{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T07:52:48Z","timestamp":1773733968349,"version":"3.50.1"},"reference-count":37,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T00:00:00Z","timestamp":1773446400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>This work investigates the extension of StyleGAN2-ADA to three-dimensional prostate T2-weighted (T2W) MRI generation. The architecture is adapted to operate on 3D anisotropic volumes, enabling stable training at a clinically relevant resolution of 256\u00d7256\u00d724, where a baseline 3D-StyleGAN fails to converge. Quantitative evaluation using Fr\u00e9chet Inception Distance (FID), Kernel Inception Distance (KID), and generative Precision\u2013Recall metrics demonstrates substantial improvements over a 3D-StyleGAN baseline. Specifically, FID decreased from 114.2 to 27.3, while generative Precision increased from 0.22 to 0.82, indicating markedly improved fidelity and alignment with the real data distribution. Beyond generative metrics, the synthetic volumes were evaluated through radiomic feature analysis and downstream prostate segmentation. Synthetic data augmentation resulted in segmentation performance comparable to real-data training, supporting that volumetric generation preserves anatomically relevant structures, while multivariate radiomic analyses showed strong global feature alignment between real and synthetic volumes. These findings indicate that a 3D extension of StyleGAN2-ADA enables stable high-resolution volumetric prostate MRI synthesis while preserving anatomically coherent structure and global radiomic characteristics.<\/jats:p>","DOI":"10.3390\/jimaging12030130","type":"journal-article","created":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T08:41:26Z","timestamp":1773650486000},"page":"130","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["3D-StyleGAN2-ADA: Volumetric Synthesis of Realistic Prostate T2W MRI"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2670-7069","authenticated-orcid":false,"given":"Claudia","family":"Giardina","sequence":"first","affiliation":[{"name":"Signal Theory and Communications, Universitat Polit\u00e8cnica de Catalunya\u2014BarcelonaTech (UPC), 08034 Barcelona, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6924-9961","authenticated-orcid":false,"given":"Ver\u00f3nica","family":"Vilaplana","sequence":"additional","affiliation":[{"name":"Signal Theory and Communications, Universitat Polit\u00e8cnica de Catalunya\u2014BarcelonaTech (UPC), 08034 Barcelona, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,14]]},"reference":[{"key":"ref_1","unstructured":"American Cancer Society (2024, November 28). Key Statistics for Prostate Cancer, 2024. Updated 19 January 2024. Available online: https:\/\/www.cancer.org\/cancer\/types\/prostate-cancer\/about\/key-statistics.html."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Feng, X., Chen, X., Peng, P., Zhou, H., Hong, Y., Zhu, C., Lu, L., Xie, S., Zhang, S., and Long, L. (2024). Values of multiparametric and biparametric MRI in diagnosing clinically significant prostate cancer: A multivariate analysis. BMC Urol., 24.","DOI":"10.1186\/s12894-024-01411-0"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Zhen, L., Liu, X., Chen, Y., Yang, Y., Xu, Y., Kang, J., Wang, X., Song, Y., Hu, R., and Zhang, W. (2019). Accuracy of multiparametric magnetic resonance imaging for diagnosing prostate cancer: A systematic review and meta-analysis. BMC Cancer, 19.","DOI":"10.1186\/s12885-019-6434-2"},{"key":"ref_4","first-page":"831","article-title":"Multiparametric prostate MRI: Focus on T2-weighted imaging and role in staging of prostate cancer","volume":"41","author":"Brown","year":"2015","journal-title":"Abdom. Imaging"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1083","DOI":"10.1109\/TMI.2014.2303821","article-title":"Computer-Aided Detection of Prostate Cancer in MRI","volume":"33","author":"Litjens","year":"2014","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"e230031","DOI":"10.1148\/ryai.230031","article-title":"Semi-supervised Learning with Report-guided Pseudo Labels for Deep Learning-based Prostate Cancer Detection Using Biparametric MRI","volume":"5","author":"Bosma","year":"2023","journal-title":"Radiol. Artif. Intell."},{"key":"ref_7","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014, January 8\u201313). Generative adversarial nets. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Hu, L., Zhou, D., Fu, C., Benkert, T., Xiao, Y., Wei, L., and Zhao, J. (2021). Calculation of Apparent Diffusion Coefficients in Prostate Cancer Using Deep Learning Algorithms: A Pilot Study. Front. Oncol., 11.","DOI":"10.3389\/fonc.2021.697721"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"e200237","DOI":"10.1148\/ryai.2021200237","article-title":"Synthesizing High-b-Value Diffusion-weighted Imaging of the Prostate Using Generative Adversarial Networks","volume":"3","author":"Hu","year":"2021","journal-title":"Radiol. Artif. Intell."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Ramanarayanan, S., Sarkar, A., Gayathri, M.N., Ram, K., and Sivaprakasam, M. (2024, January 17\u201318). DCE-diff: Diffusion Model for Synthesis of Early and Late Dynamic Contrast-Enhanced MR Images from Non-Contrast Multimodal Inputs. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Seattle, WA, USA.","DOI":"10.1109\/CVPRW63382.2024.00525"},{"key":"ref_11","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., and Foersch, S. (2023). Medical Diffusion: Denoising Diffusion Probabilistic Models for 3D Medical Image Generation. arXiv.","DOI":"10.1038\/s41598-023-34341-2"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Xu, I.R.L., Van Booven, D.J., Goberdhan, S., Breto, A., Porto, J., Alhusseini, M., Algohary, A., Stoyanova, R., Punnen, S., and Mahne, A. (2023). Generative Adversarial Networks Can Create High Quality Artificial Prostate Cancer Magnetic Resonance Images. J. Pers. Med., 13.","DOI":"10.3390\/jpm13030547"},{"key":"ref_13","first-page":"120331M","article-title":"Improving prostate cancer triage with GAN-based synthetically generated prostate ADC MRI","volume":"Volume 12033","author":"Drukker","year":"2022","journal-title":"Medical Imaging 2022: Computer-Aided Diagnosis"},{"key":"ref_14","unstructured":"Giardina, C., Vilaplana, V., Pard\u00e0s, M., and Guardia, O. (2024, January 19\u201321). Synthesis of Prostate MRI Scans: A Comparison of StyleGAN2-ADA and Latent Diffusion Models. Proceedings of the Conferencia de la Asociaci\u00f3n Espa\u00f1ola para la Inteligencia Artificial, IABioMed Workshop, Coru\u00f1a, Spain."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Kwon, G., Han, C., and Kim, D. (2019). Generation of 3D Brain MRI Using Auto-Encoding Generative Adversarial Networks. arXiv.","DOI":"10.1007\/978-3-030-32248-9_14"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Rekik, I., Adeli, E., Park, S.H., and Vald\u00e9s Hern\u00e1ndez, M.d.C. (2020). Conditional Generative Adversarial Network for Predicting 3D Medical Images Affected by Alzheimer\u2019s Diseases. Predictive Intelligence in Medicine, Springer.","DOI":"10.1007\/978-3-030-59354-4"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"3966","DOI":"10.1109\/JBHI.2022.3172976","article-title":"Hierarchical Amortized GAN for 3D High Resolution Medical Image Synthesis","volume":"26","author":"Sun","year":"2022","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Hong, S., Marinescu, R., Dalca, A.V., Bonkhoff, A.K., Bretzner, M., Rost, N.S., and Golland, P. (2021). 3D-StyleGAN: A Style-Based Generative Adversarial Network for Generative Modeling of Three-Dimensional Medical Images. arXiv.","DOI":"10.1007\/978-3-030-88210-5_3"},{"key":"ref_19","unstructured":"Xin, B., Young, T., Wainwright, C.E., Blake, T., Lebrat, L., Gaass, T., Benkert, T., Stemmer, A., Coman, D., and Dowling, J. (2024). Deformation-aware GAN for Medical Image Synthesis with Substantially Misaligned Pairs. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Ha, J., Park, J.S., Crandall, D., Garyfallidis, E., and Zhang, X. (2024). Multi-resolution Guided 3D GANs for Medical Image Translation. arXiv.","DOI":"10.1109\/WACV61041.2025.00426"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Rafiq, M., Ali, H., Mujtaba, G., Shah, Z., and Azmat, S. (2025). Cross Modality Medical Image Synthesis for Improving Liver Segmentation. arXiv.","DOI":"10.1080\/21681163.2025.2476702"},{"key":"ref_22","unstructured":"Hu, X., Chung, A.G., Fieguth, P.W., Khalvati, F., Haider, M.A., and Wong, A. (2018). ProstateGAN: Mitigating Data Bias via Prostate Diffusion Imaging Synthesis with Generative Adversarial Networks. arXiv."},{"key":"ref_23","unstructured":"Wang, Z., Lin, Y., Cheng, K., and Yang, X. (2018). Semi-supervised mp-MRI Data Synthesis with StitchLayer and Auxiliary Distance Maximization. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"855","DOI":"10.1109\/JBHI.2019.2922986","article-title":"Bi-Modality Medical Image Synthesis Using Semi-Supervised Sequential Generative Adversarial Networks","volume":"24","author":"Yang","year":"2020","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"879","DOI":"10.1016\/S1470-2045(24)00220-1","article-title":"Artificial intelligence and radiologists in prostate cancer detection on MRI (PI-CAI): An international, paired, non-inferiority, confirmatory study","volume":"25","author":"Saha","year":"2024","journal-title":"Lancet Oncol."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., and Aila, T. (2019). Analyzing and Improving the Image Quality of StyleGAN. arXiv.","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref_27","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Klambauer, G., and Hochreiter, S. (2017). GANs Trained by a Two Time-Scale Update Rule Converge to a Nash Equilibrium. arXiv."},{"key":"ref_28","unstructured":"Bi\u0144kowski, M., Sutherland, D.J., Arbel, M., and Gretton, A. (2021). Demystifying MMD GANs. arXiv."},{"key":"ref_29","unstructured":"Kynk\u00e4\u00e4nniemi, T., Karras, T., Laine, S., Lehtinen, J., and Aila, T. (2019). Improved Precision and Recall Metric for Assessing Generative Models. arXiv."},{"key":"ref_30","unstructured":"Betzalel, E., Penso, C., Navon, A., and Fetaya, E. (2022). A Study on the Evaluation of Generative Models. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnU-Net\u2014A Self-Configuring Method for Deep Learning-Based Biomedical Image Segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nat. Methods"},{"key":"ref_32","unstructured":"Litjens, G., Debats, O., Barentsz, J., Karssemeijer, N., and Huisman, H. (2023, September 22). SPIE-AAPM-NCI PROSTATEx Challenges (PROSTATEx). The Cancer Imaging Archive. Available online: https:\/\/doi.org\/10.7937\/K9TCIA.2017.MURS5CL."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"105817","DOI":"10.1016\/j.compbiomed.2022.105817","article-title":"Prostate158\u2014An expert-annotated 3T MRI dataset and algorithm for prostate cancer detection","volume":"148","author":"Adams","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1148\/radiol.2020191145","article-title":"The Image Biomarker Standardization Initiative: Standardized quantitative radiomics for high-throughput image-based phenotyping","volume":"295","author":"Zwanenburg","year":"2020","journal-title":"Radiology"},{"key":"ref_35","unstructured":"DIAGNijmegen (2024, July 30). picai_labels: Annotations for the PI-CAI Challenge Public Training and Development Dataset. Available online: https:\/\/github.com\/DIAGNijmegen\/picai_labels."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"e104","DOI":"10.1158\/0008-5472.CAN-17-0339","article-title":"Computational radiomics system to decode the radiographic phenotype","volume":"77","author":"Fedorov","year":"2017","journal-title":"Cancer Res."},{"key":"ref_37","unstructured":"Hong, S. (2024, April 22). 3DStyleGAN: A Style-Based Generative Adversarial Network for 3D Image Synthesis. Available online: https:\/\/github.com\/sh4174\/3DStyleGAN."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/3\/130\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T05:29:48Z","timestamp":1773725388000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/3\/130"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":37,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["jimaging12030130"],"URL":"https:\/\/doi.org\/10.3390\/jimaging12030130","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}