image synthesis of dermoscopic images","volume":"10","author":"Shavlokhova","year":"2023","journal-title":"Front. Med."},{"issue":"1","key":"10.1016\/j.media.2026.104191_b70","doi-asserted-by":"crossref","first-page":"18134","DOI":"10.1038\/s41598-022-22644-9","article-title":"Skin lesion classification of dermoscopic images using machine learning and convolutional neural network","volume":"12","author":"Shetty","year":"2022","journal-title":"Sci. Rep."},{"issue":"1","key":"10.1016\/j.media.2026.104191_b71","first-page":"12","article-title":"Cancer statistics, 2024","volume":"74","author":"Siegel","year":"2024","journal-title":"CA: Cancer J. Clin."},{"issue":"1","key":"10.1016\/j.media.2026.104191_b72","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1109\/JSTSP.2008.2011119","article-title":"Comparison of segmentation methods for melanoma diagnosis in dermoscopy images","volume":"3","author":"Silveira","year":"2009","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"10.1016\/j.media.2026.104191_b73","series-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2021"},{"key":"10.1016\/j.media.2026.104191_b74","doi-asserted-by":"crossref","unstructured":"Tang, R., Liu, L., Pandey, A., Jiang, Z., Yang, G., Kumar, K., Stenetorp, P., Lin, J., T\u00fcre, F., 2023. What the DAAM: Interpreting Stable Diffusion Using Cross Attention. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). pp. 5644\u20135659.","DOI":"10.18653\/v1\/2023.acl-long.310"},{"key":"10.1016\/j.media.2026.104191_b75","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2020.101915","article-title":"Interpretable deep learning systems for multi-class segmentation and classification of non-melanoma skin cancer","volume":"68","author":"Thomas","year":"2021","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2026.104191_b76","doi-asserted-by":"crossref","first-page":"11311","DOI":"10.15766\/mep_2374-8265.11311","article-title":"Melanoma: Does it present differently in darker skin tones?","volume":"19","author":"Thompson","year":"2023","journal-title":"MedEdPORTAL"},{"key":"10.1016\/j.media.2026.104191_b77","first-page":"78433","article-title":"YOLOv12: Attention-centric real-time object detectors","volume":"38","author":"Tian","year":"2026","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"1","key":"10.1016\/j.media.2026.104191_b78","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/sdata.2018.161","article-title":"The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions","volume":"5","author":"Tschandl","year":"2018","journal-title":"Sci. Data"},{"key":"10.1016\/j.media.2026.104191_b79","doi-asserted-by":"crossref","unstructured":"Tumanyan, N., Geyer, M., Bagon, S., Dekel, T., 2023. Plug-and-play diffusion features for text-driven image-to-image translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 1921\u20131930.","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"10.1016\/j.media.2026.104191_b80","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"3","key":"10.1016\/j.media.2026.104191_b81","first-page":"669","article-title":"Dermoscopy compared with naked eye examination for the diagnosis of primary melanoma: a meta-analysis of studies performed in a clinical setting","volume":"159","author":"Vestergaard","year":"2008","journal-title":"Br. J. Dermatol."},{"key":"10.1016\/j.media.2026.104191_b82","doi-asserted-by":"crossref","unstructured":"Vu Quoc, H., Tran Le Phuong, T., Trinh Xuan, M., Dinh Viet, S., 2023. LSegDiff: a latent diffusion model for medical image segmentation. In: Proceedings of the 12th International Symposium on Information and Communication Technology. pp. 456\u2013462.","DOI":"10.1145\/3628797.3629010"},{"issue":"6","key":"10.1016\/j.media.2026.104191_b83","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1109\/TMI.2023.3236037","article-title":"Xbound-former: Toward cross-scale boundary modeling in transformers","volume":"42","author":"Wang","year":"2023","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2026.104191_b84","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention, Lecture Notes in Computer Science, Vol. 15274","first-page":"14","article-title":"From majority to minority: A diffusion-based augmentation for underrepresented groups in skin lesion analysis","author":"Wang","year":"2024"},{"key":"10.1016\/j.media.2026.104191_b85","doi-asserted-by":"crossref","unstructured":"Wang, T.-C., Liu, M.-Y., Zhu, J.-Y., Tao, A., Kautz, J., Catanzaro, B., 2018. High-resolution image synthesis and semantic manipulation with conditional GANs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 8798\u20138807.","DOI":"10.1109\/CVPR.2018.00917"},{"key":"10.1016\/j.media.2026.104191_b86","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention, Lecture Notes in Computer Science, Vol. 12901","first-page":"206","article-title":"Boundary-aware transformers for skin lesion segmentation","author":"Wang","year":"2021"},{"key":"10.1016\/j.media.2026.104191_b87","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2023.102746","article-title":"Intra-class consistency and inter-class discrimination feature learning for automatic skin lesion classification","volume":"85","author":"Wang","year":"2023","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.media.2026.104191_b88","series-title":"The Surgeon General\u2019s Call to Action to Prevent Skin Cancer","first-page":"viii, 101","author":"Watson","year":"2014"},{"key":"10.1016\/j.media.2026.104191_b89","series-title":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","first-page":"180","article-title":"Cascaded latent diffusion models for high-resolution chest x-ray synthesis","volume":"vol. 13937","author":"Weber","year":"2023"},{"key":"10.1016\/j.media.2026.104191_b90","doi-asserted-by":"crossref","first-page":"54683","DOI":"10.52202\/075280-2383","article-title":"Datasetdm: Synthesizing data with perception annotations using diffusion models","volume":"36","author":"Wu","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"3","key":"10.1016\/j.media.2026.104191_b91","doi-asserted-by":"crossref","first-page":"849","DOI":"10.1109\/TMI.2016.2633551","article-title":"Melanoma classification on dermoscopy images using a neural network ensemble model","volume":"36","author":"Xie","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2026.104191_b92","doi-asserted-by":"crossref","unstructured":"Xie, J., Li, Y., Huang, Y., Liu, H., Zhang, W., Zheng, Y., Shou, M.Z., 2023. Boxdiff: Text-to-image synthesis with training-free box-constrained diffusion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 7452\u20137461.","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"10.1016\/j.media.2026.104191_b93","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2023.106626","article-title":"DCSAU-Net: A deeper and more compact split-attention U-Net for medical image segmentation","volume":"154","author":"Xu","year":"2023","journal-title":"Comput. Biol. Med."},{"issue":"10","key":"10.1016\/j.media.2026.104191_b94","doi-asserted-by":"crossref","first-page":"6008","DOI":"10.1109\/JBHI.2024.3417247","article-title":"Skinformer: Learning statistical texture representation with transformer for skin lesion segmentation","volume":"28","author":"Xu","year":"2024","journal-title":"IEEE J. Biomed. Health Informatics"},{"key":"10.1016\/j.media.2026.104191_b95","unstructured":"Yamaguchi, S., Fukuda, T., 2023. On the limitation of diffusion models for synthesizing training datasets. In: NeurIPS 2023 Workshop on Synthetic Data Generation with Generative AI."},{"key":"10.1016\/j.media.2026.104191_b96","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention, Lecture Notes in Computer Science, Vol. 14225","first-page":"95","article-title":"Diffmic: Dual-guidance diffusion network for medical image classification","author":"Yang","year":"2023"},{"issue":"6","key":"10.1016\/j.media.2026.104191_b97","doi-asserted-by":"crossref","first-page":"3689","DOI":"10.1007\/s11263-025-02357-y","article-title":"Image synthesis under limited data: A survey and taxonomy","volume":"133","author":"Yang","year":"2025","journal-title":"Int. J. Comput. Vis."},{"issue":"4","key":"10.1016\/j.media.2026.104191_b98","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3626235","article-title":"Diffusion models: A comprehensive survey of methods and applications","volume":"56","author":"Yang","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.media.2026.104191_b99","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M., 2023. Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 3836\u20133847.","DOI":"10.1109\/ICCV51070.2023.00355"},{"issue":"4","key":"10.1016\/j.media.2026.104191_b100","doi-asserted-by":"crossref","first-page":"3899","DOI":"10.1007\/s10489-022-03609-x","article-title":"MinimalGAN: diverse medical image synthesis for data augmentation using minimal training data","volume":"53","author":"Zhang","year":"2023","journal-title":"Appl. Intell."},{"issue":"9","key":"10.1016\/j.media.2026.104191_b101","doi-asserted-by":"crossref","first-page":"3670","DOI":"10.1109\/TMI.2024.3519307","article-title":"Diffboost: Enhancing medical image segmentation via text-guided diffusion model","volume":"44","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.media.2026.104191_b102","doi-asserted-by":"crossref","first-page":"40831","DOI":"10.52202\/079017-1291","article-title":"Simple and fast distillation of diffusion models","volume":"37","author":"Zhou","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Medical Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526002604?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526002604?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T06:55:09Z","timestamp":1785826509000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1361841526002604"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":102,"alternative-id":["S1361841526002604"],"URL":"https:\/\/doi.org\/10.1016\/j.media.2026.104191","relation":{},"ISSN":["1361-8415"],"issn-type":[{"value":"1361-8415","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Controllable synthesis of dermoscopic images using diffusion models for enhanced computer aided diagnosis and detection","name":"articletitle","label":"Article Title"},{"value":"Medical Image Analysis","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.media.2026.104191","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"104191"}}