2021/08/18 by Mariana da Silva, Da Silva, Mariana, Carole H. Sudre +9 · 1 citation
Medicine · #Advanced Neuroimaging Techniques and Applications #FOS: Biological sciences #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Neurons and Cognition (q-bio.NC) #Tissues and Organs (q-bio.TO) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2108.08214
openalex publication_date 2021/08/18 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
Biomechanical modeling of tissue deformation can be used to simulate\ndifferent scenarios of longitudinal brain evolution. In this work,we present a\ndeep learning framework for hyper-elastic strain modelling of brain atrophy,\nduring healthy ageing and in Alzheimer's Disease. The framework directly models\nthe effects of age, disease status, and scan interval to regress regional\npatterns of atrophy, from which a strain-based model estimates deformations.\nThis model is trained and validated using 3D structural magnetic resonance\nimaging data from the ADNI cohort. Results show that the framework can estimate\nrealistic deformations, following the known course of Alzheimer's disease, that\nclearly differentiate between healthy and demented patterns of ageing. This\nsuggests the framework has potential to be incorporated into explainable models\nof disease, for the exploration of interventions and counterfactual examples.\n