Visualizing definitional divergence in high-dimensional data by manifold alignment: Application to 3D right ventricular strain computations
Researchers have developed a new method to visualize how different definitions of medical descriptors impact data analysis. This approach uses manifold alignment to match latent representations of these varied definitions, focusing on myocardial deformation as a key example. The technique can generate a parametric map to illustrate definitional divergence, with initial demonstrations on toy experiments and later application to right ventricular strain data. AI