{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T03:19:17Z","timestamp":1793330357618,"version":"4.5.0"},"reference-count":72,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T00:00:00Z","timestamp":1788134400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T00:00:00Z","timestamp":1788134400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Digit Imaging. Inform. med."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Removing patient-identifying information from medical images is a prerequisite for sharing image data directly, as in public dataset release and open benchmarks, where the images themselves, rather than only model updates must leave the originating institution. However, many methods currently used for de-identification, e.g., cropping or blacking out image regions to eliminate burned-in text, can have negative effects on downstream image analysis tasks because of removal of relevant but non-identifiable information. This work presents an end-to-end deep learning framework for transforming raw clinical image volumes into de-identified, analysis-ready datasets without compromising downstream utility. The methodology developed and tested in this work first detects and redacts regions likely to contain protected health information (PHI), such as burned-in text and metadata, and then uses a generative deep learning model to inpaint the redacted areas with anatomically and imaging-plausible content. The proposed pipeline leverages a lightweight hybrid architecture, combining CRNN-based redaction with a latent-diffusion inpainting restoration module (Stable Diffusion 2). We evaluate the approach using both privacy-oriented metrics, which quantify residual PHI and success of redaction, and image-quality and task-based metrics, which assess the fidelity of restored volumes for representative deep learning applications. The binary mask performance shows strong overall PHI identification (F1 score = 0.891 \u00b1 0.037, recall of 0.912 \u00b1 0.053, and precision of 0.875 \u00b1 0.058, indicating accurate localization of PHI-containing regions with few missed detections or false-positive redactions. Downstream anatomy identification (segmentation) tasks remain markedly similar across after applying varied inpainting strategies (Diffusion with\/without context and Telea with Dice ranging from 0.936 to 0.948 on one dataset and 0.955 to 0.959 on another. Our results suggest that the proposed method yields de-identified medical images that are visually coherent, maintaining fidelity for downstream models and clinical tasks, while substantially reducing the risk of patient re-identification. By automating de-identification and image reconstruction within a single workflow and disseminating large-scale medical imaging collections, thereby lowering a key barrier to data sharing and multi-institutional collaboration in medical imaging AI.<\/jats:p>","DOI":"10.1007\/s10278-026-02241-2","type":"journal-article","created":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T16:13:12Z","timestamp":1788192792000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["From Redaction to Restoration: Deep Learning for Medical Image Deidentification and Reconstruction"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0052-0685","authenticated-orcid":false,"given":"Adrienne","family":"Kline","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abhijit","family":"Gaonkar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Pittman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chris","family":"Kuehn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nils","family":"Forkert","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,31]]},"reference":[{"key":"2241_CR1","doi-asserted-by":"crossref","unstructured":"Patel BN, Rosenberg L, Willcox G, Baltaxe D, Lyons M, Irvin J, et\u00a0al. Human\u2013machine partnership with artificial intelligence for chest radiograph diagnosis. NPJ digital medicine. 2019;2(1):111.","DOI":"10.1038\/s41746-019-0189-7"},{"key":"2241_CR2","doi-asserted-by":"crossref","unstructured":"Kamran SA, Saha S, Sabbir AS, Tavakkoli A. Optic-net: A novel convolutional neural network for diagnosis of retinal diseases from optical tomography images. In: 2019 18th IEEE international conference on machine learning and applications (ICMLA). IEEE; 2019. p. 964\u2013971.","DOI":"10.1109\/ICMLA.2019.00165"},{"key":"2241_CR3","doi-asserted-by":"crossref","unstructured":"Madani A, Arnaout R, Mofrad M, Arnaout R. Fast and accurate view classification of echocardiograms using deep learning. NPJ digital medicine. 2018;1(1):6.","DOI":"10.1038\/s41746-017-0013-1"},{"key":"2241_CR4","unstructured":"Alzheimer\u2019s Disease Neuroimaging Initiative (ADNI). Alzheimer\u2019s Disease Neuroimaging Initiative (ADNI); 2022. Alzheimer\u2019s Disease Neuroimaging Initiative (ADNI). Data resource. Available from: https:\/\/adni.loni.usc.edu\/."},{"key":"2241_CR5","unstructured":"National Institutes of Health (NIH). The Osteoarthritis Initiative (OAI); 2022. NIH: The Osteoarthritis Initiative (OAI). Data resource. Available from: https:\/\/www.nia.nih.gov\/research\/resource\/osteoarthritis-initiative-oai."},{"key":"2241_CR6","unstructured":"Johnson AEW, Pollard TJ, Mark RG, Berkowitz SJ, Horng S. MIMIC-CXR (version 2.1.0); 2024. PhysioNet. Available from: https:\/\/physionet.org\/content\/mimic-cxr\/2.1.0\/."},{"key":"2241_CR7","doi-asserted-by":"crossref","unstructured":"Balc\u0131 M, Alkan A. Retinal Diabetic Macular Edema Detection in OCT Images Using DeepLabv3+ with ResNet-18 Architecture. Sensing and Imaging. 2026;27(1):43.","DOI":"10.1007\/s11220-026-00743-5"},{"key":"2241_CR8","unstructured":"Biswas M, Kuppili V, Saba L, Edla DR, Suri HS, Cuadrado-Godia E, et\u00a0al. State-of-the-art review on deep learning in medical imaging. Frontiers in Bioscience-Landmark. 2019;24(3):380\u2013406."},{"key":"2241_CR9","doi-asserted-by":"crossref","unstructured":"Hering A, Hansen L, Mok TC, Chung AC, Siebert H, H\u00e4ger S, et\u00a0al. Learn2Reg: comprehensive multi-task medical image registration challenge, dataset and evaluation in the era of deep learning. IEEE Transactions on Medical Imaging. 2022;42(3):697\u2013712.","DOI":"10.1109\/TMI.2022.3213983"},{"key":"2241_CR10","doi-asserted-by":"crossref","unstructured":"Balc\u0131 M, Alkan A. A Comparative Analysis of Modern CNN and Transformer Architectures for Multi-Class Retinal Disease Classification with Statistical Validation and Explainability. Neurocomputing. 2026;p. 134387.","DOI":"10.1016\/j.neucom.2026.134387"},{"key":"2241_CR11","doi-asserted-by":"crossref","unstructured":"Vahdati S, Khosravi B, Mahmoudi E, Zhang K, Rouzrokh P, Faghani S, et\u00a0al. A Guideline for Open-Source Tools to Make Medical Imaging Data Ready for Artificial Intelligence Applications: A Society of Imaging Informatics in Medicine (SIIM) Survey. Journal of Imaging Informatics in Medicine. 2024;37:2015 \u2013 2024. Available from: https:\/\/api.semanticscholar.org\/CorpusID:268854242.","DOI":"10.1007\/s10278-024-01083-0"},{"key":"2241_CR12","doi-asserted-by":"crossref","unstructured":"Balc\u0131 M, Alkan A. Identification of wart treatment evaluation by using optimum ensemble based classification techniques. Biomedical Signal Processing and Control. 2024;95:106491.","DOI":"10.1016\/j.bspc.2024.106491"},{"key":"2241_CR13","unstructured":"Bee DICOM. Bee DICOM Viewer; 2024. Mac App Store. Accessed 2026\/08\/21 21:34:28. https:\/\/apps.apple.com\/us\/app\/bee-dicom-viewer\/id1590273176?mt=12."},{"key":"2241_CR14","doi-asserted-by":"crossref","unstructured":"Newhauser W, Jones T, Swerdloff S, Newhauser W, Cilia M, Carver R, et\u00a0al. Anonymization of DICOM electronic medical records for radiation therapy. Computers in biology and medicine. 2014;53:134\u2013140.","DOI":"10.1016\/j.compbiomed.2014.07.010"},{"key":"2241_CR15","doi-asserted-by":"crossref","unstructured":"Shi B, Bai X, Yao C. An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE transactions on pattern analysis and machine intelligence. 2016;39(11):2298\u20132304.","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"2241_CR16","doi-asserted-by":"crossref","unstructured":"Fezai L, Urruty T, Bourdon P, Fernandez-Maloigne C, Initiative ADN. Deep anonymization of medical imaging. Multimedia Tools and Applications. 2023;82(6):9533\u20139547.","DOI":"10.1007\/s11042-022-13686-2"},{"key":"2241_CR17","doi-asserted-by":"crossref","unstructured":"Monteiro E, Costa C, Oliveira JL. A de-identification pipeline for ultrasound medical images in DICOM format. Journal of medical systems. 2017;41(5):89.","DOI":"10.1007\/s10916-017-0736-1"},{"key":"2241_CR18","doi-asserted-by":"crossref","unstructured":"Huang LC, Chu HC, Lien CY, Hsiao CH, Kao T. Privacy preservation and information security protection for patients\u2019 portable electronic health records. Computers in Biology and Medicine. 2009;39(9):743\u2013750.","DOI":"10.1016\/j.compbiomed.2009.06.004"},{"key":"2241_CR19","doi-asserted-by":"crossref","unstructured":"Parker W, Jaremko JL, Cicero M, Azar M, El-Emam K, Gray BG, et\u00a0al. Canadian association of radiologists white paper on de-identification of medical imaging: part 1, general principles. Canadian Association of Radiologists Journal. 2021;72(1):13\u201324.","DOI":"10.1177\/0846537120967349"},{"key":"2241_CR20","doi-asserted-by":"crossref","unstructured":"Zech JR, Badgeley MA, Liu M, Costa AB, Titano JJ, Oermann EK. Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: a cross-sectional study. PLoS medicine. 2018;15(11):e1002683.","DOI":"10.1371\/journal.pmed.1002683"},{"key":"2241_CR21","doi-asserted-by":"crossref","unstructured":"Geirhos R, Jacobsen JH, Michaelis C, Zemel R, Brendel W, Bethge M, et\u00a0al. Shortcut learning in deep neural networks. Nature Machine Intelligence. 2020;2(11):665\u2013673.","DOI":"10.1038\/s42256-020-00257-z"},{"key":"2241_CR22","doi-asserted-by":"crossref","unstructured":"DeGrave AJ, Janizek JD, Lee SI. AI for radiographic COVID-19 detection selects shortcuts over signal. Nature Machine Intelligence. 2021;3(7):610\u2013619.","DOI":"10.1038\/s42256-021-00338-7"},{"key":"2241_CR23","doi-asserted-by":"crossref","unstructured":"Gu J, Lu H, Zuo W, Dong C. Blind super-resolution with iterative kernel correction. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition; 2019. p. 1604\u20131613.","DOI":"10.1109\/CVPR.2019.00170"},{"key":"2241_CR24","doi-asserted-by":"crossref","unstructured":"Ravi S, Climent-P\u00e9rez P, Florez-Revuelta F. A review on visual privacy preservation techniques for active and assisted living. Multimedia Tools and Applications. 2024;83(5):14715\u201314755.","DOI":"10.1007\/s11042-023-15775-2"},{"key":"2241_CR25","doi-asserted-by":"crossref","unstructured":"Santos JC, Tom\u00e1s Pereira\u00a0Alexandre H, Seoane\u00a0Santos M, Henriques\u00a0Abreu P. The Role of Deep Learning in Medical Image Inpainting: A Systematic Review. ACM Transactions on Computing for Healthcare. 2025;6(3):1\u201324.","DOI":"10.1145\/3712710"},{"key":"2241_CR26","doi-asserted-by":"crossref","unstructured":"Saharia C, Chan W, Chang H, Lee C, Ho J, Salimans T, et\u00a0al. Palette: Image-to-Image Diffusion Models. ACM SIGGRAPH 2022 Conference Proceedings. 2021;Available from: https:\/\/api.semanticscholar.org\/CorpusID:243938678.","DOI":"10.1145\/3528233.3530757"},{"key":"2241_CR27","unstructured":"Meaney C, Hakimpour W, Kalia S, Moineddin R. A comparative evaluation of transformer models for de-identification of clinical text data. arXiv preprint arXiv:2204.07056. 2022;."},{"key":"2241_CR28","doi-asserted-by":"crossref","unstructured":"Wiest IC, Le\u00dfmann ME, Wolf F, Ferber D, Treeck MV, Zhu J, et\u00a0al. Deidentifying medical documents with local, privacy-preserving large language models: the LLM-anonymizer. NEJM AI. 2025;2(4):AIdbp2400537.","DOI":"10.1056\/AIdbp2400537"},{"key":"2241_CR29","doi-asserted-by":"crossref","unstructured":"Truong T, Baltruschat IM, Klemens M, Werner G, Lenga M. Exploring AI-Based System Design for Pixel-Level Protected Health Information Detection in Medical Images. Journal of Imaging Informatics in Medicine. 2025;p. 1\u201320.","DOI":"10.1007\/s10278-025-01619-y"},{"key":"2241_CR30","unstructured":"Melnyk M. DICOM de-identification at scale in Visual NLP (1\/3); 2023. Accessed: 2025-12-09. John Snow Labs Blog. Available from: https:\/\/www.johnsnowlabs.com\/dicom-de-identification-at-scale-in-visual-nlp-1-3\/."},{"key":"2241_CR31","doi-asserted-by":"crossref","unstructured":"Rempe M, Heine L, Seibold C, H\u00f6rst F, Kleesiek J. De-identification of medical imaging data: a comprehensive tool for ensuring patient privacy. European radiology. 2025;p. 1\u201310.","DOI":"10.1007\/s00330-025-11695-x"},{"key":"2241_CR32","doi-asserted-by":"crossref","unstructured":"Shahid A, Bazargani MH, Banahan P, Mac\u00a0Namee B, Kechadi T, Treacy C, et\u00a0al. A two-stage de-identification process for privacy-preserving medical image analysis. In: Healthcare. vol.\u00a010. MDPI; 2022. p. 755.","DOI":"10.3390\/healthcare10050755"},{"key":"2241_CR33","doi-asserted-by":"crossref","unstructured":"Kondylakis H, Catalan R, Alabart SM, Barelle C, Bizopoulos P, Bobowicz M, et\u00a0al. Documenting the de-identification process of clinical and imaging data for AI for health imaging projects. Insights into Imaging. 2024;15(1):130.","DOI":"10.1186\/s13244-024-01711-x"},{"key":"2241_CR34","unstructured":"Koutsoubis N, Yilmaz Y, Ramachandran RP, Schabath M, Rasool G. Privacy preserving federated learning in medical imaging with uncertainty estimation. arXiv preprint arXiv:2406.12815. 2024;."},{"key":"2241_CR35","doi-asserted-by":"crossref","unstructured":"Shin HC, Tenenholtz NA, Rogers JK, Schwarz CG, Senjem ML, Gunter JL, et\u00a0al. Medical image synthesis for data augmentation and anonymization using generative adversarial networks. In: International workshop on simulation and synthesis in medical imaging. Springer; 2018. p. 1\u201311.","DOI":"10.1007\/978-3-030-00536-8_1"},{"key":"2241_CR36","doi-asserted-by":"crossref","unstructured":"Packh\u00e4user K, G\u00fcndel S, M\u00fcnster N, Syben C, Christlein V, Maier A. Deep learning-based patient re-identification is able to exploit the biometric nature of medical chest X-ray data. Scientific Reports. 2022;12(1):14851.","DOI":"10.1038\/s41598-022-19045-3"},{"key":"2241_CR37","unstructured":"Wiggins J. De-identify medical images with the help of Amazon Comprehend Medical and Amazon Rekognition; 2019. Accessed: 2025-12-02. AWS Machine Learning Blog. AWS ML Blog."},{"key":"2241_CR38","doi-asserted-by":"crossref","unstructured":"Adnan M, Kalra S, Cresswell JC, Taylor GW, Tizhoosh HR. Federated learning and differential privacy for medical image analysis. Scientific reports. 2022;12(1):1953.","DOI":"10.1038\/s41598-022-05539-7"},{"key":"2241_CR39","unstructured":"Momot A. Common Carotid Artery Ultrasound Images. Mendeley Data; 2022."},{"key":"2241_CR40","unstructured":"K\u00f3nya S. CT Lung & Heart & Trachea Segmentation; 2020. Kaggle dataset. Accessed: 2026-07-21. https:\/\/www.kaggle.com\/datasets\/sandorkonya\/ct-lung-heart-trachea-segmentation."},{"key":"2241_CR41","unstructured":"National Institutes of Health Clinical Center. NIH Chest X-ray Dataset (ChestX-ray14); 2017. Accessed: 2026-07-21. https:\/\/nihcc.app.box.com\/v\/ChestXray-NIHCC."},{"key":"2241_CR42","unstructured":"Summers R. Nih chest x-ray dataset of 14 common thorax disease categories. NIH Clinical Center: Bethesda, MD, USA. 2019;."},{"key":"2241_CR43","doi-asserted-by":"crossref","unstructured":"Wang X, Peng Y, Lu L, Lu Z, Bagheri M, Summers RM. Chestx-ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In: Proceedings of the IEEE conference on computer vision and pattern recognition; 2017. p. 2097\u20132106.","DOI":"10.1109\/CVPR.2017.369"},{"key":"2241_CR44","doi-asserted-by":"crossref","unstructured":"Popov M, Amanturdieva A, Zhaksylyk N, Alkanov A, Saniyazbekov A, Aimyshev T, et\u00a0al. Dataset for automatic region-based coronary artery disease diagnostics using X-ray angiography images. Scientific data. 2024;11(1):20.","DOI":"10.1038\/s41597-023-02871-z"},{"key":"2241_CR45","doi-asserted-by":"crossref","unstructured":"Popov M, Amanturdieva A, Zhaksylyk N, Alkanov A, Saniyazbekov A, Aimyshev T, et\u00a0al.. ARCADE: Automatic Region-based Coronary Artery Disease Diagnostics Using X-ray Angiography Images Dataset. Zenodo; 2023. Available from: https:\/\/doi.org\/10.5281\/zenodo.10390295.","DOI":"10.1038\/s41597-023-02871-z"},{"key":"2241_CR46","doi-asserted-by":"crossref","unstructured":"Ma J, Zhang Y, Gu S, Zhu C, Ge C, Zhang Y, et\u00a0al. Abdomenct-1k: Is abdominal organ segmentation a solved problem? IEEE Transactions on Pattern Analysis and Machine Intelligence. 2021;44(10):6695\u20136714.","DOI":"10.1109\/TPAMI.2021.3100536"},{"key":"2241_CR47","unstructured":"Ma J, Zhang Y, Gu S, Zhu C, Ge C, Zhang Y, et\u00a0al.. AbdomenCT-1K: Fully Supervised Learning Benchmark. Zenodo; 2022. Available from: https:\/\/doi.org\/10.5281\/zenodo.5903037."},{"key":"2241_CR48","doi-asserted-by":"crossref","unstructured":"Jaeger S, Karargyris A, Candemir S, Folio L, Siegelman J, Callaghan F, et\u00a0al. Automatic tuberculosis screening using chest radiographs. IEEE transactions on medical imaging. 2013;33(2):233\u2013245.","DOI":"10.1109\/TMI.2013.2284099"},{"key":"2241_CR49","doi-asserted-by":"crossref","unstructured":"Candemir S, Jaeger S, Palaniappan K, Musco JP, Singh RK, Xue Z, et\u00a0al. Lung segmentation in chest radiographs using anatomical atlases with nonrigid registration. IEEE transactions on medical imaging. 2013;33(2):577\u2013590.","DOI":"10.1109\/TMI.2013.2290491"},{"key":"2241_CR50","unstructured":"Pandey N. Chest X-Ray Masks and Labels. Kaggle; 2020. Accessed: 2026-07-21. Available from: https:\/\/www.kaggle.com\/datasets\/nikhilpandey360\/chest-xray-masks-and-labels."},{"key":"2241_CR51","unstructured":"Kay A. Tesseract: an open-source optical character recognition engine. Linux Journal. 2007;2007(159):2."},{"key":"2241_CR52","unstructured":"Kittinaradorn R. EasyOCR; 2020. Accessed: 2026-07-31. https:\/\/github.com\/JaidedAI\/EasyOCR."},{"key":"2241_CR53","doi-asserted-by":"crossref","unstructured":"Gupta A, Vedaldi A, Zisserman A. Synthetic data for text localisation in natural images. In: Proceedings of the IEEE conference on computer vision and pattern recognition; 2016. p. 2315\u20132324.","DOI":"10.1109\/CVPR.2016.254"},{"key":"2241_CR54","unstructured":"Gupta A. SynthText: Code for generating synthetic text images. GitHub; 2016. https:\/\/github.com\/ankush-me\/SynthText."},{"key":"2241_CR55","doi-asserted-by":"crossref","unstructured":"Karatzas D, Gomez-Bigorda L, Nicolaou A, Ghosh S, Bagdanov A, Iwamura M, et\u00a0al. ICDAR 2015 competition on robust reading. In: 2015 13th international conference on document analysis and recognition (ICDAR). IEEE; 2015. p. 1156\u20131160.","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"2241_CR56","doi-asserted-by":"crossref","unstructured":"Karatzas D, Shafait F, Uchida S, Iwamura M, i\u00a0Bigorda LG, Mestre SR, et\u00a0al. ICDAR 2013 robust reading competition. In: 2013 12th international conference on document analysis and recognition. IEEE; 2013. p. 1484\u20131493.","DOI":"10.1109\/ICDAR.2013.221"},{"key":"2241_CR57","unstructured":"U S Department of Health and Human Services, Office for Civil Rights. Guidance Regarding\u00a0Methods for De-identification of Protected Health Information in Accordance with the Health Insurance Portability and Accountability Act (HIPAA) Privacy Rule; 2025. Content last reviewed February 3, 2025. Accessed: 2025-12-23. HHS.gov. Available from: https:\/\/www.hhs.gov\/hipaa\/for-professionals\/special-topics\/de-identification\/index.html."},{"key":"2241_CR58","doi-asserted-by":"crossref","unstructured":"Baek Y, Lee B, Han D, Yun S, Lee H. Character region awareness for text detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition; 2019. p. 9365\u20139374.","DOI":"10.1109\/CVPR.2019.00959"},{"key":"2241_CR59","doi-asserted-by":"crossref","unstructured":"Bengio Y, Simard PY, Frasconi P. Learning long-term dependencies with gradient descent is difficult. IEEE transactions on neural networks. 1994;5 2:157\u201366. Available from: https:\/\/api.semanticscholar.org\/CorpusID:206457500.","DOI":"10.1109\/72.279181"},{"key":"2241_CR60","doi-asserted-by":"crossref","unstructured":"Hochreiter S, Schmidhuber J. Long Short-Term Memory. Neural Computation. 1997;9:1735\u20131780. Available from: https:\/\/api.semanticscholar.org\/CorpusID:1915014.","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"2241_CR61","doi-asserted-by":"crossref","unstructured":"Telea A. An image inpainting technique based on the fast marching method. Journal of graphics tools. 2004;9(1):23\u201334.","DOI":"10.1080\/10867651.2004.10487596"},{"key":"2241_CR62","unstructured":"sd2-community. Stable Diffusion 2 Inpainting; 2022. Accessed: 2025-12-09. Hugging Face model card. Available from: https:\/\/huggingface.co\/sd2-community\/stable-diffusion-2-inpainting."},{"key":"2241_CR63","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; 2022. p. 10684\u201310695.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2241_CR64","unstructured":"Salimans T, Ho J. Progressive distillation for fast sampling of diffusion models. arXiv preprint arXiv:2202.00512. 2022;."},{"key":"2241_CR65","unstructured":"Ho J, Salimans T. Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598. 2022;."},{"key":"2241_CR66","unstructured":"Hugging Face. Stable Diffusion Pipelines; 2025. Accessed: 2025-12-09. Hugging Face Diffusers Documentation. Available from: https:\/\/huggingface.co\/docs\/diffusers\/en\/api\/pipelines\/stable_diffusion\/overview."},{"key":"2241_CR67","unstructured":"CompVis, Stability AI, Runway. CreativeML OpenRAIL-M License; 2022. Accessed: 2025-12-09. Stable Diffusion License Text. Available from: https:\/\/huggingface.co\/spaces\/CompVis\/stable-diffusion-license\/raw\/main\/license.txt."},{"key":"2241_CR68","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L. Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition. Ieee; 2009. p. 248\u2013255.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2241_CR69","unstructured":"Oquab M, Darcet T, Moutakanni T, Vo H, Szafraniec M, Khalidov V, et\u00a0al. Dinov2: Learning robust visual features without supervision. Transactions on Machine Learning Research Journal. 2024;."},{"key":"2241_CR70","doi-asserted-by":"crossref","unstructured":"Lien CY, Onken M, Eichelberg M, Kao T, Hein A. Open source tools for standardized privacy protection of medical images. In: Medical Imaging 2011: Advanced PACS-based Imaging Informatics and Therapeutic Applications. vol. 7967. SPIE; 2011. p. 177\u2013183.","DOI":"10.1117\/12.877989"},{"key":"2241_CR71","doi-asserted-by":"crossref","unstructured":"Rodr\u00edguez\u00a0Gonz\u00e1lez D, Carpenter T, van Hemert JI, Wardlaw J. An open source toolkit for medical imaging de-identification. European radiology. 2010;20(8):1896\u20131904.","DOI":"10.1007\/s00330-010-1745-3"},{"key":"2241_CR72","doi-asserted-by":"crossref","unstructured":"Kline A, Wang H, Li Y, Dennis S, Hutch M, Xu Z, et\u00a0al. Multimodal machine learning in precision health: A scoping review. NPJ digital medicine. 2022;5(1):171.","DOI":"10.1038\/s41746-022-00712-8"}],"container-title":["Journal of Imaging Informatics in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-026-02241-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10278-026-02241-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-026-02241-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T16:13:24Z","timestamp":1788192804000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10278-026-02241-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,31]]},"references-count":72,"alternative-id":["2241"],"URL":"https:\/\/doi.org\/10.1007\/s10278-026-02241-2","relation":{},"ISSN":["2948-2933"],"issn-type":[{"value":"2948-2933","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,31]]},"assertion":[{"value":"26 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 August 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 August 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 August 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This was an analysis of retrospective datasets, whose availability is outlined in the manuscript; therefore, no ethical approval is required.","order":1,"name":"Ethics","label":"Ethical Approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"N\/A\u2014this was an analysis of retrospective datasets.","order":2,"name":"Ethics","label":"Consent to Participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors consent to the publication of the manuscript.","order":3,"name":"Ethics","label":"Consent for Publication","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","label":"Competing Interests","group":{"name":"EthicsHeading","label":"Declarations"}}]}}