An End-to-End Deep Learning Generative Framework for Refinable Shape Matching and Generation
This addresses the need for cost-effective synthetic anatomical shapes in medical device validation, though it appears incremental as an extension of existing geometric deep learning approaches.
The paper tackles the challenge of generating realistic 3D anatomical shapes for In-Silico Clinical Trials by developing an unsupervised geometric deep-learning model that establishes refinable shape correspondences and generates synthetic shapes, demonstrating applicability with liver and left-ventricular models.
Generative modelling for shapes is a prerequisite for In-Silico Clinical Trials (ISCTs), which aim to cost-effectively validate medical device interventions using synthetic anatomical shapes, often represented as 3D surface meshes. However, constructing AI models to generate shapes closely resembling the real mesh samples is challenging due to variable vertex counts, connectivities, and the lack of dense vertex-wise correspondences across the training data. Employing graph representations for meshes, we develop a novel unsupervised geometric deep-learning model to establish refinable shape correspondences in a latent space, construct a population-derived atlas and generate realistic synthetic shapes. We additionally extend our proposed base model to a joint shape generative-clustering multi-atlas framework to incorporate further variability and preserve more details in the generated shapes. Experimental results using liver and left-ventricular models demonstrate the approach's applicability to computational medicine, highlighting its suitability for ISCTs through a comparative analysis.