Fig. 5From: MRXCAT2.0: Synthesis of realistic numerical phantoms by combining left-ventricular shape learning, biophysical simulations and tissue texture generationVisualization of the latent space variables of the shape model for the Automated Cardiac Diagnosis Challenge (ACDC) dataset. Anatomies are color coded according to the clinical label: healthy (NOR, green squares), hypertrophic cardiomyopathy (HCM, grey triangles) and dilated cardiomyopathy (DCM, orange circles). Black symbols show the clusters' positions calculated using the k-means algorithm on the latent-space variable vectors. Note that due to the non-linear nature of the embedding, the cluster means do not necessarily match the barycenter of the point cloudsBack to article page