Bridging Imaging and Clinical Scores in Parkinson’s Progression Via Multimodal Self-Supervised Deep Learning
LATiDOS
neurodegenerative disease progression
Alzheimer’s Disease
Francisco J. Martinez-Murcia 
Abstract
Neurodegenerative diseases pose a formidable challenge to medical research, demanding a nuanced understanding of their progressive nature. In this regard, latent generative models can effectively be used in a data-driven modeling of different dimensions of neurodegeneration, framed within the context of the manifold hypothesis. This paper proposes a joint framework for a multi-modal, common latent generative model to address the need for a more comprehensive understanding of the neurodegenerative landscape in the context of Parkinson’s disease (PD). The proposed architecture uses coupled variational autoencoders (VAEs) to joint model a common latent space to both neuroimaging and clinical data from the Parkinson’s Progression Markers Initiative (PPMI). Alternative loss functions, different normalization procedures, and the interpretability and explainability of latent generative models are addressed, leading to a model that was able to predict clinical symptomatology in the test set, as measured by the unified Parkinson’s disease rating scale (UPDRS), with R2 up to 0.86 for same-modality and 0.441 cross-modality (using solely neuroimaging). The findings provide a foundation for further advancements in the field of clinical research and practice, with potential applications in decision-making processes for PD. The study also highlights the limitations and capabilities of the proposed model, emphasizing its direct interpretability and potential impact on understanding and interpreting neuroimaging patterns associated with PD symptomatology.
Citation
BibTeX citation:
@article{martinez-murcia2024,
author = {Martinez-Murcia, Francisco J. and Arco, Juan Eloy and
Jimenez-Mesa, Carmen and Segovia, Fermin and Illan, Ignacio A. and
Ramirez, Javier and Gorriz, Juan Manuel},
title = {Bridging {Imaging} and {Clinical} {Scores} in {Parkinson’s}
{Progression} {Via} {Multimodal} {Self-Supervised} {Deep}
{Learning}},
journal = {International Journal of Neural Systems},
volume = {34},
number = {08},
pages = {2450043},
date = {2024-05-22},
url = {https://www.worldscientific.com/doi/abs/10.1142/S0129065724500436},
doi = {10.1142/S0129065724500436},
langid = {en},
abstract = {Neurodegenerative diseases pose a formidable challenge to
medical research, demanding a nuanced understanding of their
progressive nature. In this regard, latent generative models can
effectively be used in a data-driven modeling of different
dimensions of neurodegeneration, framed within the context of the
manifold hypothesis. This paper proposes a joint framework for a
multi-modal, common latent generative model to address the need for
a more comprehensive understanding of the neurodegenerative
landscape in the context of Parkinson’s disease (PD). The proposed
architecture uses coupled variational autoencoders (VAEs) to joint
model a common latent space to both neuroimaging and clinical data
from the Parkinson’s Progression Markers Initiative (PPMI).
Alternative loss functions, different normalization procedures, and
the interpretability and explainability of latent generative models
are addressed, leading to a model that was able to predict clinical
symptomatology in the test set, as measured by the unified
Parkinson’s disease rating scale (UPDRS), with R2 up to 0.86 for
same-modality and 0.441 cross-modality (using solely neuroimaging).
The findings provide a foundation for further advancements in the
field of clinical research and practice, with potential applications
in decision-making processes for PD. The study also highlights the
limitations and capabilities of the proposed model, emphasizing its
direct interpretability and potential impact on understanding and
interpreting neuroimaging patterns associated with PD
symptomatology.}
}
For attribution, please cite this work as:
Martinez-Murcia, Francisco J., Juan Eloy Arco, Carmen Jimenez-Mesa,
Fermin Segovia, Ignacio A. Illan, Javier Ramirez, and Juan Manuel
Gorriz. 2024. “Bridging Imaging and Clinical Scores in Parkinson’s
Progression Via Multimodal Self-Supervised Deep Learning.”
International Journal of Neural Systems 34 (08): 2450043. https://doi.org/10.1142/S0129065724500436.