Generative AI for spatial tumor growth on MRI: a proof-of-principle study in pediatric diffuse midline glioma
Rattachement africain : ch, us, es. Niveau de preuve : code pays fourni par la source.
Le résumé fourni par la source
Abstract Background Magnetic resonance imaging (MRI) is a cornerstone of non-invasive diagnosis and response monitoring in neuro-oncology, and predictions of spatial tumor progression conditioned on the patients’ anatomy are increasingly important. We present a proof-of-principle of personalized spatial tumor progression on MRI through generative AI, focusing on pediatric Diffuse Midline Glioma (DMG). Methods We employed guided Denoising Diffusion Implicit Models (DDIM) to model anatomical tumor growth in pediatric DMGs on MRI. Multiparametric scans from adult (n = 1,251) and pediatric (n = 144) patients from the BraTS23 challenge were used to train a slice-based framework, conditioned on baseline scans and a target tumor size. Repeated image generations produce probabilistic tumor growth maps highlighting likely regions of progression. The realism of the generated MRIs was evaluated quantitatively and qualitatively through expert assessment. Spatial growth predictions were validated against an independent dataset of longitudinal MRI scans from a multi-institutional pre-radiotherapy DMG dataset (n = 178 paired slices). Results We generated anatomically coherent, patient-specific T2-FLAIR (fluid-attenuated inversion recovery) MRI axial slices. Quantitative measures and expert evaluations confirmed the high quality of the generated images, which trained radiologists were unable to reliably distinguish from real scans (accuracy 0.53 ± 0.03). While radiomic features analyses showed good agreement (83% non-significant features) between synthetic and real images, a classifier detected subtle pixel-wise differences (accuracy of 0.69). Tumor growth probability maps aligned well with true tumor growth observed in follow-up imaging, obtaining a mean continuous DICE score of 0.79 ± 0.13. Conclusions We present guided DDIMs as a predictive tool for spatial tumor growth, illustrated for the progression of DMGs, that demonstrates potential for its integration in personalized radiotherapy planning. Our comprehensive image quality analysis highlights the importance of carefully evaluating synthetic data and its integration in research and clinical workflows.
Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.
Le contrôle bibliographique ouvert
Où se fait cette recherche
-
SIB Swiss Institute of Bioinformatics pays non établi dans la noticeOrganisation à but non lucratif
-
ETH Zurich pays non établi dans la noticeUniversité ou école supérieure
-
Yale University pays non établi dans la noticeUniversité ou école supérieure
-
University Children's Hospital Zurich pays non établi dans la noticeÉtablissement de santé
-
University of California pays non établi dans la noticeUniversité ou école supérieure
-
Children's Hospital of Philadelphia pays non établi dans la noticeOrganisme public
-
Stanford University pays non établi dans la noticeUniversité ou école supérieure
-
Children's National pays non établi dans la noticeÉtablissement de santé
-
Universidad Politécnica de Madrid pays non établi dans la noticeUniversité ou école supérieure
-
California University of Pennsylvania pays non établi dans la noticeUniversité ou école supérieure
-
George Washington University pays non établi dans la noticeUniversité ou école supérieure
-
University of Bern pays non établi dans la noticeUniversité ou école supérieure
SIB Swiss Institute of Bioinformatics, ETH Zurich et Yale University, avec 9 autres affiliations.
Une affiliation ne permet pas de déduire la nationalité d’un auteur.