171048 20260505142650.0 doi 10.1007/s10439-026-04115-8 sideral 149159 ART-2026-149159 eng Rosales, Ricardo M. 3D Segmentation of Multi-contrast Cardiac Magnetic Resonances With Topological Correction and Synthetic Data Augmentation 2026 Purpose: Automatic segmentation of cardiac magnetic resonance (CMR) images improves the evaluation of heart structure and function, helping clinical diagnosis and the generation of in silico models. Recent advances have introduced synthetic augmentation (SA) using generative adversarial networks (GANs) and topological correction (TC) via persistent homology to enhance segmentation with convolutional neural networks (CNNs). However, their combined effectiveness remains unexplored. Here, we extend and systematically evaluate these techniques, individually and in combination, for the first time in the context of three-dimensional (3D) CMR segmentation across challenging multi-vendor, multi-center, multi-class, and multi-contrast data sets. Methods: Data involved anisotropic, topologically inconsistent cine and late gadolinium-enhanced (LGE) CMRs, and isotropic, topologically consistent ex vivo CMRs. Topological priors were defined in each data set from ground truth label (GTL) assessments, and TC was applied by retraining the baseline 3D CNN with a loss function accounting for topological discrepancies. For SA, deformed GTLs were used to generate synthetic images using trained 3D GANs. Results: Consistent segmentation improvements were observed for the ex vivo data in both overlap with GTLs and topological precision when applying TC and SA individually and in combination. Notably, an enhanced identification of the infarction was obtained when SA and TC were used in the LGE data. Overall, SA increased the predictions overlap with GTLs, while TC reduced the topological discrepancies across all data sets. Conclusion: TC and SA demonstrate strong potential for improving 3D CMR segmentation on complex, real-world data sets, especially when topologically consistent data are available for training. Access copy available to the general public Unrestricted info:eu-repo/grantAgreement/ES/DGA/LMP97_21 info:eu-repo/grantAgreement/ES/DGA/T39-23R info:eu-repo/grantAgreement/EC/H2020/638284/EU/Is your heart aging well? A systems biology approach to characterize cardiac aging from the cell to the body surface/MODELAGE This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No H2020 638284-MODELAGE info:eu-repo/grantAgreement/EC/H2020/874827/EU/Computational biomechanics and bioengineering 3D printing to develop a personalized regenerative biological ventricular assist device to provide lasting functional support to damaged hearts/BRAV3 This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No H2020 874827-BRAV3 info:eu-repo/grantAgreement/ES/MCIN/PLEC2021-008127 info:eu-repo/grantAgreement/ES/MICINN/PID2022-1405560B-I00 info:eu-repo/grantAgreement/EUR/MICINN/TED2021-130459B-I00 info:eu-repo/semantics/openAccess by https://creativecommons.org/licenses/by/4.0/deed.es info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion Doblaré, Manuel Universidad de Zaragoza (orcid)0000-0001-8741-6452 Pueyo, Esther Universidad de Zaragoza (orcid)0000-0002-1960-407X 5008 800 Universidad de Zaragoza Dpto. Ingeniería Electrón.Com. Área Teoría Señal y Comunicac. 5004 605 Universidad de Zaragoza Dpto. Ingeniería Mecánica Área Mec.Med.Cont. y Teor.Est. (2026), [18 pp.] Ann. biomed. eng. Annals of Biomedical Engineering 0090-6964 4750505 http://zaguan.unizar.es/record/171048/files/texto_completo.pdf Versión publicada 2318890 http://zaguan.unizar.es/record/171048/files/texto_completo.jpg?subformat=icon icon Versión publicada oai:zaguan.unizar.es:171048 articulos driver 2026-05-05-13:36:33 ARTICLE