Generative AI for spatial tumor growth on MRI: a proof-of-principle study in pediatric diffuse midline glioma.
Authors
Affiliations (17)
Affiliations (17)
- D-HEST, ETH Zurich, Zurich, Switzerland.
- Swiss Institute of Bioinformatics, Lausanne, Switzerland.
- Department of Biomedical Informatics and Data Science, Yale School of Medicine, New Haven, CT, USA.
- Department of Diagnostic Imaging, University Children's Hospital Zurich, Zurich, Switzerland.
- Neurosurgery, University Children's Hospital Zurich, Zurich, Switzerland.
- Center for Intelligent Imaging, Department of Radiology & Biomedical Imaging, University of California San Francisco, San Francisco, USA.
- The Center for Data Driven Discovery of Biomedicine, The Children's Hospital of Philadelphia, Philadelphia, USA.
- Division of Pediatric Oncology, Stanford University, Stanford, USA.
- Sheikh Zayed Institute, Children's National Hospital, Washington, DC, USA.
- ETSIT, Universidad Politécnica de Madrid, Madrid, Spain.
- Department of Pediatrics, University Children's Hospital Zurich, Zurich, Switzerland.
- University of Pennsylvania, Philadelphia, USA.
- Center for Cancer and Immunology Research, Children's National Hospital, Washington, DC, USA.
- School of Medicine and Health Sciences, George Washington University, Washington, DC, USA.
- Neurosurgery and Pediatrics, University of California San Francisco, San Francisco, USA.
- Department of Radiation Oncology, Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland. [email protected].
- Department of Digital Medicine, University of Bern, Bern, Switzerland. [email protected].
Abstract
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). 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). 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. 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.