Recursive Variational Autoencoders for 3D Blood Vessel Generative Modeling
This work addresses the need for accurate and diverse 3D blood vessel models for medical training and simulations, representing an incremental advancement by applying a known generative technique to a new domain.
The authors tackled the problem of generating realistic 3D blood vessel models by developing a Recursive Variational Neural Network (RvNN) that learns a low-dimensional manifold to encode hierarchical structures, resulting in generated vessels that closely resemble real data with high similarity in radii, length, and tortuosity.
Anatomical trees play an important role in clinical diagnosis and treatment planning. Yet, accurately representing these structures poses significant challenges owing to their intricate and varied topology and geometry. Most existing methods to synthesize vasculature are rule based, and despite providing some degree of control and variation in the structures produced, they fail to capture the diversity and complexity of actual anatomical data. We developed a Recursive variational Neural Network (RvNN) that fully exploits the hierarchical organization of the vessel and learns a low-dimensional manifold encoding branch connectivity along with geometry features describing the target surface. After training, the RvNN latent space can be sampled to generate new vessel geometries. By leveraging the power of generative neural networks, we generate 3D models of blood vessels that are both accurate and diverse, which is crucial for medical and surgical training, hemodynamic simulations, and many other purposes. These results closely resemble real data, achieving high similarity in vessel radii, length, and tortuosity across various datasets, including those with aneurysms. To the best of our knowledge, this work is the first to utilize this technique for synthesizing blood vessels.