Aperçu du projet

Amyotrophic lateral sclerosis (ALS) is a neurodegenerative disorder with no known cure, leading to progressive loss of motor function and ultimately the death of the patient. While it is known that patients with ALS experience brain changes, particularly in motor areas, the relationships between brain-related changes, patient symptom profiles, and survival outcomes are still unknown. Deformation-based morphometry (DBM) is a sensitive magnetic resonance imaging (MRI)-based method that quantifies regional atrophy in grey and white matter, as well as expansion of the ventricles and sulci. Our previous study with a relatively small cohort of ALS patients demonstrated the potential of DBM as a biomarker of ALS, providing promising results cross-sectionally and longitudinally. We now have access to a significantly larger cohort (N=250 ALS, 200 controls) with longer follow-ups and detailed clinical assessments, allowing us to expand our previous work.

This proposal is based on two main hypotheses: i) DBM can be used as a sensitive biomarker of ALS and ii) using DBM features at baseline will increase the predictive power of survival and disease progression models, with more severe changes in brain anatomy being associated with shorter survival. Therefore, our specific aims are to study cross-sectional and longitudinal disease-related brain changes in ALS using DBM, assess sex differences in patients with ALS, assess the relationship between DBM and all clinical variables of interest, and investigate whether ALS-specific brain changes detected by DBM can improve the predictive power of deep learning survival models.

Our study has significant clinical implications, as longitudinal and survival studies in ALS are crucial for identifying biomarkers and potential treatments that can extend the lifespan of patients with ALS and improve their quality of life. Furthermore, by combining advanced MRI analysis techniques, such as DBM, with innovative machine learning or deep learning approaches, we have the potential to uncover complex data patterns that would remain undetectable with any individual method, providing further insights into the mechanisms involved in disease progression, survival, and clinical disability.

Chef d'équipe

Isabelle Lajoie , Douglas Hospital Research Centre

Partenaire et Donateurs

ALS Society of Canada