Learning Riemannian metric for disease progression modeling - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

Learning Riemannian metric for disease progression modeling


Linear mixed-effect models provide a natural baseline for estimating disease progression using longitudinal data. They provide interpretable models at the cost of modeling assumptions on the progression profiles and their variability across subjects. A significant improvement is to embed the data in a Riemannian manifold and learn patient-specific trajectories distributed around a central geodesic. A few interpretable parameters characterize subject trajectories at the cost of a prior choice of the metric, which determines the shape of the trajectories. We extend this approach by learning the metric from the data allowing more flexibility while keeping the interpretability. Specifically, we learn the metric as the push-forward of the Euclidean metric by a diffeomorphism. This diffeomorphism is estimated iteratively as the composition of radial basis functions belonging to a reproducible kernel Hilbert space. The metric update allows us to improve the forecasting of imaging and clinical biomarkers in the Alzheimer’s Disease Neuroimaging Initiative (ADNI) cohort. Our results compare favorably to the 56 methods benchmarked in the TADPOLE challenge.
Fichier principal
Vignette du fichier
NeurIPS_2021_final.pdf (1.17 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03485975 , version 1 (27-12-2021)


  • HAL Id : hal-03485975 , version 1


Samuel Gruffaz, Pierre-Emmanuel Poulet, Etienne Maheux, Bruno Jedynak, Stanley Durrleman​. Learning Riemannian metric for disease progression modeling. NeurIPS 2021 - Thirty-fifth Conference on Neural Information Processing Systems, Dec 2021, Virtual event, France. ⟨hal-03485975⟩
112 View
69 Download


Gmail Mastodon Facebook X LinkedIn More